System

Abstract

A system is provided.SOLUTION: A system including means for capturing image data or audio data with respect to an analog teaching material or a natural environment, means for transmitting the captured image data and audio data to a server, means for analyzing the received image data and audio data and performing multimodal recognition of an object and a question content, means for generating related explanation or supplementary information based on a recognition result, means for transmitting the generated explanation or supplementary information to a terminal or a display device, and means for displaying the transmitted explanation or supplementary information.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Modern education is becoming increasingly digitalized, with a variety of digital tools and applications becoming widespread. However, there is a lack of learning methods that combine analog learning materials and natural experiences with the latest technology. As a result, there is a lack of effective, low-barrier learning environments for reskilling and acquiring new skills. Furthermore, it is difficult to provide individualized explanations and supplementary information, which often results in insufficient learning outcomes. [Means for solving the problem]

[0005] The present invention provides a means for capturing image data or audio data from analog learning materials or natural environments, and a means for transmitting the captured image data and audio data to a server. It also includes a means for analyzing the received image data and audio data on the server side and performing multimodal recognition of the object and question content. It also includes a means for generating related explanations and supplemental information based on the recognition results and transmitting the explanations and supplemental information to a terminal or display device. These means allow users to interact with analog learning materials and natural environments and receive easily understandable explanations tailored to their individual needs, providing an effective learning environment.

[0006] "Analog learning materials" refers to non-digital learning materials such as books, notebooks, and printed materials.

[0007] "Natural environment" refers to elements that exist in nature, such as flowers, insects, animals, scenery, and music.

[0008] "Image data" refers to electronic files containing visual information captured by a camera or other photographic device.

[0009] "Audio Data" means electronic files containing sound information captured by a microphone or other recording device.

[0010] "Capture" refers to the act of acquiring images and audio using a camera or microphone and saving them as digital data.

[0011] A "server" refers to a highly functional computer system that receives and processes data from terminals via a network.

[0012] "Multimodal recognition" refers to the technology of simultaneously analyzing data from multiple sources, such as images and audio.

[0013] An "explanation" refers to a detailed and easy-to-understand explanation of a particular object or phenomenon.

[0014] "Supplementary Information" refers to relevant information that adds to the main commentary.

[0015] "Device" refers to a digital device that can be directly operated by a user (e.g., smartphone, tablet, AR glasses).

[0016] "Display device" refers to a device for visually presenting digital information to a user. [Brief explanation of the drawings]

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

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

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

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

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

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

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

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] As an embodiment of the present invention, a system will be specifically described that acquires image data or audio data from analog teaching materials or natural environments and provides individually tailored commentary using digital technology.

[0039] Server Processing

[0040] 1. Initial Setup:

[0041] The server initializes a database that stores the user's unique ID and associated learning history and personalized data, enabling the provision of personalized information.

[0042] 2. Data reception:

[0043] The server receives image data and audio data sent from the device or AR glasses. The received data is managed together with the user ID.

[0044] 3. Multimodal Recognition:

[0045] The server runs image and voice recognition algorithms on the received data to identify the object and convert the voice content into text. For example, it can identify the type of flower from a received image and analyze the user's question from the voice.

[0046] 4. Content Generation:

[0047] The server generates relevant explanatory text and supplementary information based on the recognition results, including information retrieved from a pre-prepared educational content database. For example, it generates explanatory text about the identified flower.

[0048] 5. Data Transmission:

[0049] The server then sends the generated commentary and supplementary information to the device or AR glasses in a format that is easy for the user to understand.

[0050] Processing of devices (smartphones and tablets)

[0051] 1. User Interface:

[0052] The device provides an interface for users to use the camera to point it at analog learning materials or natural environments. For example, the user can activate the camera through an application and display a screen where they can check the subject being photographed.

[0053] 2. Data capture:

[0054] The device captures image data and audio data from a camera and microphone. For example, a user can take a picture of a page in a book or a flower with the camera and input a question by voice.

[0055] 3. Data transmission:

[0056] The device sends the captured data to a server, which also includes the user ID, allowing for personalized information to be provided.

[0057] 4. Data reception:

[0058] The terminal receives commentary and supplementary information sent from the server, and the received data is displayed in real time.

[0059] 5.Display:

[0060] The device then uses AR technology to present the received information to the user, for example by overlaying a description onto a specific book page or displaying related information on objects in the natural environment.

[0061] User Behavior

[0062] 1. Start learning:

[0063] Users use a device or AR glasses to access the analog learning materials and natural environments they want to learn from.

[0064] 2. Inquiries:

[0065] The user holds the camera over the object they want to inquire about and asks a question by voice, for example, "What kind of flower is this?"

[0066] 3. Receiving information:

[0067] Users can deepen their learning by viewing explanations and supplementary information displayed on their device or AR glasses. They can refer to the displayed information and move on to the next question or object.

[0068] Specific examples

[0069] Example 1: Book description

[0070] 1. User:

[0071] The user scans a page of a book with their smartphone camera and says, "Tell me what this page is about."

[0072] 2. Terminal:

[0073] The image data and audio data of the page are sent to the server.

[0074] 3. Server:

[0075] It uses image recognition to analyze the pages of a book, converts voice data into text, and identifies the user's question. It then generates an explanatory text based on the content of the page.

[0076] 4. Server:

[0077] Sends explanatory text to the device.

[0078] 5. Terminal:

[0079] The device displays explanatory text, which the user reads to understand the content.

[0080] Example 2: Nature Observation

[0081] 1. User:

[0082] Go out into the field, scan a flower with your smartphone camera, and ask, "What kind of flower is this?"

[0083] 2. Terminal:

[0084] Image data and audio data of the flower are sent to the server.

[0085] 3. Server:

[0086] It uses image recognition to identify the type and characteristics of flowers, converts voice data into text, and analyzes user questions.

[0087] 4. Server:

[0088] Generate flower names and descriptions of their characteristics.

[0089] 5. Server:

[0090] Sends a description to the device.

[0091] 6. Terminal:

[0092] The device displays an AR-based explanation overlaid on the image of the flower, allowing the user to observe the flower while viewing the detailed explanation.

[0093] In this way, the present invention effectively combines digital technology with analog learning materials and natural experiences to provide a fun and hands-on learning environment.

[0094] The processing flow will be explained below.

[0095] Step 1:

[0096] User: Launches the application and sets camera and microphone permissions, so that image and audio data can be captured.

[0097] Step 2:

[0098] Device: Activate the camera and capture an analog learning material or an object in the natural environment specified by the user. For example, take a picture of a page in a book or a flower.

[0099] Step 3:

[0100] Device: Activate the microphone to capture the user's voice input, for example, to record a question such as "What is this page about?"

[0101] Step 4:

[0102] Device: Captured image and audio data is sent to the server. At this time, the user's ID is also sent, making it possible to provide individually tailored commentary.

[0103] Step 5:

[0104] Server: Analyzes the received image data using an image recognition algorithm to identify the object, for example, identify the type of flower from a captured image.

[0105] Step 6:

[0106] Server: Converts the received voice data into text using a speech recognition algorithm and analyzes the user's question. For example, converting a question like "What kind of flower is this?" into text.

[0107] Step 7:

[0108] Server: Based on the image and voice recognition results, it retrieves relevant explanatory text and supplementary information from the educational content database and generates explanatory content.

[0109] Step 8:

[0110] Server: Sends the generated commentary content to the device or display device, including not only the text information but also related images and information for AR display.

[0111] Step 9:

[0112] Terminal: Receives explanatory content sent from the server and displays it through a user interface. For example, the explanatory text is displayed overlaid on the pages of a book.

[0113] Step 10:

[0114] User: Check the received explanations and supplementary information to advance their learning. Furthermore, they can continue learning by pointing the camera at new questions or objects.

[0115] This series of processes allows users to interact with analog learning materials and natural environments and receive individually tailored commentary using digital technology, resulting in an effective and enjoyable learning experience.

[0116] Example 1

[0117] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0118] In today's world, learning methods that use analog learning materials and natural environments face the challenge of providing personalized explanations and supplementary information. Furthermore, there is a lack of systems that provide detailed explanations efficiently and in real time, which reduces learning efficiency.

[0119] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0120] In this invention, the server includes means for acquiring image data or audio data from analog learning materials or natural environments, means for transmitting the acquired image data and audio data to a central processing unit, means for analyzing the received image data and audio data and performing multimodal recognition of the object and question content, means for generating related explanations and supplemental information based on the recognition results, means for transmitting the generated explanations and supplemental information to a terminal or display device, and means for displaying the transmitted explanations and supplemental information, thereby providing each user with a personalized learning experience and improving learning efficiency.

[0121] "Analog learning materials" refers to learning materials that are not in digital format, such as paper or physical objects.

[0122] The "natural environment" refers to natural objects such as plants, animals, and terrain that exist outdoors or in nature.

[0123] "Image data" refers to the digital form of visual information captured by a camera or other photographic device.

[0124] "Audio data" refers to a recording of sound captured using a microphone or other device and converted into digital format.

[0125] "Means for acquiring" refers to the technology or method for capturing image data or audio data using a terminal or device.

[0126] "Central Processing Unit" refers to the computer system or server that receives, analyzes, and processes data.

[0127] "Means of transmission" refers to the technology or method for sending data to other devices or servers via a network.

[0128] "Analyzing" refers to the application of computational processes and algorithms to analyze acquired data and understand its meaning and content.

[0129] "Multimodal recognition" refers to a technology that integrates and analyzes multiple different data formats (images, audio, etc.) to extract meaning.

[0130] "Recognition result" refers to the analysis result obtained by multimodal recognition.

[0131] "Explanation and supplementary information" refers to detailed explanations and additional information about the subject matter.

[0132] "Terminal" refers to a display device used by a user, such as a smartphone or tablet.

[0133] "Display device" refers to hardware for visually presenting information to a user.

[0134] This invention is a system that acquires image data or audio data from analog learning materials or natural environments and provides individually tailored commentary using digital technology. Specific embodiments of this system are described in detail below.

[0135] Hardware and software used

[0136] server

[0137] The server is hardware for large-scale data processing and analysis, and specifically uses the following software:

[0138] Database management system: Stores user IDs, learning history, and personalized data. For example, MySQL (registered trademark) or PostgreSQL is used.

[0139] Image Recognition Algorithms: Deep learning frameworks such as TENSORFLOW® and PyTorch are used to analyze the transmitted image data and identify objects.

[0140] Speech recognition algorithms: Use cloud-based speech recognition services such as Google® Speech-to-Text or IBM Watson® to convert voice data into text.

[0141] Natural Language Generation (NLG) model: Using generative AI models such as OpenAI (registered trademark) GPT-3 (registered trademark), explanatory text is automatically generated based on the analysis results.

[0142] Device (smartphone / tablet)

[0143] The terminal is a device that allows users to scan analog learning materials and the natural environment, acquire and display information, and utilizes the following specific software:

[0144] Camera application: Provides an interface for users to capture image data.

[0145] Voice input applications: Provide users with the ability to input and capture voice data.

[0146] Data sending and receiving module: Sends and receives data to and from the server using HTTP or WebSocket protocols.

[0147] AR technology: Augmented reality (AR) technology will be used to display received commentary and supplementary information in real time, specifically ARKit (iOS) and ARCore (ANDROID (registered trademark)).

[0148] Specific examples

[0149] Example 1: Book description

[0150] 1. The user scans a page of a book with their smartphone camera and says, "Tell me what this page is about."

[0151] 2. The device sends the image data and audio data of the page to the server.

[0152] 3. The server analyzes the page using image recognition, converts the voice data into text, and identifies the question. It then generates an explanation based on the content of the page.

[0153] 4. The server sends the generated explanatory text to the device.

[0154] 5. The device displays explanatory text, and the user reads it to understand the content.

[0155] Example 2: Nature Observation

[0156] 1. A user goes out into the field, scans a flower with their smartphone camera, and asks, "What kind of flower is this?"

[0157] 2. The device sends the flower image data and audio data to the server.

[0158] 3. The server performs image recognition to identify the type and characteristics of the flower, converts the voice data into text, and analyzes the user's question.

[0159] 4. The server generates the name of the flower and a description of its characteristics.

[0160] 5. The server sends the generated commentary to the device.

[0161] 6. The device displays an AR explanation overlaid on the flower image, allowing the user to observe the flower while viewing the detailed explanation.

[0162] Prompt Sentence Examples

[0163] Example 1: Book description prompt

[0164] "Tell me what's on this page."

[0165] Example 2: Nature observation prompt

[0166] "What is this flower?"

[0167] As described above, the system for implementing the present invention provides users with a real-time and personalized learning experience, significantly improving learning efficiency.

[0168] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0169] Step 1:

[0170] Input: A user launches the camera application on their smartphone or tablet and captures image data (e.g., a page in a book or an image of a natural object).

[0171] Specific behavior:

[0172] The device uses the camera to capture an image of the object and stores the captured image data in memory. The user can then decide what to photograph by viewing the camera's preview screen.

[0173] Output: The captured image data is stored in the device's memory.

[0174] Step 2:

[0175] Input: A user uses a voice input application to type a question into a microphone as voice data (e.g., "What is this page about?").

[0176] Specific behavior:

[0177] The device captures voice data through the microphone and stores it in memory, and the user records their question using a voice input application.

[0178] Output: The captured audio data is stored in the device's memory.

[0179] Step 3:

[0180] Input: Image and audio data stored on the device. User ID information.

[0181] Specific behavior:

[0182] The device converts the captured image and audio data, along with the user ID, into JSON format and sends it to the server using HTTP or WebSocket protocol.

[0183] Output: Image data, audio data and user ID are sent to the server.

[0184] Step 4:

[0185] Input: Image data and audio data sent to the server, user ID.

[0186] Specific behavior:

[0187] The server applies image recognition algorithms to the received image data using TensorFlow or PyTorch, and performs speech recognition on the audio data using Google Speech-to-Text or similar to convert it into text.

[0188] Output: Image analysis results (e.g., identification of objects in the image) and textual questions.

[0189] Step 5:

[0190] Input: Image analysis results and textual questions.

[0191] Specific behavior:

[0192] The server generates explanatory text and supplementary information using a generative AI model (e.g., OpenAI GPT-3) based on the image analysis results and the textual question content. It also retrieves related information from an educational content database and integrates it as supplementary information.

[0193] Output: Generated explanatory text and supporting information.

[0194] Step 6:

[0195] Input: Generated explanation and additional information. User ID.

[0196] Specific behavior:

[0197] The server compiles the generated explanatory text and supplementary information into JSON format and sends it to the terminal using HTTP or WebSocket protocol.

[0198] Output: Explanatory text and additional information are sent to the terminal.

[0199] Step 7:

[0200] Input: Explanation and additional information sent from the server.

[0201] Specific behavior:

[0202] The device then uses AR technology to display the received commentary and supplementary information on the user interface. For example, the device uses ARKit or ARCore to overlay the commentary on the subject of the photo.

[0203] Output: Users can view explanatory text and supplementary information in real time.

[0204] (Application example 1)

[0205] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0206] Although there are existing systems that provide individually tailored explanations by utilizing data capture and analysis technology for analog learning materials and natural environments, there are no systems that can handle the dynamic and diverse products and environments found in physical stores. Therefore, there is a need to provide a system that can instantly obtain product information and features in physical stores and improve the user experience.

[0207] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0208] In this invention, the server includes means for capturing image data or audio data from analog teaching materials, a natural environment, or a brick-and-mortar store, means for transmitting the captured image data and audio data to the server, means for analyzing the received image data and audio data and performing multimodal recognition of the object and question content, means for generating related explanations and supplemental information based on the recognition results, means for transmitting the generated explanations and supplemental information to a terminal or display device, and means for displaying the transmitted explanations and supplemental information using augmented reality technology. This makes it possible to instantly provide product information and explanations in a brick-and-mortar store to users, significantly improving convenience and user experience.

[0209] "Analog teaching materials" refers to physical media such as printed books, notebooks, and posters.

[0210] "Natural environment" refers to outdoor scenery, plants, animals, and other elements of the natural world.

[0211] "Brick and Mortar Store" means a physical store for selling goods and services.

[0212] "Image data" refers to still image and video data captured by a camera or other photographic device.

[0213] "Audio Data" means audio data captured by a microphone or other recording device.

[0214] A "server" refers to a computer system that processes data and provides information via a network.

[0215] "Capturing means" refers to a method or device for capturing images or sounds, such as a camera or microphone.

[0216] "Transmitting means" refers to a method or apparatus for sending data over a network to another system or device.

[0217] "Multimodal recognition" refers to the technology of analyzing multiple sensory data (e.g., images and audio) to understand their meaning.

[0218] "Recognition results" refers to the information obtained from analyzed image and audio data.

[0219] "Explanation and supplementary information" refers to detailed explanations or additional information related to the subject matter.

[0220] "Display device" refers to a device for visually displaying information (e.g., smartphone, augmented reality glasses, etc.).

[0221] "Augmented reality technology" refers to technology that displays virtual information overlaid on the real-world environment.

[0222] In order to implement the present invention, the following hardware and software are used.

[0223] Hardware used

[0224] 1. Smartphone: For image capture and data transmission.

[0225] 2. Smart glasses: For displaying information using augmented reality technology (e.g., Google Glass (registered trademark), Vuzix)

[0226] 3. Server: For data analysis and information generation.

[0227] Software used

[0228] 1. Image recognition library: To analyze image data. (e.g., Google Cloud Vision, Microsoft® Azure® Computer Vision)

[0229] 2. Speech recognition library: To convert voice data into text (e.g., Google Speech-to-Text, Azure Speech Services).

[0230] 3. Cloud platforms: for server hosting and data processing (e.g., AWS (registered trademark), Azure)

[0231] 4. Application development frameworks: For developing applications for smartphones and smart glasses (e.g., React Native, Flutter (registered trademark)).

[0232] System Overview

[0233] The server analyzes the image data and audio data received from the user, recognizes the object, and analyzes the user's question. Based on the analysis results, it generates an explanation and supplementary information that is optimal for the user and sends it to the user's device or display device. The received explanation and supplementary information are displayed using augmented reality technology, allowing the user to refer to it directly.

[0234] Processing Description

[0235] 1. Server process:

[0236] The server uses a database that stores user-specific IDs, learning histories, and personalized data, in order to provide individual information to each user.

[0237] The server analyzes the received image data using an image recognition library such as Google Cloud Vision to identify the target object.

[0238] The server converts the received voice data into text using a voice recognition library such as Google Speech-to-Text and analyzes the user's question.

[0239] Based on these recognition results, the server uses a generative AI model to create relevant commentary and supplementary information.

[0240] 2. Terminal processing:

[0241] The user captures an object with their smartphone camera and asks a question aloud using a prompt such as, "Please write a detailed description of this product. The name of this product is XX."

[0242] The smartphone transmits the captured image data and audio data to a server.

[0243] Commentary and supplementary information sent from the server is received and displayed on the smartphone or smart glasses display.

[0244] Augmented reality technology is used to overlay commentary and supplementary information on the object.

[0245] Specific examples

[0246] Example 1: Use in a home appliance store

[0247] A user can scan a refrigerator in an appliance section and ask, "What are the features of this refrigerator?" The smart glasses will then overlay information such as rated capacity and energy efficiency on top of the refrigerator, allowing the user to instantly check the detailed information.

[0248] Prompt Sentence Examples

[0249] "Please write a detailed description of this product. The product name is a 4-door inverter refrigerator."

[0250] This makes it possible to provide users with product information from physical stores quickly and accurately, improving the user experience.

[0251] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0252] Step 1:

[0253] A user scans a product with smart glasses. The input is the product image, and the output is the captured image data. The user looks at the product through the smart glasses, and the camera on the glasses captures the product image.

[0254] Step 2:

[0255] The terminal sends the captured image data to the server. The input is the captured image data, and the output is the data sent to the server. The smart glasses send the image data to the server via wireless communication.

[0256] Step 3:

[0257] The server uses an image recognition algorithm to analyze the received image data. The input is the received image data, and the output is the recognition result (e.g., product name, model number). The server identifies the object using an image recognition library such as Google Cloud Vision. The product name and model number are obtained as the analysis result.

[0258] Step 4:

[0259] The user asks a question about a product by voice. The input is the user's voice data, and the output is the captured voice data. The user speaks to the smart glasses and asks, "Tell me about the features of this product."

[0260] Step 5:

[0261] The terminal sends the captured voice data to the server. The input is the captured voice data, and the output is the data sent to the server. The smart glasses send the voice data to the server via wireless communication.

[0262] Step 6:

[0263] The server uses a speech recognition algorithm to convert the voice data into text. The input is the received voice data, and the output is text data (the user's question). The server then converts the voice data into text using a speech recognition library such as Google Speech-to-Text and analyzes the user's question.

[0264] Step 7:

[0265] The server generates explanations and supplementary information based on the text data and image recognition results. The input is text data and image recognition results, and the output is the generated explanations and supplementary information. The server uses a generative AI model to generate relevant explanations and information based on the recognition results and the user's question.

[0266] Step 8:

[0267] The server sends the generated commentary and supplementary information to the device. The input is the generated commentary and supplementary information, and the output is the data sent to the device. The server sends the commentary and supplementary information to the smart glasses.

[0268] Step 9:

[0269] The device displays the explanation and supplementary information using augmented reality technology. The input is the received explanation and supplementary information, and the output is the augmented reality information displayed to the user. The smart glasses display the received explanation and supplementary information, providing the user with detailed information about the product.

[0270] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0271] As an embodiment of the present invention, a system that acquires image data or audio data from analog learning materials or natural environments and provides individually tailored commentary using digital technology will be specifically described. Furthermore, a form incorporating an emotion recognition engine that recognizes the user's emotions and provides personalized information based on those emotions will be described.

[0272] Server Processing

[0273] 1. Initial Setup:

[0274] The server initializes a database that stores a user's unique ID and associated learning history, personalization data, and emotion recognition data, enabling personalized information delivery based on emotions.

