System

Abstract

A system is provided.SOLUTION: A system including means for acquiring information within a visual range of a wearable device worn by a user, means for analyzing the acquired information to extract a feature value, means for transmitting the extracted feature value to a server via a communication network, means for generating relevant information based on the feature value received by the server using generative artificial intelligence, means for transmitting the generated information to the wearable device via the communication network, and means for visually displaying the information received by the wearable device as augmented reality.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] Access to knowledge and information is becoming increasingly important in modern society. However, it remains difficult to quickly and accurately acquire and understand vast amounts of information in real time. In particular, there is still a lack of efficient means to instantly acquire information needed for learning, research, and everyday life. Against this background, there is a demand for systems that can analyze visual information in real time and instantly provide additional information to users.

[0005] Furthermore, conventional wearable devices have limitations in terms of the speed and accuracy of information acquisition and display, and new approaches are needed to improve the user experience. Therefore, there is an urgent need to develop more efficient and accurate information provision systems. [Means for solving the problem]

[0006] In order to solve the above problems, the present invention provides the following means.

[0007] The system includes a means for acquiring information within the visual range of a wearable device worn by a user, thereby acquiring the user's visual information in real time, and a means for analyzing the acquired information and extracting features. This analysis includes a means for acquiring video data within the visual range using a camera and extracting features using an object detection algorithm.

[0008] The system further provides a means for transmitting the extracted features to a server via a communications network, and for the server to generate related information based on the received features using artificial intelligence. The system then provides a means for transmitting the generated information to a wearable device via the communications network. As a result, the wearable device can visually display the received information as augmented reality, providing additional information to the user in real time.

[0009] Furthermore, by periodically sending user data to a server and adding a means to receive updated information from the server as needed, it is possible to always provide users with the latest information. This allows users to instantly acquire a wealth of knowledge and information based on visual information, improving the quality of their learning, research, and daily life. It also enables efficient and accurate information provision, which is expected to significantly improve the user experience.

[0010] A "wearable device" refers to an electronic device that can be worn by a user and is usually worn on the body.

[0011] "Information within visual range" refers to all visual data that is within the range that the user can see through the wearable device.

[0012] "Capture means" refers to the combination of hardware and software used to capture information within visual range, such as a camera or sensor.

[0013] "Analyzing and extracting features" refers to analyzing the acquired visual data and extracting specific patterns or features from it.

[0014] A "communications network" is an infrastructure for sending and receiving data between devices and servers, and includes a variety of technologies such as Wi-Fi and mobile data communications.

[0015] "Server" refers to a large-capacity computer system for data processing, storage, and management.

[0016] "Generative artificial intelligence (generative AI)" refers to software systems that use machine learning models and algorithms to create relevant information based on the data they receive.

[0017] "Augmented reality (AR)" refers to a technology that displays virtual information overlaid on real visual information.

[0018] An "object detection algorithm" refers to a computational method for automatically detecting specific objects or features in video data.

[0019] "Periodic transmission" refers to the operation of continuously sending data to the server at regular time intervals.

[0020] "Updated information" refers to the latest data or information generated or acquired by the server, and is provided to users in real time. [Brief explanation of the drawings]

[0021] [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

[0022] 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.

[0023] First, the terms used in the following description will be explained.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 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.

[0032] 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).

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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."

[0042] The present invention is implemented using a system including a wearable device worn by a user, a server, and a network for communication therebetween. The specific processing flow of the program is described in detail below.

[0043] System Overview

[0044] The main components are as follows:

[0045] Wearable devices (terminals)

[0046] server

[0047] communication network

[0048] Terminal

[0049] The system is activated when the user puts on the wearable device. The device's camera captures objects within the user's visual field in real time. This video data is preprocessed by an internal processor, and features are extracted using an object detection algorithm. These features are then sent to a server via a communications network.

[0050] server

[0051] The server receives the feature data sent from the device. Based on the received data, generative artificial intelligence (generative AI) generates related information. The generative AI uses a deep learning model (e.g., CNN or RNN) to identify the type of object and its related information. The generated information is then sent back to the device via the communication network.

[0052] Information display

[0053] The device visually displays the received relevant information as augmented reality (AR), allowing the user to obtain augmented information within their field of vision in real time. The displayed information is overlaid at an appropriate size and angle based on the user's viewpoint and the object's position.

[0054] Specific examples

[0055] Example 1: Museum use

[0056] Consider a scenario in which a user is looking at "ancient statues" in a history museum.

[0057] The device's camera captures video of the statue and extracts features such as shape, color, and texture.

[0058] The terminal transmits these features to a server via a communication network.

[0059] The server analyzes the features and determines that "this is an ancient Greek statue from 500 BC," and the generation AI generates information such as the historical background, the origin and significance of the statue.

[0060] The device analyzes the information received from the server and displays text such as "500 BC Ancient Greek Statues: Their Historical Background and Origins" and related images on the statue as AR.

[0061] Example 2: Use in daily life

[0062] Consider a scenario where a user is looking at "product packaging" in a supermarket.

[0063] The device's camera captures images of the product packaging and extracts features from the barcode and label information.

[0064] The terminal transmits these features to a server via a communication network.

[0065] The server analyzes the features and determines that "this is an organic food and does not contain specific allergens," and the generation AI generates detailed product information, nutritional information, consumer reviews, etc.

[0066] The device analyzes the information received from the server and displays text such as "organic food, ingredient information, consumer reviews" and related images on the product packaging as AR.

[0067] This allows users to instantly acquire a wealth of knowledge and data based on visual information, improving the quality of their learning, research, and daily life.The system based on this invention aims to provide efficient and highly accurate information, significantly improving the user experience.

[0068] The processing flow will be explained below.

[0069] Step 1:

[0070] The user puts on the wearable device. The wearable device starts up and the camera begins capturing video data within the user's visual field. This video data is captured frame by frame and processed at 30 frames per second (FPS).

[0071] Step 2:

[0072] The device receives the captured video data and performs preprocessing, which includes removing noise from the video data and adjusting the resolution. It then uses object detection algorithms to detect objects and features within its visual range. Specifically, it extracts color, shape, texture, and identifiers such as barcodes and QR codes from the camera's video data.

[0073] Step 3:

[0074] The extracted feature data is converted into JSON format and sent to a server via a communication network, using Wi-Fi or mobile data communication.

[0075] Step 4:

[0076] The server receives the feature data sent from the device. The received data is analyzed by generative artificial intelligence (generative AI). The generative AI uses a deep learning model (e.g., CNN or RNN) to determine the type of object from the features.

[0077] Step 5:

[0078] The server generates relevant information based on the results of the judgment. The generation AI collects relevant information from databases and the Internet and generates that information in natural language. The generated information is then converted back into JSON format.

[0079] Step 6:

[0080] The server generates information and sends it to the terminal via a communication network. The transmitted data includes specific information about the object, related images, text, and so on.

[0081] Step 7:

[0082] The device parses the information received from the server and converts it into a format for display. The received data is parsed appropriately and formatted into a visual display format using an AR library (e.g., Unity or ARKit).

[0083] Step 8:

[0084] The device displays the analyzed information in the user's field of view as augmented reality (AR), overlaying text information and images on top of the visual data based on the object's position, angle, and size, allowing the user to obtain additional information about objects within their field of view in real time.

[0085] Step 9:

[0086] The device periodically sends user data to the server and receives updated information as needed. New video data is captured at regular intervals, and features are extracted again and sent to the server. The server continues to generate new information, and the device continues to receive this updated information, so that the latest information is always provided to the user.

[0087] In this way, users can instantly acquire a wealth of knowledge and data based on visual information, improving the quality of their learning, research, and daily life.

[0088] Example 1

[0089] 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."

[0090] Conventional wearable devices have limited the information that users can visually obtain, making it difficult to provide information in real time. Furthermore, analyzing acquired data, extracting features, and generating and displaying relevant information require significant time, which can detract from the user experience. Furthermore, they are limited to use in specific situations and environments, limiting their versatile use. Furthermore, conventional systems often lack the accuracy and relevance of the generated information, failing to provide useful information to users.

[0091] 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.

[0092] In this invention, the server includes means for acquiring information within the visual range of a device worn by a user, means for analyzing the acquired information and extracting features using a trained algorithm, means for transmitting the extracted features to a central processing unit via a communication network, means for generating related information based on the features received by the central processing unit using generative artificial intelligence, means for transmitting the generated information to the device via the communication network, and means for displaying the information received by the device as visual augmentation, thereby enabling users to expand the information they can visually obtain in real time and instantly acquire a wealth of knowledge and data.

[0093] "User" in this invention refers to an individual who wears and uses the device.

[0094] "Device" refers to a wearable device worn by a user that acquires and displays information within visual range.

[0095] "Visual information" refers to video and other data captured by a user's device using cameras and sensors.

[0096] "Trained algorithm" refers to the process of analyzing and extracting features using a machine learning model that has been trained on a large dataset in advance.

[0097] "Features" refers to attribute data such as shape, color, texture, barcode, and label information extracted from information within the visual range.

[0098] "Communication network" refers to the internet line or wireless communication technology (e.g., Wi-Fi, 5G, etc.) used to transmit the extracted feature data to the server.

[0099] "Central Processing Unit" refers to a computer system that functions as a server, receives and analyzes feature data, and generates and transmits related information.

[0100] "Generative artificial intelligence" refers to the process of using deep learning models (e.g., CNN, RNN) to generate relevant information based on received feature data.

[0101] "Related information" refers to information that is useful to the user, such as the type of generated object, its background information, history information, product information, and the like.

[0102] "Visual augmentation" refers to augmented reality (AR) technology that displays generated relevant information on a device to enhance a user's visual experience.

[0103] The present invention is embodied in a system including a wearable device worn by a user, a server, and a communication network connecting them. Specific configurations and processes for promoting the invention are described below.

[0104] System Configuration

[0105] 1. Wearable devices (terminals)

[0106] The wearable device worn by the user is equipped with a high-resolution camera and a built-in processor. The camera captures the user's visual field in real time, and the processor processes and pre-processes the video data. The wearable device also has a wireless communication module and communicates with a server via the Internet.

[0107] 2. Server

[0108] The server acts as a central processing unit, receiving and analyzing the feature data sent from the device. The server is equipped with hardware and software to run deep learning models (e.g., CNN, RNN). The generative AI uses this deep learning model to generate relevant information based on the feature data.

[0109] Data Processing and Flow

[0110] Video capture and pre-processing

[0111] The device's camera captures images within the user's visual field in real time, and the captured image data is pre-processed by a processor to remove noise and improve image quality.

[0112] Feature extraction

[0113] The preprocessed video data is then analyzed by an on-device trained algorithm (e.g., an object detection algorithm such as YOLO or SSD) to extract features (e.g., shape, color, texture, barcode, or label information) from the objects in the video.

[0114] Data transmission

[0115] The extracted feature data is sent to a server via a communication network using wireless communication such as Wi-Fi or 5G, and the data format used is a lightweight format such as JSON.

[0116] Server-side data analysis and information generation

[0117] The server receives the feature data sent from the device and generates relevant information using a deep learning model. For example, a CNN model can be used to identify an object in a video as an ancient Greek statue from 500 BC, and the AI ​​will generate information about its historical background, origin, significance, etc.

[0118] Information transmission and display

[0119] The generated related information is then sent from the server to the terminal via the communication network. The terminal analyzes the received information and displays it as an extension of the user's visual field. The information is overlaid at an appropriate size and position and presented visually to the user.

[0120] Specific examples

[0121] Example 1: Museum use

[0122] Consider a scenario in which a user is looking at ancient statues in a history museum.

[0123] The device's camera captures video of the statue and extracts its features.

[0124] The device transmits the extracted features to the server.

[0125] The server analyzes the features and determines that "this is an ancient Greek statue from 500 BC," and the generation AI generates information such as the historical background, origin, and significance of the statue.

[0126] The device displays the received information as a visual augmentation, and the user can see text such as "500 BC Ancient Greek Statue: Its Historical Background and Origin" on top of the statue in AR.

[0127] Example 2: Use in daily life

[0128] Consider a scenario where a user is looking at product packaging in a supermarket.

[0129] The device's camera captures images of the product packaging and extracts features from the barcode and label information.

[0130] The device transmits the extracted features to the server.

[0131] The server analyzes the features and determines that "this is an organic food and does not contain specific allergens," and the generation AI generates detailed product information, nutritional information, consumer reviews, etc.

[0132] The device displays the received information as a visual augmentation, and users can see text such as "Organic Food, Ingredient Information, Consumer Reviews" and related information on the product packaging in AR.

[0133] Prompt Sentence Examples

[0134] "Please tell me about the historical background, origins, and significance of ancient Greek statues."

[0135] "Based on the information on this product package, please tell me if it is organic, what ingredients it contains, and what consumer reviews it has."

[0136] In this way, the present invention provides a system that expands the information that users can visually obtain and allows them to instantly obtain a wealth of knowledge and data, thereby significantly improving the quality of their learning, research, and daily life.

[0137] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0138] Step 1: Booting the device

[0139] The wearable device worn by the user starts up automatically. At startup, various sensors inside the device begin to operate, and the camera and processor enter a ready state. The input is the user wearing the device, and the output is the device being ready. Specifically, the sensors detect that the user is wearing the device and prepare the environment for the entire system to operate.

[0140] Step 2: Capture footage

[0141] The device's camera captures objects within the user's visual field in real time. The input is the visual field image detected by the camera, and the output is the captured high-resolution video data. Specifically, the camera captures video at a rate of 30 frames per second or more and sends the data to a processor in either raw or compressed format.

[0142] Step 3: Preprocessing the video data

[0143] The processor inside the device receives the video data and performs preprocessing such as noise removal and image quality correction. The input is the captured video data, and the output is the preprocessed video data. Specifically, the processor performs noise removal using a Gaussian filter and contrast correction using histogram equalization.

[0144] Step 4: Feature extraction

[0145] A trained algorithm on the device extracts features from the preprocessed video data. The input is the preprocessed video data, and the output is object features (e.g., shape, color, texture, barcode, label information, etc.). Specifically, object detection algorithms such as YOLO and SSD are used to analyze important parts of the video and extract the necessary features as data.

[0146] Step 5: Send feature data

[0147] The device transmits feature data to a central processing unit (server) via wireless communication (e.g., Wi-Fi, 5G). The input is the extracted feature data, and the output is the data transmitted via the communication network. Specifically, the feature data is converted to a format such as JSON, compressed, and transmitted via the wireless communication module.

[0148] Step 6: Data reception and analysis

[0149] The server receives and analyzes the feature data. The input is the feature data sent from the device, and the output is related information generated by the generative AI model. Specifically, the data is received in the execution environment of the deep learning model (e.g., CNN, RNN), and the analysis program analyzes the features and generates related information.

[0150] Step 7: Generate related information

[0151] The server uses generative AI to generate relevant information based on the received feature data. The input is the feature data obtained through analysis, and the output is relevant information (e.g., historical information, product information, etc.). Specifically, the deep learning model identifies the type of object, and the relevant information is generated using a natural language generation model. For example, background information about an ancient Greek statue and its significance are generated.

[0152] Step 8: Submit relevant information

[0153] The server transmits the generated related information to the terminal via a communication network. The input is the generated related information, and the output is the transmitted information. Specifically, the server converts the related information into an appropriate format and transmits it to the terminal via a wireless communication network.

[0154] Step 9: Displaying Information as a Visual Augmentation

[0155] The device analyzes the relevant information received and displays it as augmented reality (AR). The input is the relevant information sent from the server, and the output is the augmented reality information displayed within the user's visual field. Specifically, the relevant information is overlaid at an appropriate size and position to fit the user's visual environment. For example, text or images may be displayed on a statue, seamlessly integrating with the user's visual field.

[0156] (Application example 1)

[0157] 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."

[0158] At logistics centers, the ability to quickly and accurately pick and pack large quantities of products is a major challenge. However, conventional methods require workers to locate products using only visual information, which creates challenges in terms of work efficiency and accuracy. Furthermore, there are limitations to how much information workers can grasp manually, making errors more likely. Therefore, there is a need for a system that provides both visual and auditory support for work.

[0159] 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.

[0160] In this invention, the server includes: means for acquiring information within the visual range of a wearable device worn by a user; means for analyzing the acquired information and extracting features; means for transmitting the extracted features to the server via a communications network; means for generating related information based on the features received by the server using generative artificial intelligence; means for transmitting the generated information to the wearable device via the communications network; and means for visually displaying the received information as augmented reality on the wearable device, which is further worn by a worker to support work at a logistics center. This allows workers to obtain visual and auditory information in real time through the wearable device, enabling them to pick and pack products quickly and accurately.

[0161] A "wearable device" is an electronic device that can be worn by the user on the body. It is a terminal that has a built-in camera, display, and sensor and can acquire and display information.

[0162] "Information within visual range" refers to all information within the user's field of view that is captured by a camera attached to a wearable device.

[0163] "Features" refer to specific patterns, attributes, and data extracted from information within the visual field that are necessary to identify objects.

[0164] "Communications network" refers to the entire infrastructure for transmitting and receiving data between wearable devices and servers, and between multiple devices.

[0165] "Server" refers to the computer system that receives data sent from a wearable device and processes, analyzes, and generates information.

[0166] "Generative artificial intelligence" refers to AI that uses machine learning and deep learning algorithms based on large amounts of data to generate relevant information based on features.

[0167] "Augmented reality" refers to the technology of overlaying computer-generated information onto real-world visual information.

[0168] A "logistics center" refers to a facility where logistics operations such as collection, delivery, storage, sorting, packaging, and shipping of goods are carried out.

[0169] "Work support" refers to providing visual and auditory information to workers so that they can perform their work more efficiently and accurately.

[0170] The present invention provides a system that uses wearable devices, a server, and a communication network to improve work efficiency in a logistics center.

[0171] System Overview

[0172] The main components are as follows:

[0173] Wearable devices (e.g., smart glasses or smart eyeglasses)

[0174] server

[0175] Communication network (Wi-Fi or 5G)

[0176] Wearable devices

[0177] The system is activated when a worker puts on the wearable device. The device's built-in camera captures information within the worker's visual range (products, barcodes, QR codes, etc.) in real time. This video data is preprocessed by the device's processor, and feature values ​​are extracted. These feature values ​​are then sent to a server via a communications network.

[0178] server

[0179] The server receives the feature data sent from the device. Generative artificial intelligence (generative AI) analyzes this feature data and generates related product information and picking instructions. The generative AI analyzes the features using a deep learning model (e.g., CNN or RNN) and generates information. The generated information is then sent back to the wearable device via the communication network.

[0180] Augmented reality information display

[0181] The wearable device visually displays the received information as augmented reality (AR), allowing workers to see augmented information in real time within their field of vision. The displayed information is overlaid at the appropriate size and angle based on the worker's viewpoint and the location of the item.

[0182] Specific examples

[0183] Use at logistics centers

[0184] Consider a scenario where a worker is picking items at a logistics center.

[0185] The camera in the wearable device captures images of the shelves and extracts features such as barcodes, QR codes, and shapes.

[0186] The wearable device transmits these features to a server via a communication network.

[0187] The server analyzes the features and determines, "This is product A, and its shelf number is 12B," and the generation AI generates picking instructions and inventory information for this product.

[0188] The wearable device analyzes the information received from the server and displays text such as "Product A, shelf number 12B, quantity in stock 30" and related images, as well as audio guidance, on the shelf as AR.

[0189] Hardware and Software Description

[0190] Hardware:

[0191] Wearable devices (smart glasses, etc.)

[0192] Camera (built into wearable device)

[0193] Communication networks (Wi-Fi, 5G)

[0194] software:

[0195] Python (image processing, running generative AI models)

[0196] OpenCV (image processing library)

[0197] Requests (HTTP communication library)

[0198] ARModule (AR display library)

[0199] Examples of prompt statements

[0200] Imagine a scenario in which a worker wearing smart glasses at a distribution center is searching for an item in a picking area. An example prompt is as follows:

[0201] "Analyze product information from the video data and generate the information to be displayed. For example, if the product shown in the video is 'Product A', generate and respond with its name, stock quantity, and shelf number as 'Product A, stock quantity 30, shelf number 12B'."

[0202] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0203] Step 1:

[0204] The user puts on the wearable device and begins work in the logistics center.

[0205] Input: Visual information from a wearable device worn by the user

[0206] How it works: A camera built into the wearable device captures information in real time that comes within the user's visual field.

[0207] Output: Captured video data

[0208] Step 2:

[0209] The device analyzes the video data and extracts features.

[0210] Input: Captured video data

[0211] How it works: The device's processor processes the video data and uses an image recognition algorithm (e.g., OpenCV) to extract features such as product shelves, barcodes, and QR codes.

[0212] Output: Extracted feature data

[0213] Step 3:

[0214] The terminal transmits the feature data to the server via a communication network.

[0215] Input: Extracted feature data

[0216] Action: The device formats the feature data and sends it to the server using an HTTP communication library (e.g., Requests).

[0217] Output: Feature data received by the server

[0218] Step 4:

[0219] The server generates related information using artificial intelligence based on the received feature data.

[0220] Input: Feature data sent from the device

[0221] Operation: The generative AI model runs on the server, analyzes feature data using deep learning algorithms (CNN or RNN), and generates related product information, picking instructions, inventory information, etc.

[0222] Output: Related information generated

[0223] Step 5:

[0224] The server transmits the generated related information to the terminal via a communication network.

[0225] Input: Generated related information

[0226] How it works: The server formats the relevant information and sends it to the device using an HTTP communication library.

[0227] Output: Relevant information received by the device

[0228] Step 6:

[0229] The device analyzes the relevant information received and displays it visually as augmented reality (AR).

[0230] Input: Relevant information received by the device

[0231] Operation: Using an AR library (e.g., ARModule), the device overlays relevant information received with an appropriate position and size based on the user's viewpoint and the location of the item. Audio guidance is also integrated to provide voice instructions to the worker.

[0232] Output: The information the user receives visually and audibly.

[0233] Step 7:

[0234] Picking and packing are carried out quickly and accurately based on information provided by the user through the wearable device.

[0235] Input: AR and related information provided as audio guide

[0236] Action: The user uses visual and auditory information to pick the specified item and transport or pack it to the appropriate location.

[0237] Output: Users working efficiently and accurately

[0238] 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.

[0239] This invention is implemented using a system including a wearable device worn by a user, a server, and a network for communication between them. In particular, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide more personalized information. The specific processing flow of the program is described in detail below.

[0240] System Overview

[0241] The main components are as follows:

[0242] Wearable devices (terminals)

[0243] server

[0244] communication network

[0245] Emotion Engine

[0246] Terminal

[0247] The system is activated when the user puts on the wearable device. The device's camera captures objects within the user's visual field in real time. This video data is preprocessed by an internal processor, and features are extracted using an object detection algorithm. These features are then sent to a server via a communications network.

[0248] Emotion Engine

[0249] The device is equipped with an emotion engine that recognizes the user's emotions from their facial expressions and voice. The emotion engine analyzes camera footage and audio data to identify the user's emotional state (e.g., joy, surprise, sadness, anger, etc.). The detected emotion data, along with the feature values, is also sent to a server via a communication network.

[0250] server

[0251] The server receives the feature data and emotion data sent from the device. Based on the received data, generative artificial intelligence (generative AI) generates relevant information. The generative AI uses a deep learning model (e.g., CNN or RNN) to determine the type of object from the feature data and combines it with emotion data to generate information that best suits the user's current state. The generated information is then sent back to the device via the communications network.

[0252] Information display

[0253] The device visually displays the received relevant information as augmented reality (AR), allowing users to obtain augmented information within their field of vision in real time. The displayed information is overlaid at an appropriate size and angle based on the user's viewpoint and the object's position. Furthermore, the content and format of the information are personalized based on emotional data.

[0254] Specific examples

[0255] Example 1: Museum use

[0256] Consider a scenario in which a user is looking at "ancient statues" in a history museum.

[0257] The device's camera captures video of the statue and extracts features such as shape, color, and texture.

[0258] The terminal transmits these features to a server via a communication network.

[0259] The device's emotion engine analyzes the user's facial expression and determines that the user is expressing surprise.

[0260] The server analyzes both pieces of data and generates a summary that says, "This is an ancient Greek statue from 500 BC, and provides context and origins, as well as additional facts that may surprise the user."

[0261] The device analyzes the information received from the server and displays text and related images such as "500 BC Ancient Greek Statues: Their Historical Background and Amazing Facts" on the statue as AR.

[0262] Example 2: Use in daily life

[0263] Consider a scenario where a user is looking at "product packaging" in a supermarket.

[0264] The device's camera captures images of the product packaging and extracts features from the barcode and label information.

[0265] The terminal transmits these features to a server via a communication network.

[0266] The device's emotion engine analyzes the user's voice and determines whether the user is happy.

[0267] The server analyzes both sets of data and generates encouraging information about the food, including that it's organic, that it's free of certain allergens, and its health benefits.

[0268] The device analyzes the information received from the server and displays text such as "organic food, allergen information, health benefits" and related images as AR on the product packaging.

[0269] In this way, users can instantly acquire a wealth of knowledge and data based on visual information, and by receiving personalized information based on their emotions, the quality of their learning, research, and daily life can be further improved.

[0270] The processing flow will be explained below.

[0271] Step 1:

[0272] The user puts on the wearable device. The wearable device starts up and the camera begins capturing video data within the user's visual field. This video data is captured frame by frame and processed at 30 frames per second (FPS).

[0273] Step 2:

[0274] The device receives the captured video data and performs preprocessing, which includes removing noise from the video data and adjusting the resolution. It then uses object detection algorithms to detect objects and features within its visual range. Specifically, it extracts color, shape, texture, and identifiers such as barcodes and QR codes from the camera's video data.

[0275] Step 3:

[0276] The device's emotion engine analyzes the user's facial expressions and voice to determine their emotional state. The emotion engine uses facial recognition and voice analysis algorithms to determine whether the user is happy, surprised, sad, angry, or other emotions.

[0277] Step 4:

[0278] The extracted feature data and emotion data are converted into JSON format and sent to a server via a communication network, using Wi-Fi or mobile data.

[0279] Step 5:

[0280] The server receives the feature data and emotion data sent from the device. The received data is analyzed by generative artificial intelligence (generative AI). The generative AI uses a deep learning model (e.g., CNN or RNN) to determine the type of object from the feature data and generate related information taking emotion data into account.

[0281] Step 6:

[0282] The server generates relevant information based on the judgment results and emotion data. The generation AI collects relevant information from databases and the internet, generates that information in natural language, and personalizes the information to match the user's emotions. The generated information is then converted back into JSON format.

[0283] Step 7:

[0284] The server generates information and sends it to the terminal via a communication network. The transmitted data includes specific information about the object, related images, text, and so on.

[0285] Step 8:

[0286] The device parses the information received from the server and converts it into a format for display. The received data is parsed appropriately and formatted into a visual display format using an AR library (e.g., Unity or ARKit).

[0287] Step 9:

[0288] The device displays the analyzed information as augmented reality (AR) within the user's field of view. Specifically, text information and images are overlaid on top of the visual data based on the object's position, angle, and size. Furthermore, the content and format of the information are personalized based on the user's emotional data, providing information that corresponds to the user's emotions.

[0289] Step 10:

[0290] The device periodically sends user data to the server and receives updated information as needed. New video data is captured at regular intervals, and feature and emotion data are extracted again and sent to the server. The server continues to generate new information, and the device receives this updated information, always providing the user with the latest information.

[0291] In this way, users can instantly acquire a wealth of knowledge and data based on visual information, and by receiving personalized information based on their emotions, the quality of their learning, research, and daily life can be further improved.

[0292] Example 2

[0293] 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."

[0294] Current information provision systems using wearable devices are limited to acquiring and displaying information within the user's visual field, and do not adequately provide personalized information that takes into account the user's emotional state. This limits the quality of the user experience and makes it difficult to display appropriate information according to the usage scenario.

[0295] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for acquiring information within the visual range of a wearable device worn by a user; means for analyzing the acquired information and extracting features; means for analyzing the user's facial expressions and voice to acquire emotional data; means for transmitting the extracted features and emotional data to the server via a communication network; means for generating related information based on the features and emotional data received by the server using artificial intelligence; means for transmitting the generated information to the wearable device via the communication network; and means for visually displaying the information received by the wearable device as augmented reality. This enables the provision of personalized information according to the user's emotional state. Furthermore, combining visually acquired information with emotional data can improve the quality of the user experience and provide more appropriate information.

[0296] A "wearable device" is a terminal device with computing functions that is worn on the user's body.

[0297] "Visual range" refers to the area that a user can see through a wearable device.

[0298] "Means for acquiring information" refers to devices or methods that use cameras or sensors installed in wearable devices to collect images and data within the visual range.

[0299] "Means for extracting features" refers to algorithms or devices that analyze and extract characteristic data such as the shape, color, and texture of objects from images and data acquired by cameras or sensors.

[0300] A "communications network" is a system that provides an infrastructure for transmitting and receiving data, and includes wired or wireless networks.

[0301] "Server" refers to a computer system that processes and stores data over a network and provides services to client devices.

[0302] "Emotion data" refers to information obtained by analyzing data that represents the emotional state of a user, such as facial expressions and voice.