[0275] 2. Data reception:

[0276] The server receives image data, voice data, and emotion data sent from the device or AR glasses. The received data is managed together with the user ID.

[0277] 3. Multimodal Recognition:

[0278] The server runs image and voice recognition algorithms on the received data to identify the object and convert the voice content into text. For example, it can identify the type of flower from a received image and analyze the user's question from the voice.

[0279] 4. Emotion recognition:

[0280] The server analyzes the received data and uses an emotion recognition engine to identify the user's emotional state, for example by analyzing facial expressions and tone of voice when the user captures the image.

[0281] 5. Content Generation:

[0282] The server generates relevant commentary and supplemental information based on the image, voice, and emotion recognition results. This information is personalized according to the user's emotional state. For example, if the user is in a difficult emotional state, a more detailed commentary is generated.

[0283] 6. Data Transmission:

[0284] The server then transmits the generated commentary content to the device or display device. The transmitted data includes not only the text information but also related images and information for AR display.

[0285] Processing of devices (smartphones and tablets)

[0286] 1. User Interface:

[0287] The device provides an interface for users to use the camera to point it at analog learning materials or natural environments. For example, the user can activate the camera through an application and display a screen where they can check the subject being photographed.

[0288] 2. Data capture:

[0289] The device captures image data, voice data, and emotion data from a camera and microphone. For example, a user can take a picture of a page in a book or a flower with the camera and input a question by voice.

[0290] 3. Data transmission:

[0291] The device sends the captured data to a server, which also includes the user's ID and emotional data, allowing for personalized information to be provided.

[0292] 4. Data reception:

[0293] The terminal receives commentary and supplementary information sent from the server, and the received data is displayed in real time.

[0294] 5.Display:

[0295] The device then uses AR technology to present the received information to the user, for example by overlaying a description onto a specific book page or by displaying related information on objects in the natural environment.

[0296] User Behavior

[0297] 1. Start learning:

[0298] Users use a device or AR glasses to access the analog learning materials and natural environments they want to learn from.

[0299] 2. Inquiries:

[0300] The user holds the camera over the object they want to inquire about and asks a question by voice, for example, "What kind of flower is this?"

[0301] 3. Receiving information:

[0302] Users can deepen their learning by viewing explanations and supplementary information displayed on their device or AR glasses. They can refer to the displayed information and move on to the next question or object.

[0303] Specific examples

[0304] Example 1: Book description

[0305] 1. User: Scan a page of a book with the smartphone camera. Say, "Tell me what's on this page."

[0306] 2. Terminal: Sends the image data, voice data, and facial expression data of the page to the server.

[0307] 3. Server: Analyzes the book pages using image recognition, converts voice data into text, and identifies the user's question. Recognizes emotions based on facial expression data.

[0308] 4. Server: Based on the content of the page, generate an explanatory text that matches the user's emotional state. For example, if the user has a troubled expression, provide a detailed explanation.

[0309] 5. Server: Sends explanatory text to the device.

[0310] 6. Terminal: The terminal displays explanatory text, which the user reads to understand the content.

[0311] Example 2: Nature observation

[0312] 1. User: Go out into the field and scan a flower with your smartphone camera. Ask, "What flower is this?"

[0313] 2. Terminal: Sends flower image data, audio data, and tone of voice data to the server.

[0314] 3. Server: Performs image recognition to identify the type and characteristics of flowers. Converts voice data into text and performs emotion recognition based on the tone of voice.

[0315] 4. Server: Generates a description based on the flower's name, characteristics, and user's emotions.

[0316] 5. Server: Sends the commentary to the device.

[0317] 6. Device: The device displays an AR explanation overlaid on the image of the flower. The user can observe the flower while looking at the detailed explanation.

[0318] In this way, the present invention effectively combines digital technology with analog learning materials and natural experiences to provide a fun and hands-on learning environment. Furthermore, the use of an emotion recognition engine enables personalization based on the user's emotional state, resulting in a more effective and personalized learning experience.

[0319] The processing flow will be explained below.

[0320] Step 1:

[0321] User: Launches the application and sets camera and microphone permissions, ready to capture image and audio data.

[0322] Step 2:

[0323] Device: Activate the camera and capture an analog learning material or an object in the natural environment specified by the user. For example, take a picture of a page in a book or a flower.

[0324] Step 3:

[0325] Device: Activate the microphone to capture the user's voice input, for example, to record a question such as "What is this page about?"

[0326] Step 4:

[0327] Device: The device captures the user's facial expression with a camera and simultaneously captures emotional data. For example, it records image data to analyze whether the user's facial expression is troubled.

[0328] Step 5:

[0329] Device: Captured image data, audio data, and emotional data are sent to the server. This data also includes the user ID, enabling personalized commentary.

[0330] Step 6:

[0331] Server: Analyzes the received image data using an image recognition algorithm to identify the object, for example, identify the type of flower from a captured image.

[0332] Step 7:

[0333] Server: Converts the received voice data into text using a speech recognition algorithm and analyzes the user's question. For example, converting a question like "What kind of flower is this?" into text.

[0334] Step 8:

[0335] Server: Uses an emotion recognition engine to identify the user's emotional state from the received data. For example, it analyzes whether the user is distressed, interested, confused, etc.

[0336] Step 9:

[0337] Server: Generates relevant explanatory text and supplementary information based on the image, voice, and emotion recognition results. For example, it generates information such as "This flower is a cherry blossom and blooms in spring."

[0338] Step 10:

[0339] Server: Personalize the generated explanatory content based on the user's emotional state. For example, include more detailed explanations or additional illustrations if the user is struggling.

[0340] Step 11:

[0341] Server: Sends personalized commentary content to the device or display device. The transmitted data includes not only text information but also related images and information for AR display.

[0342] Step 12:

[0343] Terminal: Receives explanatory content sent from the server and displays it through a user interface. For example, the explanatory text is displayed overlaid on the pages of a book.

[0344] Step 13:

[0345] User: Check the received explanations and supplementary information to advance their learning. Furthermore, they can continue learning by pointing the camera at new questions or objects.

[0346] This process allows users to receive personalized instruction through analog learning materials and natural environments, and then use digital technology to effectively learn. Furthermore, by utilizing an emotion recognition engine, a more personalized learning experience is provided based on the user's emotional state.

[0347] Example 2

[0348] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0349] Conventional learning methods using analog learning materials or natural environments provide uniform information, lacking in personalization tailored to each user's emotional state and learning progress. As a result, users may lack understanding or lose motivation to learn. Furthermore, even if image and audio data are captured, there is a lack of technology to effectively analyze that data and provide explanatory information tailored to the user's needs. There is a need to solve these issues.

[0350] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0351] In this invention, the server includes means for capturing image data or audio data from analog learning materials or natural environments, means for transmitting the captured image data and audio data to the server, means for analyzing the received image data and audio data and performing multimodal recognition of the object and question content, means for recognizing the user's emotional state and generating personalized commentary and supplemental information based on the emotion, means for transmitting the generated commentary and supplemental information to a terminal or display device, and means for displaying the transmitted commentary and supplemental information, thereby enabling the provision of detailed commentary information tailored to the user's emotional state and learning needs.

[0352] "Analog teaching materials" are educational materials that use paper media or physical objects.

[0353] The "natural environment" refers to the natural elements and ecosystems that exist outdoors.

[0354] "Image data" is visual information captured by a camera or other photographic device.

[0355] "Audio Data" means audio information captured by a microphone or other recording device.

[0356] A "capturing means" is a device or equipment for acquiring image data and audio data.

[0357] The "transmitting means" is a communication means for transmitting the acquired data to the server.

[0358] The "analyzing means" refers to the technology or algorithm for analyzing the received image data and audio data and extracting the necessary information.

[0359] "Multimodal recognition" is a technology that combines image data and audio data to analyze information and identify the target object or question.

[0360] The "means for generating personalized commentary and supplementary information" is a technology for creating personalized information according to the individual characteristics and emotional state of the user.

[0361] The "transmitting means" is a communication means for transmitting the generated commentary and supplementary information to a terminal or a display device.

[0362] The "display means" refers to a technique or device for visually presenting the transmitted commentary or supplemental information to the user.

[0363] "Emotional state" refers to a psychological state that can be inferred from a user's facial expression, tone of voice, and other behavior.

[0364] This system acquires image or audio data from analog learning materials or natural environments and uses digital technology to provide individually tailored commentary. It also incorporates an emotion recognition engine that recognizes the user's emotions and provides personalized information based on those emotions. This system operates among three parties: a server, a terminal, and the user.

[0365] Server Processing

[0366] 1. Initial Setup:

[0367] The server initializes the database. Specifically, it creates a table that manages each user's unique ID, learning history, personalized data, and emotion recognition data. This allows it to store learning data for each user and provide personalized information based on their emotions.

[0368] 2. Data reception:

[0369] The server receives image data, voice data, and emotion data sent from the device. The received data is managed by checking it against the user ID. For example, this data can be received using a REST API.

[0370] 3. Multimodal Recognition:

[0371] The server performs the following processing on the received data: it uses an image recognition algorithm (e.g., TensorFlow) to identify the object, and a speech recognition algorithm (e.g., Google Cloud Speech-to-Text API) to convert the speech into text, which allows it to analyze the user's question.

[0372] 4. Emotion recognition:

[0373] The server uses an emotion recognition engine (e.g., Microsoft Azure Emotion API) to identify the user's emotional state based on the received data. For example, it analyzes the user's facial expressions and tone of voice when capturing an image to infer the user's mental state.

[0374] 5. Content Generation:

[0375] The server generates relevant commentary and supplemental information based on the image, voice, and emotion recognition results. This allows for personalized information to be provided according to the user's emotional state. For example, if the user is having trouble, the server can generate detailed explanations to help the user progress smoothly through the learning process.

[0376] 6. Data Transmission:

[0377] The server then sends the generated commentary content to the device, which includes not only text information but also related images and information for AR display.

[0378] Processing of devices (smartphones and tablets)

[0379] 1. User Interface:

[0380] The device provides an interface for pointing the camera at analog learning materials or natural environments. This is implemented as an application, and the user can check the object being scanned through the camera preview.

[0381] 2. Data capture:

[0382] The device captures image data, voice data, and emotion data from a camera and microphone. For example, data is acquired when a user takes a picture of a particular flower with a camera and inputs a question by voice.

[0383] 3. Data transmission:

[0384] The device then sends the captured data, including the user ID and emotional data, to the server, where accurate personalization is performed.

[0385] 4. Data reception:

[0386] The terminal receives the commentary and supplementary information sent from the server, and the received data is displayed on the terminal's display in real time.

[0387] 5.Display:

[0388] The device then uses AR technology to present the received information to the user, for example by overlaying explanations on specific book pages to provide visual support for the user's learning.

[0389] User Behavior

[0390] Users use a device or AR glasses to access the analog learning materials or natural environment they want to learn from. They point the camera at the object they want to inquire about and ask a question by voice, for example, "What kind of flower is this?" Explanations and supplementary information are displayed on the device in real time, allowing users to view them and deepen their learning.

[0391] Specific examples

[0392] Example 1: Book description

[0393] 1. User: Scans a page of a book with the smartphone camera and says, "Tell me what this page is about."

[0394] 2. Terminal: Sends the page's image data, voice data, and emotion data to the server.

[0395] 3. Server: Analyzes the book pages using image recognition, converts voice data into text, and identifies the user's question. Recognizes emotions based on facial expression data.

[0396] 4. Server: Based on the content of the page, generate an explanatory text that matches the user's emotional state. For example, if the user has a troubled expression, provide a detailed explanation.

[0397] 5. Server: Sends explanatory text to the device.

[0398] 6. Terminal: The terminal displays explanatory text, which the user reads to understand the content.

[0399] Example 2: Nature observation

[0400] 1. User: Go out into the field and scan a flower with your smartphone camera. Ask, "What flower is this?"

[0401] 2. Terminal: Sends flower image data, audio data, and tone of voice data to the server.

[0402] 3. Server: Performs image recognition to identify the type and characteristics of flowers. Converts voice data into text and performs emotion recognition based on the tone of voice.

[0403] 4. Server: Generates a description based on the flower's name, characteristics, and user's emotions.

[0404] 5. Server: Sends the commentary to the device.

[0405] 6. Device: The device displays an AR explanation overlaid on the image of the flower. The user can observe the flower while looking at the detailed explanation.

[0406] In this way, the present invention is a system that effectively combines digital technology with analog learning materials and natural experiences to support user learning. Furthermore, the use of an emotion recognition engine enables personalization according to the user's emotional state, resulting in a more effective and individualized learning experience.

[0407] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0408] Server Processing

[0409] Step 1: Initial Setup

[0410] The server initializes the database. Specifically, it creates tables to store the user's unique ID, learning history, personalization data, and emotion recognition data. The input to this step is a specific table schema, and the output is an initialized database. For example, the tables are created by executing SQL queries.

[0411] Step 2: Receiving data

[0412] The server receives image data, audio data, and emotion data sent from the device. The input of this step is the data payload from the device, and the output is the raw data stored in the server. Specifically, it receives an HTTP POST request and saves the data in an appropriate folder or database.

[0413] Step 3: Multimodal Recognition

[0414] The server analyzes the received image data and voice data and performs multimodal recognition of the object and the question. The input for this step is image data and voice data, and the output is the recognized object and the question converted into text. Specifically, an image recognition algorithm is used to identify the type of flower, and a voice recognition algorithm is used to convert the user's question into text.

[0415] Step 4: Emotion Recognition

[0416] The server runs an emotion recognition engine based on the received data to identify the user's emotional state. The input for this step is a variety of data sets, including image data and audio data, and the output is the identified emotional state. Specific operations include facial expression recognition algorithms and tone of voice analysis.

[0417] Step 5: Content Generation

[0418] The server generates relevant commentary and supplemental information based on the image, voice, and emotion recognition results. The input to this step is the recognition results from the previous step, and the output is the generated commentary and supplemental information. For example, if the user is in a difficult emotional state, the server runs an algorithm to generate a more detailed commentary.

[0419] Step 6: Send data

[0420] The server sends the generated commentary content to the terminal. The input of this step is the generated commentary content, and the output is the status of completion of transmission. Specifically, the commentary and supplementary information are sent to the terminal using an HTTP POST request.

[0421] Processing of devices (smartphones and tablets)

[0422] Step 1: User Interface

[0423] The device provides an interface for pointing the camera at analog learning materials or natural environments. The input for this step is user operation, and the output is the display of the camera preview. Specifically, the camera preview of the application is launched.

[0424] Step 2: Data Capture

[0425] The device captures image data, audio data, and emotion data from the camera and microphone. The input of this step is physical objects and audio, and the output is digitized data. Specifically, images are Base64 encoded and audio is recorded.

[0426] Step 3: Send data

[0427] The device sends the captured data to the server. The input of this step is the captured data, and the output is the status of the completion of the transmission. Specifically, an HTTP POST request is created and sent.

[0428] Step 4: Receiving Data

[0429] The device receives the explanation and supplementary information sent from the server. The input of this step is the data from the server, and the output is the received explanation and supplementary information. Specifically, the data is obtained using an HTTP GET request.

[0430] Step 5: Display

[0431] The device then uses AR technology to present the received information to the user. The input for this step is the received explanatory information, and the output is the explanatory information displayed on the screen. Specifically, the explanatory information is displayed overlaid on a specific book page or natural object.

[0432] User Behavior

[0433] Step 1: Start learning

[0434] The user uses a device or AR glasses to access the analog learning materials or natural environment they want to learn from. The input of this step is the user's intention, and the output is the launch of an app. For example, launching a learning app and preparing the camera.

[0435] Step 2: Inquiry

[0436] The user points the camera at the object they want to inquire about and asks the question by voice. The input for this step is the object and the voice question, and the output is the captured data. For example, they might ask, "What is this flower?"

[0437] Step 3: Receiving information

[0438] The user can view explanations and supplementary information displayed on the device or AR glasses to further their learning. The input for this step is the information received from the server, and the output is the user's understanding. The user can then proceed to the next question or object.

[0439] (Application example 2)

[0440] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0441] Current factory robots struggle to provide advanced analytical functions or interactive assistance to improve the accuracy and efficiency of quality checks when inspecting or manipulating products. They also struggle to recognize the user's emotional state and provide information based on that. Even when an operator is confused, it is rare for them to provide appropriate support promptly. This results in issues such as reduced efficiency and increased human error.

[0442] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing image data or audio data, means for transmitting the captured data to the server, means for analyzing the received data and performing multimodal recognition of the object and the question content, means for generating personalized related explanations and supplemental information based on the recognition results and the user's emotional state, means for transmitting the generated explanations and supplemental information to a terminal or display device, and means for displaying the transmitted explanations and supplemental information. This enables the factory robot to provide appropriate support for product inspection and operation while taking the user's emotional state into consideration.

[0443] "Image data" is visual information captured using a camera or other imaging device.

[0444] "Audio Data" is a recording of sound collected using a microphone or other sound capture device.

[0445] "Capture" is the process of capturing information using a particular device.

[0446] A "server" is a computer system that provides a service to a group of other computers on a network.

[0447] "Transmission" is the process of moving data from one point to another.

[0448] "Analysis" is the process of understanding the type and structure of data and extracting its meaning and value.

[0449] "Multimodal recognition" is a technology that integrates and analyzes multiple input formats (images, audio, text, etc.).

[0450] "Related explanations and supplementary information" is explanatory text or additional information based on the recognized data.

[0451] "Terminal" means a computing device with input and output devices that can be directly operated by a user.

[0452] "Display" is the process of visually presenting acquired information to the user.

[0453] An "emotional state" is the state of emotions or feelings a user has at a given time.

[0454] A "generative AI model" is a model trained using machine learning algorithms that has the ability to generate content based on new data.

[0455] A "prompt" is a sentence that formats and inputs a specific question or command.

[0456] "Personalization" is the process of customizing something to suit the characteristics and circumstances of each individual user.

[0457] The present invention relates to a smart assistant system for factory robots, and a specific embodiment of the system will be described herein.

[0458] Server Processing

[0459] The server first receives image data and audio data. This data was acquired by factory robots using cameras, and each robot is assigned an individual user ID. The received data is managed in association with that user ID. The server then analyzes this data using the following methods to generate content.

[0460] Hardware and Software:

[0461] Hardware: Servers and cloud computing infrastructure

[0462] Software: OpenCV (image recognition), SpeechRecognition (voice recognition), Affectiva (emotion recognition), TensorFlow (machine learning), Flask (server-side)

[0463] The server uses an image recognition algorithm to analyze the received image data and identify the type and condition of the object, and a voice recognition algorithm to convert the voice data into text and extract the user's question.

[0464] Furthermore, an emotion recognition engine is used to identify the user's emotional state. For example, if an operator is confused, the emotional state is determined by analyzing facial image data and voice tone. Based on this emotional data, relevant commentary and supplementary information are generated in a personalized manner.

[0465] The information generated is sent to factory robots in real time, enabling them to provide appropriate feedback and assistance to operators.

[0466] Terminal (factory robot) processing

[0467] Factory robots are equipped with cameras and microphones and are used to inspect parts and products. A user (operator) uses the robot's camera to scan a specific part or product and then voice-inputs questions. The robot then sends this data to a server.

[0468] The received personalized information is then displayed on the robot's display. For example, if a factory robot is inspecting a part, the robot will scan the part and check for quality issues. If the operator is confused, the robot can provide a detailed explanation and explain next steps if an issue is found.

[0469] User Behavior

[0470] The user (operator) uses a factory robot to take pictures of parts or products and input quality-related questions by voice. For example, the user might ask, "Please tell me the condition of this part." The robot then uses its camera and microphone to capture the data and sends it to the server. The robot then receives feedback from the server and provides detailed explanations and instructions. This process allows the operator to efficiently perform quality checks.

[0471] Examples of concrete examples and prompts

[0472] As a concrete example, the following scenario can be considered.

[0473] Scene: A robot inspects parts on a factory assembly line.

[0474] Robot: Scans parts and sends quality check messages to operators.

[0475] Operator: There seems to be something wrong with the part and I'm confused (troubled expression).

[0476] System: The robot analyzes the operator's facial expressions and provides detailed instructions and next steps.

[0477] Example prompt sentence:

[0478] Keyword prompts: "Part image," "Audio question," "Confused expression," "Detailed explanation"

[0479] Prompt statement:

[0480] "I'm currently operating a robot. I'm concerned about the quality of the part. What's the problem with this part?"

[0481] "The operator is having trouble. Please check the details of the part."

[0482] As described above, the present invention enables a factory robot to provide assistance based on the user's emotional state, thereby improving efficiency and reducing human error.

[0483] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0484] Step 1:

[0485] The user operates the factory robot, scans the parts or products to be inspected with a camera, and inputs voice questions through a microphone. The input includes image data and voice data of the parts or products. For example, the user may ask a specific question such as, "Please tell me the condition of this part."

[0486] Step 2:

[0487] The terminal (factory robot) captures image data and audio data using a camera and microphone. This captured data is sent to the server along with the user ID. The input includes image data, audio data, and the user ID. The terminal sends this all together to the server.

[0488] Step 3:

[0489] The server analyzes the image data and audio data received from the device. The server first uses an image recognition algorithm (using OpenCV or TensorFlow) to identify the type and state of the object from the image data. Next, it uses a voice recognition algorithm (using SpeechRecognition) to convert the audio data into text. The server then analyzes the content of the question and extracts it as text data. The input includes image data and audio data, and the output generates the result of identifying the object and text data.

[0490] Step 4:

[0491] The server uses an emotion recognition engine (powered by Affectiva) to analyze the user's emotional state from the received image data and voice tone data. For example, it detects the operator's confused facial expression and tone. The input includes image data and voice tone data, and the output generates emotion data.

[0492] Step 5:

[0493] The server uses a generative AI model to personalize relevant commentary and supplemental information based on image, voice, and emotion recognition results. For example, if the user is confused, a more detailed commentary can be generated. This process involves generating appropriate prompts, based on which the AI ​​model generates content. Inputs include image, voice, and emotion recognition results, and the output is personalized commentary and supplemental information.