[0303] "Generative artificial intelligence" refers to technology that uses machine learning and deep learning models to analyze data and generate new information.

[0304] "Augmented reality" refers to a technology that displays computer-generated visual information overlaid on a real-world environment.

[0305] This invention is a system that uses a wearable device worn by a user to analyze information within the user's visual field and provide related information. This system is realized mainly by a wearable device, a server, a communication network, and an emotion engine.

[0306] Hardware and Software Configuration

[0307] A wearable device includes the following elements:

[0308] Camera: Captures objects within its visual range.

[0309] Microphone: Captures user voice.

[0310] Processor: Performs data preprocessing.

[0311] Communication module: Sends and receives data.

[0312] A server is a computer system with high-performance computing power that includes the following elements:

[0313] Generative AI models (e.g., CNNs and RNNs): Analyze data and generate information.

[0314] Database: Stores the acquired and generated data.

[0315] The emotion engine is a software component that analyzes emotions from the user's facial expressions and voice.

[0316] A communications network is the infrastructure that enables data communication over the web.

[0317] Operation explanation

[0318] When a user puts on the wearable device, the system is activated. The camera captures objects within the user's visual field in real time, and the processor analyzes the video data to extract features. These features are then sent to a server via a communication network.

[0319] The emotion engine installed in the wearable device analyzes the captured video and audio data to identify the user's emotional state, which is then transmitted to a server via a communication network.

[0320] The server analyzes the received feature data and emotion data and generates relevant information using a generative AI model (e.g., CNN or RNN). This generated information is personalized and best suited to the type of object and the user's emotional state. The generated information is then sent back to the wearable device via the communication network.

[0321] Specific examples

[0322] Example 1: Museum use

[0323] Consider a case where a user is looking at an "ancient statue" in a history museum. The device's camera captures video of the statue and extracts features such as shape, color, and texture. The device then sends these features to a server via a communications network. The device's emotion engine analyzes the user's facial expression and determines that the user is expressing surprise. The server analyzes both sets of data and generates content that explains, "This is an ancient Greek statue from 500 BC, and provides its historical background and origin, as well as additional facts that may surprise the user." The device then analyzes the information received from the server and displays text such as "500 BC Ancient Greek statue, its historical background, and surprising facts" and related images on top of the statue as AR.

[0324] Example 2: Use in daily life

[0325] Consider a case where a user is looking at a "product package" in a supermarket. The device's camera captures an image of the product package and extracts features from the barcode and label information. The device then sends these features to a server via a communications network. The device's emotion engine analyzes the user's voice and determines that the user is happy. The server analyzes both sets of data and generates encouraging information about "this is organic food, does not contain specific allergens, and its health benefits." The device analyzes the information received from the server and displays text such as "organic food, allergen information, health benefits" and related images on the product package as AR.

[0326] Examples of prompt statements

[0327] 1. "A user looks surprised while looking at an ancient statue in a museum. The statue's features are: Shape: 'Cylindrical', Color: 'Gray', Texture: 'Rough'. Generate historical information about this statue."

[0328] 2. "A user is looking at a product package in a supermarket and exclaims with delight. The product is organic and has barcode: '123456789'. Please generate more information about this."

[0329] This system allows users to obtain visual information in real time and enjoy personalized content that responds to their emotions.

[0330] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0331] Step 1:

[0332] The user puts on the wearable device and the system is started. The input can be a gesture of putting on the device or a voice command. The output can be the activation of each component of the wearable device (camera, microphone, processor, communication module).

[0333] Step 2:

[0334] The device's camera captures objects within the user's field of vision in real time. The input is video data from the camera, and the output is the captured video data. The processor receives the video data and performs preprocessing, specifically image processing such as noise reduction and color filtering.

[0335] Step 3:

[0336] The device applies an object detection algorithm (such as YOLO or SSD) to the preprocessed video data to extract features such as the shape, color, and texture of the object. The input is the preprocessed video data, and the output is the extracted feature data. Specifically, the extracted features include the statue's shape being "cylindrical," its color being "gray," and its texture being "rough."

[0337] Step 4:

[0338] The device's emotion engine analyzes camera footage and microphone audio to identify the user's emotional state. The input is camera footage and microphone audio, and the output is emotion data. Specifically, it analyzes the user's facial expressions and tone of voice to identify emotions such as "surprise" or "joy."

[0339] Step 5:

[0340] The device transmits the extracted feature data and emotion data to a server via a communication network. The input is the feature data and emotion data, and the output is the data transmitted to the server. Specifically, the feature data (shape: 'cylindrical', color: 'gray', texture: 'rough') and emotion data (surprise) are transmitted to the server.

[0341] Step 6:

[0342] The server receives feature data and emotion data sent from the device. The input is the data sent from the device, and the output is the received data. The server inputs the received data into a generative AI model (e.g., CNN or RNN) to generate related information. Specifically, historical information and additional facts about ancient Greek statues are generated.

[0343] Step 7:

[0344] The server transmits the generated related information to the terminal via a communication network. The input is the generated information, and the output is the information transmitted to the terminal. The terminal receives and analyzes this information.

[0345] Step 8:

[0346] Based on the received information, the device visually displays the information on top of the object as augmented reality (AR). The input is the information received from the server, and the output is the AR information displayed within the user's field of vision. Specifically, text such as "500 BC Ancient Greek Statues: Their Historical Background and Amazing Facts" and related images are displayed on top of the statue.

[0347] This allows users to get real-time personalized information related to objects within their field of vision.

[0348] (Application example 2)

[0349] 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."

[0350] Conventional factory robots and assistance systems have difficulty monitoring the operator's condition in real time and providing assistance information at the appropriate time. Furthermore, few systems recognize the operator's emotions and provide work assistance, and they have not adequately improved work efficiency or prevented errors. This has led to problems such as reduced work efficiency and an increased risk of errors.

[0351] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0352] means for transmitting emotion data to a server;

[0353] means for generating related information based on the features received by the server using a generating artificial intelligence;

[0354] means for transmitting the generated information to a wearable device via a communication network;

[0355] This includes:

[0356] It is possible to detect the user's emotions in real time and provide personalized work support information and advice based on that, thereby improving the operator's work efficiency.

[0357] A "wearable device" is an electronic device that can be worn by a user and has the ability to acquire, analyze, and display information in real time.

[0358] An "emotion engine" is a software or hardware system that recognizes and analyzes emotions from a user's facial expressions and voice.

[0359] A "communications network" is an infrastructure for transmitting and receiving data, including the Internet and dedicated data communication lines.

[0360] A "server" is a computing resource that receives data transmitted from wearable devices over a network and generates analysis and related information.

[0361] "Generative artificial intelligence" refers to algorithms and models that generate information from data using techniques such as machine learning and deep learning.

[0362] "Features" are numerical data used to analyze information such as objects within the visual range and the emotional state of the user.

[0363] "Augmented reality" is a technology that displays digital information overlaid on real-world visual information, providing users with a richer information environment.

[0364] "Personalized information" is information that is specifically tailored to a user's emotional state and individual needs.

[0365] An "operator" is a human user who operates machinery or equipment in a factory or work environment.

[0366] "Work support information" is information that includes guidelines and advice for operators to perform work safely and efficiently.

[0367] This invention is implemented in a system that uses a wearable device worn by an operator in a factory or work environment, a server, and a network for communication between them. In particular, by combining it with an emotion engine that recognizes the operator's emotions, it is possible to provide more personalized work support information in real time.

[0368] System Overview

[0369] The main components are as follows:

[0370] Wearable device (terminal): A device worn by the operator that captures video, recognizes emotions, and displays AR.

[0371] Server: Analyzes the received data and generates relevant information using generation AI.

[0372] Communications network: The infrastructure through which devices and servers send and receive data.

[0373] Terminal

[0374] The wearable device is worn by the operator, and the camera captures images within the visual range in real time. This image data is preprocessed by an internal processor, and features are extracted using an object detection algorithm. In addition, an emotion engine analyzes the operator's facial expressions and voice to generate emotion data. This data is sent to a server via a communication network.

[0375] Emotion Engine

[0376] The wearable device is equipped with an emotion engine that analyzes the operator's emotional state in real time. The emotion engine identifies the operator's emotions (e.g., stress, joy, anxiety, etc.) based on camera footage and audio data. The analyzed emotion data is sent to a server along with feature data.

[0377] server

[0378] The server receives the feature data and emotion data sent from the device and generates relevant information using a generative AI model. The generated information uses a deep learning model (e.g., CNN or RNN) to adapt to the operator's current emotional state and work context. This information is then sent back to the wearable device via the communication network.

[0379] Information display

[0380] The wearable device visually displays the work support information received from the server as augmented reality (AR), allowing the operator to obtain augmented information within their visual range in real time. The displayed information is overlaid at an appropriate size and angle based on the operator's viewpoint and work situation. Furthermore, the content and format of the information are personalized based on emotional data.

[0381] Specific examples

[0382] Example: Factory use

[0383] Consider an operator picking up a part on an assembly line.

[0384] The device's camera captures images of the parts and extracts features such as shape, color, and texture.

[0385] The terminal transmits these features to a server via a communication network.

[0386] The device's emotion engine analyzes the operator's facial expressions and voice to determine if the operator is confused.

[0387] The server analyzes both sets of data and generates "This part is used on XYZ machine, and its assembly instructions and common error countermeasures."

[0388] The device analyzes the information received from the server and displays text such as "XYZ machine assembly procedure common error countermeasures" and related images on top of the part as AR.

[0389] Prompt Sentence Examples

[0390] "Build an application that recognizes an operator's emotions in real time and provides assembly assistance information based on his / her psychological state. The specific steps are as follows:"

[0391] "If an operator is confused, think about what information you should provide and display it in AR."

[0392] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0393] Step 1:

[0394] The terminal uses the camera of the wearable device worn by the operator to capture images within its visual range in real time. The input is the camera image, and the output is the captured image data. Specifically, the camera captures images at a constant frame rate and stores them in an internal buffer.

[0395] Step 2:

[0396] The device preprocesses the captured video data and extracts features using an object detection algorithm (e.g., YOLO or SSD). The input is the captured video data, and the output is the extracted features. Specific operations include noise removal, resizing, and filtering to enhance features in the video data.

[0397] Step 3:

[0398] The terminal uses an emotion engine to analyze emotions from the operator's facial expressions and voice data. The input is facial expression data and voice data, and the output is analyzed emotion data. Specific operations include extracting face areas from camera footage and performing spectrum analysis of voice data.

[0399] Step 4:

[0400] The device transmits the extracted feature data and emotion data to a server via a communication network. The input is the feature data and emotion data, and the output is a data packet transmitted over the network. Specifically, the data is serialized and packetized according to the network protocol.

[0401] Step 5:

[0402] The server analyzes the received feature data and emotion data and generates related information using a generative AI model. The input is feature data and emotion data, and the output is the generated related information. Specifically, the server analyzes the feature data using a convolutional neural network (CNN) and the emotion data using a recurrent neural network (RNN) to generate appropriate assistance information.

[0403] Step 6:

[0404] The server transmits the generated related information to the terminal via a communication network. The input is the generated related information, and the output is a data packet transmitted via the network. Specific operations include serializing the information and packetizing it into data packets.

[0405] Step 7:

[0406] The device interprets the received related information and visually displays it as augmented reality (AR). The input is the received related information, and the output is the AR content displayed on the display of the wearable device. Specifically, the related information is overlaid on the video data as an overlay and displayed in the appropriate position and size.

[0407] Step 8:

[0408] The user performs tasks based on personalized work support information displayed as augmented reality. The input is the visually displayed support information, and the output is the user's work results. Specifically, the user follows the guidelines provided through AR to properly progress through the task.

[0409] 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.

[0410] 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.

[0411] 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.

[0412] [Second embodiment]

[0413] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0414] 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.

[0415] 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).

[0416] 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.

[0417] 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.

[0418] 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).

[0419] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[0420] 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.

[0421] 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.

[0422] 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.

[0423] 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.

[0424] 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."

[0425] The present invention is implemented using a system including a wearable device worn by a user, a server, and a network for communication therebetween. The specific processing flow of the program is described in detail below.

[0426] System Overview

[0427] The main components are as follows:

[0428] Wearable devices (terminals)

[0429] server

[0430] communication network

[0431] Terminal

[0432] The system is activated when the user puts on the wearable device. The device's camera captures objects within the user's visual field in real time. This video data is preprocessed by an internal processor, and features are extracted using an object detection algorithm. These features are then sent to a server via a communications network.

[0433] server

[0434] The server receives the feature data sent from the device. Based on the received data, generative artificial intelligence (generative AI) generates related information. The generative AI uses a deep learning model (e.g., CNN or RNN) to identify the type of object and its related information. The generated information is then sent back to the device via the communication network.

[0435] Information display

[0436] The device visually displays the received relevant information as augmented reality (AR), allowing the user to obtain augmented information within their field of vision in real time. The displayed information is overlaid at an appropriate size and angle based on the user's viewpoint and the object's position.

[0437] Specific examples

[0438] Example 1: Museum use

[0439] Consider a scenario in which a user is looking at "ancient statues" in a history museum.

[0440] The device's camera captures video of the statue and extracts features such as shape, color, and texture.

[0441] The terminal transmits these features to a server via a communication network.

[0442] The server analyzes the features and determines that "this is an ancient Greek statue from 500 BC," and the generation AI generates information such as the historical background, the origin and significance of the statue.

[0443] The device analyzes the information received from the server and displays text such as "500 BC Ancient Greek Statues: Their Historical Background and Origins" and related images on the statue as AR.

[0444] Example 2: Use in daily life

[0445] Consider a scenario where a user is looking at "product packaging" in a supermarket.

[0446] The device's camera captures images of the product packaging and extracts features from the barcode and label information.

[0447] The terminal transmits these features to a server via a communication network.

[0448] The server analyzes the features and determines that "this is an organic food and does not contain specific allergens," and the generation AI generates detailed product information, nutritional information, consumer reviews, etc.

[0449] The device analyzes the information received from the server and displays text such as "organic food, ingredient information, consumer reviews" and related images on the product packaging as AR.

[0450] This allows users to instantly acquire a wealth of knowledge and data based on visual information, improving the quality of their learning, research, and daily life.The system based on this invention aims to provide efficient and highly accurate information, significantly improving the user experience.

[0451] The processing flow will be explained below.

[0452] Step 1:

[0453] The user puts on the wearable device. The wearable device starts up and the camera begins capturing video data within the user's visual field. This video data is captured frame by frame and processed at 30 frames per second (FPS).

[0454] Step 2:

[0455] The device receives the captured video data and performs preprocessing, which includes removing noise from the video data and adjusting the resolution. It then uses object detection algorithms to detect objects and features within its visual range. Specifically, it extracts color, shape, texture, and identifiers such as barcodes and QR codes from the camera's video data.

[0456] Step 3:

[0457] The extracted feature data is converted into JSON format and sent to a server via a communication network, using Wi-Fi or mobile data communication.

[0458] Step 4:

[0459] The server receives the feature data sent from the device. The received data is analyzed by generative artificial intelligence (generative AI). The generative AI uses a deep learning model (e.g., CNN or RNN) to determine the type of object from the features.

[0460] Step 5:

[0461] The server generates relevant information based on the results of the judgment. The generation AI collects relevant information from databases and the Internet and generates that information in natural language. The generated information is then converted back into JSON format.

[0462] Step 6:

[0463] The server generates information and sends it to the terminal via a communication network. The transmitted data includes specific information about the object, related images, text, and so on.

[0464] Step 7:

[0465] The device parses the information received from the server and converts it into a format for display. The received data is parsed appropriately and formatted into a visual display format using an AR library (e.g., Unity or ARKit).

[0466] Step 8:

[0467] The device displays the analyzed information in the user's field of view as augmented reality (AR), overlaying text information and images on top of the visual data based on the object's position, angle, and size, allowing the user to obtain additional information about objects within their field of view in real time.

[0468] Step 9:

[0469] The device periodically sends user data to the server and receives updated information as needed. New video data is captured at regular intervals, and features are extracted again and sent to the server. The server continues to generate new information, and the device continues to receive this updated information, so that the latest information is always provided to the user.

[0470] In this way, users can instantly acquire a wealth of knowledge and data based on visual information, improving the quality of their learning, research, and daily life.

[0471] Example 1

[0472] 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."

[0473] Conventional wearable devices have limited the information that users can visually obtain, making it difficult to provide information in real time. Furthermore, analyzing acquired data, extracting features, and generating and displaying relevant information require significant time, which can detract from the user experience. Furthermore, they are limited to use in specific situations and environments, limiting their versatile use. Furthermore, conventional systems often lack the accuracy and relevance of the generated information, failing to provide useful information to users.

[0474] 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.

[0475] In this invention, the server includes means for acquiring information within the visual range of a device worn by a user, means for analyzing the acquired information and extracting features using a trained algorithm, means for transmitting the extracted features to a central processing unit via a communication network, means for generating related information based on the features received by the central processing unit using generative artificial intelligence, means for transmitting the generated information to the device via the communication network, and means for displaying the information received by the device as visual augmentation, thereby enabling users to expand the information they can visually obtain in real time and instantly acquire a wealth of knowledge and data.

[0476] "User" in this invention refers to an individual who wears and uses the device.

[0477] "Device" refers to a wearable device worn by a user that acquires and displays information within visual range.

[0478] "Visual information" refers to video and other data captured by a user's device using cameras and sensors.

[0479] "Trained algorithm" refers to the process of analyzing and extracting features using a machine learning model that has been trained on a large dataset in advance.

[0480] "Features" refers to attribute data such as shape, color, texture, barcode, and label information extracted from information within the visual range.

[0481] "Communication network" refers to the internet line or wireless communication technology (e.g., Wi-Fi, 5G, etc.) used to transmit the extracted feature data to the server.

[0482] "Central Processing Unit" refers to a computer system that functions as a server, receives and analyzes feature data, and generates and transmits related information.

[0483] "Generative artificial intelligence" refers to the process of using deep learning models (e.g., CNN, RNN) to generate relevant information based on received feature data.

[0484] "Related information" refers to information that is useful to the user, such as the type of generated object, its background information, history information, product information, and the like.

[0485] "Visual augmentation" refers to augmented reality (AR) technology that displays generated relevant information on a device to enhance a user's visual experience.

[0486] The present invention is embodied in a system including a wearable device worn by a user, a server, and a communication network connecting them. Specific configurations and processes for promoting the invention are described below.

[0487] System Configuration

[0488] 1. Wearable devices (terminals)

[0489] The wearable device worn by the user is equipped with a high-resolution camera and a built-in processor. The camera captures the user's visual field in real time, and the processor processes and pre-processes the video data. The wearable device also has a wireless communication module and communicates with a server via the Internet.

[0490] 2. Server

[0491] The server acts as a central processing unit, receiving and analyzing the feature data sent from the device. The server is equipped with hardware and software to run deep learning models (e.g., CNN, RNN). The generative AI uses this deep learning model to generate relevant information based on the feature data.

[0492] Data Processing and Flow

[0493] Video capture and pre-processing

[0494] The device's camera captures images within the user's visual field in real time, and the captured image data is pre-processed by a processor to remove noise and improve image quality.

[0495] Feature extraction

[0496] The preprocessed video data is then analyzed by an on-device trained algorithm (e.g., an object detection algorithm such as YOLO or SSD) to extract features (e.g., shape, color, texture, barcode, or label information) from the objects in the video.

[0497] Data transmission

[0498] The extracted feature data is sent to a server via a communication network using wireless communication such as Wi-Fi or 5G, and the data format used is a lightweight format such as JSON.

[0499] Server-side data analysis and information generation

[0500] The server receives the feature data sent from the device and generates relevant information using a deep learning model. For example, a CNN model can be used to identify an object in a video as an ancient Greek statue from 500 BC, and the AI ​​will generate information about its historical background, origin, significance, etc.

[0501] Information transmission and display

[0502] The generated related information is then sent from the server to the terminal via the communication network. The terminal analyzes the received information and displays it as an extension of the user's visual field. The information is overlaid at an appropriate size and position and presented visually to the user.

[0503] Specific examples

[0504] Example 1: Museum use

[0505] Consider a scenario in which a user is looking at ancient statues in a history museum.

[0506] The device's camera captures video of the statue and extracts its features.

[0507] The device transmits the extracted features to the server.

[0508] The server analyzes the features and determines that "this is an ancient Greek statue from 500 BC," and the generation AI generates information such as the historical background, origin, and significance of the statue.

[0509] The device displays the received information as a visual augmentation, and the user can see text such as "500 BC Ancient Greek Statue: Its Historical Background and Origin" on top of the statue in AR.

[0510] Example 2: Use in daily life

[0511] Consider a scenario where a user is looking at product packaging in a supermarket.

[0512] The device's camera captures images of the product packaging and extracts features from the barcode and label information.

[0513] The device transmits the extracted features to the server.

[0514] The server analyzes the features and determines that "this is an organic food and does not contain specific allergens," and the generation AI generates detailed product information, nutritional information, consumer reviews, etc.

[0515] The device displays the received information as a visual augmentation, and users can see text such as "Organic Food, Ingredient Information, Consumer Reviews" and related information on the product packaging in AR.

[0516] Prompt Sentence Examples

[0517] "Please tell me about the historical background, origins, and significance of ancient Greek statues."

[0518] "Based on the information on this product package, please tell me if it is organic, what ingredients it contains, and what consumer reviews it has."

[0519] In this way, the present invention provides a system that expands the information that users can visually obtain and allows them to instantly obtain a wealth of knowledge and data, thereby significantly improving the quality of their learning, research, and daily life.

[0520] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0521] Step 1: Booting the device

[0522] The wearable device worn by the user starts up automatically. At startup, various sensors inside the device begin to operate, and the camera and processor enter a ready state. The input is the user wearing the device, and the output is the device being ready. Specifically, the sensors detect that the user is wearing the device and prepare the environment for the entire system to operate.

[0523] Step 2: Capture footage

[0524] The device's camera captures objects within the user's visual field in real time. The input is the visual field image detected by the camera, and the output is the captured high-resolution video data. Specifically, the camera captures video at a rate of 30 frames per second or more and sends the data to a processor in either raw or compressed format.

[0525] Step 3: Preprocessing the video data

[0526] The processor inside the device receives the video data and performs preprocessing such as noise removal and image quality correction. The input is the captured video data, and the output is the preprocessed video data. Specifically, the processor performs noise removal using a Gaussian filter and contrast correction using histogram equalization.

[0527] Step 4: Feature extraction

[0528] A trained algorithm on the device extracts features from the preprocessed video data. The input is the preprocessed video data, and the output is object features (e.g., shape, color, texture, barcode, label information, etc.). Specifically, object detection algorithms such as YOLO and SSD are used to analyze important parts of the video and extract the necessary features as data.

[0529] Step 5: Send feature data

[0530] The device transmits feature data to a central processing unit (server) via wireless communication (e.g., Wi-Fi, 5G). The input is the extracted feature data, and the output is the data transmitted via the communication network. Specifically, the feature data is converted to a format such as JSON, compressed, and transmitted via the wireless communication module.

[0531] Step 6: Data reception and analysis

[0532] The server receives and analyzes the feature data. The input is the feature data sent from the device, and the output is related information generated by the generative AI model. Specifically, the data is received in the execution environment of the deep learning model (e.g., CNN, RNN), and the analysis program analyzes the features and generates related information.

[0533] Step 7: Generate related information

[0534] The server uses generative AI to generate relevant information based on the received feature data. The input is the feature data obtained through analysis, and the output is relevant information (e.g., historical information, product information, etc.). Specifically, the deep learning model identifies the type of object, and the relevant information is generated using a natural language generation model. For example, background information about an ancient Greek statue and its significance are generated.

[0535] Step 8: Submit relevant information

[0536] The server transmits the generated related information to the terminal via a communication network. The input is the generated related information, and the output is the transmitted information. Specifically, the server converts the related information into an appropriate format and transmits it to the terminal via a wireless communication network.

[0537] Step 9: Displaying Information as a Visual Augmentation

[0538] The device analyzes the relevant information received and displays it as augmented reality (AR). The input is the relevant information sent from the server, and the output is the augmented reality information displayed within the user's visual field. Specifically, the relevant information is overlaid at an appropriate size and position to fit the user's visual environment. For example, text or images may be displayed on a statue, seamlessly integrating with the user's visual field.

[0539] (Application example 1)

[0540] 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."

[0541] At logistics centers, the ability to quickly and accurately pick and pack large quantities of products is a major challenge. However, conventional methods require workers to locate products using only visual information, which creates challenges in terms of work efficiency and accuracy. Furthermore, there are limitations to how much information workers can grasp manually, making errors more likely. Therefore, there is a need for a system that provides both visual and auditory support for work.

[0542] 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.

[0543] In this invention, the server includes: means for acquiring information within the visual range of a wearable device worn by a user; means for analyzing the acquired information and extracting features; means for transmitting the extracted features to the server via a communications network; means for generating related information based on the features received by the server using generative artificial intelligence; means for transmitting the generated information to the wearable device via the communications network; and means for visually displaying the received information as augmented reality on the wearable device, which is further worn by a worker to support work at a logistics center. This allows workers to obtain visual and auditory information in real time through the wearable device, enabling them to pick and pack products quickly and accurately.

[0544] A "wearable device" is an electronic device that can be worn by the user on the body. It is a terminal that has a built-in camera, display, and sensor and can acquire and display information.

[0545] "Information within visual range" refers to all information within the user's field of view that is captured by a camera attached to a wearable device.

[0546] "Features" refer to specific patterns, attributes, and data extracted from information within the visual field that are necessary to identify objects.

[0547] "Communications network" refers to the entire infrastructure for transmitting and receiving data between wearable devices and servers, and between multiple devices.

[0548] "Server" refers to the computer system that receives data sent from a wearable device and processes, analyzes, and generates information.

[0549] "Generative artificial intelligence" refers to AI that uses machine learning and deep learning algorithms based on large amounts of data to generate relevant information based on features.

[0550] "Augmented reality" refers to the technology of overlaying computer-generated information onto real-world visual information.

[0551] A "logistics center" refers to a facility where logistics operations such as collection, delivery, storage, sorting, packaging, and shipping of goods are carried out.

[0552] "Work support" refers to providing visual and auditory information to workers so that they can perform their work more efficiently and accurately.

[0553] The present invention provides a system that uses wearable devices, a server, and a communication network to improve work efficiency in a logistics center.

[0554] System Overview

[0555] The main components are as follows:

[0556] Wearable devices (e.g., smart glasses or smart eyeglasses)

[0557] server

[0558] Communication network (Wi-Fi or 5G)

[0559] Wearable devices

[0560] The system is activated when a worker puts on the wearable device. The device's built-in camera captures information within the worker's visual range (products, barcodes, QR codes, etc.) in real time. This video data is preprocessed by the device's processor, and feature values ​​are extracted. These feature values ​​are then sent to a server via a communications network.

[0561] server

[0562] The server receives the feature data sent from the device. Generative artificial intelligence (generative AI) analyzes this feature data and generates related product information and picking instructions. The generative AI analyzes the features using a deep learning model (e.g., CNN or RNN) and generates information. The generated information is then sent back to the wearable device via the communication network.

[0563] Augmented reality information display

[0564] The wearable device visually displays the received information as augmented reality (AR), allowing workers to see augmented information in real time within their field of vision. The displayed information is overlaid at the appropriate size and angle based on the worker's viewpoint and the location of the item.

[0565] Specific examples

[0566] Use at logistics centers

[0567] Consider a scenario where a worker is picking items at a logistics center.

[0568] The camera in the wearable device captures images of the shelves and extracts features such as barcodes, QR codes, and shapes.

[0569] The wearable device transmits these features to a server via a communication network.

[0570] The server analyzes the features and determines, "This is product A, and its shelf number is 12B," and the generation AI generates picking instructions and inventory information for this product.

[0571] The wearable device analyzes the information received from the server and displays text such as "Product A, shelf number 12B, quantity in stock 30" and related images, as well as audio guidance, on the shelf as AR.

[0572] Hardware and Software Description

[0573] Hardware:

[0574] Wearable devices (smart glasses, etc.)

[0575] Camera (built into wearable device)

[0576] Communication networks (Wi-Fi, 5G)

[0577] software:

[0578] Python (image processing, running generative AI models)

[0579] OpenCV (image processing library)

[0580] Requests (HTTP communication library)

[0581] ARModule (AR display library)

[0582] Examples of prompt statements

[0583] Imagine a scenario in which a worker wearing smart glasses at a distribution center is searching for an item in a picking area. An example prompt is as follows:

[0584] "Analyze product information from the video data and generate the information to be displayed. For example, if the product shown in the video is 'Product A', generate and respond with its name, stock quantity, and shelf number as 'Product A, stock quantity 30, shelf number 12B'."

[0585] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0586] Step 1:

[0587] The user puts on the wearable device and begins work in the logistics center.

[0588] Input: Visual information from a wearable device worn by the user

[0589] How it works: A camera built into the wearable device captures information in real time that comes within the user's visual field.

[0590] Output: Captured video data

[0591] Step 2:

[0592] The device analyzes the video data and extracts features.

[0593] Input: Captured video data

[0594] How it works: The device's processor processes the video data and uses an image recognition algorithm (e.g., OpenCV) to extract features such as product shelves, barcodes, and QR codes.