[0494] Step 6:

[0495] The server transmits the generated commentary and supplementary information to the terminal (factory robot). The input includes the generated commentary and supplementary information data, and the output becomes the transmitted data.

[0496] Step 7:

[0497] The terminal (factory robot) receives the explanation and supplementary information sent from the server and displays it to the user. For example, a detailed explanation and the next steps are displayed on the robot's display. The input includes the sent explanation and supplementary information, and the output is displayed to the user. The user can use this information to check the quality or carry out the next task.

[0498] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0499] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0500] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0501] [Second embodiment]

[0502] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0503] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0504] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0505] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0506] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0507] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0508] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0509] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0510] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0511] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0512] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0513] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0514] As an embodiment of the present invention, a system will be specifically described that acquires image data or audio data from analog teaching materials or natural environments and provides individually tailored commentary using digital technology.

[0515] Server Processing

[0516] 1. Initial Setup:

[0517] The server initializes a database that stores the user's unique ID and associated learning history and personalized data, enabling the provision of personalized information.

[0518] 2. Data reception:

[0519] The server receives image data and audio data sent from the device or AR glasses. The received data is managed together with the user ID.

[0520] 3. Multimodal Recognition:

[0521] The server runs image and voice recognition algorithms on the received data to identify the object and convert the voice content into text. For example, it can identify the type of flower from a received image and analyze the user's question from the voice.

[0522] 4. Content Generation:

[0523] The server generates relevant explanatory text and supplementary information based on the recognition results, including information retrieved from a pre-prepared educational content database. For example, it generates explanatory text about the identified flower.

[0524] 5. Data Transmission:

[0525] The server then sends the generated commentary and supplementary information to the device or AR glasses in a format that is easy for the user to understand.

[0526] Processing of devices (smartphones and tablets)

[0527] 1. User Interface:

[0528] The device provides an interface for users to use the camera to point it at analog learning materials or natural environments. For example, the user can activate the camera through an application and display a screen where they can check the subject being photographed.

[0529] 2. Data capture:

[0530] The device captures image data and audio data from a camera and microphone. For example, a user can take a picture of a page in a book or a flower with the camera and input a question by voice.

[0531] 3. Data transmission:

[0532] The device sends the captured data to a server, which also includes the user ID, allowing for personalized information to be provided.

[0533] 4. Data reception:

[0534] The terminal receives commentary and supplementary information sent from the server, and the received data is displayed in real time.

[0535] 5.Display:

[0536] The device then uses AR technology to present the received information to the user, for example by overlaying a description onto a specific book page or displaying related information on objects in the natural environment.

[0537] User Behavior

[0538] 1. Start learning:

[0539] Users use a device or AR glasses to access the analog learning materials and natural environments they want to learn from.

[0540] 2. Inquiries:

[0541] The user holds the camera over the object they want to inquire about and asks a question by voice, for example, "What kind of flower is this?"

[0542] 3. Receiving information:

[0543] Users can deepen their learning by viewing explanations and supplementary information displayed on their device or AR glasses. They can refer to the displayed information and move on to the next question or object.

[0544] Specific examples

[0545] Example 1: Book description

[0546] 1. User:

[0547] The user scans a page of a book with their smartphone camera and says, "Tell me what this page is about."

[0548] 2. Terminal:

[0549] The image data and audio data of the page are sent to the server.

[0550] 3. Server:

[0551] It uses image recognition to analyze the pages of a book, converts voice data into text, and identifies the user's question. It then generates an explanatory text based on the content of the page.

[0552] 4. Server:

[0553] Sends explanatory text to the device.

[0554] 5. Terminal:

[0555] The device displays explanatory text, which the user reads to understand the content.

[0556] Example 2: Nature Observation

[0557] 1. User:

[0558] Go out into the field, scan a flower with your smartphone camera, and ask, "What kind of flower is this?"

[0559] 2. Terminal:

[0560] Image data and audio data of the flower are sent to the server.

[0561] 3. Server:

[0562] It uses image recognition to identify the type and characteristics of flowers, converts voice data into text, and analyzes user questions.

[0563] 4. Server:

[0564] Generate flower names and descriptions of their characteristics.

[0565] 5. Server:

[0566] Sends a description to the device.

[0567] 6. Terminal:

[0568] The device displays an AR-based explanation overlaid on the image of the flower, allowing the user to observe the flower while viewing the detailed explanation.

[0569] In this way, the present invention effectively combines digital technology with analog learning materials and natural experiences to provide a fun and hands-on learning environment.

[0570] The processing flow will be explained below.

[0571] Step 1:

[0572] User: Launches the application and sets camera and microphone permissions, so that image and audio data can be captured.

[0573] Step 2:

[0574] Device: Activate the camera and capture an analog learning material or an object in the natural environment specified by the user. For example, take a picture of a page in a book or a flower.

[0575] Step 3:

[0576] Device: Activate the microphone to capture the user's voice input, for example, to record a question such as "What is this page about?"

[0577] Step 4:

[0578] Device: Captured image and audio data is sent to the server. At this time, the user's ID is also sent, making it possible to provide individually tailored commentary.

[0579] Step 5:

[0580] Server: Analyzes the received image data using an image recognition algorithm to identify the object, for example, identify the type of flower from a captured image.

[0581] Step 6:

[0582] Server: Converts the received voice data into text using a speech recognition algorithm and analyzes the user's question. For example, converting a question like "What kind of flower is this?" into text.

[0583] Step 7:

[0584] Server: Based on the image and voice recognition results, it retrieves relevant explanatory text and supplementary information from the educational content database and generates explanatory content.

[0585] Step 8:

[0586] Server: Sends the generated commentary content to the device or display device, including not only the text information but also related images and information for AR display.

[0587] Step 9:

[0588] Terminal: Receives explanatory content sent from the server and displays it through a user interface. For example, the explanatory text is displayed overlaid on the pages of a book.

[0589] Step 10:

[0590] User: Check the received explanations and supplementary information to advance their learning. Furthermore, they can continue learning by pointing the camera at new questions or objects.

[0591] This series of processes allows users to interact with analog learning materials and natural environments and receive individually tailored commentary using digital technology, resulting in an effective and enjoyable learning experience.

[0592] Example 1

[0593] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0594] In today's world, learning methods that use analog learning materials and natural environments face the challenge of providing personalized explanations and supplementary information. Furthermore, there is a lack of systems that provide detailed explanations efficiently and in real time, which reduces learning efficiency.

[0595] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0596] In this invention, the server includes means for acquiring image data or audio data from analog learning materials or natural environments, means for transmitting the acquired image data and audio data to a central processing unit, means for analyzing the received image data and audio data and performing multimodal recognition of the object and question content, means for generating related explanations and supplemental information based on the recognition results, means for transmitting the generated explanations and supplemental information to a terminal or display device, and means for displaying the transmitted explanations and supplemental information, thereby providing each user with a personalized learning experience and improving learning efficiency.

[0597] "Analog learning materials" refers to learning materials that are not in digital format, such as paper or physical objects.

[0598] The "natural environment" refers to natural objects such as plants, animals, and terrain that exist outdoors or in nature.

[0599] "Image data" refers to the digital form of visual information captured by a camera or other photographic device.

[0600] "Audio data" refers to a recording of sound captured using a microphone or other device and converted into digital format.

[0601] "Means for acquiring" refers to the technology or method for capturing image data or audio data using a terminal or device.

[0602] "Central Processing Unit" refers to the computer system or server that receives, analyzes, and processes data.

[0603] "Means of transmission" refers to the technology or method for sending data to other devices or servers via a network.

[0604] "Analyzing" refers to the application of computational processes and algorithms to analyze acquired data and understand its meaning and content.

[0605] "Multimodal recognition" refers to a technology that integrates and analyzes multiple different data formats (images, audio, etc.) to extract meaning.

[0606] "Recognition result" refers to the analysis result obtained by multimodal recognition.

[0607] "Explanation and supplementary information" refers to detailed explanations and additional information about the subject matter.

[0608] "Terminal" refers to a display device used by a user, such as a smartphone or tablet.

[0609] "Display device" refers to hardware for visually presenting information to a user.

[0610] This invention is a system that acquires image data or audio data from analog learning materials or natural environments and provides individually tailored commentary using digital technology. Specific embodiments of this system are described in detail below.

[0611] Hardware and software used

[0612] server

[0613] The server is hardware for large-scale data processing and analysis, and specifically uses the following software:

[0614] Database management system: Stores user IDs, learning history, and personalized data. For example, MySQL or PostgreSQL is used.

[0615] Image recognition algorithms: Deep learning frameworks such as TensorFlow and PyTorch are used to analyze the transmitted image data and identify objects.

[0616] Speech recognition algorithms: Use cloud-based speech recognition services such as Google Speech-to-Text or IBM Watson to convert the audio data into text.

[0617] Natural Language Generation (NLG) model: Using generative AI models such as OpenAI GPT-3, explanatory text is automatically generated based on the analysis results.

[0618] Device (smartphone / tablet)

[0619] The terminal is a device that allows users to scan analog learning materials and the natural environment, acquire and display information, and utilizes the following specific software:

[0620] Camera application: Provides an interface for users to capture image data.

[0621] Voice input applications: Provide users with the ability to input and capture voice data.

[0622] Data sending and receiving module: Sends and receives data to and from the server using HTTP or WebSocket protocols.

[0623] AR technology: Augmented reality (AR) technology will be used to display received commentary and supplementary information in real time, specifically ARKit (iOS) and ARCore (Android).

[0624] Specific examples

[0625] Example 1: Book description

[0626] 1. The user scans a page of a book with their smartphone camera and says, "Tell me what this page is about."

[0627] 2. The device sends the image data and audio data of the page to the server.

[0628] 3. The server analyzes the page using image recognition, converts the voice data into text, and identifies the question. It then generates an explanation based on the content of the page.

[0629] 4. The server sends the generated explanatory text to the device.

[0630] 5. The device displays explanatory text, and the user reads it to understand the content.

[0631] Example 2: Nature Observation

[0632] 1. A user goes out into the field, scans a flower with their smartphone camera, and asks, "What kind of flower is this?"

[0633] 2. The device sends the flower image data and audio data to the server.

[0634] 3. The server performs image recognition to identify the type and characteristics of the flower, converts the voice data into text, and analyzes the user's question.

[0635] 4. The server generates the name of the flower and a description of its characteristics.

[0636] 5. The server sends the generated commentary to the device.

[0637] 6. The device displays an AR explanation overlaid on the flower image, allowing the user to observe the flower while viewing the detailed explanation.

[0638] Prompt Sentence Examples

[0639] Example 1: Book description prompt

[0640] "Tell me what's on this page."

[0641] Example 2: Nature observation prompt

[0642] "What is this flower?"

[0643] As described above, the system for implementing the present invention provides users with a real-time and personalized learning experience, significantly improving learning efficiency.

[0644] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0645] Step 1:

[0646] Input: A user launches the camera application on their smartphone or tablet and captures image data (e.g., a page in a book or an image of a natural object).

[0647] Specific behavior:

[0648] The device uses the camera to capture an image of the object and stores the captured image data in memory. The user can then decide what to photograph by viewing the camera's preview screen.

[0649] Output: The captured image data is stored in the device's memory.

[0650] Step 2:

[0651] Input: A user uses a voice input application to type a question into a microphone as voice data (e.g., "What is this page about?").

[0652] Specific behavior:

[0653] The device captures voice data through the microphone and stores it in memory, and the user records their question using a voice input application.

[0654] Output: The captured audio data is stored in the device's memory.

[0655] Step 3:

[0656] Input: Image and audio data stored on the device. User ID information.

[0657] Specific behavior:

[0658] The device converts the captured image and audio data, along with the user ID, into JSON format and sends it to the server using HTTP or WebSocket protocol.

[0659] Output: Image data, audio data and user ID are sent to the server.

[0660] Step 4:

[0661] Input: Image data and audio data sent to the server, user ID.

[0662] Specific behavior:

[0663] The server applies image recognition algorithms to the received image data using TensorFlow or PyTorch, and performs speech recognition on the audio data using Google Speech-to-Text or similar to convert it into text.

[0664] Output: Image analysis results (e.g., identification of objects in the image) and textual questions.

[0665] Step 5:

[0666] Input: Image analysis results and textual questions.

[0667] Specific behavior:

[0668] The server generates explanatory text and supplementary information using a generative AI model (e.g., OpenAI GPT-3) based on the image analysis results and the textual question content. It also retrieves related information from an educational content database and integrates it as supplementary information.

[0669] Output: Generated explanatory text and supporting information.

[0670] Step 6:

[0671] Input: Generated explanation and additional information. User ID.

[0672] Specific behavior:

[0673] The server compiles the generated explanatory text and supplementary information into JSON format and sends it to the terminal using HTTP or WebSocket protocol.

[0674] Output: Explanatory text and additional information are sent to the terminal.

[0675] Step 7:

[0676] Input: Explanation and additional information sent from the server.

[0677] Specific behavior:

[0678] The device then uses AR technology to display the received commentary and supplementary information on the user interface. For example, the device uses ARKit or ARCore to overlay the commentary on the subject of the photo.

[0679] Output: Users can view explanatory text and supplementary information in real time.

[0680] (Application example 1)

[0681] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0682] Although there are existing systems that provide individually tailored explanations by utilizing data capture and analysis technology for analog learning materials and natural environments, there are no systems that can handle the dynamic and diverse products and environments found in physical stores. Therefore, there is a need to provide a system that can instantly obtain product information and features in physical stores and improve the user experience.

[0683] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0684] In this invention, the server includes means for capturing image data or audio data from analog teaching materials, a natural environment, or a brick-and-mortar store, means for transmitting the captured image data and audio data to the server, means for analyzing the received image data and audio data and performing multimodal recognition of the object and question content, means for generating related explanations and supplemental information based on the recognition results, means for transmitting the generated explanations and supplemental information to a terminal or display device, and means for displaying the transmitted explanations and supplemental information using augmented reality technology. This makes it possible to instantly provide product information and explanations in a brick-and-mortar store to users, significantly improving convenience and user experience.

[0685] "Analog teaching materials" refers to physical media such as printed books, notebooks, and posters.

[0686] "Natural environment" refers to outdoor scenery, plants, animals, and other elements of the natural world.

[0687] "Brick and Mortar Store" means a physical store for selling goods and services.

[0688] "Image data" refers to still image and video data captured by a camera or other photographic device.

[0689] "Audio Data" means audio data captured by a microphone or other recording device.

[0690] A "server" refers to a computer system that processes data and provides information via a network.

[0691] "Capturing means" refers to a method or device for capturing images or sounds, such as a camera or microphone.

[0692] "Transmitting means" refers to a method or apparatus for sending data over a network to another system or device.

[0693] "Multimodal recognition" refers to the technology of analyzing multiple sensory data (e.g., images and audio) to understand their meaning.

[0694] "Recognition results" refers to the information obtained from analyzed image and audio data.

[0695] "Explanation and supplementary information" refers to detailed explanations or additional information related to the subject matter.

[0696] "Display device" refers to a device for visually displaying information (e.g., smartphone, augmented reality glasses, etc.).

[0697] "Augmented reality technology" refers to technology that displays virtual information overlaid on the real-world environment.

[0698] In order to implement the present invention, the following hardware and software are used.

[0699] Hardware used

[0700] 1. Smartphone: For image capture and data transmission.

[0701] 2. Smart glasses: For displaying information using augmented reality technology (e.g., Google Glass, Vuzix)

[0702] 3. Server: For data analysis and information generation.

[0703] Software used

[0704] 1. Image recognition libraries: To analyze image data (e.g., Google Cloud Vision, Microsoft Azure Computer Vision).

[0705] 2. Speech recognition library: To convert voice data into text (e.g., Google Speech-to-Text, Azure Speech Services).

[0706] 3. Cloud platforms: for server hosting and data processing (e.g., AWS, Azure).

[0707] 4. Application development frameworks: For developing applications for smartphones and smart glasses (e.g., React Native, Flutter).

[0708] System Overview

[0709] The server analyzes the image data and audio data received from the user, recognizes the object, and analyzes the user's question. Based on the analysis results, it generates an explanation and supplementary information that is optimal for the user and sends it to the user's device or display device. The received explanation and supplementary information are displayed using augmented reality technology, allowing the user to refer to it directly.

[0710] Processing Description

[0711] 1. Server process:

[0712] The server uses a database that stores user-specific IDs, learning histories, and personalized data, in order to provide individual information to each user.

[0713] The server analyzes the received image data using an image recognition library such as Google Cloud Vision to identify the target object.

[0714] The server converts the received voice data into text using a voice recognition library such as Google Speech-to-Text and analyzes the user's question.

[0715] Based on these recognition results, the server uses a generative AI model to create relevant commentary and supplementary information.

[0716] 2. Terminal processing:

[0717] The user captures an object with their smartphone camera and asks a question aloud using a prompt such as, "Please write a detailed description of this product. The name of this product is XX."

[0718] The smartphone transmits the captured image data and audio data to a server.

[0719] Commentary and supplementary information sent from the server is received and displayed on the smartphone or smart glasses display.

[0720] Augmented reality technology is used to overlay commentary and supplementary information on the object.

[0721] Specific examples

[0722] Example 1: Use in a home appliance store

[0723] A user can scan a refrigerator in an appliance section and ask, "What are the features of this refrigerator?" The smart glasses will then overlay information such as rated capacity and energy efficiency on top of the refrigerator, allowing the user to instantly check the detailed information.

[0724] Prompt Sentence Examples

[0725] "Please write a detailed description of this product. The product name is a 4-door inverter refrigerator."

[0726] This makes it possible to provide users with product information from physical stores quickly and accurately, improving the user experience.

[0727] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0728] Step 1:

[0729] A user scans a product with smart glasses. The input is the product image, and the output is the captured image data. The user looks at the product through the smart glasses, and the camera on the glasses captures the product image.

[0730] Step 2:

[0731] The terminal sends the captured image data to the server. The input is the captured image data, and the output is the data sent to the server. The smart glasses send the image data to the server via wireless communication.

[0732] Step 3:

[0733] The server uses an image recognition algorithm to analyze the received image data. The input is the received image data, and the output is the recognition result (e.g., product name, model number). The server identifies the object using an image recognition library such as Google Cloud Vision. The product name and model number are obtained as the analysis result.

[0734] Step 4:

[0735] The user asks a question about a product by voice. The input is the user's voice data, and the output is the captured voice data. The user speaks to the smart glasses and asks, "Tell me about the features of this product."

[0736] Step 5:

[0737] The terminal sends the captured voice data to the server. The input is the captured voice data, and the output is the data sent to the server. The smart glasses send the voice data to the server via wireless communication.

[0738] Step 6:

[0739] The server uses a speech recognition algorithm to convert the voice data into text. The input is the received voice data, and the output is text data (the user's question). The server then converts the voice data into text using a speech recognition library such as Google Speech-to-Text and analyzes the user's question.

[0740] Step 7:

[0741] The server generates explanations and supplementary information based on the text data and image recognition results. The input is text data and image recognition results, and the output is the generated explanations and supplementary information. The server uses a generative AI model to generate relevant explanations and information based on the recognition results and the user's question.

[0742] Step 8:

[0743] The server sends the generated commentary and supplementary information to the device. The input is the generated commentary and supplementary information, and the output is the data sent to the device. The server sends the commentary and supplementary information to the smart glasses.

[0744] Step 9:

[0745] The device displays the explanation and supplementary information using augmented reality technology. The input is the received explanation and supplementary information, and the output is the augmented reality information displayed to the user. The smart glasses display the received explanation and supplementary information, providing the user with detailed information about the product.

[0746] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0747] As an embodiment of the present invention, a system that acquires image data or audio data from analog learning materials or natural environments and provides individually tailored commentary using digital technology will be specifically described. Furthermore, a form incorporating an emotion recognition engine that recognizes the user's emotions and provides personalized information based on those emotions will be described.

[0748] Server Processing

[0749] 1. Initial Setup:

[0750] The server initializes a database that stores a user's unique ID and associated learning history, personalization data, and emotion recognition data, enabling personalized information delivery based on emotions.

[0751] 2. Data reception:

[0752] The server receives image data, voice data, and emotion data sent from the device or AR glasses. The received data is managed together with the user ID.

[0753] 3. Multimodal Recognition:

[0754] The server runs image and voice recognition algorithms on the received data to identify the object and convert the voice content into text. For example, it can identify the type of flower from a received image and analyze the user's question from the voice.

[0755] 4. Emotion recognition:

[0756] The server analyzes the received data and uses an emotion recognition engine to identify the user's emotional state, for example by analyzing facial expressions and tone of voice when the user captures the image.

[0757] 5. Content Generation:

[0758] The server generates relevant commentary and supplemental information based on the image, voice, and emotion recognition results. This information is personalized according to the user's emotional state. For example, if the user is in a difficult emotional state, a more detailed commentary is generated.

[0759] 6. Data Transmission:

[0760] The server then transmits the generated commentary content to the device or display device. The transmitted data includes not only the text information but also related images and information for AR display.

[0761] Processing of devices (smartphones and tablets)

[0762] 1. User Interface:

[0763] The device provides an interface for users to use the camera to point it at analog learning materials or natural environments. For example, the user can activate the camera through an application and display a screen where they can check the subject being photographed.

[0764] 2. Data capture:

[0765] The device captures image data, voice data, and emotion data from a camera and microphone. For example, a user can take a picture of a page in a book or a flower with the camera and input a question by voice.

[0766] 3. Data transmission:

[0767] The device sends the captured data to a server, which also includes the user's ID and emotional data, allowing for personalized information to be provided.

[0768] 4. Data reception:

[0769] The terminal receives commentary and supplementary information sent from the server, and the received data is displayed in real time.

[0770] 5.Display:

[0771] The device then uses AR technology to present the received information to the user, for example by overlaying a description onto a specific book page or by displaying related information on objects in the natural environment.

[0772] User Behavior

[0773] 1. Start learning:

[0774] Users use a device or AR glasses to access the analog learning materials and natural environments they want to learn from.