[0595] Output: Extracted feature data

[0596] Step 3:

[0597] The terminal transmits the feature data to the server via a communication network.

[0598] Input: Extracted feature data

[0599] Action: The device formats the feature data and sends it to the server using an HTTP communication library (e.g., Requests).

[0600] Output: Feature data received by the server

[0601] Step 4:

[0602] The server generates related information using artificial intelligence based on the received feature data.

[0603] Input: Feature data sent from the device

[0604] Operation: The generative AI model runs on the server, analyzes feature data using deep learning algorithms (CNN or RNN), and generates related product information, picking instructions, inventory information, etc.

[0605] Output: Related information generated

[0606] Step 5:

[0607] The server transmits the generated related information to the terminal via a communication network.

[0608] Input: Generated related information

[0609] How it works: The server formats the relevant information and sends it to the device using an HTTP communication library.

[0610] Output: Relevant information received by the device

[0611] Step 6:

[0612] The device analyzes the relevant information received and displays it visually as augmented reality (AR).

[0613] Input: Relevant information received by the device

[0614] Operation: Using an AR library (e.g., ARModule), the device overlays relevant information received with an appropriate position and size based on the user's viewpoint and the location of the item. Audio guidance is also integrated to provide voice instructions to the worker.

[0615] Output: The information the user receives visually and audibly.

[0616] Step 7:

[0617] Picking and packing are carried out quickly and accurately based on information provided by the user through the wearable device.

[0618] Input: AR and related information provided as audio guide

[0619] Action: The user uses visual and auditory information to pick the specified item and transport or pack it to the appropriate location.

[0620] Output: Users working efficiently and accurately

[0621] 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.

[0622] This invention is implemented using a system including a wearable device worn by a user, a server, and a network for communication between them. In particular, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide more personalized information. The specific processing flow of the program is described in detail below.

[0623] System Overview

[0624] The main components are as follows:

[0625] Wearable devices (terminals)

[0626] server

[0627] communication network

[0628] Emotion Engine

[0629] Terminal

[0630] The system is activated when the user puts on the wearable device. The device's camera captures objects within the user's visual field in real time. This video data is preprocessed by an internal processor, and features are extracted using an object detection algorithm. These features are then sent to a server via a communications network.

[0631] Emotion Engine

[0632] The device is equipped with an emotion engine that recognizes the user's emotions from their facial expressions and voice. The emotion engine analyzes camera footage and audio data to identify the user's emotional state (e.g., joy, surprise, sadness, anger, etc.). The detected emotion data, along with the feature values, is also sent to a server via a communication network.

[0633] server

[0634] The server receives the feature data and emotion data sent from the device. Based on the received data, generative artificial intelligence (generative AI) generates relevant information. The generative AI uses a deep learning model (e.g., CNN or RNN) to determine the type of object from the feature data and combines it with emotion data to generate information that best suits the user's current state. The generated information is then sent back to the device via the communications network.

[0635] Information display

[0636] The device visually displays the received relevant information as augmented reality (AR), allowing users to obtain augmented information within their field of vision in real time. The displayed information is overlaid at an appropriate size and angle based on the user's viewpoint and the object's position. Furthermore, the content and format of the information are personalized based on emotional data.

[0637] Specific examples

[0638] Example 1: Museum use

[0639] Consider a scenario in which a user is looking at "ancient statues" in a history museum.

[0640] The device's camera captures video of the statue and extracts features such as shape, color, and texture.

[0641] The terminal transmits these features to a server via a communication network.

[0642] The device's emotion engine analyzes the user's facial expression and determines that the user is expressing surprise.

[0643] The server analyzes both pieces of data and generates a summary that says, "This is an ancient Greek statue from 500 BC, and provides context and origins, as well as additional facts that may surprise the user."

[0644] The device analyzes the information received from the server and displays text and related images such as "500 BC Ancient Greek Statues: Their Historical Background and Amazing Facts" on the statue as AR.

[0645] Example 2: Use in daily life

[0646] Consider a scenario where a user is looking at "product packaging" in a supermarket.

[0647] The device's camera captures images of the product packaging and extracts features from the barcode and label information.

[0648] The terminal transmits these features to a server via a communication network.

[0649] The device's emotion engine analyzes the user's voice and determines whether the user is happy.

[0650] The server analyzes both sets of data and generates encouraging information about the food, including that it's organic, that it's free of certain allergens, and its health benefits.

[0651] The device analyzes the information received from the server and displays text such as "organic food, allergen information, health benefits" and related images as AR on the product packaging.

[0652] In this way, users can instantly acquire a wealth of knowledge and data based on visual information, and by receiving personalized information based on their emotions, the quality of their learning, research, and daily life can be further improved.

[0653] The processing flow will be explained below.

[0654] Step 1:

[0655] The user puts on the wearable device. The wearable device starts up and the camera begins capturing video data within the user's visual field. This video data is captured frame by frame and processed at 30 frames per second (FPS).

[0656] Step 2:

[0657] The device receives the captured video data and performs preprocessing, which includes removing noise from the video data and adjusting the resolution. It then uses object detection algorithms to detect objects and features within its visual range. Specifically, it extracts color, shape, texture, and identifiers such as barcodes and QR codes from the camera's video data.

[0658] Step 3:

[0659] The device's emotion engine analyzes the user's facial expressions and voice to determine their emotional state. The emotion engine uses facial recognition and voice analysis algorithms to determine whether the user is happy, surprised, sad, angry, or other emotions.

[0660] Step 4:

[0661] The extracted feature data and emotion data are converted into JSON format and sent to a server via a communication network, using Wi-Fi or mobile data.

[0662] Step 5:

[0663] The server receives the feature data and emotion data sent from the device. The received data is analyzed by generative artificial intelligence (generative AI). The generative AI uses a deep learning model (e.g., CNN or RNN) to determine the type of object from the feature data and generate related information taking emotion data into account.

[0664] Step 6:

[0665] The server generates relevant information based on the judgment results and emotion data. The generation AI collects relevant information from databases and the internet, generates that information in natural language, and personalizes the information to match the user's emotions. The generated information is then converted back into JSON format.

[0666] Step 7:

[0667] The server generates information and sends it to the terminal via a communication network. The transmitted data includes specific information about the object, related images, text, and so on.

[0668] Step 8:

[0669] The device parses the information received from the server and converts it into a format for display. The received data is parsed appropriately and formatted into a visual display format using an AR library (e.g., Unity or ARKit).

[0670] Step 9:

[0671] The device displays the analyzed information as augmented reality (AR) within the user's field of view. Specifically, text information and images are overlaid on top of the visual data based on the object's position, angle, and size. Furthermore, the content and format of the information are personalized based on the user's emotional data, providing information that corresponds to the user's emotions.

[0672] Step 10:

[0673] The device periodically sends user data to the server and receives updated information as needed. New video data is captured at regular intervals, and feature and emotion data are extracted again and sent to the server. The server continues to generate new information, and the device receives this updated information, always providing the user with the latest information.

[0674] In this way, users can instantly acquire a wealth of knowledge and data based on visual information, and by receiving personalized information based on their emotions, the quality of their learning, research, and daily life can be further improved.

[0675] Example 2

[0676] 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."

[0677] Current information provision systems using wearable devices are limited to acquiring and displaying information within the user's visual field, and do not adequately provide personalized information that takes into account the user's emotional state. This limits the quality of the user experience and makes it difficult to display appropriate information according to the usage scenario.

[0678] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for acquiring information within the visual range of a wearable device worn by a user; means for analyzing the acquired information and extracting features; means for analyzing the user's facial expressions and voice to acquire emotional data; means for transmitting the extracted features and emotional data to the server via a communication network; means for generating related information based on the features and emotional data received by the server using artificial intelligence; means for transmitting the generated information to the wearable device via the communication network; and means for visually displaying the information received by the wearable device as augmented reality. This enables the provision of personalized information according to the user's emotional state. Furthermore, combining visually acquired information with emotional data can improve the quality of the user experience and provide more appropriate information.

[0679] A "wearable device" is a terminal device with computing functions that is worn on the user's body.

[0680] "Visual range" refers to the area that a user can see through a wearable device.

[0681] "Means for acquiring information" refers to devices or methods that use cameras or sensors installed in wearable devices to collect images and data within the visual range.

[0682] "Means for extracting features" refers to algorithms or devices that analyze and extract characteristic data such as the shape, color, and texture of objects from images and data acquired by cameras or sensors.

[0683] A "communications network" is a system that provides an infrastructure for transmitting and receiving data, and includes wired or wireless networks.

[0684] "Server" refers to a computer system that processes and stores data over a network and provides services to client devices.

[0685] "Emotion data" refers to information obtained by analyzing data that represents the emotional state of a user, such as facial expressions and voice.

[0686] "Generative artificial intelligence" refers to technology that uses machine learning and deep learning models to analyze data and generate new information.

[0687] "Augmented reality" refers to a technology that displays computer-generated visual information overlaid on a real-world environment.

[0688] This invention is a system that uses a wearable device worn by a user to analyze information within the user's visual field and provide related information. This system is realized mainly by a wearable device, a server, a communication network, and an emotion engine.

[0689] Hardware and Software Configuration

[0690] A wearable device includes the following elements:

[0691] Camera: Captures objects within its visual range.

[0692] Microphone: Captures user voice.

[0693] Processor: Performs data preprocessing.

[0694] Communication module: Sends and receives data.

[0695] A server is a computer system with high-performance computing power that includes the following elements:

[0696] Generative AI models (e.g., CNNs and RNNs): Analyze data and generate information.

[0697] Database: Stores the acquired and generated data.

[0698] The emotion engine is a software component that analyzes emotions from the user's facial expressions and voice.

[0699] A communications network is the infrastructure that enables data communication over the web.

[0700] Operation explanation

[0701] When a user puts on the wearable device, the system is activated. The camera captures objects within the user's visual field in real time, and the processor analyzes the video data to extract features. These features are then sent to a server via a communication network.

[0702] The emotion engine installed in the wearable device analyzes the captured video and audio data to identify the user's emotional state, which is then transmitted to a server via a communication network.

[0703] The server analyzes the received feature data and emotion data and generates relevant information using a generative AI model (e.g., CNN or RNN). This generated information is personalized and best suited to the type of object and the user's emotional state. The generated information is then sent back to the wearable device via the communication network.

[0704] Specific examples

[0705] Example 1: Museum use

[0706] Consider a case where a user is looking at an "ancient statue" in a history museum. The device's camera captures video of the statue and extracts features such as shape, color, and texture. The device then sends these features to a server via a communications network. The device's emotion engine analyzes the user's facial expression and determines that the user is expressing surprise. The server analyzes both sets of data and generates content that explains, "This is an ancient Greek statue from 500 BC, and provides its historical background and origin, as well as additional facts that may surprise the user." The device then analyzes the information received from the server and displays text such as "500 BC Ancient Greek statue, its historical background, and surprising facts" and related images on top of the statue as AR.

[0707] Example 2: Use in daily life

[0708] Consider a case where a user is looking at a "product package" in a supermarket. The device's camera captures an image of the product package and extracts features from the barcode and label information. The device then sends these features to a server via a communications network. The device's emotion engine analyzes the user's voice and determines that the user is happy. The server analyzes both sets of data and generates encouraging information about "this is organic food, does not contain specific allergens, and its health benefits." The device analyzes the information received from the server and displays text such as "organic food, allergen information, health benefits" and related images on the product package as AR.

[0709] Examples of prompt statements

[0710] 1. "A user looks surprised while looking at an ancient statue in a museum. The statue's features are: Shape: 'Cylindrical', Color: 'Gray', Texture: 'Rough'. Generate historical information about this statue."

[0711] 2. "A user is looking at a product package in a supermarket and exclaims with delight. The product is organic and has barcode: '123456789'. Please generate more information about this."

[0712] This system allows users to obtain visual information in real time and enjoy personalized content that responds to their emotions.

[0713] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0714] Step 1:

[0715] The user puts on the wearable device and the system is started. The input can be a gesture of putting on the device or a voice command. The output can be the activation of each component of the wearable device (camera, microphone, processor, communication module).

[0716] Step 2:

[0717] The device's camera captures objects within the user's field of vision in real time. The input is video data from the camera, and the output is the captured video data. The processor receives the video data and performs preprocessing, specifically image processing such as noise reduction and color filtering.

[0718] Step 3:

[0719] The device applies an object detection algorithm (such as YOLO or SSD) to the preprocessed video data to extract features such as the shape, color, and texture of the object. The input is the preprocessed video data, and the output is the extracted feature data. Specifically, the extracted features include the statue's shape being "cylindrical," its color being "gray," and its texture being "rough."

[0720] Step 4:

[0721] The device's emotion engine analyzes camera footage and microphone audio to identify the user's emotional state. The input is camera footage and microphone audio, and the output is emotion data. Specifically, it analyzes the user's facial expressions and tone of voice to identify emotions such as "surprise" or "joy."

[0722] Step 5:

[0723] The device transmits the extracted feature data and emotion data to a server via a communication network. The input is the feature data and emotion data, and the output is the data transmitted to the server. Specifically, the feature data (shape: 'cylindrical', color: 'gray', texture: 'rough') and emotion data (surprise) are transmitted to the server.

[0724] Step 6:

[0725] The server receives feature data and emotion data sent from the device. The input is the data sent from the device, and the output is the received data. The server inputs the received data into a generative AI model (e.g., CNN or RNN) to generate related information. Specifically, historical information and additional facts about ancient Greek statues are generated.

[0726] Step 7:

[0727] The server transmits the generated related information to the terminal via a communication network. The input is the generated information, and the output is the information transmitted to the terminal. The terminal receives and analyzes this information.

[0728] Step 8:

[0729] Based on the received information, the device visually displays the information on top of the object as augmented reality (AR). The input is the information received from the server, and the output is the AR information displayed within the user's field of vision. Specifically, text such as "500 BC Ancient Greek Statues: Their Historical Background and Amazing Facts" and related images are displayed on top of the statue.

[0730] This allows users to get real-time personalized information related to objects within their field of vision.

[0731] (Application example 2)

[0732] 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."

[0733] Conventional factory robots and assistance systems have difficulty monitoring the operator's condition in real time and providing assistance information at the appropriate time. Furthermore, few systems recognize the operator's emotions and provide work assistance, and they have not adequately improved work efficiency or prevented errors. This has led to problems such as reduced work efficiency and an increased risk of errors.

[0734] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0735] means for transmitting emotion data to a server;

[0736] means for generating related information based on the features received by the server using a generating artificial intelligence;

[0737] means for transmitting the generated information to a wearable device via a communication network;

[0738] This includes:

[0739] It is possible to detect the user's emotions in real time and provide personalized work support information and advice based on that, thereby improving the operator's work efficiency.

[0740] A "wearable device" is an electronic device that can be worn by a user and has the ability to acquire, analyze, and display information in real time.

[0741] An "emotion engine" is a software or hardware system that recognizes and analyzes emotions from a user's facial expressions and voice.

[0742] A "communications network" is an infrastructure for transmitting and receiving data, including the Internet and dedicated data communication lines.

[0743] A "server" is a computing resource that receives data transmitted from wearable devices over a network and generates analysis and related information.

[0744] "Generative artificial intelligence" refers to algorithms and models that generate information from data using techniques such as machine learning and deep learning.

[0745] "Features" are numerical data used to analyze information such as objects within the visual range and the emotional state of the user.

[0746] "Augmented reality" is a technology that displays digital information overlaid on real-world visual information, providing users with a richer information environment.

[0747] "Personalized information" is information that is specifically tailored to a user's emotional state and individual needs.

[0748] An "operator" is a human user who operates machinery or equipment in a factory or work environment.

[0749] "Work support information" is information that includes guidelines and advice for operators to perform work safely and efficiently.

[0750] This invention is implemented in a system that uses a wearable device worn by an operator in a factory or work environment, a server, and a network for communication between them. In particular, by combining it with an emotion engine that recognizes the operator's emotions, it is possible to provide more personalized work support information in real time.

[0751] System Overview

[0752] The main components are as follows:

[0753] Wearable device (terminal): A device worn by the operator that captures video, recognizes emotions, and displays AR.

[0754] Server: Analyzes the received data and generates relevant information using generation AI.

[0755] Communications network: The infrastructure through which devices and servers send and receive data.

[0756] Terminal

[0757] The wearable device is worn by the operator, and the camera captures images within the visual range in real time. This image data is preprocessed by an internal processor, and features are extracted using an object detection algorithm. In addition, an emotion engine analyzes the operator's facial expressions and voice to generate emotion data. This data is sent to a server via a communication network.

[0758] Emotion Engine

[0759] The wearable device is equipped with an emotion engine that analyzes the operator's emotional state in real time. The emotion engine identifies the operator's emotions (e.g., stress, joy, anxiety, etc.) based on camera footage and audio data. The analyzed emotion data is sent to a server along with feature data.

[0760] server

[0761] The server receives the feature data and emotion data sent from the device and generates relevant information using a generative AI model. The generated information uses a deep learning model (e.g., CNN or RNN) to adapt to the operator's current emotional state and work context. This information is then sent back to the wearable device via the communication network.

[0762] Information display

[0763] The wearable device visually displays the work support information received from the server as augmented reality (AR), allowing the operator to obtain augmented information within their visual range in real time. The displayed information is overlaid at an appropriate size and angle based on the operator's viewpoint and work situation. Furthermore, the content and format of the information are personalized based on emotional data.

[0764] Specific examples

[0765] Example: Factory use

[0766] Consider an operator picking up a part on an assembly line.

[0767] The device's camera captures images of the parts and extracts features such as shape, color, and texture.

[0768] The terminal transmits these features to a server via a communication network.

[0769] The device's emotion engine analyzes the operator's facial expressions and voice to determine if the operator is confused.

[0770] The server analyzes both sets of data and generates "This part is used on XYZ machine, and its assembly instructions and common error countermeasures."

[0771] The device analyzes the information received from the server and displays text such as "XYZ machine assembly procedure common error countermeasures" and related images on top of the part as AR.

[0772] Prompt Sentence Examples

[0773] "Build an application that recognizes an operator's emotions in real time and provides assembly assistance information based on his / her psychological state. The specific steps are as follows:"

[0774] "If an operator is confused, think about what information you should provide and display it in AR."

[0775] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0776] Step 1:

[0777] The terminal uses the camera of the wearable device worn by the operator to capture images within its visual range in real time. The input is the camera image, and the output is the captured image data. Specifically, the camera captures images at a constant frame rate and stores them in an internal buffer.

[0778] Step 2:

[0779] The device preprocesses the captured video data and extracts features using an object detection algorithm (e.g., YOLO or SSD). The input is the captured video data, and the output is the extracted features. Specific operations include noise removal, resizing, and filtering to enhance features in the video data.

[0780] Step 3:

[0781] The terminal uses an emotion engine to analyze emotions from the operator's facial expressions and voice data. The input is facial expression data and voice data, and the output is analyzed emotion data. Specific operations include extracting face areas from camera footage and performing spectrum analysis of voice data.

[0782] Step 4:

[0783] The device transmits the extracted feature data and emotion data to a server via a communication network. The input is the feature data and emotion data, and the output is a data packet transmitted over the network. Specifically, the data is serialized and packetized according to the network protocol.

[0784] Step 5:

[0785] The server analyzes the received feature data and emotion data and generates related information using a generative AI model. The input is feature data and emotion data, and the output is the generated related information. Specifically, the server analyzes the feature data using a convolutional neural network (CNN) and the emotion data using a recurrent neural network (RNN) to generate appropriate assistance information.

[0786] Step 6:

[0787] The server transmits the generated related information to the terminal via a communication network. The input is the generated related information, and the output is a data packet transmitted via the network. Specific operations include serializing the information and packetizing it into data packets.

[0788] Step 7:

[0789] The device interprets the received related information and visually displays it as augmented reality (AR). The input is the received related information, and the output is the AR content displayed on the display of the wearable device. Specifically, the related information is overlaid on the video data as an overlay and displayed in the appropriate position and size.

[0790] Step 8:

[0791] The user performs tasks based on personalized work support information displayed as augmented reality. The input is the visually displayed support information, and the output is the user's work results. Specifically, the user follows the guidelines provided through AR to properly progress through the task.

[0792] 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.

[0793] 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.

[0794] 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.

[0795] [Third embodiment]

[0796] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0797] 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.

[0798] 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).

[0799] 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.

[0800] 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.

[0801] 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).

[0802] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[0803] 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.

[0804] 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.

[0805] 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.

[0806] 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.

[0807] 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."

[0808] The present invention is implemented using a system including a wearable device worn by a user, a server, and a network for communication therebetween. The specific processing flow of the program is described in detail below.

[0809] System Overview

[0810] The main components are as follows:

[0811] Wearable devices (terminals)

[0812] server

[0813] communication network

[0814] Terminal

[0815] The system is activated when the user puts on the wearable device. The device's camera captures objects within the user's visual field in real time. This video data is preprocessed by an internal processor, and features are extracted using an object detection algorithm. These features are then sent to a server via a communications network.

[0816] server

[0817] The server receives the feature data sent from the device. Based on the received data, generative artificial intelligence (generative AI) generates related information. The generative AI uses a deep learning model (e.g., CNN or RNN) to identify the type of object and its related information. The generated information is then sent back to the device via the communication network.

[0818] Information display

[0819] The device visually displays the received relevant information as augmented reality (AR), allowing the user to obtain augmented information within their field of vision in real time. The displayed information is overlaid at an appropriate size and angle based on the user's viewpoint and the object's position.

[0820] Specific examples

[0821] Example 1: Museum use

[0822] Consider a scenario in which a user is looking at "ancient statues" in a history museum.

[0823] The device's camera captures video of the statue and extracts features such as shape, color, and texture.

[0824] The terminal transmits these features to a server via a communication network.

[0825] The server analyzes the features and determines that "this is an ancient Greek statue from 500 BC," and the generation AI generates information such as the historical background, the origin and significance of the statue.

[0826] The device analyzes the information received from the server and displays text such as "500 BC Ancient Greek Statues: Their Historical Background and Origins" and related images on the statue as AR.

[0827] Example 2: Use in daily life

[0828] Consider a scenario where a user is looking at "product packaging" in a supermarket.

[0829] The device's camera captures images of the product packaging and extracts features from the barcode and label information.

[0830] The terminal transmits these features to a server via a communication network.

[0831] The server analyzes the features and determines that "this is an organic food and does not contain specific allergens," and the generation AI generates detailed product information, nutritional information, consumer reviews, etc.

[0832] The device analyzes the information received from the server and displays text such as "organic food, ingredient information, consumer reviews" and related images on the product packaging as AR.

[0833] This allows users to instantly acquire a wealth of knowledge and data based on visual information, improving the quality of their learning, research, and daily life.The system based on this invention aims to provide efficient and highly accurate information, significantly improving the user experience.

[0834] The processing flow will be explained below.

[0835] Step 1:

[0836] The user puts on the wearable device. The wearable device starts up and the camera begins capturing video data within the user's visual field. This video data is captured frame by frame and processed at 30 frames per second (FPS).

[0837] Step 2:

[0838] The device receives the captured video data and performs preprocessing, which includes removing noise from the video data and adjusting the resolution. It then uses object detection algorithms to detect objects and features within its visual range. Specifically, it extracts color, shape, texture, and identifiers such as barcodes and QR codes from the camera's video data.

[0839] Step 3:

[0840] The extracted feature data is converted into JSON format and sent to a server via a communication network, using Wi-Fi or mobile data communication.

[0841] Step 4:

[0842] The server receives the feature data sent from the device. The received data is analyzed by generative artificial intelligence (generative AI). The generative AI uses a deep learning model (e.g., CNN or RNN) to determine the type of object from the features.

[0843] Step 5:

[0844] The server generates relevant information based on the results of the judgment. The generation AI collects relevant information from databases and the Internet and generates that information in natural language. The generated information is then converted back into JSON format.

[0845] Step 6:

[0846] The server generates information and sends it to the terminal via a communication network. The transmitted data includes specific information about the object, related images, text, and so on.

[0847] Step 7:

[0848] The device parses the information received from the server and converts it into a format for display. The received data is parsed appropriately and formatted into a visual display format using an AR library (e.g., Unity or ARKit).

[0849] Step 8:

[0850] The device displays the analyzed information in the user's field of view as augmented reality (AR), overlaying text information and images on top of the visual data based on the object's position, angle, and size, allowing the user to obtain additional information about objects within their field of view in real time.

[0851] Step 9:

[0852] The device periodically sends user data to the server and receives updated information as needed. New video data is captured at regular intervals, and features are extracted again and sent to the server. The server continues to generate new information, and the device continues to receive this updated information, so that the latest information is always provided to the user.

[0853] In this way, users can instantly acquire a wealth of knowledge and data based on visual information, improving the quality of their learning, research, and daily life.

[0854] Example 1

[0855] 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."

[0856] Conventional wearable devices have limited the information that users can visually obtain, making it difficult to provide information in real time. Furthermore, analyzing acquired data, extracting features, and generating and displaying relevant information require significant time, which can detract from the user experience. Furthermore, they are limited to use in specific situations and environments, limiting their versatile use. Furthermore, conventional systems often lack the accuracy and relevance of the generated information, failing to provide useful information to users.

[0857] 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.

[0858] In this invention, the server includes means for acquiring information within the visual range of a device worn by a user, means for analyzing the acquired information and extracting features using a trained algorithm, means for transmitting the extracted features to a central processing unit via a communication network, means for generating related information based on the features received by the central processing unit using generative artificial intelligence, means for transmitting the generated information to the device via the communication network, and means for displaying the information received by the device as visual augmentation, thereby enabling users to expand the information they can visually obtain in real time and instantly acquire a wealth of knowledge and data.

[0859] "User" in this invention refers to an individual who wears and uses the device.

[0860] "Device" refers to a wearable device worn by a user that acquires and displays information within visual range.

[0861] "Visual information" refers to video and other data captured by a user's device using cameras and sensors.

[0862] "Trained algorithm" refers to the process of analyzing and extracting features using a machine learning model that has been trained on a large dataset in advance.

[0863] "Features" refers to attribute data such as shape, color, texture, barcode, and label information extracted from information within the visual range.

[0864] "Communication network" refers to the internet line or wireless communication technology (e.g., Wi-Fi, 5G, etc.) used to transmit the extracted feature data to the server.

[0865] "Central Processing Unit" refers to a computer system that functions as a server, receives and analyzes feature data, and generates and transmits related information.

[0866] "Generative artificial intelligence" refers to the process of using deep learning models (e.g., CNN, RNN) to generate relevant information based on received feature data.

[0867] "Related information" refers to information that is useful to the user, such as the type of generated object, its background information, history information, product information, and the like.

[0868] "Visual augmentation" refers to augmented reality (AR) technology that displays generated relevant information on a device to enhance a user's visual experience.

[0869] The present invention is embodied in a system including a wearable device worn by a user, a server, and a communication network connecting them. Specific configurations and processes for promoting the invention are described below.

[0870] System Configuration

[0871] 1. Wearable devices (terminals)

[0872] The wearable device worn by the user is equipped with a high-resolution camera and a built-in processor. The camera captures the user's visual field in real time, and the processor processes and pre-processes the video data. The wearable device also has a wireless communication module and communicates with a server via the Internet.

[0873] 2. Server

[0874] The server acts as a central processing unit, receiving and analyzing the feature data sent from the device. The server is equipped with hardware and software to run deep learning models (e.g., CNN, RNN). The generative AI uses this deep learning model to generate relevant information based on the feature data.

[0875] Data Processing and Flow

[0876] Video capture and pre-processing

[0877] The device's camera captures images within the user's visual field in real time, and the captured image data is pre-processed by a processor to remove noise and improve image quality.

[0878] Feature extraction

[0879] The preprocessed video data is then analyzed by an on-device trained algorithm (e.g., an object detection algorithm such as YOLO or SSD) to extract features (e.g., shape, color, texture, barcode, or label information) from the objects in the video.

[0880] Data transmission

[0881] The extracted feature data is sent to a server via a communication network using wireless communication such as Wi-Fi or 5G, and the data format used is a lightweight format such as JSON.

[0882] Server-side data analysis and information generation

[0883] The server receives the feature data sent from the device and generates relevant information using a deep learning model. For example, a CNN model can be used to identify an object in a video as an ancient Greek statue from 500 BC, and the AI ​​will generate information about its historical background, origin, significance, etc.

[0884] Information transmission and display

[0885] The generated related information is then sent from the server to the terminal via the communication network. The terminal analyzes the received information and displays it as an extension of the user's visual field. The information is overlaid at an appropriate size and position and presented visually to the user.

[0886] Specific examples

[0887] Example 1: Museum use

[0888] Consider a scenario in which a user is looking at ancient statues in a history museum.

[0889] The device's camera captures video of the statue and extracts its features.

[0890] The device transmits the extracted features to the server.

[0891] The server analyzes the features and determines that "this is an ancient Greek statue from 500 BC," and the generation AI generates information such as the historical background, origin, and significance of the statue.

[0892] The device displays the received information as a visual augmentation, and the user can see text such as "500 BC Ancient Greek Statue: Its Historical Background and Origin" on top of the statue in AR.

[0893] Example 2: Use in daily life

[0894] Consider a scenario where a user is looking at product packaging in a supermarket.