[0775] 2. Inquiries:

[0776] The user holds the camera over the object they want to inquire about and asks a question by voice, for example, "What kind of flower is this?"

[0777] 3. Receiving information:

[0778] Users can deepen their learning by viewing explanations and supplementary information displayed on their device or AR glasses. They can refer to the displayed information and move on to the next question or object.

[0779] Specific examples

[0780] Example 1: Book description

[0781] 1. User: Scan a page of a book with the smartphone camera. Say, "Tell me what's on this page."

[0782] 2. Terminal: Sends the image data, voice data, and facial expression data of the page to the server.

[0783] 3. Server: Analyzes the book pages using image recognition, converts voice data into text, and identifies the user's question. Recognizes emotions based on facial expression data.

[0784] 4. Server: Based on the content of the page, generate an explanatory text that matches the user's emotional state. For example, if the user has a troubled expression, provide a detailed explanation.

[0785] 5. Server: Sends explanatory text to the device.

[0786] 6. Terminal: The terminal displays explanatory text, which the user reads to understand the content.

[0787] Example 2: Nature observation

[0788] 1. User: Go out into the field and scan a flower with your smartphone camera. Ask, "What flower is this?"

[0789] 2. Terminal: Sends flower image data, audio data, and tone of voice data to the server.

[0790] 3. Server: Performs image recognition to identify the type and characteristics of flowers. Converts voice data into text and performs emotion recognition based on the tone of voice.

[0791] 4. Server: Generates a description based on the flower's name, characteristics, and user's emotions.

[0792] 5. Server: Sends the commentary to the device.

[0793] 6. Device: The device displays an AR explanation overlaid on the image of the flower. The user can observe the flower while looking at the detailed explanation.

[0794] In this way, the present invention effectively combines digital technology with analog learning materials and natural experiences to provide a fun and hands-on learning environment. Furthermore, the use of an emotion recognition engine enables personalization based on the user's emotional state, resulting in a more effective and personalized learning experience.

[0795] The processing flow will be explained below.

[0796] Step 1:

[0797] User: Launches the application and sets camera and microphone permissions, ready to capture image and audio data.

[0798] Step 2:

[0799] Device: Activate the camera and capture an analog learning material or an object in the natural environment specified by the user. For example, take a picture of a page in a book or a flower.

[0800] Step 3:

[0801] Device: Activate the microphone to capture the user's voice input, for example, to record a question such as "What is this page about?"

[0802] Step 4:

[0803] Device: The device captures the user's facial expression with a camera and simultaneously captures emotional data. For example, it records image data to analyze whether the user's facial expression is troubled.

[0804] Step 5:

[0805] Device: Captured image data, audio data, and emotional data are sent to the server. This data also includes the user ID, enabling personalized commentary.

[0806] Step 6:

[0807] Server: Analyzes the received image data using an image recognition algorithm to identify the object, for example, identify the type of flower from a captured image.

[0808] Step 7:

[0809] Server: Converts the received voice data into text using a speech recognition algorithm and analyzes the user's question. For example, converting a question like "What kind of flower is this?" into text.

[0810] Step 8:

[0811] Server: Uses an emotion recognition engine to identify the user's emotional state from the received data. For example, it analyzes whether the user is distressed, interested, confused, etc.

[0812] Step 9:

[0813] Server: Generates relevant explanatory text and supplementary information based on the image, voice, and emotion recognition results. For example, it generates information such as "This flower is a cherry blossom and blooms in spring."

[0814] Step 10:

[0815] Server: Personalize the generated explanatory content based on the user's emotional state. For example, include more detailed explanations or additional illustrations if the user is struggling.

[0816] Step 11:

[0817] Server: Sends personalized commentary content to the device or display device. The transmitted data includes not only text information but also related images and information for AR display.

[0818] Step 12:

[0819] Terminal: Receives explanatory content sent from the server and displays it through a user interface. For example, the explanatory text is displayed overlaid on the pages of a book.

[0820] Step 13:

[0821] User: Check the received explanations and supplementary information to advance their learning. Furthermore, they can continue learning by pointing the camera at new questions or objects.

[0822] This process allows users to receive personalized instruction through analog learning materials and natural environments, and then use digital technology to effectively learn. Furthermore, by utilizing an emotion recognition engine, a more personalized learning experience is provided based on the user's emotional state.

[0823] Example 2

[0824] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0825] Conventional learning methods using analog learning materials or natural environments provide uniform information, lacking in personalization tailored to each user's emotional state and learning progress. As a result, users may lack understanding or lose motivation to learn. Furthermore, even if image and audio data are captured, there is a lack of technology to effectively analyze that data and provide explanatory information tailored to the user's needs. There is a need to solve these issues.

[0826] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0827] In this invention, the server includes means for capturing image data or audio data from analog learning materials or natural environments, means for transmitting the captured image data and audio data to the server, means for analyzing the received image data and audio data and performing multimodal recognition of the object and question content, means for recognizing the user's emotional state and generating personalized commentary and supplemental information based on the emotion, means for transmitting the generated commentary and supplemental information to a terminal or display device, and means for displaying the transmitted commentary and supplemental information, thereby enabling the provision of detailed commentary information tailored to the user's emotional state and learning needs.

[0828] "Analog teaching materials" are educational materials that use paper media or physical objects.

[0829] The "natural environment" refers to the natural elements and ecosystems that exist outdoors.

[0830] "Image data" is visual information captured by a camera or other photographic device.

[0831] "Audio Data" means audio information captured by a microphone or other recording device.

[0832] A "capturing means" is a device or equipment for acquiring image data and audio data.

[0833] The "transmitting means" is a communication means for transmitting the acquired data to the server.

[0834] The "analyzing means" refers to the technology or algorithm for analyzing the received image data and audio data and extracting the necessary information.

[0835] "Multimodal recognition" is a technology that combines image data and audio data to analyze information and identify the target object or question.

[0836] The "means for generating personalized commentary and supplementary information" is a technology for creating personalized information according to the individual characteristics and emotional state of the user.

[0837] The "transmitting means" is a communication means for transmitting the generated commentary and supplementary information to a terminal or a display device.

[0838] The "display means" refers to a technique or device for visually presenting the transmitted commentary or supplemental information to the user.

[0839] "Emotional state" refers to a psychological state that can be inferred from a user's facial expression, tone of voice, and other behavior.

[0840] This system acquires image or audio data from analog learning materials or natural environments and uses digital technology to provide individually tailored commentary. It also incorporates an emotion recognition engine that recognizes the user's emotions and provides personalized information based on those emotions. This system operates among three parties: a server, a terminal, and the user.

[0841] Server Processing

[0842] 1. Initial Setup:

[0843] The server initializes the database. Specifically, it creates a table that manages each user's unique ID, learning history, personalized data, and emotion recognition data. This allows it to store learning data for each user and provide personalized information based on their emotions.

[0844] 2. Data reception:

[0845] The server receives image data, voice data, and emotion data sent from the device. The received data is managed by checking it against the user ID. For example, this data can be received using a REST API.

[0846] 3. Multimodal Recognition:

[0847] The server performs the following processing on the received data: it uses an image recognition algorithm (e.g., TensorFlow) to identify the object, and a speech recognition algorithm (e.g., Google Cloud Speech-to-Text API) to convert the speech into text, which allows it to analyze the user's question.

[0848] 4. Emotion recognition:

[0849] The server uses an emotion recognition engine (e.g., Microsoft Azure Emotion API) to identify the user's emotional state based on the received data. For example, it analyzes the user's facial expressions and tone of voice when capturing an image to infer the user's mental state.

[0850] 5. Content Generation:

[0851] The server generates relevant commentary and supplemental information based on the image, voice, and emotion recognition results. This allows for personalized information to be provided according to the user's emotional state. For example, if the user is having trouble, the server can generate detailed explanations to help the user progress smoothly through the learning process.

[0852] 6. Data Transmission:

[0853] The server then sends the generated commentary content to the device, which includes not only text information but also related images and information for AR display.

[0854] Processing of devices (smartphones and tablets)

[0855] 1. User Interface:

[0856] The device provides an interface for pointing the camera at analog learning materials or natural environments. This is implemented as an application, and the user can check the object being scanned through the camera preview.

[0857] 2. Data capture:

[0858] The device captures image data, voice data, and emotion data from a camera and microphone. For example, data is acquired when a user takes a picture of a particular flower with a camera and inputs a question by voice.

[0859] 3. Data transmission:

[0860] The device then sends the captured data, including the user ID and emotional data, to the server, where accurate personalization is performed.

[0861] 4. Data reception:

[0862] The terminal receives the commentary and supplementary information sent from the server, and the received data is displayed on the terminal's display in real time.

[0863] 5.Display:

[0864] The device then uses AR technology to present the received information to the user, for example by overlaying explanations on specific book pages to provide visual support for the user's learning.

[0865] User Behavior

[0866] Users use a device or AR glasses to access the analog learning materials or natural environment they want to learn from. They point the camera at the object they want to inquire about and ask a question by voice, for example, "What kind of flower is this?" Explanations and supplementary information are displayed on the device in real time, allowing users to view them and deepen their learning.

[0867] Specific examples

[0868] Example 1: Book description

[0869] 1. User: Scans a page of a book with the smartphone camera and says, "Tell me what this page is about."

[0870] 2. Terminal: Sends the page's image data, voice data, and emotion data to the server.

[0871] 3. Server: Analyzes the book pages using image recognition, converts voice data into text, and identifies the user's question. Recognizes emotions based on facial expression data.

[0872] 4. Server: Based on the content of the page, generate an explanatory text that matches the user's emotional state. For example, if the user has a troubled expression, provide a detailed explanation.

[0873] 5. Server: Sends explanatory text to the device.

[0874] 6. Terminal: The terminal displays explanatory text, which the user reads to understand the content.

[0875] Example 2: Nature observation

[0876] 1. User: Go out into the field and scan a flower with your smartphone camera. Ask, "What flower is this?"

[0877] 2. Terminal: Sends flower image data, audio data, and tone of voice data to the server.

[0878] 3. Server: Performs image recognition to identify the type and characteristics of flowers. Converts voice data into text and performs emotion recognition based on the tone of voice.

[0879] 4. Server: Generates a description based on the flower's name, characteristics, and user's emotions.

[0880] 5. Server: Sends the commentary to the device.

[0881] 6. Device: The device displays an AR explanation overlaid on the image of the flower. The user can observe the flower while looking at the detailed explanation.

[0882] In this way, the present invention is a system that effectively combines digital technology with analog learning materials and natural experiences to support user learning. Furthermore, the use of an emotion recognition engine enables personalization according to the user's emotional state, resulting in a more effective and individualized learning experience.

[0883] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0884] Server Processing

[0885] Step 1: Initial Setup

[0886] The server initializes the database. Specifically, it creates tables to store the user's unique ID, learning history, personalization data, and emotion recognition data. The input to this step is a specific table schema, and the output is an initialized database. For example, the tables are created by executing SQL queries.

[0887] Step 2: Receiving data

[0888] The server receives image data, audio data, and emotion data sent from the device. The input of this step is the data payload from the device, and the output is the raw data stored in the server. Specifically, it receives an HTTP POST request and saves the data in an appropriate folder or database.

[0889] Step 3: Multimodal Recognition

[0890] The server analyzes the received image data and voice data and performs multimodal recognition of the object and the question. The input for this step is image data and voice data, and the output is the recognized object and the question converted into text. Specifically, an image recognition algorithm is used to identify the type of flower, and a voice recognition algorithm is used to convert the user's question into text.

[0891] Step 4: Emotion Recognition

[0892] The server runs an emotion recognition engine based on the received data to identify the user's emotional state. The input for this step is a variety of data sets, including image data and audio data, and the output is the identified emotional state. Specific operations include facial expression recognition algorithms and tone of voice analysis.

[0893] Step 5: Content Generation

[0894] The server generates relevant commentary and supplemental information based on the image, voice, and emotion recognition results. The input to this step is the recognition results from the previous step, and the output is the generated commentary and supplemental information. For example, if the user is in a difficult emotional state, the server runs an algorithm to generate a more detailed commentary.

[0895] Step 6: Send data

[0896] The server sends the generated commentary content to the terminal. The input of this step is the generated commentary content, and the output is the status of completion of transmission. Specifically, the commentary and supplementary information are sent to the terminal using an HTTP POST request.

[0897] Processing of devices (smartphones and tablets)

[0898] Step 1: User Interface

[0899] The device provides an interface for pointing the camera at analog learning materials or natural environments. The input for this step is user operation, and the output is the display of the camera preview. Specifically, the camera preview of the application is launched.

[0900] Step 2: Data Capture

[0901] The device captures image data, audio data, and emotion data from the camera and microphone. The input of this step is physical objects and audio, and the output is digitized data. Specifically, images are Base64 encoded and audio is recorded.

[0902] Step 3: Send data

[0903] The device sends the captured data to the server. The input of this step is the captured data, and the output is the status of the completion of the transmission. Specifically, an HTTP POST request is created and sent.

[0904] Step 4: Receiving Data

[0905] The device receives the explanation and supplementary information sent from the server. The input of this step is the data from the server, and the output is the received explanation and supplementary information. Specifically, the data is obtained using an HTTP GET request.

[0906] Step 5: Display

[0907] The device then uses AR technology to present the received information to the user. The input for this step is the received explanatory information, and the output is the explanatory information displayed on the screen. Specifically, the explanatory information is displayed overlaid on a specific book page or natural object.

[0908] User Behavior

[0909] Step 1: Start learning

[0910] The user uses a device or AR glasses to access the analog learning materials or natural environment they want to learn from. The input of this step is the user's intention, and the output is the launch of an app. For example, launching a learning app and preparing the camera.

[0911] Step 2: Inquiry

[0912] The user points the camera at the object they want to inquire about and asks the question by voice. The input for this step is the object and the voice question, and the output is the captured data. For example, they might ask, "What is this flower?"

[0913] Step 3: Receiving information

[0914] The user can view explanations and supplementary information displayed on the device or AR glasses to further their learning. The input for this step is the information received from the server, and the output is the user's understanding. The user can then proceed to the next question or object.

[0915] (Application example 2)

[0916] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0917] Current factory robots struggle to provide advanced analytical functions or interactive assistance to improve the accuracy and efficiency of quality checks when inspecting or manipulating products. They also struggle to recognize the user's emotional state and provide information based on that. Even when an operator is confused, it is rare for them to provide appropriate support promptly. This results in issues such as reduced efficiency and increased human error.

[0918] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing image data or audio data, means for transmitting the captured data to the server, means for analyzing the received data and performing multimodal recognition of the object and the question content, means for generating personalized related explanations and supplemental information based on the recognition results and the user's emotional state, means for transmitting the generated explanations and supplemental information to a terminal or display device, and means for displaying the transmitted explanations and supplemental information. This enables the factory robot to provide appropriate support for product inspection and operation while taking the user's emotional state into consideration.

[0919] "Image data" is visual information captured using a camera or other imaging device.

[0920] "Audio Data" is a recording of sound collected using a microphone or other sound capture device.

[0921] "Capture" is the process of capturing information using a particular device.

[0922] A "server" is a computer system that provides a service to a group of other computers on a network.

[0923] "Transmission" is the process of moving data from one point to another.

[0924] "Analysis" is the process of understanding the type and structure of data and extracting its meaning and value.

[0925] "Multimodal recognition" is a technology that integrates and analyzes multiple input formats (images, audio, text, etc.).

[0926] "Related explanations and supplementary information" is explanatory text or additional information based on the recognized data.

[0927] "Terminal" means a computing device with input and output devices that can be directly operated by a user.

[0928] "Display" is the process of visually presenting acquired information to the user.

[0929] An "emotional state" is the state of emotions or feelings a user has at a given time.

[0930] A "generative AI model" is a model trained using machine learning algorithms that has the ability to generate content based on new data.

[0931] A "prompt" is a sentence that formats and inputs a specific question or command.

[0932] "Personalization" is the process of customizing something to suit the characteristics and circumstances of each individual user.

[0933] The present invention relates to a smart assistant system for factory robots, and a specific embodiment of the system will be described herein.

[0934] Server Processing

[0935] The server first receives image data and audio data. This data was acquired by factory robots using cameras, and each robot is assigned an individual user ID. The received data is managed in association with that user ID. The server then analyzes this data using the following methods to generate content.

[0936] Hardware and Software:

[0937] Hardware: Servers and cloud computing infrastructure

[0938] Software: OpenCV (image recognition), SpeechRecognition (voice recognition), Affectiva (emotion recognition), TensorFlow (machine learning), Flask (server-side)

[0939] The server uses an image recognition algorithm to analyze the received image data and identify the type and condition of the object, and a voice recognition algorithm to convert the voice data into text and extract the user's question.

[0940] Furthermore, an emotion recognition engine is used to identify the user's emotional state. For example, if an operator is confused, the emotional state is determined by analyzing facial image data and voice tone. Based on this emotional data, relevant commentary and supplementary information are generated in a personalized manner.

[0941] The information generated is sent to factory robots in real time, enabling them to provide appropriate feedback and assistance to operators.

[0942] Terminal (factory robot) processing

[0943] Factory robots are equipped with cameras and microphones and are used to inspect parts and products. A user (operator) uses the robot's camera to scan a specific part or product and then voice-inputs questions. The robot then sends this data to a server.

[0944] The received personalized information is then displayed on the robot's display. For example, if a factory robot is inspecting a part, the robot will scan the part and check for quality issues. If the operator is confused, the robot can provide a detailed explanation and explain next steps if an issue is found.

[0945] User Behavior

[0946] The user (operator) uses a factory robot to take pictures of parts or products and input quality-related questions by voice. For example, the user might ask, "Please tell me the condition of this part." The robot then uses its camera and microphone to capture the data and sends it to the server. The robot then receives feedback from the server and provides detailed explanations and instructions. This process allows the operator to efficiently perform quality checks.

[0947] Examples of concrete examples and prompts

[0948] As a concrete example, the following scenario can be considered.

[0949] Scene: A robot inspects parts on a factory assembly line.

[0950] Robot: Scans parts and sends quality check messages to operators.

[0951] Operator: There seems to be something wrong with the part and I'm confused (troubled expression).

[0952] System: The robot analyzes the operator's facial expressions and provides detailed instructions and next steps.

[0953] Example prompt sentence:

[0954] Keyword prompts: "Part image," "Audio question," "Confused expression," "Detailed explanation"

[0955] Prompt statement:

[0956] "I'm currently operating a robot. I'm concerned about the quality of the part. What's the problem with this part?"

[0957] "The operator is having trouble. Please check the details of the part."

[0958] As described above, the present invention enables a factory robot to provide assistance based on the user's emotional state, thereby improving efficiency and reducing human error.

[0959] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0960] Step 1:

[0961] The user operates the factory robot, scans the parts or products to be inspected with a camera, and inputs voice questions through a microphone. The input includes image data and voice data of the parts or products. For example, the user may ask a specific question such as, "Please tell me the condition of this part."

[0962] Step 2:

[0963] The terminal (factory robot) captures image data and audio data using a camera and microphone. This captured data is sent to the server along with the user ID. The input includes image data, audio data, and the user ID. The terminal sends this all together to the server.

[0964] Step 3:

[0965] The server analyzes the image data and audio data received from the device. The server first uses an image recognition algorithm (using OpenCV or TensorFlow) to identify the type and state of the object from the image data. Next, it uses a voice recognition algorithm (using SpeechRecognition) to convert the audio data into text. The server then analyzes the content of the question and extracts it as text data. The input includes image data and audio data, and the output generates the result of identifying the object and text data.

[0966] Step 4:

[0967] The server uses an emotion recognition engine (powered by Affectiva) to analyze the user's emotional state from the received image data and voice tone data. For example, it detects the operator's confused facial expression and tone. The input includes image data and voice tone data, and the output generates emotion data.

[0968] Step 5:

[0969] The server uses a generative AI model to personalize relevant commentary and supplemental information based on image, voice, and emotion recognition results. For example, if the user is confused, a more detailed commentary can be generated. This process involves generating appropriate prompts, based on which the AI ​​model generates content. Inputs include image, voice, and emotion recognition results, and the output is personalized commentary and supplemental information.

[0970] Step 6:

[0971] The server transmits the generated commentary and supplementary information to the terminal (factory robot). The input includes the generated commentary and supplementary information data, and the output becomes the transmitted data.

[0972] Step 7:

[0973] The terminal (factory robot) receives the explanation and supplementary information sent from the server and displays it to the user. For example, a detailed explanation and the next steps are displayed on the robot's display. The input includes the sent explanation and supplementary information, and the output is displayed to the user. The user can use this information to check the quality or carry out the next task.

[0974] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0975] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0976] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0977] [Third embodiment]

[0978] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0979] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0980] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0981] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0982] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0983] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0984] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0985] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0986] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0987] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0988] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0989] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0990] As an embodiment of the present invention, a system will be specifically described that acquires image data or audio data from analog teaching materials or natural environments and provides individually tailored commentary using digital technology.

[0991] Server Processing

[0992] 1. Initial Setup:

[0993] The server initializes a database that stores the user's unique ID and associated learning history and personalized data, enabling the provision of personalized information.

[0994] 2. Data reception:

[0995] The server receives image data and audio data sent from the device or AR glasses. The received data is managed together with the user ID.

[0996] 3. Multimodal Recognition:

[0997] The server runs image and voice recognition algorithms on the received data to identify the object and convert the voice content into text. For example, it can identify the type of flower from a received image and analyze the user's question from the voice.

[0998] 4. Content Generation:

[0999] The server generates relevant explanatory text and supplementary information based on the recognition results, including information retrieved from a pre-prepared educational content database. For example, it generates explanatory text about the identified flower.

[1000] 5. Data Transmission:

[1001] The server then sends the generated commentary and supplementary information to the device or AR glasses in a format that is easy for the user to understand.

[1002] Processing of devices (smartphones and tablets)

[1003] 1. User Interface:

[1004] The device provides an interface for users to use the camera to point it at analog learning materials or natural environments. For example, the user can activate the camera through an application and display a screen where they can check the subject being photographed.

[1005] 2. Data capture:

[1006] The device captures image data and audio data from a camera and microphone. For example, a user can take a picture of a page in a book or a flower with the camera and input a question by voice.

[1007] 3. Data transmission:

[1008] The device sends the captured data to a server, which also includes the user ID, allowing for personalized information to be provided.

[1009] 4. Data reception:

[1010] The terminal receives commentary and supplementary information sent from the server, and the received data is displayed in real time.

[1011] 5.Display:

[1012] The device then uses AR technology to present the received information to the user, for example by overlaying a description onto a specific book page or displaying related information on objects in the natural environment.

[1013] User Behavior

[1014] 1. Start learning:

[1015] Users use a device or AR glasses to access the analog learning materials and natural environments they want to learn from.

[1016] 2. Inquiries:

[1017] The user holds the camera over the object they want to inquire about and asks a question by voice, for example, "What kind of flower is this?"

[1018] 3. Receiving information:

[1019] Users can deepen their learning by viewing explanations and supplementary information displayed on their device or AR glasses. They can refer to the displayed information and move on to the next question or object.

[1020] Specific examples

[1021] Example 1: Book description

[1022] 1. User:

[1023] The user scans a page of a book with their smartphone camera and says, "Tell me what this page is about."

[1024] 2. Terminal:

[1025] The image data and audio data of the page are sent to the server.

[1026] 3. Server:

[1027] It uses image recognition to analyze the pages of a book, converts voice data into text, and identifies the user's question. It then generates an explanatory text based on the content of the page.

[1028] 4. Server:

[1029] Sends explanatory text to the device.

[1030] 5. Terminal:

[1031] The device displays explanatory text, which the user reads to understand the content.

[1032] Example 2: Nature Observation

[1033] 1. User:

[1034] Go out into the field, scan a flower with your smartphone camera, and ask, "What kind of flower is this?"

[1035] 2. Terminal:

[1036] Image data and audio data of the flower are sent to the server.

[1037] 3. Server:

[1038] It uses image recognition to identify the type and characteristics of flowers, converts voice data into text, and analyzes user questions.

[1039] 4. Server:

[1040] Generate flower names and descriptions of their characteristics.

[1041] 5. Server:

[1042] Sends a description to the device.

[1043] 6. Terminal:

[1044] The device displays an AR-based explanation overlaid on the image of the flower, allowing the user to observe the flower while viewing the detailed explanation.

[1045] In this way, the present invention effectively combines digital technology with analog learning materials and natural experiences to provide a fun and hands-on learning environment.

[1046] The processing flow will be explained below.

[1047] Step 1:

[1048] User: Launches the application and sets camera and microphone permissions, so that image and audio data can be captured.

[1049] Step 2:

[1050] Device: Activate the camera and capture an analog learning material or an object in the natural environment specified by the user. For example, take a picture of a page in a book or a flower.

[1051] Step 3:

[1052] Device: Activate the microphone to capture the user's voice input, for example, to record a question such as "What is this page about?"

[1053] Step 4:

[1054] Device: Captured image and audio data is sent to the server. At this time, the user's ID is also sent, making it possible to provide individually tailored commentary.

[1055] Step 5:

[1056] Server: Analyzes the received image data using an image recognition algorithm to identify the object, for example, identify the type of flower from a captured image.

[1057] Step 6:

[1058] Server: Converts the received voice data into text using a speech recognition algorithm and analyzes the user's question. For example, converting a question like "What kind of flower is this?" into text.

[1059] Step 7:

[1060] Server: Based on the image and voice recognition results, it retrieves relevant explanatory text and supplementary information from the educational content database and generates explanatory content.

[1061] Step 8:

[1062] Server: Sends the generated commentary content to the device or display device, including not only the text information but also related images and information for AR display.

[1063] Step 9:

[1064] Terminal: Receives explanatory content sent from the server and displays it through a user interface. For example, the explanatory text is displayed overlaid on the pages of a book.

[1065] Step 10:

[1066] User: Check the received explanations and supplementary information to advance their learning. Furthermore, they can continue learning by pointing the camera at new questions or objects.

[1067] This series of processes allows users to interact with analog learning materials and natural environments and receive individually tailored commentary using digital technology, resulting in an effective and enjoyable learning experience.

[1068] Example 1

[1069] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1070] In today's world, learning methods that use analog learning materials and natural environments face the challenge of providing personalized explanations and supplementary information. Furthermore, there is a lack of systems that provide detailed explanations efficiently and in real time, which reduces learning efficiency.

[1071] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1072] In this invention, the server includes means for acquiring image data or audio data from analog learning materials or natural environments, means for transmitting the acquired image data and audio data to a central processing unit, means for analyzing the received image data and audio data and performing multimodal recognition of the object and question content, means for generating related explanations and supplemental information based on the recognition results, means for transmitting the generated explanations and supplemental information to a terminal or display device, and means for displaying the transmitted explanations and supplemental information, thereby providing each user with a personalized learning experience and improving learning efficiency.

[1073] "Analog learning materials" refers to learning materials that are not in digital format, such as paper or physical objects.

[1074] The "natural environment" refers to natural objects such as plants, animals, and terrain that exist outdoors or in nature.

[1075] "Image data" refers to the digital form of visual information captured by a camera or other photographic device.

[1076] "Audio data" refers to a recording of sound captured using a microphone or other device and converted into digital format.

[1077] "Means for acquiring" refers to the technology or method for capturing image data or audio data using a terminal or device.

[1078] "Central Processing Unit" refers to the computer system or server that receives, analyzes, and processes data.

[1079] "Means of transmission" refers to the technology or method for sending data to other devices or servers via a network.

[1080] "Analyzing" refers to the application of computational processes and algorithms to analyze acquired data and understand its meaning and content.

[1081] "Multimodal recognition" refers to a technology that integrates and analyzes multiple different data formats (images, audio, etc.) to extract meaning.

[1082] "Recognition result" refers to the analysis result obtained by multimodal recognition.

[1083] "Explanation and supplementary information" refers to detailed explanations and additional information about the subject matter.

[1084] "Terminal" refers to a display device used by a user, such as a smartphone or tablet.

[1085] "Display device" refers to hardware for visually presenting information to a user.

[1086] This invention is a system that acquires image data or audio data from analog learning materials or natural environments and provides individually tailored commentary using digital technology. Specific embodiments of this system are described in detail below.

[1087] Hardware and software used

[1088] server

[1089] The server is hardware for large-scale data processing and analysis, and specifically uses the following software:

[1090] Database management system: Stores user IDs, learning history, and personalized data. For example, MySQL or PostgreSQL is used.

[1091] Image recognition algorithms: Deep learning frameworks such as TensorFlow and PyTorch are used to analyze the transmitted image data and identify objects.

[1092] Speech recognition algorithms: Use cloud-based speech recognition services such as Google Speech-to-Text or IBM Watson to convert the audio data into text.

[1093] Natural Language Generation (NLG) model: Using generative AI models such as OpenAI GPT-3, explanatory text is automatically generated based on the analysis results.

[1094] Device (smartphone / tablet)

[1095] The terminal is a device that allows users to scan analog learning materials and the natural environment, acquire and display information, and utilizes the following specific software:

[1096] Camera application: Provides an interface for users to capture image data.

[1097] Voice input applications: Provide users with the ability to input and capture voice data.

[1098] Data sending and receiving module: Sends and receives data to and from the server using HTTP or WebSocket protocols.

[1099] AR technology: Augmented reality (AR) technology will be used to display received commentary and supplementary information in real time, specifically ARKit (iOS) and ARCore (Android).

[1100] Specific examples

[1101] Example 1: Book description

[1102] 1. The user scans a page of a book with their smartphone camera and says, "Tell me what this page is about."

[1103] 2. The device sends the image data and audio data of the page to the server.

[1104] 3. The server analyzes the page using image recognition, converts the voice data into text, and identifies the question. It then generates an explanation based on the content of the page.

[1105] 4. The server sends the generated explanatory text to the device.

[1106] 5. The device displays explanatory text, and the user reads it to understand the content.

[1107] Example 2: Nature Observation

[1108] 1. A user goes out into the field, scans a flower with their smartphone camera, and asks, "What kind of flower is this?"

[1109] 2. The device sends the flower image data and audio data to the server.

[1110] 3. The server performs image recognition to identify the type and characteristics of the flower, converts the voice data into text, and analyzes the user's question.

[1111] 4. The server generates the name of the flower and a description of its characteristics.

[1112] 5. The server sends the generated commentary to the device.

[1113] 6. The device displays an AR explanation overlaid on the flower image, allowing the user to observe the flower while viewing the detailed explanation.

[1114] Prompt Sentence Examples

[1115] Example 1: Book description prompt

[1116] "Tell me what's on this page."

[1117] Example 2: Nature observation prompt

[1118] "What is this flower?"

[1119] As described above, the system for implementing the present invention provides users with a real-time and personalized learning experience, significantly improving learning efficiency.

[1120] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1121] Step 1:

[1122] Input: A user launches the camera application on their smartphone or tablet and captures image data (e.g., a page in a book or an image of a natural object).

[1123] Specific behavior:

[1124] The device uses the camera to capture an image of the object and stores the captured image data in memory. The user can then decide what to photograph by viewing the camera's preview screen.

[1125] Output: The captured image data is stored in the device's memory.

[1126] Step 2:

[1127] Input: A user uses a voice input application to type a question into a microphone as voice data (e.g., "What is this page about?").

[1128] Specific behavior:

[1129] The device captures voice data through the microphone and stores it in memory, and the user records their question using a voice input application.

[1130] Output: The captured audio data is stored in the device's memory.

[1131] Step 3:

[1132] Input: Image and audio data stored on the device. User ID information.

[1133] Specific behavior:

[1134] The device converts the captured image and audio data, along with the user ID, into JSON format and sends it to the server using HTTP or WebSocket protocol.

[1135] Output: Image data, audio data and user ID are sent to the server.

[1136] Step 4:

[1137] Input: Image data and audio data sent to the server, user ID.

[1138] Specific behavior:

[1139] The server applies image recognition algorithms to the received image data using TensorFlow or PyTorch, and performs speech recognition on the audio data using Google Speech-to-Text or similar to convert it into text.

[1140] Output: Image analysis results (e.g., identification of objects in the image) and textual questions.

[1141] Step 5:

[1142] Input: Image analysis results and textual questions.

[1143] Specific behavior:

[1144] The server generates explanatory text and supplementary information using a generative AI model (e.g., OpenAI GPT-3) based on the image analysis results and the textual question content. It also retrieves related information from an educational content database and integrates it as supplementary information.

[1145] Output: Generated explanatory text and supporting information.

[1146] Step 6:

[1147] Input: Generated explanation and additional information. User ID.

[1148] Specific behavior:

[1149] The server compiles the generated explanatory text and supplementary information into JSON format and sends it to the terminal using HTTP or WebSocket protocol.

[1150] Output: Explanatory text and additional information are sent to the terminal.

[1151] Step 7:

[1152] Input: Explanation and additional information sent from the server.

[1153] Specific behavior:

[1154] The device then uses AR technology to display the received commentary and supplementary information on the user interface. For example, the device uses ARKit or ARCore to overlay the commentary on the subject of the photo.

[1155] Output: Users can view explanatory text and supplementary information in real time.

[1156] (Application example 1)

[1157] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1158] Although there are existing systems that provide individually tailored explanations by utilizing data capture and analysis technology for analog learning materials and natural environments, there are no systems that can handle the dynamic and diverse products and environments found in physical stores. Therefore, there is a need to provide a system that can instantly obtain product information and features in physical stores and improve the user experience.

[1159] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1160] In this invention, the server includes means for capturing image data or audio data from analog teaching materials, a natural environment, or a brick-and-mortar store, means for transmitting the captured image data and audio data to the server, means for analyzing the received image data and audio data and performing multimodal recognition of the object and question content, means for generating related explanations and supplemental information based on the recognition results, means for transmitting the generated explanations and supplemental information to a terminal or display device, and means for displaying the transmitted explanations and supplemental information using augmented reality technology. This makes it possible to instantly provide product information and explanations in a brick-and-mortar store to users, significantly improving convenience and user experience.

[1161] "Analog teaching materials" refers to physical media such as printed books, notebooks, and posters.

[1162] "Natural environment" refers to outdoor scenery, plants, animals, and other elements of the natural world.

[1163] "Brick and Mortar Store" means a physical store for selling goods and services.

[1164] "Image data" refers to still image and video data captured by a camera or other photographic device.

[1165] "Audio Data" means audio data captured by a microphone or other recording device.

[1166] A "server" refers to a computer system that processes data and provides information via a network.

[1167] "Capturing means" refers to a method or device for capturing images or sounds, such as a camera or microphone.

[1168] "Transmitting means" refers to a method or apparatus for sending data over a network to another system or device.

[1169] "Multimodal recognition" refers to the technology of analyzing multiple sensory data (e.g., images and audio) to understand their meaning.

[1170] "Recognition results" refers to the information obtained from analyzed image and audio data.

[1171] "Explanation and supplementary information" refers to detailed explanations or additional information related to the subject matter.

[1172] "Display device" refers to a device for visually displaying information (e.g., smartphone, augmented reality glasses, etc.).

[1173] "Augmented reality technology" refers to technology that displays virtual information overlaid on the real-world environment.

[1174] In order to implement the present invention, the following hardware and software are used.

[1175] Hardware used

[1176] 1. Smartphone: For image capture and data transmission.

[1177] 2. Smart glasses: For displaying information using augmented reality technology (e.g., Google Glass, Vuzix)

[1178] 3. Server: For data analysis and information generation.

[1179] Software used

[1180] 1. Image recognition libraries: To analyze image data (e.g., Google Cloud Vision, Microsoft Azure Computer Vision).

[1181] 2. Speech recognition library: To convert voice data into text (e.g., Google Speech-to-Text, Azure Speech Services).

[1182] 3. Cloud platforms: for server hosting and data processing (e.g., AWS, Azure).

[1183] 4. Application development frameworks: For developing applications for smartphones and smart glasses (e.g., React Native, Flutter).

[1184] System Overview

[1185] The server analyzes the image data and audio data received from the user, recognizes the object, and analyzes the user's question. Based on the analysis results, it generates an explanation and supplementary information that is optimal for the user and sends it to the user's device or display device. The received explanation and supplementary information are displayed using augmented reality technology, allowing the user to refer to it directly.

[1186] Processing Description

[1187] 1. Server process:

[1188] The server uses a database that stores user-specific IDs, learning histories, and personalized data, in order to provide individual information to each user.

[1189] The server analyzes the received image data using an image recognition library such as Google Cloud Vision to identify the target object.

[1190] The server converts the received voice data into text using a voice recognition library such as Google Speech-to-Text and analyzes the user's question.

[1191] Based on these recognition results, the server uses a generative AI model to create relevant commentary and supplementary information.

[1192] 2. Terminal processing:

[1193] The user captures an object with their smartphone camera and asks a question aloud using a prompt such as, "Please write a detailed description of this product. The name of this product is XX."

[1194] The smartphone transmits the captured image data and audio data to a server.

[1195] Commentary and supplementary information sent from the server is received and displayed on the smartphone or smart glasses display.

[1196] Augmented reality technology is used to overlay commentary and supplementary information on the object.

[1197] Specific examples

[1198] Example 1: Use in a home appliance store

[1199] A user can scan a refrigerator in an appliance section and ask, "What are the features of this refrigerator?" The smart glasses will then overlay information such as rated capacity and energy efficiency on top of the refrigerator, allowing the user to instantly check the detailed information.

[1200] Prompt Sentence Examples

[1201] "Please write a detailed description of this product. The product name is a 4-door inverter refrigerator."

[1202] This makes it possible to provide users with product information from physical stores quickly and accurately, improving the user experience.

[1203] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1204] Step 1:

[1205] A user scans a product with smart glasses. The input is the product image, and the output is the captured image data. The user looks at the product through the smart glasses, and the camera on the glasses captures the product image.

[1206] Step 2:

[1207] The terminal sends the captured image data to the server. The input is the captured image data, and the output is the data sent to the server. The smart glasses send the image data to the server via wireless communication.

[1208] Step 3:

[1209] The server uses an image recognition algorithm to analyze the received image data. The input is the received image data, and the output is the recognition result (e.g., product name, model number). The server identifies the object using an image recognition library such as Google Cloud Vision. The product name and model number are obtained as the analysis result.

[1210] Step 4:

[1211] The user asks a question about a product by voice. The input is the user's voice data, and the output is the captured voice data. The user speaks to the smart glasses and asks, "Tell me about the features of this product."

[1212] Step 5:

[1213] The terminal sends the captured voice data to the server. The input is the captured voice data, and the output is the data sent to the server. The smart glasses send the voice data to the server via wireless communication.

[1214] Step 6:

[1215] The server uses a speech recognition algorithm to convert the voice data into text. The input is the received voice data, and the output is text data (the user's question). The server then converts the voice data into text using a speech recognition library such as Google Speech-to-Text and analyzes the user's question.

[1216] Step 7:

[1217] The server generates explanations and supplementary information based on the text data and image recognition results. The input is text data and image recognition results, and the output is the generated explanations and supplementary information. The server uses a generative AI model to generate relevant explanations and information based on the recognition results and the user's question.

[1218] Step 8:

[1219] The server sends the generated commentary and supplementary information to the device. The input is the generated commentary and supplementary information, and the output is the data sent to the device. The server sends the commentary and supplementary information to the smart glasses.

[1220] Step 9:

[1221] The device displays the explanation and supplementary information using augmented reality technology. The input is the received explanation and supplementary information, and the output is the augmented reality information displayed to the user. The smart glasses display the received explanation and supplementary information, providing the user with detailed information about the product.

[1222] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1223] As an embodiment of the present invention, a system that acquires image data or audio data from analog learning materials or natural environments and provides individually tailored commentary using digital technology will be specifically described. Furthermore, a form incorporating an emotion recognition engine that recognizes the user's emotions and provides personalized information based on those emotions will be described.

[1224] Server Processing

[1225] 1. Initial Setup:

[1226] The server initializes a database that stores a user's unique ID and associated learning history, personalization data, and emotion recognition data, enabling personalized information delivery based on emotions.

[1227] 2. Data reception:

[1228] The server receives image data, voice data, and emotion data sent from the device or AR glasses. The received data is managed together with the user ID.

[1229] 3. Multimodal Recognition:

[1230] The server runs image and voice recognition algorithms on the received data to identify the object and convert the voice content into text. For example, it can identify the type of flower from a received image and analyze the user's question from the voice.

[1231] 4. Emotion recognition:

[1232] The server analyzes the received data and uses an emotion recognition engine to identify the user's emotional state, for example by analyzing facial expressions and tone of voice when the user captures the image.

[1233] 5. Content Generation:

[1234] The server generates relevant commentary and supplemental information based on the image, voice, and emotion recognition results. This information is personalized according to the user's emotional state. For example, if the user is in a difficult emotional state, a more detailed commentary is generated.

[1235] 6. Data Transmission:

[1236] The server then transmits the generated commentary content to the device or display device. The transmitted data includes not only the text information but also related images and information for AR display.

[1237] Processing of devices (smartphones and tablets)

[1238] 1. User Interface:

[1239] The device provides an interface for users to use the camera to point it at analog learning materials or natural environments. For example, the user can activate the camera through an application and display a screen where they can check the subject being photographed.

[1240] 2. Data capture:

[1241] The device captures image data, voice data, and emotion data from a camera and microphone. For example, a user can take a picture of a page in a book or a flower with the camera and input a question by voice.

[1242] 3. Data transmission:

[1243] The device sends the captured data to a server, which also includes the user's ID and emotional data, allowing for personalized information to be provided.

[1244] 4. Data reception:

[1245] The terminal receives commentary and supplementary information sent from the server, and the received data is displayed in real time.

[1246] 5.Display:

[1247] The device then uses AR technology to present the received information to the user, for example by overlaying a description onto a specific book page or by displaying related information on objects in the natural environment.

[1248] User Behavior

[1249] 1. Start learning:

[1250] Users use a device or AR glasses to access the analog learning materials and natural environments they want to learn from.

[1251] 2. Inquiries:

[1252] The user holds the camera over the object they want to inquire about and asks a question by voice, for example, "What kind of flower is this?"

[1253] 3. Receiving information:

[1254] Users can deepen their learning by viewing explanations and supplementary information displayed on their device or AR glasses. They can refer to the displayed information and move on to the next question or object.

[1255] Specific examples

[1256] Example 1: Book description

[1257] 1. User: Scan a page of a book with the smartphone camera. Say, "Tell me what's on this page."

[1258] 2. Terminal: Sends the image data, voice data, and facial expression data of the page to the server.

[1259] 3. Server: Analyzes the book pages using image recognition, converts voice data into text, and identifies the user's question. Recognizes emotions based on facial expression data.

[1260] 4. Server: Based on the content of the page, generate an explanatory text that matches the user's emotional state. For example, if the user has a troubled expression, provide a detailed explanation.

[1261] 5. Server: Sends explanatory text to the device.

[1262] 6. Terminal: The terminal displays explanatory text, which the user reads to understand the content.

[1263] Example 2: Nature observation

[1264] 1. User: Go out into the field and scan a flower with your smartphone camera. Ask, "What flower is this?"

[1265] 2. Terminal: Sends flower image data, audio data, and tone of voice data to the server.

[1266] 3. Server: Performs image recognition to identify the type and characteristics of flowers. Converts voice data into text and performs emotion recognition based on the tone of voice.

[1267] 4. Server: Generates a description based on the flower's name, characteristics, and user's emotions.

[1268] 5. Server: Sends the commentary to the device.

[1269] 6. Device: The device displays an AR explanation overlaid on the image of the flower. The user can observe the flower while looking at the detailed explanation.

[1270] In this way, the present invention effectively combines digital technology with analog learning materials and natural experiences to provide a fun and hands-on learning environment. Furthermore, the use of an emotion recognition engine enables personalization based on the user's emotional state, resulting in a more effective and personalized learning experience.