[0895] The device's camera captures images of the product packaging and extracts features from the barcode and label information.

[0896] The device transmits the extracted features to the server.

[0897] The server analyzes the features and determines that "this is an organic food and does not contain specific allergens," and the generation AI generates detailed product information, nutritional information, consumer reviews, etc.

[0898] The device displays the received information as a visual augmentation, and users can see text such as "Organic Food, Ingredient Information, Consumer Reviews" and related information on the product packaging in AR.

[0899] Prompt Sentence Examples

[0900] "Please tell me about the historical background, origins, and significance of ancient Greek statues."

[0901] "Based on the information on this product package, please tell me if it is organic, what ingredients it contains, and what consumer reviews it has."

[0902] In this way, the present invention provides a system that expands the information that users can visually obtain and allows them to instantly obtain a wealth of knowledge and data, thereby significantly improving the quality of their learning, research, and daily life.

[0903] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0904] Step 1: Booting the device

[0905] The wearable device worn by the user starts up automatically. At startup, various sensors inside the device begin to operate, and the camera and processor enter a ready state. The input is the user wearing the device, and the output is the device being ready. Specifically, the sensors detect that the user is wearing the device and prepare the environment for the entire system to operate.

[0906] Step 2: Capture footage

[0907] The device's camera captures objects within the user's visual field in real time. The input is the visual field image detected by the camera, and the output is the captured high-resolution video data. Specifically, the camera captures video at a rate of 30 frames per second or more and sends the data to a processor in either raw or compressed format.

[0908] Step 3: Preprocessing the video data

[0909] The processor inside the device receives the video data and performs preprocessing such as noise removal and image quality correction. The input is the captured video data, and the output is the preprocessed video data. Specifically, the processor performs noise removal using a Gaussian filter and contrast correction using histogram equalization.

[0910] Step 4: Feature extraction

[0911] A trained algorithm on the device extracts features from the preprocessed video data. The input is the preprocessed video data, and the output is object features (e.g., shape, color, texture, barcode, label information, etc.). Specifically, object detection algorithms such as YOLO and SSD are used to analyze important parts of the video and extract the necessary features as data.

[0912] Step 5: Send feature data

[0913] The device transmits feature data to a central processing unit (server) via wireless communication (e.g., Wi-Fi, 5G). The input is the extracted feature data, and the output is the data transmitted via the communication network. Specifically, the feature data is converted to a format such as JSON, compressed, and transmitted via the wireless communication module.

[0914] Step 6: Data reception and analysis

[0915] The server receives and analyzes the feature data. The input is the feature data sent from the device, and the output is related information generated by the generative AI model. Specifically, the data is received in the execution environment of the deep learning model (e.g., CNN, RNN), and the analysis program analyzes the features and generates related information.

[0916] Step 7: Generate related information

[0917] The server uses generative AI to generate relevant information based on the received feature data. The input is the feature data obtained through analysis, and the output is relevant information (e.g., historical information, product information, etc.). Specifically, the deep learning model identifies the type of object, and the relevant information is generated using a natural language generation model. For example, background information about an ancient Greek statue and its significance are generated.

[0918] Step 8: Submit relevant information

[0919] The server transmits the generated related information to the terminal via a communication network. The input is the generated related information, and the output is the transmitted information. Specifically, the server converts the related information into an appropriate format and transmits it to the terminal via a wireless communication network.

[0920] Step 9: Displaying Information as a Visual Augmentation

[0921] The device analyzes the relevant information received and displays it as augmented reality (AR). The input is the relevant information sent from the server, and the output is the augmented reality information displayed within the user's visual field. Specifically, the relevant information is overlaid at an appropriate size and position to fit the user's visual environment. For example, text or images may be displayed on a statue, seamlessly integrating with the user's visual field.

[0922] (Application example 1)

[0923] 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."

[0924] At logistics centers, the ability to quickly and accurately pick and pack large quantities of products is a major challenge. However, conventional methods require workers to locate products using only visual information, which creates challenges in terms of work efficiency and accuracy. Furthermore, there are limitations to how much information workers can grasp manually, making errors more likely. Therefore, there is a need for a system that provides both visual and auditory support for work.

[0925] 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.

[0926] In this invention, the server includes: means for acquiring information within the visual range of a wearable device worn by a user; means for analyzing the acquired information and extracting features; means for transmitting the extracted features to the server via a communications network; means for generating related information based on the features received by the server using generative artificial intelligence; means for transmitting the generated information to the wearable device via the communications network; and means for visually displaying the received information as augmented reality on the wearable device, which is further worn by a worker to support work at a logistics center. This allows workers to obtain visual and auditory information in real time through the wearable device, enabling them to pick and pack products quickly and accurately.

[0927] A "wearable device" is an electronic device that can be worn by the user on the body. It is a terminal that has a built-in camera, display, and sensor and can acquire and display information.

[0928] "Information within visual range" refers to all information within the user's field of view that is captured by a camera attached to a wearable device.

[0929] "Features" refer to specific patterns, attributes, and data extracted from information within the visual field that are necessary to identify objects.

[0930] "Communications network" refers to the entire infrastructure for transmitting and receiving data between wearable devices and servers, and between multiple devices.

[0931] "Server" refers to the computer system that receives data sent from a wearable device and processes, analyzes, and generates information.

[0932] "Generative artificial intelligence" refers to AI that uses machine learning and deep learning algorithms based on large amounts of data to generate relevant information based on features.

[0933] "Augmented reality" refers to the technology of overlaying computer-generated information onto real-world visual information.

[0934] A "logistics center" refers to a facility where logistics operations such as collection, delivery, storage, sorting, packaging, and shipping of goods are carried out.

[0935] "Work support" refers to providing visual and auditory information to workers so that they can perform their work more efficiently and accurately.

[0936] The present invention provides a system that uses wearable devices, a server, and a communication network to improve work efficiency in a logistics center.

[0937] System Overview

[0938] The main components are as follows:

[0939] Wearable devices (e.g., smart glasses or smart eyeglasses)

[0940] server

[0941] Communication network (Wi-Fi or 5G)

[0942] Wearable devices

[0943] The system is activated when a worker puts on the wearable device. The device's built-in camera captures information within the worker's visual range (products, barcodes, QR codes, etc.) in real time. This video data is preprocessed by the device's processor, and feature values ​​are extracted. These feature values ​​are then sent to a server via a communications network.

[0944] server

[0945] The server receives the feature data sent from the device. Generative artificial intelligence (generative AI) analyzes this feature data and generates related product information and picking instructions. The generative AI analyzes the features using a deep learning model (e.g., CNN or RNN) and generates information. The generated information is then sent back to the wearable device via the communication network.

[0946] Augmented reality information display

[0947] The wearable device visually displays the received information as augmented reality (AR), allowing workers to see augmented information in real time within their field of vision. The displayed information is overlaid at the appropriate size and angle based on the worker's viewpoint and the location of the item.

[0948] Specific examples

[0949] Use at logistics centers

[0950] Consider a scenario where a worker is picking items at a logistics center.

[0951] The camera in the wearable device captures images of the shelves and extracts features such as barcodes, QR codes, and shapes.

[0952] The wearable device transmits these features to a server via a communication network.

[0953] The server analyzes the features and determines, "This is product A, and its shelf number is 12B," and the generation AI generates picking instructions and inventory information for this product.

[0954] The wearable device analyzes the information received from the server and displays text such as "Product A, shelf number 12B, quantity in stock 30" and related images, as well as audio guidance, on the shelf as AR.

[0955] Hardware and Software Description

[0956] Hardware:

[0957] Wearable devices (smart glasses, etc.)

[0958] Camera (built into wearable device)

[0959] Communication networks (Wi-Fi, 5G)

[0960] software:

[0961] Python (image processing, running generative AI models)

[0962] OpenCV (image processing library)

[0963] Requests (HTTP communication library)

[0964] ARModule (AR display library)

[0965] Examples of prompt statements

[0966] Imagine a scenario in which a worker wearing smart glasses at a distribution center is searching for an item in a picking area. An example prompt is as follows:

[0967] "Analyze product information from the video data and generate the information to be displayed. For example, if the product shown in the video is 'Product A', generate and respond with its name, stock quantity, and shelf number as 'Product A, stock quantity 30, shelf number 12B'."

[0968] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0969] Step 1:

[0970] The user puts on the wearable device and begins work in the logistics center.

[0971] Input: Visual information from a wearable device worn by the user

[0972] How it works: A camera built into the wearable device captures information in real time that comes within the user's visual field.

[0973] Output: Captured video data

[0974] Step 2:

[0975] The device analyzes the video data and extracts features.

[0976] Input: Captured video data

[0977] How it works: The device's processor processes the video data and uses an image recognition algorithm (e.g., OpenCV) to extract features such as product shelves, barcodes, and QR codes.

[0978] Output: Extracted feature data

[0979] Step 3:

[0980] The terminal transmits the feature data to the server via a communication network.

[0981] Input: Extracted feature data

[0982] Action: The device formats the feature data and sends it to the server using an HTTP communication library (e.g., Requests).

[0983] Output: Feature data received by the server

[0984] Step 4:

[0985] The server generates related information using artificial intelligence based on the received feature data.

[0986] Input: Feature data sent from the device

[0987] Operation: The generative AI model runs on the server, analyzes feature data using deep learning algorithms (CNN or RNN), and generates related product information, picking instructions, inventory information, etc.

[0988] Output: Related information generated

[0989] Step 5:

[0990] The server transmits the generated related information to the terminal via a communication network.

[0991] Input: Generated related information

[0992] How it works: The server formats the relevant information and sends it to the device using an HTTP communication library.

[0993] Output: Relevant information received by the device

[0994] Step 6:

[0995] The device analyzes the relevant information received and displays it visually as augmented reality (AR).

[0996] Input: Relevant information received by the device

[0997] Operation: Using an AR library (e.g., ARModule), the device overlays relevant information received with an appropriate position and size based on the user's viewpoint and the location of the item. Audio guidance is also integrated to provide voice instructions to the worker.

[0998] Output: The information the user receives visually and audibly.

[0999] Step 7:

[1000] Picking and packing are carried out quickly and accurately based on information provided by the user through the wearable device.

[1001] Input: AR and related information provided as audio guide

[1002] Action: The user uses visual and auditory information to pick the specified item and transport or pack it to the appropriate location.

[1003] Output: Users working efficiently and accurately

[1004] 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.

[1005] This invention is implemented using a system including a wearable device worn by a user, a server, and a network for communication between them. In particular, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide more personalized information. The specific processing flow of the program is described in detail below.

[1006] System Overview

[1007] The main components are as follows:

[1008] Wearable devices (terminals)

[1009] server

[1010] communication network

[1011] Emotion Engine

[1012] Terminal

[1013] The system is activated when the user puts on the wearable device. The device's camera captures objects within the user's visual field in real time. This video data is preprocessed by an internal processor, and features are extracted using an object detection algorithm. These features are then sent to a server via a communications network.

[1014] Emotion Engine

[1015] The device is equipped with an emotion engine that recognizes the user's emotions from their facial expressions and voice. The emotion engine analyzes camera footage and audio data to identify the user's emotional state (e.g., joy, surprise, sadness, anger, etc.). The detected emotion data, along with the feature values, is also sent to a server via a communication network.

[1016] server

[1017] The server receives the feature data and emotion data sent from the device. Based on the received data, generative artificial intelligence (generative AI) generates relevant information. The generative AI uses a deep learning model (e.g., CNN or RNN) to determine the type of object from the feature data and combines it with emotion data to generate information that best suits the user's current state. The generated information is then sent back to the device via the communications network.

[1018] Information display

[1019] The device visually displays the received relevant information as augmented reality (AR), allowing users to obtain augmented information within their field of vision in real time. The displayed information is overlaid at an appropriate size and angle based on the user's viewpoint and the object's position. Furthermore, the content and format of the information are personalized based on emotional data.

[1020] Specific examples

[1021] Example 1: Museum use

[1022] Consider a scenario in which a user is looking at "ancient statues" in a history museum.

[1023] The device's camera captures video of the statue and extracts features such as shape, color, and texture.

[1024] The terminal transmits these features to a server via a communication network.

[1025] The device's emotion engine analyzes the user's facial expression and determines that the user is expressing surprise.

[1026] The server analyzes both pieces of data and generates a summary that says, "This is an ancient Greek statue from 500 BC, and provides context and origins, as well as additional facts that may surprise the user."

[1027] The device analyzes the information received from the server and displays text and related images such as "500 BC Ancient Greek Statues: Their Historical Background and Amazing Facts" on the statue as AR.

[1028] Example 2: Use in daily life

[1029] Consider a scenario where a user is looking at "product packaging" in a supermarket.

[1030] The device's camera captures images of the product packaging and extracts features from the barcode and label information.

[1031] The terminal transmits these features to a server via a communication network.

[1032] The device's emotion engine analyzes the user's voice and determines whether the user is happy.

[1033] The server analyzes both sets of data and generates encouraging information about the food, including that it's organic, that it's free of certain allergens, and its health benefits.

[1034] The device analyzes the information received from the server and displays text such as "organic food, allergen information, health benefits" and related images as AR on the product packaging.

[1035] In this way, users can instantly acquire a wealth of knowledge and data based on visual information, and by receiving personalized information based on their emotions, the quality of their learning, research, and daily life can be further improved.

[1036] The processing flow will be explained below.

[1037] Step 1:

[1038] The user puts on the wearable device. The wearable device starts up and the camera begins capturing video data within the user's visual field. This video data is captured frame by frame and processed at 30 frames per second (FPS).

[1039] Step 2:

[1040] The device receives the captured video data and performs preprocessing, which includes removing noise from the video data and adjusting the resolution. It then uses object detection algorithms to detect objects and features within its visual range. Specifically, it extracts color, shape, texture, and identifiers such as barcodes and QR codes from the camera's video data.

[1041] Step 3:

[1042] The device's emotion engine analyzes the user's facial expressions and voice to determine their emotional state. The emotion engine uses facial recognition and voice analysis algorithms to determine whether the user is happy, surprised, sad, angry, or other emotions.

[1043] Step 4:

[1044] The extracted feature data and emotion data are converted into JSON format and sent to a server via a communication network, using Wi-Fi or mobile data.

[1045] Step 5:

[1046] The server receives the feature data and emotion data sent from the device. The received data is analyzed by generative artificial intelligence (generative AI). The generative AI uses a deep learning model (e.g., CNN or RNN) to determine the type of object from the feature data and generate related information taking emotion data into account.

[1047] Step 6:

[1048] The server generates relevant information based on the judgment results and emotion data. The generation AI collects relevant information from databases and the internet, generates that information in natural language, and personalizes the information to match the user's emotions. The generated information is then converted back into JSON format.