[1271] The processing flow will be explained below.

[1272] Step 1:

[1273] User: Launches the application and sets camera and microphone permissions, ready to capture image and audio data.

[1274] Step 2:

[1275] Device: Activate the camera and capture an analog learning material or an object in the natural environment specified by the user. For example, take a picture of a page in a book or a flower.

[1276] Step 3:

[1277] Device: Activate the microphone to capture the user's voice input, for example, to record a question such as "What is this page about?"

[1278] Step 4:

[1279] Device: The device captures the user's facial expression with a camera and simultaneously captures emotional data. For example, it records image data to analyze whether the user's facial expression is troubled.

[1280] Step 5:

[1281] Device: Captured image data, audio data, and emotional data are sent to the server. This data also includes the user ID, enabling personalized commentary.

[1282] Step 6:

[1283] Server: Analyzes the received image data using an image recognition algorithm to identify the object, for example, identify the type of flower from a captured image.

[1284] Step 7:

[1285] Server: Converts the received voice data into text using a speech recognition algorithm and analyzes the user's question. For example, converting a question like "What kind of flower is this?" into text.

[1286] Step 8:

[1287] Server: Uses an emotion recognition engine to identify the user's emotional state from the received data. For example, it analyzes whether the user is distressed, interested, confused, etc.

[1288] Step 9:

[1289] Server: Generates relevant explanatory text and supplementary information based on the image, voice, and emotion recognition results. For example, it generates information such as "This flower is a cherry blossom and blooms in spring."

[1290] Step 10:

[1291] Server: Personalize the generated explanatory content based on the user's emotional state. For example, include more detailed explanations or additional illustrations if the user is struggling.

[1292] Step 11:

[1293] Server: Sends personalized commentary content to the device or display device. The transmitted data includes not only text information but also related images and information for AR display.

[1294] Step 12:

[1295] Terminal: Receives explanatory content sent from the server and displays it through a user interface. For example, the explanatory text is displayed overlaid on the pages of a book.

[1296] Step 13:

[1297] User: Check the received explanations and supplementary information to advance their learning. Furthermore, they can continue learning by pointing the camera at new questions or objects.

[1298] This process allows users to receive personalized instruction through analog learning materials and natural environments, and then use digital technology to effectively learn. Furthermore, by utilizing an emotion recognition engine, a more personalized learning experience is provided based on the user's emotional state.

[1299] Example 2

[1300] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1301] Conventional learning methods using analog learning materials or natural environments provide uniform information, lacking in personalization tailored to each user's emotional state and learning progress. As a result, users may lack understanding or lose motivation to learn. Furthermore, even if image and audio data are captured, there is a lack of technology to effectively analyze that data and provide explanatory information tailored to the user's needs. There is a need to solve these issues.

[1302] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1303] In this invention, the server includes means for capturing image data or audio data from analog learning materials or natural environments, means for transmitting the captured image data and audio data to the server, means for analyzing the received image data and audio data and performing multimodal recognition of the object and question content, means for recognizing the user's emotional state and generating personalized commentary and supplemental information based on the emotion, means for transmitting the generated commentary and supplemental information to a terminal or display device, and means for displaying the transmitted commentary and supplemental information, thereby enabling the provision of detailed commentary information tailored to the user's emotional state and learning needs.

[1304] "Analog teaching materials" are educational materials that use paper media or physical objects.

[1305] The "natural environment" refers to the natural elements and ecosystems that exist outdoors.

[1306] "Image data" is visual information captured by a camera or other photographic device.

[1307] "Audio Data" means audio information captured by a microphone or other recording device.

[1308] A "capturing means" is a device or equipment for acquiring image data and audio data.

[1309] The "transmitting means" is a communication means for transmitting the acquired data to the server.

[1310] The "analyzing means" refers to the technology or algorithm for analyzing the received image data and audio data and extracting the necessary information.

[1311] "Multimodal recognition" is a technology that combines image data and audio data to analyze information and identify the target object or question.

[1312] The "means for generating personalized commentary and supplementary information" is a technology for creating personalized information according to the individual characteristics and emotional state of the user.

[1313] The "transmitting means" is a communication means for transmitting the generated commentary and supplementary information to a terminal or a display device.

[1314] The "display means" refers to a technique or device for visually presenting the transmitted commentary or supplemental information to the user.

[1315] "Emotional state" refers to a psychological state that can be inferred from a user's facial expression, tone of voice, and other behavior.

[1316] This system acquires image or audio data from analog learning materials or natural environments and uses digital technology to provide individually tailored commentary. It also incorporates an emotion recognition engine that recognizes the user's emotions and provides personalized information based on those emotions. This system operates among three parties: a server, a terminal, and the user.

[1317] Server Processing

[1318] 1. Initial Setup:

[1319] The server initializes the database. Specifically, it creates a table that manages each user's unique ID, learning history, personalized data, and emotion recognition data. This allows it to store learning data for each user and provide personalized information based on their emotions.

[1320] 2. Data reception:

[1321] The server receives image data, voice data, and emotion data sent from the device. The received data is managed by checking it against the user ID. For example, this data can be received using a REST API.

[1322] 3. Multimodal Recognition:

[1323] The server performs the following processing on the received data: it uses an image recognition algorithm (e.g., TensorFlow) to identify the object, and a speech recognition algorithm (e.g., Google Cloud Speech-to-Text API) to convert the speech into text, which allows it to analyze the user's question.

[1324] 4. Emotion recognition:

[1325] The server uses an emotion recognition engine (e.g., Microsoft Azure Emotion API) to identify the user's emotional state based on the received data. For example, it analyzes the user's facial expressions and tone of voice when capturing an image to infer the user's mental state.

[1326] 5. Content Generation:

[1327] The server generates relevant commentary and supplemental information based on the image, voice, and emotion recognition results. This allows for personalized information to be provided according to the user's emotional state. For example, if the user is having trouble, the server can generate detailed explanations to help the user progress smoothly through the learning process.

[1328] 6. Data Transmission:

[1329] The server then sends the generated commentary content to the device, which includes not only text information but also related images and information for AR display.

[1330] Processing of devices (smartphones and tablets)

[1331] 1. User Interface:

[1332] The device provides an interface for pointing the camera at analog learning materials or natural environments. This is implemented as an application, and the user can check the object being scanned through the camera preview.

[1333] 2. Data capture:

[1334] The device captures image data, voice data, and emotion data from a camera and microphone. For example, data is acquired when a user takes a picture of a particular flower with a camera and inputs a question by voice.

[1335] 3. Data transmission:

[1336] The device then sends the captured data, including the user ID and emotional data, to the server, where accurate personalization is performed.

[1337] 4. Data reception:

[1338] The terminal receives the commentary and supplementary information sent from the server, and the received data is displayed on the terminal's display in real time.

[1339] 5.Display:

[1340] The device then uses AR technology to present the received information to the user, for example by overlaying explanations on specific book pages to provide visual support for the user's learning.

[1341] User Behavior

[1342] Users use a device or AR glasses to access the analog learning materials or natural environment they want to learn from. They point the camera at the object they want to inquire about and ask a question by voice, for example, "What kind of flower is this?" Explanations and supplementary information are displayed on the device in real time, allowing users to view them and deepen their learning.

[1343] Specific examples

[1344] Example 1: Book description

[1345] 1. User: Scans a page of a book with the smartphone camera and says, "Tell me what this page is about."

[1346] 2. Terminal: Sends the page's image data, voice data, and emotion data to the server.

[1347] 3. Server: Analyzes the book pages using image recognition, converts voice data into text, and identifies the user's question. Recognizes emotions based on facial expression data.

[1348] 4. Server: Based on the content of the page, generate an explanatory text that matches the user's emotional state. For example, if the user has a troubled expression, provide a detailed explanation.

[1349] 5. Server: Sends explanatory text to the device.

[1350] 6. Terminal: The terminal displays explanatory text, which the user reads to understand the content.

[1351] Example 2: Nature observation

[1352] 1. User: Go out into the field and scan a flower with your smartphone camera. Ask, "What flower is this?"

[1353] 2. Terminal: Sends flower image data, audio data, and tone of voice data to the server.

[1354] 3. Server: Performs image recognition to identify the type and characteristics of flowers. Converts voice data into text and performs emotion recognition based on the tone of voice.

[1355] 4. Server: Generates a description based on the flower's name, characteristics, and user's emotions.

[1356] 5. Server: Sends the commentary to the device.

[1357] 6. Device: The device displays an AR explanation overlaid on the image of the flower. The user can observe the flower while looking at the detailed explanation.

[1358] In this way, the present invention is a system that effectively combines digital technology with analog learning materials and natural experiences to support user learning. Furthermore, the use of an emotion recognition engine enables personalization according to the user's emotional state, resulting in a more effective and individualized learning experience.

[1359] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1360] Server Processing

[1361] Step 1: Initial Setup

[1362] The server initializes the database. Specifically, it creates tables to store the user's unique ID, learning history, personalization data, and emotion recognition data. The input to this step is a specific table schema, and the output is an initialized database. For example, the tables are created by executing SQL queries.

[1363] Step 2: Receiving data

[1364] The server receives image data, audio data, and emotion data sent from the device. The input of this step is the data payload from the device, and the output is the raw data stored in the server. Specifically, it receives an HTTP POST request and saves the data in an appropriate folder or database.

[1365] Step 3: Multimodal Recognition

[1366] The server analyzes the received image data and voice data and performs multimodal recognition of the object and the question. The input for this step is image data and voice data, and the output is the recognized object and the question converted into text. Specifically, an image recognition algorithm is used to identify the type of flower, and a voice recognition algorithm is used to convert the user's question into text.

[1367] Step 4: Emotion Recognition

[1368] The server runs an emotion recognition engine based on the received data to identify the user's emotional state. The input for this step is a variety of data sets, including image data and audio data, and the output is the identified emotional state. Specific operations include facial expression recognition algorithms and tone of voice analysis.

[1369] Step 5: Content Generation

[1370] The server generates relevant commentary and supplemental information based on the image, voice, and emotion recognition results. The input to this step is the recognition results from the previous step, and the output is the generated commentary and supplemental information. For example, if the user is in a difficult emotional state, the server runs an algorithm to generate a more detailed commentary.

[1371] Step 6: Send data

[1372] The server sends the generated commentary content to the terminal. The input of this step is the generated commentary content, and the output is the status of completion of transmission. Specifically, the commentary and supplementary information are sent to the terminal using an HTTP POST request.

[1373] Processing of devices (smartphones and tablets)

[1374] Step 1: User Interface

[1375] The device provides an interface for pointing the camera at analog learning materials or natural environments. The input for this step is user operation, and the output is the display of the camera preview. Specifically, the camera preview of the application is launched.

[1376] Step 2: Data Capture

[1377] The device captures image data, audio data, and emotion data from the camera and microphone. The input of this step is physical objects and audio, and the output is digitized data. Specifically, images are Base64 encoded and audio is recorded.

[1378] Step 3: Send data

[1379] The device sends the captured data to the server. The input of this step is the captured data, and the output is the status of the completion of the transmission. Specifically, an HTTP POST request is created and sent.

[1380] Step 4: Receiving Data

[1381] The device receives the explanation and supplementary information sent from the server. The input of this step is the data from the server, and the output is the received explanation and supplementary information. Specifically, the data is obtained using an HTTP GET request.

[1382] Step 5: Display

[1383] The device then uses AR technology to present the received information to the user. The input for this step is the received explanatory information, and the output is the explanatory information displayed on the screen. Specifically, the explanatory information is displayed overlaid on a specific book page or natural object.

[1384] User Behavior

[1385] Step 1: Start learning

[1386] The user uses a device or AR glasses to access the analog learning materials or natural environment they want to learn from. The input of this step is the user's intention, and the output is the launch of an app. For example, launching a learning app and preparing the camera.

[1387] Step 2: Inquiry

[1388] The user points the camera at the object they want to inquire about and asks the question by voice. The input for this step is the object and the voice question, and the output is the captured data. For example, they might ask, "What is this flower?"

[1389] Step 3: Receiving information

[1390] The user can view explanations and supplementary information displayed on the device or AR glasses to further their learning. The input for this step is the information received from the server, and the output is the user's understanding. The user can then proceed to the next question or object.

[1391] (Application example 2)

[1392] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1393] Current factory robots struggle to provide advanced analytical functions or interactive assistance to improve the accuracy and efficiency of quality checks when inspecting or manipulating products. They also struggle to recognize the user's emotional state and provide information based on that. Even when an operator is confused, it is rare for them to provide appropriate support promptly. This results in issues such as reduced efficiency and increased human error.

[1394] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing image data or audio data, means for transmitting the captured data to the server, means for analyzing the received data and performing multimodal recognition of the object and the question content, means for generating personalized related explanations and supplemental information based on the recognition results and the user's emotional state, means for transmitting the generated explanations and supplemental information to a terminal or display device, and means for displaying the transmitted explanations and supplemental information. This enables the factory robot to provide appropriate support for product inspection and operation while taking the user's emotional state into consideration.

[1395] "Image data" is visual information captured using a camera or other imaging device.

[1396] "Audio Data" is a recording of sound collected using a microphone or other sound capture device.

[1397] "Capture" is the process of capturing information using a particular device.

[1398] A "server" is a computer system that provides a service to a group of other computers on a network.

[1399] "Transmission" is the process of moving data from one point to another.

[1400] "Analysis" is the process of understanding the type and structure of data and extracting its meaning and value.

[1401] "Multimodal recognition" is a technology that integrates and analyzes multiple input formats (images, audio, text, etc.).

[1402] "Related explanations and supplementary information" is explanatory text or additional information based on the recognized data.

[1403] "Terminal" means a computing device with input and output devices that can be directly operated by a user.

[1404] "Display" is the process of visually presenting acquired information to the user.

[1405] An "emotional state" is the state of emotions or feelings a user has at a given time.

[1406] A "generative AI model" is a model trained using machine learning algorithms that has the ability to generate content based on new data.

[1407] A "prompt" is a sentence that formats and inputs a specific question or command.

[1408] "Personalization" is the process of customizing something to suit the characteristics and circumstances of each individual user.

[1409] The present invention relates to a smart assistant system for factory robots, and a specific embodiment of the system will be described herein.

[1410] Server Processing

[1411] The server first receives image data and audio data. This data was acquired by factory robots using cameras, and each robot is assigned an individual user ID. The received data is managed in association with that user ID. The server then analyzes this data using the following methods to generate content.

[1412] Hardware and Software:

[1413] Hardware: Servers and cloud computing infrastructure

[1414] Software: OpenCV (image recognition), SpeechRecognition (voice recognition), Affectiva (emotion recognition), TensorFlow (machine learning), Flask (server-side)

[1415] The server uses an image recognition algorithm to analyze the received image data and identify the type and condition of the object, and a voice recognition algorithm to convert the voice data into text and extract the user's question.

[1416] Furthermore, an emotion recognition engine is used to identify the user's emotional state. For example, if an operator is confused, the emotional state is determined by analyzing facial image data and voice tone. Based on this emotional data, relevant commentary and supplementary information are generated in a personalized manner.

[1417] The information generated is sent to factory robots in real time, enabling them to provide appropriate feedback and assistance to operators.

[1418] Terminal (factory robot) processing

[1419] Factory robots are equipped with cameras and microphones and are used to inspect parts and products. A user (operator) uses the robot's camera to scan a specific part or product and then voice-inputs questions. The robot then sends this data to a server.

[1420] The received personalized information is then displayed on the robot's display. For example, if a factory robot is inspecting a part, the robot will scan the part and check for quality issues. If the operator is confused, the robot can provide a detailed explanation and explain next steps if an issue is found.

[1421] User Behavior

[1422] The user (operator) uses a factory robot to take pictures of parts or products and input quality-related questions by voice. For example, the user might ask, "Please tell me the condition of this part." The robot then uses its camera and microphone to capture the data and sends it to the server. The robot then receives feedback from the server and provides detailed explanations and instructions. This process allows the operator to efficiently perform quality checks.

[1423] Examples of concrete examples and prompts

[1424] As a concrete example, the following scenario can be considered.

[1425] Scene: A robot inspects parts on a factory assembly line.

[1426] Robot: Scans parts and sends quality check messages to operators.

[1427] Operator: There seems to be something wrong with the part and I'm confused (troubled expression).

[1428] System: The robot analyzes the operator's facial expressions and provides detailed instructions and next steps.

[1429] Example prompt sentence:

[1430] Keyword prompts: "Part image," "Audio question," "Confused expression," "Detailed explanation"

[1431] Prompt statement:

[1432] "I'm currently operating a robot. I'm concerned about the quality of the part. What's the problem with this part?"

[1433] "The operator is having trouble. Please check the details of the part."

[1434] As described above, the present invention enables a factory robot to provide assistance based on the user's emotional state, thereby improving efficiency and reducing human error.

[1435] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1436] Step 1:

[1437] The user operates the factory robot, scans the parts or products to be inspected with a camera, and inputs voice questions through a microphone. The input includes image data and voice data of the parts or products. For example, the user may ask a specific question such as, "Please tell me the condition of this part."

[1438] Step 2:

[1439] The terminal (factory robot) captures image data and audio data using a camera and microphone. This captured data is sent to the server along with the user ID. The input includes image data, audio data, and the user ID. The terminal sends this all together to the server.

[1440] Step 3:

[1441] The server analyzes the image data and audio data received from the device. The server first uses an image recognition algorithm (using OpenCV or TensorFlow) to identify the type and state of the object from the image data. Next, it uses a voice recognition algorithm (using SpeechRecognition) to convert the audio data into text. The server then analyzes the content of the question and extracts it as text data. The input includes image data and audio data, and the output generates the result of identifying the object and text data.

[1442] Step 4:

[1443] The server uses an emotion recognition engine (powered by Affectiva) to analyze the user's emotional state from the received image data and voice tone data. For example, it detects the operator's confused facial expression and tone. The input includes image data and voice tone data, and the output generates emotion data.

[1444] Step 5:

[1445] The server uses a generative AI model to personalize relevant commentary and supplemental information based on image, voice, and emotion recognition results. For example, if the user is confused, a more detailed commentary can be generated. This process involves generating appropriate prompts, based on which the AI ​​model generates content. Inputs include image, voice, and emotion recognition results, and the output is personalized commentary and supplemental information.

[1446] Step 6:

[1447] The server transmits the generated commentary and supplementary information to the terminal (factory robot). The input includes the generated commentary and supplementary information data, and the output becomes the transmitted data.

[1448] Step 7:

[1449] The terminal (factory robot) receives the explanation and supplementary information sent from the server and displays it to the user. For example, a detailed explanation and the next steps are displayed on the robot's display. The input includes the sent explanation and supplementary information, and the output is displayed to the user. The user can use this information to check the quality or carry out the next task.

[1450] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1451] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1452] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1453] [Fourth embodiment]

[1454] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1455] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1456] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1457] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1458] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1459] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1460] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1461] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1462] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1463] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1464] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1465] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1466] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1467] As an embodiment of the present invention, a system will be specifically described that acquires image data or audio data from analog teaching materials or natural environments and provides individually tailored commentary using digital technology.

[1468] Server Processing

[1469] 1. Initial Setup:

[1470] The server initializes a database that stores the user's unique ID and associated learning history and personalized data, enabling the provision of personalized information.

[1471] 2. Data reception:

[1472] The server receives image data and audio data sent from the device or AR glasses. The received data is managed together with the user ID.

[1473] 3. Multimodal Recognition:

[1474] The server runs image and voice recognition algorithms on the received data to identify the object and convert the voice content into text. For example, it can identify the type of flower from a received image and analyze the user's question from the voice.

[1475] 4. Content Generation:

[1476] The server generates relevant explanatory text and supplementary information based on the recognition results, including information retrieved from a pre-prepared educational content database. For example, it generates explanatory text about the identified flower.

[1477] 5. Data Transmission:

[1478] The server then sends the generated commentary and supplementary information to the device or AR glasses in a format that is easy for the user to understand.

[1479] Processing of devices (smartphones and tablets)

[1480] 1. User Interface:

[1481] The device provides an interface for users to use the camera to point it at analog learning materials or natural environments. For example, the user can activate the camera through an application and display a screen where they can check the subject being photographed.

[1482] 2. Data capture:

[1483] The device captures image data and audio data from a camera and microphone. For example, a user can take a picture of a page in a book or a flower with the camera and input a question by voice.

[1484] 3. Data transmission:

[1485] The device sends the captured data to a server, which also includes the user ID, allowing for personalized information to be provided.

[1486] 4. Data reception:

[1487] The terminal receives commentary and supplementary information sent from the server, and the received data is displayed in real time.

[1488] 5.Display:

[1489] The device then uses AR technology to present the received information to the user, for example by overlaying a description onto a specific book page or displaying related information on objects in the natural environment.

[1490] User Behavior

[1491] 1. Start learning:

[1492] Users use a device or AR glasses to access the analog learning materials and natural environments they want to learn from.

[1493] 2. Inquiries:

[1494] The user holds the camera over the object they want to inquire about and asks a question by voice, for example, "What kind of flower is this?"

[1495] 3. Receiving information:

[1496] Users can deepen their learning by viewing explanations and supplementary information displayed on their device or AR glasses. They can refer to the displayed information and move on to the next question or object.

[1497] Specific examples

[1498] Example 1: Book description

[1499] 1. User:

[1500] The user scans a page of a book with their smartphone camera and says, "Tell me what this page is about."

[1501] 2. Terminal:

[1502] The image data and audio data of the page are sent to the server.

[1503] 3. Server:

[1504] It uses image recognition to analyze the pages of a book, converts voice data into text, and identifies the user's question. It then generates an explanatory text based on the content of the page.

[1505] 4. Server:

[1506] Sends explanatory text to the device.

[1507] 5. Terminal:

[1508] The device displays explanatory text, which the user reads to understand the content.

[1509] Example 2: Nature Observation

[1510] 1. User:

[1511] Go out into the field, scan a flower with your smartphone camera, and ask, "What kind of flower is this?"

[1512] 2. Terminal:

[1513] Image data and audio data of the flower are sent to the server.

[1514] 3. Server:

[1515] It uses image recognition to identify the type and characteristics of flowers, converts voice data into text, and analyzes user questions.

[1516] 4. Server:

[1517] Generate flower names and descriptions of their characteristics.

[1518] 5. Server:

[1519] Sends a description to the device.

[1520] 6. Terminal:

[1521] The device displays an AR-based explanation overlaid on the image of the flower, allowing the user to observe the flower while viewing the detailed explanation.

[1522] In this way, the present invention effectively combines digital technology with analog learning materials and natural experiences to provide a fun and hands-on learning environment.

[1523] The processing flow will be explained below.

[1524] Step 1:

[1525] User: Launches the application and sets camera and microphone permissions, so that image and audio data can be captured.

[1526] Step 2:

[1527] Device: Activate the camera and capture an analog learning material or an object in the natural environment specified by the user. For example, take a picture of a page in a book or a flower.

[1528] Step 3:

[1529] Device: Activate the microphone to capture the user's voice input, for example, to record a question such as "What is this page about?"

[1530] Step 4:

[1531] Device: Captured image and audio data is sent to the server. At this time, the user's ID is also sent, making it possible to provide individually tailored commentary.

[1532] Step 5:

[1533] Server: Analyzes the received image data using an image recognition algorithm to identify the object, for example, identify the type of flower from a captured image.

[1534] Step 6:

[1535] Server: Converts the received voice data into text using a speech recognition algorithm and analyzes the user's question. For example, converting a question like "What kind of flower is this?" into text.

[1536] Step 7:

[1537] Server: Based on the image and voice recognition results, it retrieves relevant explanatory text and supplementary information from the educational content database and generates explanatory content.

[1538] Step 8:

[1539] Server: Sends the generated commentary content to the device or display device, including not only the text information but also related images and information for AR display.

[1540] Step 9:

[1541] Terminal: Receives explanatory content sent from the server and displays it through a user interface. For example, the explanatory text is displayed overlaid on the pages of a book.

[1542] Step 10:

[1543] User: Check the received explanations and supplementary information to advance their learning. Furthermore, they can continue learning by pointing the camera at new questions or objects.

[1544] This series of processes allows users to interact with analog learning materials and natural environments and receive individually tailored commentary using digital technology, resulting in an effective and enjoyable learning experience.

[1545] Example 1

[1546] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1547] In today's world, learning methods that use analog learning materials and natural environments face the challenge of providing personalized explanations and supplementary information. Furthermore, there is a lack of systems that provide detailed explanations efficiently and in real time, which reduces learning efficiency.

[1548] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1549] In this invention, the server includes means for acquiring image data or audio data from analog learning materials or natural environments, means for transmitting the acquired image data and audio data to a central processing unit, means for analyzing the received image data and audio data and performing multimodal recognition of the object and question content, means for generating related explanations and supplemental information based on the recognition results, means for transmitting the generated explanations and supplemental information to a terminal or display device, and means for displaying the transmitted explanations and supplemental information, thereby providing each user with a personalized learning experience and improving learning efficiency.

[1550] "Analog learning materials" refers to learning materials that are not in digital format, such as paper or physical objects.

[1551] The "natural environment" refers to natural objects such as plants, animals, and terrain that exist outdoors or in nature.

[1552] "Image data" refers to the digital form of visual information captured by a camera or other photographic device.

[1553] "Audio data" refers to a recording of sound captured using a microphone or other device and converted into digital format.

[1554] "Means for acquiring" refers to the technology or method for capturing image data or audio data using a terminal or device.

[1555] "Central Processing Unit" refers to the computer system or server that receives, analyzes, and processes data.

[1556] "Means of transmission" refers to the technology or method for sending data to other devices or servers via a network.

[1557] "Analyzing" refers to the application of computational processes and algorithms to analyze acquired data and understand its meaning and content.

[1558] "Multimodal recognition" refers to a technology that integrates and analyzes multiple different data formats (images, audio, etc.) to extract meaning.

[1559] "Recognition result" refers to the analysis result obtained by multimodal recognition.

[1560] "Explanation and supplementary information" refers to detailed explanations and additional information about the subject matter.

[1561] "Terminal" refers to a display device used by a user, such as a smartphone or tablet.

[1562] "Display device" refers to hardware for visually presenting information to a user.

[1563] This invention is a system that acquires image data or audio data from analog learning materials or natural environments and provides individually tailored commentary using digital technology. Specific embodiments of this system are described in detail below.

[1564] Hardware and software used

[1565] server

[1566] The server is hardware for large-scale data processing and analysis, and specifically uses the following software:

[1567] Database management system: Stores user IDs, learning history, and personalized data. For example, MySQL or PostgreSQL is used.

[1568] Image recognition algorithms: Deep learning frameworks such as TensorFlow and PyTorch are used to analyze the transmitted image data and identify objects.

[1569] Speech recognition algorithms: Use cloud-based speech recognition services such as Google Speech-to-Text or IBM Watson to convert the audio data into text.

[1570] Natural Language Generation (NLG) model: Using generative AI models such as OpenAI GPT-3, explanatory text is automatically generated based on the analysis results.

[1571] Device (smartphone / tablet)

[1572] The terminal is a device that allows users to scan analog learning materials and the natural environment, acquire and display information, and utilizes the following specific software:

[1573] Camera application: Provides an interface for users to capture image data.

[1574] Voice input applications: Provide users with the ability to input and capture voice data.

[1575] Data sending and receiving module: Sends and receives data to and from the server using HTTP or WebSocket protocols.

[1576] AR technology: Augmented reality (AR) technology will be used to display received commentary and supplementary information in real time, specifically ARKit (iOS) and ARCore (Android).

[1577] Specific examples

[1578] Example 1: Book description

[1579] 1. The user scans a page of a book with their smartphone camera and says, "Tell me what this page is about."

[1580] 2. The device sends the image data and audio data of the page to the server.

[1581] 3. The server analyzes the page using image recognition, converts the voice data into text, and identifies the question. It then generates an explanation based on the content of the page.

[1582] 4. The server sends the generated explanatory text to the device.

[1583] 5. The device displays explanatory text, and the user reads it to understand the content.

[1584] Example 2: Nature Observation

[1585] 1. A user goes out into the field, scans a flower with their smartphone camera, and asks, "What kind of flower is this?"

[1586] 2. The device sends the flower image data and audio data to the server.

[1587] 3. The server performs image recognition to identify the type and characteristics of the flower, converts the voice data into text, and analyzes the user's question.

[1588] 4. The server generates the name of the flower and a description of its characteristics.

[1589] 5. The server sends the generated commentary to the device.

[1590] 6. The device displays an AR explanation overlaid on the flower image, allowing the user to observe the flower while viewing the detailed explanation.

[1591] Prompt Sentence Examples

[1592] Example 1: Book description prompt

[1593] "Tell me what's on this page."

[1594] Example 2: Nature observation prompt

[1595] "What is this flower?"

[1596] As described above, the system for implementing the present invention provides users with a real-time and personalized learning experience, significantly improving learning efficiency.

[1597] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1598] Step 1:

[1599] Input: A user launches the camera application on their smartphone or tablet and captures image data (e.g., a page in a book or an image of a natural object).

[1600] Specific behavior:

[1601] The device uses the camera to capture an image of the object and stores the captured image data in memory. The user can then decide what to photograph by viewing the camera's preview screen.

[1602] Output: The captured image data is stored in the device's memory.

[1603] Step 2:

[1604] Input: A user uses a voice input application to type a question into a microphone as voice data (e.g., "What is this page about?").

[1605] Specific behavior:

[1606] The device captures voice data through the microphone and stores it in memory, and the user records their question using a voice input application.

[1607] Output: The captured audio data is stored in the device's memory.

[1608] Step 3:

[1609] Input: Image and audio data stored on the device. User ID information.

[1610] Specific behavior:

[1611] The device converts the captured image and audio data, along with the user ID, into JSON format and sends it to the server using HTTP or WebSocket protocol.

[1612] Output: Image data, audio data and user ID are sent to the server.

[1613] Step 4:

[1614] Input: Image data and audio data sent to the server, user ID.

[1615] Specific behavior:

[1616] The server applies image recognition algorithms to the received image data using TensorFlow or PyTorch, and performs speech recognition on the audio data using Google Speech-to-Text or similar to convert it into text.

[1617] Output: Image analysis results (e.g., identification of objects in the image) and textual questions.

[1618] Step 5:

[1619] Input: Image analysis results and textual questions.

[1620] Specific behavior:

[1621] The server generates explanatory text and supplementary information using a generative AI model (e.g., OpenAI GPT-3) based on the image analysis results and the textual question content. It also retrieves related information from an educational content database and integrates it as supplementary information.

[1622] Output: Generated explanatory text and supporting information.

[1623] Step 6:

[1624] Input: Generated explanation and additional information. User ID.

[1625] Specific behavior:

[1626] The server compiles the generated explanatory text and supplementary information into JSON format and sends it to the terminal using HTTP or WebSocket protocol.

[1627] Output: Explanatory text and additional information are sent to the terminal.

[1628] Step 7:

[1629] Input: Explanation and additional information sent from the server.

[1630] Specific behavior:

[1631] The device then uses AR technology to display the received commentary and supplementary information on the user interface. For example, the device uses ARKit or ARCore to overlay the commentary on the subject of the photo.

[1632] Output: Users can view explanatory text and supplementary information in real time.

[1633] (Application example 1)

[1634] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1635] Although there are existing systems that provide individually tailored explanations by utilizing data capture and analysis technology for analog learning materials and natural environments, there are no systems that can handle the dynamic and diverse products and environments found in physical stores. Therefore, there is a need to provide a system that can instantly obtain product information and features in physical stores and improve the user experience.

[1636] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1637] In this invention, the server includes means for capturing image data or audio data from analog teaching materials, a natural environment, or a brick-and-mortar store, means for transmitting the captured image data and audio data to the server, means for analyzing the received image data and audio data and performing multimodal recognition of the object and question content, means for generating related explanations and supplemental information based on the recognition results, means for transmitting the generated explanations and supplemental information to a terminal or display device, and means for displaying the transmitted explanations and supplemental information using augmented reality technology. This makes it possible to instantly provide product information and explanations in a brick-and-mortar store to users, significantly improving convenience and user experience.

[1638] "Analog teaching materials" refers to physical media such as printed books, notebooks, and posters.

[1639] "Natural environment" refers to outdoor scenery, plants, animals, and other elements of the natural world.

[1640] "Brick and Mortar Store" means a physical store for selling goods and services.

[1641] "Image data" refers to still image and video data captured by a camera or other photographic device.

[1642] "Audio Data" means audio data captured by a microphone or other recording device.

[1643] A "server" refers to a computer system that processes data and provides information via a network.

[1644] "Capturing means" refers to a method or device for capturing images or sounds, such as a camera or microphone.

[1645] "Transmitting means" refers to a method or apparatus for sending data over a network to another system or device.

[1646] "Multimodal recognition" refers to the technology of analyzing multiple sensory data (e.g., images and audio) to understand their meaning.

[1647] "Recognition results" refers to the information obtained from analyzed image and audio data.

[1648] "Explanation and supplementary information" refers to detailed explanations or additional information related to the subject matter.

[1649] "Display device" refers to a device for visually displaying information (e.g., smartphone, augmented reality glasses, etc.).

[1650] "Augmented reality technology" refers to technology that displays virtual information overlaid on the real-world environment.

[1651] In order to implement the present invention, the following hardware and software are used.

[1652] Hardware used

[1653] 1. Smartphone: For image capture and data transmission.

[1654] 2. Smart glasses: For displaying information using augmented reality technology (e.g., Google Glass, Vuzix)

[1655] 3. Server: For data analysis and information generation.

[1656] Software used

[1657] 1. Image recognition libraries: To analyze image data (e.g., Google Cloud Vision, Microsoft Azure Computer Vision).

[1658] 2. Speech recognition library: To convert voice data into text (e.g., Google Speech-to-Text, Azure Speech Services).

[1659] 3. Cloud platforms: for server hosting and data processing (e.g., AWS, Azure).

[1660] 4. Application development frameworks: For developing applications for smartphones and smart glasses (e.g., React Native, Flutter).

[1661] System Overview

[1662] The server analyzes the image data and audio data received from the user, recognizes the object, and analyzes the user's question. Based on the analysis results, it generates an explanation and supplementary information that is optimal for the user and sends it to the user's device or display device. The received explanation and supplementary information are displayed using augmented reality technology, allowing the user to refer to it directly.

[1663] Processing Description

[1664] 1. Server process:

[1665] The server uses a database that stores user-specific IDs, learning histories, and personalized data, in order to provide individual information to each user.

[1666] The server analyzes the received image data using an image recognition library such as Google Cloud Vision to identify the target object.

[1667] The server converts the received voice data into text using a voice recognition library such as Google Speech-to-Text and analyzes the user's question.

[1668] Based on these recognition results, the server uses a generative AI model to create relevant commentary and supplementary information.

[1669] 2. Terminal processing:

[1670] The user captures an object with their smartphone camera and asks a question aloud using a prompt such as, "Please write a detailed description of this product. The name of this product is XX."

[1671] The smartphone transmits the captured image data and audio data to a server.

[1672] Commentary and supplementary information sent from the server is received and displayed on the smartphone or smart glasses display.

[1673] Augmented reality technology is used to overlay commentary and supplementary information on the object.

[1674] Specific examples

[1675] Example 1: Use in a home appliance store

[1676] A user can scan a refrigerator in an appliance section and ask, "What are the features of this refrigerator?" The smart glasses will then overlay information such as rated capacity and energy efficiency on top of the refrigerator, allowing the user to instantly check the detailed information.

[1677] Prompt Sentence Examples

[1678] "Please write a detailed description of this product. The product name is a 4-door inverter refrigerator."

[1679] This makes it possible to provide users with product information from physical stores quickly and accurately, improving the user experience.

[1680] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1681] Step 1:

[1682] A user scans a product with smart glasses. The input is the product image, and the output is the captured image data. The user looks at the product through the smart glasses, and the camera on the glasses captures the product image.

[1683] Step 2:

[1684] The terminal sends the captured image data to the server. The input is the captured image data, and the output is the data sent to the server. The smart glasses send the image data to the server via wireless communication.

[1685] Step 3:

[1686] The server uses an image recognition algorithm to analyze the received image data. The input is the received image data, and the output is the recognition result (e.g., product name, model number). The server identifies the object using an image recognition library such as Google Cloud Vision. The product name and model number are obtained as the analysis result.

[1687] Step 4:

[1688] The user asks a question about a product by voice. The input is the user's voice data, and the output is the captured voice data. The user speaks to the smart glasses and asks, "Tell me about the features of this product."

[1689] Step 5:

[1690] The terminal sends the captured voice data to the server. The input is the captured voice data, and the output is the data sent to the server. The smart glasses send the voice data to the server via wireless communication.

[1691] Step 6:

[1692] The server uses a speech recognition algorithm to convert the voice data into text. The input is the received voice data, and the output is text data (the user's question). The server then converts the voice data into text using a speech recognition library such as Google Speech-to-Text and analyzes the user's question.

[1693] Step 7:

[1694] The server generates explanations and supplementary information based on the text data and image recognition results. The input is text data and image recognition results, and the output is the generated explanations and supplementary information. The server uses a generative AI model to generate relevant explanations and information based on the recognition results and the user's question.

[1695] Step 8:

[1696] The server sends the generated commentary and supplementary information to the device. The input is the generated commentary and supplementary information, and the output is the data sent to the device. The server sends the commentary and supplementary information to the smart glasses.

[1697] Step 9:

[1698] The device displays the explanation and supplementary information using augmented reality technology. The input is the received explanation and supplementary information, and the output is the augmented reality information displayed to the user. The smart glasses display the received explanation and supplementary information, providing the user with detailed information about the product.

[1699] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1700] As an embodiment of the present invention, a system that acquires image data or audio data from analog learning materials or natural environments and provides individually tailored commentary using digital technology will be specifically described. Furthermore, a form incorporating an emotion recognition engine that recognizes the user's emotions and provides personalized information based on those emotions will be described.

[1701] Server Processing

[1702] 1. Initial Setup:

[1703] The server initializes a database that stores a user's unique ID and associated learning history, personalization data, and emotion recognition data, enabling personalized information delivery based on emotions.

[1704] 2. Data reception:

[1705] The server receives image data, voice data, and emotion data sent from the device or AR glasses. The received data is managed together with the user ID.

[1706] 3. Multimodal Recognition:

[1707] The server runs image and voice recognition algorithms on the received data to identify the object and convert the voice content into text. For example, it can identify the type of flower from a received image and analyze the user's question from the voice.

[1708] 4. Emotion recognition:

[1709] The server analyzes the received data and uses an emotion recognition engine to identify the user's emotional state, for example by analyzing facial expressions and tone of voice when the user captures the image.

[1710] 5. Content Generation:

[1711] The server generates relevant commentary and supplemental information based on the image, voice, and emotion recognition results. This information is personalized according to the user's emotional state. For example, if the user is in a difficult emotional state, a more detailed commentary is generated.

[1712] 6. Data Transmission:

[1713] The server then transmits the generated commentary content to the device or display device. The transmitted data includes not only the text information but also related images and information for AR display.

[1714] Processing of devices (smartphones and tablets)

[1715] 1. User Interface:

[1716] The device provides an interface for users to use the camera to point it at analog learning materials or natural environments. For example, the user can activate the camera through an application and display a screen where they can check the subject being photographed.

[1717] 2. Data capture:

[1718] The device captures image data, voice data, and emotion data from a camera and microphone. For example, a user can take a picture of a page in a book or a flower with the camera and input a question by voice.

[1719] 3. Data transmission:

[1720] The device sends the captured data to a server, which also includes the user's ID and emotional data, allowing for personalized information to be provided.

[1721] 4. Data reception:

[1722] The terminal receives commentary and supplementary information sent from the server, and the received data is displayed in real time.

[1723] 5.Display:

[1724] The device then uses AR technology to present the received information to the user, for example by overlaying a description onto a specific book page or by displaying related information on objects in the natural environment.

[1725] User Behavior

[1726] 1. Start learning:

[1727] Users use a device or AR glasses to access the analog learning materials and natural environments they want to learn from.

[1728] 2. Inquiries:

[1729] The user holds the camera over the object they want to inquire about and asks a question by voice, for example, "What kind of flower is this?"

[1730] 3. Receiving information:

[1731] Users can deepen their learning by viewing explanations and supplementary information displayed on their device or AR glasses. They can refer to the displayed information and move on to the next question or object.

[1732] Specific examples

[1733] Example 1: Book description

[1734] 1. User: Scan a page of a book with the smartphone camera. Say, "Tell me what's on this page."

[1735] 2. Terminal: Sends the image data, voice data, and facial expression data of the page to the server.

[1736] 3. Server: Analyzes the book pages using image recognition, converts voice data into text, and identifies the user's question. Recognizes emotions based on facial expression data.

[1737] 4. Server: Based on the content of the page, generate an explanatory text that matches the user's emotional state. For example, if the user has a troubled expression, provide a detailed explanation.

[1738] 5. Server: Sends explanatory text to the device.

[1739] 6. Terminal: The terminal displays explanatory text, which the user reads to understand the content.

[1740] Example 2: Nature observation

[1741] 1. User: Go out into the field and scan a flower with your smartphone camera. Ask, "What flower is this?"

[1742] 2. Terminal: Sends flower image data, audio data, and tone of voice data to the server.

[1743] 3. Server: Performs image recognition to identify the type and characteristics of flowers. Converts voice data into text and performs emotion recognition based on the tone of voice.

[1744] 4. Server: Generates a description based on the flower's name, characteristics, and user's emotions.

[1745] 5. Server: Sends the commentary to the device.

[1746] 6. Device: The device displays an AR explanation overlaid on the image of the flower. The user can observe the flower while looking at the detailed explanation.

[1747] In this way, the present invention effectively combines digital technology with analog learning materials and natural experiences to provide a fun and hands-on learning environment. Furthermore, the use of an emotion recognition engine enables personalization based on the user's emotional state, resulting in a more effective and personalized learning experience.

[1748] The processing flow will be explained below.

[1749] Step 1:

[1750] User: Launches the application and sets camera and microphone permissions, ready to capture image and audio data.

[1751] Step 2:

[1752] Device: Activate the camera and capture an analog learning material or an object in the natural environment specified by the user. For example, take a picture of a page in a book or a flower.

[1753] Step 3:

[1754] Device: Activate the microphone to capture the user's voice input, for example, to record a question such as "What is this page about?"

[1755] Step 4:

[1756] Device: The device captures the user's facial expression with a camera and simultaneously captures emotional data. For example, it records image data to analyze whether the user's facial expression is troubled.

[1757] Step 5:

[1758] Device: Captured image data, audio data, and emotional data are sent to the server. This data also includes the user ID, enabling personalized commentary.

[1759] Step 6:

[1760] Server: Analyzes the received image data using an image recognition algorithm to identify the object, for example, identify the type of flower from a captured image.

[1761] Step 7:

[1762] Server: Converts the received voice data into text using a speech recognition algorithm and analyzes the user's question. For example, converting a question like "What kind of flower is this?" into text.

[1763] Step 8:

[1764] Server: Uses an emotion recognition engine to identify the user's emotional state from the received data. For example, it analyzes whether the user is distressed, interested, confused, etc.

[1765] Step 9:

[1766] Server: Generates relevant explanatory text and supplementary information based on the image, voice, and emotion recognition results. For example, it generates information such as "This flower is a cherry blossom and blooms in spring."

[1767] Step 10:

[1768] Server: Personalize the generated explanatory content based on the user's emotional state. For example, include more detailed explanations or additional illustrations if the user is struggling.

[1769] Step 11:

[1770] Server: Sends personalized commentary content to the device or display device. The transmitted data includes not only text information but also related images and information for AR display.

[1771] Step 12:

[1772] Terminal: Receives explanatory content sent from the server and displays it through a user interface. For example, the explanatory text is displayed overlaid on the pages of a book.

[1773] Step 13:

[1774] User: Check the received explanations and supplementary information to advance their learning. Furthermore, they can continue learning by pointing the camera at new questions or objects.

[1775] This process allows users to receive personalized instruction through analog learning materials and natural environments, and then use digital technology to effectively learn. Furthermore, by utilizing an emotion recognition engine, a more personalized learning experience is provided based on the user's emotional state.

[1776] Example 2

[1777] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1778] Conventional learning methods using analog learning materials or natural environments provide uniform information, lacking in personalization tailored to each user's emotional state and learning progress. As a result, users may lack understanding or lose motivation to learn. Furthermore, even if image and audio data are captured, there is a lack of technology to effectively analyze that data and provide explanatory information tailored to the user's needs. There is a need to solve these issues.

[1779] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1780] In this invention, the server includes means for capturing image data or audio data from analog learning materials or natural environments, means for transmitting the captured image data and audio data to the server, means for analyzing the received image data and audio data and performing multimodal recognition of the object and question content, means for recognizing the user's emotional state and generating personalized commentary and supplemental information based on the emotion, means for transmitting the generated commentary and supplemental information to a terminal or display device, and means for displaying the transmitted commentary and supplemental information, thereby enabling the provision of detailed commentary information tailored to the user's emotional state and learning needs.

[1781] "Analog teaching materials" are educational materials that use paper media or physical objects.

[1782] The "natural environment" refers to the natural elements and ecosystems that exist outdoors.

[1783] "Image data" is visual information captured by a camera or other photographic device.

[1784] "Audio Data" means audio information captured by a microphone or other recording device.

[1785] A "capturing means" is a device or equipment for acquiring image data and audio data.

[1786] The "transmitting means" is a communication means for transmitting the acquired data to the server.

[1787] The "analyzing means" refers to the technology or algorithm for analyzing the received image data and audio data and extracting the necessary information.

[1788] "Multimodal recognition" is a technology that combines image data and audio data to analyze information and identify the target object or question.

[1789] The "means for generating personalized commentary and supplementary information" is a technology for creating personalized information according to the individual characteristics and emotional state of the user.

[1790] The "transmitting means" is a communication means for transmitting the generated commentary and supplementary information to a terminal or a display device.

[1791] The "display means" refers to a technique or device for visually presenting the transmitted commentary or supplemental information to the user.

[1792] "Emotional state" refers to a psychological state that can be inferred from a user's facial expression, tone of voice, and other behavior.

[1793] This system acquires image or audio data from analog learning materials or natural environments and uses digital technology to provide individually tailored commentary. It also incorporates an emotion recognition engine that recognizes the user's emotions and provides personalized information based on those emotions. This system operates among three parties: a server, a terminal, and the user.

[1794] Server Processing

[1795] 1. Initial Setup:

[1796] The server initializes the database. Specifically, it creates a table that manages each user's unique ID, learning history, personalized data, and emotion recognition data. This allows it to store learning data for each user and provide personalized information based on their emotions.

[1797] 2. Data reception:

[1798] The server receives image data, voice data, and emotion data sent from the device. The received data is managed by checking it against the user ID. For example, this data can be received using a REST API.

[1799] 3. Multimodal Recognition:

[1800] The server performs the following processing on the received data: it uses an image recognition algorithm (e.g., TensorFlow) to identify the object, and a speech recognition algorithm (e.g., Google Cloud Speech-to-Text API) to convert the speech into text, which allows it to analyze the user's question.

[1801] 4. Emotion recognition:

[1802] The server uses an emotion recognition engine (e.g., Microsoft Azure Emotion API) to identify the user's emotional state based on the received data. For example, it analyzes the user's facial expressions and tone of voice when capturing an image to infer the user's mental state.

[1803] 5. Content Generation:

[1804] The server generates relevant commentary and supplemental information based on the image, voice, and emotion recognition results. This allows for personalized information to be provided according to the user's emotional state. For example, if the user is having trouble, the server can generate detailed explanations to help the user progress smoothly through the learning process.

[1805] 6. Data Transmission:

[1806] The server then sends the generated commentary content to the device, which includes not only text information but also related images and information for AR display.

[1807] Processing of devices (smartphones and tablets)

[1808] 1. User Interface:

[1809] The device provides an interface for pointing the camera at analog learning materials or natural environments. This is implemented as an application, and the user can check the object being scanned through the camera preview.

[1810] 2. Data capture:

[1811] The device captures image data, voice data, and emotion data from a camera and microphone. For example, data is acquired when a user takes a picture of a particular flower with a camera and inputs a question by voice.

[1812] 3. Data transmission:

[1813] The device then sends the captured data, including the user ID and emotional data, to the server, where accurate personalization is performed.

[1814] 4. Data reception:

[1815] The terminal receives the commentary and supplementary information sent from the server, and the received data is displayed on the terminal's display in real time.

[1816] 5.Display:

[1817] The device then uses AR technology to present the received information to the user, for example by overlaying explanations on specific book pages to provide visual support for the user's learning.

[1818] User Behavior

[1819] Users use a device or AR glasses to access the analog learning materials or natural environment they want to learn from. They point the camera at the object they want to inquire about and ask a question by voice, for example, "What kind of flower is this?" Explanations and supplementary information are displayed on the device in real time, allowing users to view them and deepen their learning.

[1820] Specific examples

[1821] Example 1: Book description

[1822] 1. User: Scans a page of a book with the smartphone camera and says, "Tell me what this page is about."

[1823] 2. Terminal: Sends the page's image data, voice data, and emotion data to the server.

[1824] 3. Server: Analyzes the book pages using image recognition, converts voice data into text, and identifies the user's question. Recognizes emotions based on facial expression data.

[1825] 4. Server: Based on the content of the page, generate an explanatory text that matches the user's emotional state. For example, if the user has a troubled expression, provide a detailed explanation.

[1826] 5. Server: Sends explanatory text to the device.

[1827] 6. Terminal: The terminal displays explanatory text, which the user reads to understand the content.

[1828] Example 2: Nature observation

[1829] 1. User: Go out into the field and scan a flower with your smartphone camera. Ask, "What flower is this?"

[1830] 2. Terminal: Sends flower image data, audio data, and tone of voice data to the server.

[1831] 3. Server: Performs image recognition to identify the type and characteristics of flowers. Converts voice data into text and performs emotion recognition based on the tone of voice.

[1832] 4. Server: Generates a description based on the flower's name, characteristics, and user's emotions.

[1833] 5. Server: Sends the commentary to the device.

[1834] 6. Device: The device displays an AR explanation overlaid on the image of the flower. The user can observe the flower while looking at the detailed explanation.

[1835] In this way, the present invention is a system that effectively combines digital technology with analog learning materials and natural experiences to support user learning. Furthermore, the use of an emotion recognition engine enables personalization according to the user's emotional state, resulting in a more effective and individualized learning experience.

[1836] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1837] Server Processing

[1838] Step 1: Initial Setup

[1839] The server initializes the database. Specifically, it creates tables to store the user's unique ID, learning history, personalization data, and emotion recognition data. The input to this step is a specific table schema, and the output is an initialized database. For example, the tables are created by executing SQL queries.

[1840] Step 2: Receiving data

[1841] The server receives image data, audio data, and emotion data sent from the device. The input of this step is the data payload from the device, and the output is the raw data stored in the server. Specifically, it receives an HTTP POST request and saves the data in an appropriate folder or database.

[1842] Step 3: Multimodal Recognition

[1843] The server analyzes the received image data and voice data and performs multimodal recognition of the object and the question. The input for this step is image data and voice data, and the output is the recognized object and the question converted into text. Specifically, an image recognition algorithm is used to identify the type of flower, and a voice recognition algorithm is used to convert the user's question into text.

[1844] Step 4: Emotion Recognition

[1845] The server runs an emotion recognition engine based on the received data to identify the user's emotional state. The input for this step is a variety of data sets, including image data and audio data, and the output is the identified emotional state. Specific operations include facial expression recognition algorithms and tone of voice analysis.

[1846] Step 5: Content Generation

[1847] The server generates relevant commentary and supplemental information based on the image, voice, and emotion recognition results. The input to this step is the recognition results from the previous step, and the output is the generated commentary and supplemental information. For example, if the user is in a difficult emotional state, the server runs an algorithm to generate a more detailed commentary.

[1848] Step 6: Send data

[1849] The server sends the generated commentary content to the terminal. The input of this step is the generated commentary content, and the output is the status of completion of transmission. Specifically, the commentary and supplementary information are sent to the terminal using an HTTP POST request.

[1850] Processing of devices (smartphones and tablets)

[1851] Step 1: User Interface

[1852] The device provides an interface for pointing the camera at analog learning materials or natural environments. The input for this step is user operation, and the output is the display of the camera preview. Specifically, the camera preview of the application is launched.

[1853] Step 2: Data Capture

[1854] The device captures image data, audio data, and emotion data from the camera and microphone. The input of this step is physical objects and audio, and the output is digitized data. Specifically, images are Base64 encoded and audio is recorded.

[1855] Step 3: Send data

[1856] The device sends the captured data to the server. The input of this step is the captured data, and the output is the status of the completion of the transmission. Specifically, an HTTP POST request is created and sent.

[1857] Step 4: Receiving Data

[1858] The device receives the explanation and supplementary information sent from the server. The input of this step is the data from the server, and the output is the received explanation and supplementary information. Specifically, the data is obtained using an HTTP GET request.

[1859] Step 5: Display

[1860] The device then uses AR technology to present the received information to the user. The input for this step is the received explanatory information, and the output is the explanatory information displayed on the screen. Specifically, the explanatory information is displayed overlaid on a specific book page or natural object.

[1861] User Behavior

[1862] Step 1: Start learning

[1863] The user uses a device or AR glasses to access the analog learning materials or natural environment they want to learn from. The input of this step is the user's intention, and the output is the launch of an app. For example, launching a learning app and preparing the camera.

[1864] Step 2: Inquiry

[1865] The user points the camera at the object they want to inquire about and asks the question by voice. The input for this step is the object and the voice question, and the output is the captured data. For example, they might ask, "What is this flower?"

[1866] Step 3: Receiving information

[1867] The user can view explanations and supplementary information displayed on the device or AR glasses to further their learning. The input for this step is the information received from the server, and the output is the user's understanding. The user can then proceed to the next question or object.

[1868] (Application example 2)

[1869] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1870] Current factory robots struggle to provide advanced analytical functions or interactive assistance to improve the accuracy and efficiency of quality checks when inspecting or manipulating products. They also struggle to recognize the user's emotional state and provide information based on that. Even when an operator is confused, it is rare for them to provide appropriate support promptly. This results in issues such as reduced efficiency and increased human error.

[1871] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing image data or audio data, means for transmitting the captured data to the server, means for analyzing the received data and performing multimodal recognition of the object and the question content, means for generating personalized related explanations and supplemental information based on the recognition results and the user's emotional state, means for transmitting the generated explanations and supplemental information to a terminal or display device, and means for displaying the transmitted explanations and supplemental information. This enables the factory robot to provide appropriate support for product inspection and operation while taking the user's emotional state into consideration.

[1872] "Image data" is visual information captured using a camera or other imaging device.

[1873] "Audio Data" is a recording of sound collected using a microphone or other sound capture device.

[1874] "Capture" is the process of capturing information using a particular device.

[1875] A "server" is a computer system that provides a service to a group of other computers on a network.

[1876] "Transmission" is the process of moving data from one point to another.

[1877] "Analysis" is the process of understanding the type and structure of data and extracting its meaning and value.

[1878] "Multimodal recognition" is a technology that integrates and analyzes multiple input formats (images, audio, text, etc.).

[1879] "Related explanations and supplementary information" is explanatory text or additional information based on the recognized data.

[1880] "Terminal" means a computing device with input and output devices that can be directly operated by a user.

[1881] "Display" is the process of visually presenting acquired information to the user.

[1882] An "emotional state" is the state of emotions or feelings a user has at a given time.

[1883] A "generative AI model" is a model trained using machine learning algorithms that has the ability to generate content based on new data.

[1884] A "prompt" is a sentence that formats and inputs a specific question or command.

[1885] "Personalization" is the process of customizing something to suit the characteristics and circumstances of each individual user.

[1886] The present invention relates to a smart assistant system for factory robots, and a specific embodiment of the system will be described herein.

[1887] Server Processing

[1888] The server first receives image data and audio data. This data was acquired by factory robots using cameras, and each robot is assigned an individual user ID. The received data is managed in association with that user ID. The server then analyzes this data using the following methods to generate content.

[1889] Hardware and Software:

[1890] Hardware: Servers and cloud computing infrastructure

[1891] Software: OpenCV (image recognition), SpeechRecognition (voice recognition), Affectiva (emotion recognition), TensorFlow (machine learning), Flask (server-side)

[1892] The server uses an image recognition algorithm to analyze the received image data and identify the type and condition of the object, and a voice recognition algorithm to convert the voice data into text and extract the user's question.

[1893] Furthermore, an emotion recognition engine is used to identify the user's emotional state. For example, if an operator is confused, the emotional state is determined by analyzing facial image data and voice tone. Based on this emotional data, relevant commentary and supplementary information are generated in a personalized manner.

[1894] The information generated is sent to factory robots in real time, enabling them to provide appropriate feedback and assistance to operators.

[1895] Terminal (factory robot) processing

[1896] Factory robots are equipped with cameras and microphones and are used to inspect parts and products. A user (operator) uses the robot's camera to scan a specific part or product and then voice-inputs questions. The robot then sends this data to a server.

[1897] The received personalized information is then displayed on the robot's display. For example, if a factory robot is inspecting a part, the robot will scan the part and check for quality issues. If the operator is confused, the robot can provide a detailed explanation and explain next steps if an issue is found.

[1898] User Behavior

[1899] The user (operator) uses a factory robot to take pictures of parts or products and input quality-related questions by voice. For example, the user might ask, "Please tell me the condition of this part." The robot then uses its camera and microphone to capture the data and sends it to the server. The robot then receives feedback from the server and provides detailed explanations and instructions. This process allows the operator to efficiently perform quality checks.

[1900] Examples of concrete examples and prompts

[1901] As a concrete example, the following scenario can be considered.

[1902] Scene: A robot inspects parts on a factory assembly line.

[1903] Robot: Scans parts and sends quality check messages to operators.

[1904] Operator: There seems to be something wrong with the part and I'm confused (troubled expression).

[1905] System: The robot analyzes the operator's facial expressions and provides detailed instructions and next steps.

[1906] Example prompt sentence:

[1907] Keyword prompts: "Part image," "Audio question," "Confused expression," "Detailed explanation"

[1908] Prompt statement:

[1909] "I'm currently operating a robot. I'm concerned about the quality of the part. What's the problem with this part?"

[1910] "The operator is having trouble. Please check the details of the part."

[1911] As described above, the present invention enables a factory robot to provide assistance based on the user's emotional state, thereby improving efficiency and reducing human error.

[1912] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1913] Step 1:

[1914] The user operates the factory robot, scans the parts or products to be inspected with a camera, and inputs voice questions through a microphone. The input includes image data and voice data of the parts or products. For example, the user may ask a specific question such as, "Please tell me the condition of this part."

[1915] Step 2:

[1916] The terminal (factory robot) captures image data and audio data using a camera and microphone. This captured data is sent to the server along with the user ID. The input includes image data, audio data, and the user ID. The terminal sends this all together to the server.

[1917] Step 3:

[1918] The server analyzes the image data and audio data received from the device. The server first uses an image recognition algorithm (using OpenCV or TensorFlow) to identify the type and state of the object from the image data. Next, it uses a voice recognition algorithm (using SpeechRecognition) to convert the audio data into text. The server then analyzes the content of the question and extracts it as text data. The input includes image data and audio data, and the output generates the result of identifying the object and text data.

[1919] Step 4:

[1920] The server uses an emotion recognition engine (powered by Affectiva) to analyze the user's emotional state from the received image data and voice tone data. For example, it detects the operator's confused facial expression and tone. The input includes image data and voice tone data, and the output generates emotion data.

[1921] Step 5:

[1922] The server uses a generative AI model to personalize relevant commentary and supplemental information based on image, voice, and emotion recognition results. For example, if the user is confused, a more detailed commentary can be generated. This process involves generating appropriate prompts, based on which the AI ​​model generates content. Inputs include image, voice, and emotion recognition results, and the output is personalized commentary and supplemental information.

[1923] Step 6:

[1924] The server transmits the generated commentary and supplementary information to the terminal (factory robot). The input includes the generated commentary and supplementary information data, and the output becomes the transmitted data.

[1925] Step 7:

[1926] The terminal (factory robot) receives the explanation and supplementary information sent from the server and displays it to the user. For example, a detailed explanation and the next steps are displayed on the robot's display. The input includes the sent explanation and supplementary information, and the output is displayed to the user. The user can use this information to check the quality or carry out the next task.

[1927] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1928] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1929] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1930] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1931] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1932] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1933] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1934] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1935] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1936] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1937] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1938] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1939] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1940] 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.

[1941] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1942] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1943] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1944] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1945] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1946] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1947] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1948] The following is further disclosed regarding the above embodiment.

[1949] (Claim 1)

[1950] means for capturing image data or audio data for analog learning materials or natural environments;

[1951] means for transmitting the captured image data and audio data to a server;

[1952] means for analyzing the received image data and voice data and performing multimodal recognition of the object and the question content;

[1953] means for generating relevant commentary or supplemental information based on the recognition results;

[1954] means for transmitting the generated commentary and supplemental information to a terminal or display device;

[1955] a means for displaying the submitted commentary and supplementary information;

[1956] A system including:

[1957] (Claim 2)

[1958] 10. The system of claim 1, further comprising means for analyzing the captured image data using an image recognition algorithm.

[1959] (Claim 3)

[1960] 10. The system of claim 1, further comprising means for converting the captured voice data into text using a voice recognition algorithm.

[1961] "Example 1"

[1962] (Claim 1)

[1963] A means for acquiring image data or audio data for analog teaching materials or natural environments;

[1964] means for transmitting the acquired image data and audio data to a central processing unit;

[1965] means for analyzing the received image data and voice data and performing multimodal recognition of the object and the question content;

[1966] means for generating relevant commentary or supplemental information based on the recognition results;

[1967] means for transmitting the generated commentary and supplemental information to a terminal or display device;

[1968] a means for displaying the submitted commentary and supplementary information;

[1969] A system including:

[1970] (Claim 2)

[1971] 10. The system of claim 1, further comprising means for analyzing the acquired image data using an image recognition algorithm.

[1972] (Claim 3)

[1973] 10. The system of claim 1, further comprising means for converting the captured voice data into text using a voice recognition algorithm.

[1974] "Application Example 1"

[1975] (Claim 1)

[1976] A means for capturing image data or audio data for analog teaching materials, natural environments, or brick-and-mortar stores;

[1977] means for transmitting the captured image data and audio data to a server;

[1978] means for analyzing the received image data and voice data and performing multimodal recognition of the object and the question content;

[1979] means for generating relevant commentary or supplemental information based on the recognition results;

[1980] means for transmitting the generated commentary and supplemental information to a terminal or display device;

[1981] a means for displaying the transmitted commentary and supplemental information using augmented reality technology;

[1982] A system including:

[1983] (Claim 2)

[1984] 10. The system of claim 1, further comprising means for analyzing the captured image data using an image recognition algorithm.

[1985] (Claim 3)

[1986] 10. The system of claim 1, further comprising means for converting the captured audio data into text using a speech recognition algorithm.

[1987] "Example 2: Combining Emotion Engines"

[1988] (Claim 1)

[1989] means for capturing image data or audio data for analog learning materials or natural environments;

[1990] means for transmitting the captured image data and audio data to a server;

[1991] means for analyzing the received image data and voice data and performing multimodal recognition of the object and the question content;

[1992] means for recognizing a user's emotional state and generating personalized commentary or supplemental information based on the emotional state;

[1993] means for transmitting the generated commentary and supplemental information to a terminal or display device;

[1994] a means for displaying the submitted commentary and supplementary information;

[1995] A system including:

[1996] (Claim 2)

[1997] 10. The system of claim 1, further comprising means for analyzing the captured image data using an image recognition algorithm.

[1998] (Claim 3)

[1999] 10. The system of claim 1, further comprising means for converting the captured voice data into text using a voice recognition algorithm.

[2000] "Application example 2 when combining emotion engines"

[2001] (Claim 1)

[2002] means for capturing image data or audio data for analog learning materials or natural environments;

[2003] means for transmitting the captured image data and audio data to a server;

[2004] means for analyzing the received image data and voice data and performing multimodal recognition of the object and the question content;

[2005] means for generating personalized relevant commentary and supplemental information based on the recognition results and the user's emotional state;

[2006] means for transmitting the generated commentary and supplemental information to a terminal or display device;

[2007] a means for displaying the submitted commentary and supplementary information;

[2008] A system including:

[2009] (Claim 2)

[2010] further comprising means for analyzing the captured image data using an image recognition algorithm;

[2011] 10. The system of claim 1, further comprising means for personalizing associated commentary and supplemental information using a generative AI model.

[2012] (Claim 3)

[2013] means for converting the captured voice data into text using a voice recognition algorithm;

[2014] 10. The system of claim 1, further comprising means for generating and personalizing prompt sentences. [Explanation of symbols]

[2015] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for capturing image data or audio data for analog learning materials or natural environments; means for transmitting the captured image data and audio data to a server; means for analyzing the received image data and voice data and performing multimodal recognition of the object and the question content; means for generating relevant commentary or supplemental information based on the recognition results; means for transmitting the generated commentary and supplemental information to a terminal or display device; a means for displaying the submitted commentary and supplementary information; A system including:

2. 10. The system of claim 1, further comprising means for analyzing the captured image data using an image recognition algorithm.

3. The system of claim 1 further comprising means for converting the captured voice data into text using a voice recognition algorithm.

Images