[1049] Step 7:

[1050] The server generates information and sends it to the terminal via a communication network. The transmitted data includes specific information about the object, related images, text, and so on.

[1051] Step 8:

[1052] The device parses the information received from the server and converts it into a format for display. The received data is parsed appropriately and formatted into a visual display format using an AR library (e.g., Unity or ARKit).

[1053] Step 9:

[1054] The device displays the analyzed information as augmented reality (AR) within the user's field of view. Specifically, text information and images are overlaid on top of the visual data based on the object's position, angle, and size. Furthermore, the content and format of the information are personalized based on the user's emotional data, providing information that corresponds to the user's emotions.

[1055] Step 10:

[1056] The device periodically sends user data to the server and receives updated information as needed. New video data is captured at regular intervals, and feature and emotion data are extracted again and sent to the server. The server continues to generate new information, and the device receives this updated information, always providing the user with the latest information.

[1057] In this way, users can instantly acquire a wealth of knowledge and data based on visual information, and by receiving personalized information based on their emotions, the quality of their learning, research, and daily life can be further improved.

[1058] Example 2

[1059] 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."

[1060] Current information provision systems using wearable devices are limited to acquiring and displaying information within the user's visual field, and do not adequately provide personalized information that takes into account the user's emotional state. This limits the quality of the user experience and makes it difficult to display appropriate information according to the usage scenario.

[1061] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for acquiring information within the visual range of a wearable device worn by a user; means for analyzing the acquired information and extracting features; means for analyzing the user's facial expressions and voice to acquire emotional data; means for transmitting the extracted features and emotional data to the server via a communication network; means for generating related information based on the features and emotional data received by the server using artificial intelligence; means for transmitting the generated information to the wearable device via the communication network; and means for visually displaying the information received by the wearable device as augmented reality. This enables the provision of personalized information according to the user's emotional state. Furthermore, combining visually acquired information with emotional data can improve the quality of the user experience and provide more appropriate information.

[1062] A "wearable device" is a terminal device with computing functions that is worn on the user's body.

[1063] "Visual range" refers to the area that a user can see through a wearable device.

[1064] "Means for acquiring information" refers to devices or methods that use cameras or sensors installed in wearable devices to collect images and data within the visual range.

[1065] "Means for extracting features" refers to algorithms or devices that analyze and extract characteristic data such as the shape, color, and texture of objects from images and data acquired by cameras or sensors.

[1066] A "communications network" is a system that provides an infrastructure for transmitting and receiving data, and includes wired or wireless networks.

[1067] "Server" refers to a computer system that processes and stores data over a network and provides services to client devices.

[1068] "Emotion data" refers to information obtained by analyzing data that represents the emotional state of a user, such as facial expressions and voice.

[1069] "Generative artificial intelligence" refers to technology that uses machine learning and deep learning models to analyze data and generate new information.

[1070] "Augmented reality" refers to a technology that displays computer-generated visual information overlaid on a real-world environment.

[1071] This invention is a system that uses a wearable device worn by a user to analyze information within the user's visual field and provide related information. This system is realized mainly by a wearable device, a server, a communication network, and an emotion engine.

[1072] Hardware and Software Configuration

[1073] A wearable device includes the following elements:

[1074] Camera: Captures objects within its visual range.

[1075] Microphone: Captures user voice.

[1076] Processor: Performs data preprocessing.

[1077] Communication module: Sends and receives data.

[1078] A server is a computer system with high-performance computing power that includes the following elements:

[1079] Generative AI models (e.g., CNNs and RNNs): Analyze data and generate information.

[1080] Database: Stores the acquired and generated data.

[1081] The emotion engine is a software component that analyzes emotions from the user's facial expressions and voice.

[1082] A communications network is the infrastructure that enables data communication over the web.

[1083] Operation explanation

[1084] When a user puts on the wearable device, the system is activated. The camera captures objects within the user's visual field in real time, and the processor analyzes the video data to extract features. These features are then sent to a server via a communication network.

[1085] The emotion engine installed in the wearable device analyzes the captured video and audio data to identify the user's emotional state, which is then transmitted to a server via a communication network.

[1086] The server analyzes the received feature data and emotion data and generates relevant information using a generative AI model (e.g., CNN or RNN). This generated information is personalized and best suited to the type of object and the user's emotional state. The generated information is then sent back to the wearable device via the communication network.

[1087] Specific examples

[1088] Example 1: Museum use

[1089] Consider a case where a user is looking at an "ancient statue" in a history museum. The device's camera captures video of the statue and extracts features such as shape, color, and texture. The device then sends these features to a server via a communications network. The device's emotion engine analyzes the user's facial expression and determines that the user is expressing surprise. The server analyzes both sets of data and generates content that explains, "This is an ancient Greek statue from 500 BC, and provides its historical background and origin, as well as additional facts that may surprise the user." The device then analyzes the information received from the server and displays text such as "500 BC Ancient Greek statue, its historical background, and surprising facts" and related images on top of the statue as AR.

[1090] Example 2: Use in daily life

[1091] Consider a case where a user is looking at a "product package" in a supermarket. The device's camera captures an image of the product package and extracts features from the barcode and label information. The device then sends these features to a server via a communications network. The device's emotion engine analyzes the user's voice and determines that the user is happy. The server analyzes both sets of data and generates encouraging information about "this is organic food, does not contain specific allergens, and its health benefits." The device analyzes the information received from the server and displays text such as "organic food, allergen information, health benefits" and related images on the product package as AR.

[1092] Examples of prompt statements

[1093] 1. "A user looks surprised while looking at an ancient statue in a museum. The statue's features are: Shape: 'Cylindrical', Color: 'Gray', Texture: 'Rough'. Generate historical information about this statue."

[1094] 2. "A user is looking at a product package in a supermarket and exclaims with delight. The product is organic and has barcode: '123456789'. Please generate more information about this."

[1095] This system allows users to obtain visual information in real time and enjoy personalized content that responds to their emotions.

[1096] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1097] Step 1:

[1098] The user puts on the wearable device and the system is started. The input can be a gesture of putting on the device or a voice command. The output can be the activation of each component of the wearable device (camera, microphone, processor, communication module).

[1099] Step 2:

[1100] The device's camera captures objects within the user's field of vision in real time. The input is video data from the camera, and the output is the captured video data. The processor receives the video data and performs preprocessing, specifically image processing such as noise reduction and color filtering.

[1101] Step 3:

[1102] The device applies an object detection algorithm (such as YOLO or SSD) to the preprocessed video data to extract features such as the shape, color, and texture of the object. The input is the preprocessed video data, and the output is the extracted feature data. Specifically, the extracted features include the statue's shape being "cylindrical," its color being "gray," and its texture being "rough."

[1103] Step 4:

[1104] The device's emotion engine analyzes camera footage and microphone audio to identify the user's emotional state. The input is camera footage and microphone audio, and the output is emotion data. Specifically, it analyzes the user's facial expressions and tone of voice to identify emotions such as "surprise" or "joy."

[1105] Step 5:

[1106] The device transmits the extracted feature data and emotion data to a server via a communication network. The input is the feature data and emotion data, and the output is the data transmitted to the server. Specifically, the feature data (shape: 'cylindrical', color: 'gray', texture: 'rough') and emotion data (surprise) are transmitted to the server.

[1107] Step 6:

[1108] The server receives feature data and emotion data sent from the device. The input is the data sent from the device, and the output is the received data. The server inputs the received data into a generative AI model (e.g., CNN or RNN) to generate related information. Specifically, historical information and additional facts about ancient Greek statues are generated.

[1109] Step 7:

[1110] The server transmits the generated related information to the terminal via a communication network. The input is the generated information, and the output is the information transmitted to the terminal. The terminal receives and analyzes this information.

[1111] Step 8:

[1112] Based on the received information, the device visually displays the information on top of the object as augmented reality (AR). The input is the information received from the server, and the output is the AR information displayed within the user's field of vision. Specifically, text such as "500 BC Ancient Greek Statues: Their Historical Background and Amazing Facts" and related images are displayed on top of the statue.

[1113] This allows users to get real-time personalized information related to objects within their field of vision.

[1114] (Application example 2)

[1115] 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."

[1116] Conventional factory robots and assistance systems have difficulty monitoring the operator's condition in real time and providing assistance information at the appropriate time. Furthermore, few systems recognize the operator's emotions and provide work assistance, and they have not adequately improved work efficiency or prevented errors. This has led to problems such as reduced work efficiency and an increased risk of errors.

[1117] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1118] means for transmitting emotion data to a server;

[1119] means for generating related information based on the features received by the server using a generating artificial intelligence;

[1120] means for transmitting the generated information to a wearable device via a communication network;

[1121] This includes:

[1122] It is possible to detect the user's emotions in real time and provide personalized work support information and advice based on that, thereby improving the operator's work efficiency.

[1123] A "wearable device" is an electronic device that can be worn by a user and has the ability to acquire, analyze, and display information in real time.

[1124] An "emotion engine" is a software or hardware system that recognizes and analyzes emotions from a user's facial expressions and voice.

[1125] A "communications network" is an infrastructure for transmitting and receiving data, including the Internet and dedicated data communication lines.

[1126] A "server" is a computing resource that receives data transmitted from wearable devices over a network and generates analysis and related information.

[1127] "Generative artificial intelligence" refers to algorithms and models that generate information from data using techniques such as machine learning and deep learning.

[1128] "Features" are numerical data used to analyze information such as objects within the visual range and the emotional state of the user.

[1129] "Augmented reality" is a technology that displays digital information overlaid on real-world visual information, providing users with a richer information environment.

[1130] "Personalized information" is information that is specifically tailored to a user's emotional state and individual needs.

[1131] An "operator" is a human user who operates machinery or equipment in a factory or work environment.

[1132] "Work support information" is information that includes guidelines and advice for operators to perform work safely and efficiently.

[1133] This invention is implemented in a system that uses a wearable device worn by an operator in a factory or work environment, a server, and a network for communication between them. In particular, by combining it with an emotion engine that recognizes the operator's emotions, it is possible to provide more personalized work support information in real time.

[1134] System Overview

[1135] The main components are as follows:

[1136] Wearable device (terminal): A device worn by the operator that captures video, recognizes emotions, and displays AR.

[1137] Server: Analyzes the received data and generates relevant information using generation AI.

[1138] Communications network: The infrastructure through which devices and servers send and receive data.

[1139] Terminal

[1140] The wearable device is worn by the operator, and the camera captures images within the visual range in real time. This image data is preprocessed by an internal processor, and features are extracted using an object detection algorithm. In addition, an emotion engine analyzes the operator's facial expressions and voice to generate emotion data. This data is sent to a server via a communication network.

[1141] Emotion Engine

[1142] The wearable device is equipped with an emotion engine that analyzes the operator's emotional state in real time. The emotion engine identifies the operator's emotions (e.g., stress, joy, anxiety, etc.) based on camera footage and audio data. The analyzed emotion data is sent to a server along with feature data.

[1143] server

[1144] The server receives the feature data and emotion data sent from the device and generates relevant information using a generative AI model. The generated information uses a deep learning model (e.g., CNN or RNN) to adapt to the operator's current emotional state and work context. This information is then sent back to the wearable device via the communication network.

[1145] Information display

[1146] The wearable device visually displays the work support information received from the server as augmented reality (AR), allowing the operator to obtain augmented information within their visual range in real time. The displayed information is overlaid at an appropriate size and angle based on the operator's viewpoint and work situation. Furthermore, the content and format of the information are personalized based on emotional data.

[1147] Specific examples

[1148] Example: Factory use

[1149] Consider an operator picking up a part on an assembly line.

[1150] The device's camera captures images of the parts and extracts features such as shape, color, and texture.

[1151] The terminal transmits these features to a server via a communication network.

[1152] The device's emotion engine analyzes the operator's facial expressions and voice to determine if the operator is confused.

[1153] The server analyzes both sets of data and generates "This part is used on XYZ machine, and its assembly instructions and common error countermeasures."

[1154] The device analyzes the information received from the server and displays text such as "XYZ machine assembly procedure common error countermeasures" and related images on top of the part as AR.

[1155] Prompt Sentence Examples

[1156] "Build an application that recognizes an operator's emotions in real time and provides assembly assistance information based on his / her psychological state. The specific steps are as follows:"

[1157] "If an operator is confused, think about what information you should provide and display it in AR."

[1158] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1159] Step 1:

[1160] The terminal uses the camera of the wearable device worn by the operator to capture images within its visual range in real time. The input is the camera image, and the output is the captured image data. Specifically, the camera captures images at a constant frame rate and stores them in an internal buffer.

[1161] Step 2:

[1162] The device preprocesses the captured video data and extracts features using an object detection algorithm (e.g., YOLO or SSD). The input is the captured video data, and the output is the extracted features. Specific operations include noise removal, resizing, and filtering to enhance features in the video data.

[1163] Step 3:

[1164] The terminal uses an emotion engine to analyze emotions from the operator's facial expressions and voice data. The input is facial expression data and voice data, and the output is analyzed emotion data. Specific operations include extracting face areas from camera footage and performing spectrum analysis of voice data.

[1165] Step 4:

[1166] The device transmits the extracted feature data and emotion data to a server via a communication network. The input is the feature data and emotion data, and the output is a data packet transmitted over the network. Specifically, the data is serialized and packetized according to the network protocol.

[1167] Step 5:

[1168] The server analyzes the received feature data and emotion data and generates related information using a generative AI model. The input is feature data and emotion data, and the output is the generated related information. Specifically, the server analyzes the feature data using a convolutional neural network (CNN) and the emotion data using a recurrent neural network (RNN) to generate appropriate assistance information.

[1169] Step 6:

[1170] The server transmits the generated related information to the terminal via a communication network. The input is the generated related information, and the output is a data packet transmitted via the network. Specific operations include serializing the information and packetizing it into data packets.

[1171] Step 7:

[1172] The device interprets the received related information and visually displays it as augmented reality (AR). The input is the received related information, and the output is the AR content displayed on the display of the wearable device. Specifically, the related information is overlaid on the video data as an overlay and displayed in the appropriate position and size.

[1173] Step 8:

[1174] The user performs tasks based on personalized work support information displayed as augmented reality. The input is the visually displayed support information, and the output is the user's work results. Specifically, the user follows the guidelines provided through AR to properly progress through the task.

[1175] 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.

[1176] 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.

[1177] 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.

[1178] [Fourth embodiment]

[1179] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1180] 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.

[1181] 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).

[1182] 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.

[1183] 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.

[1184] 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).

[1185] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for 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.

[1186] 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.

[1187] 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.

[1188] 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.

[1189] 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.

[1190] 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.

[1191] 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."

[1192] The present invention is implemented using a system including a wearable device worn by a user, a server, and a network for communication therebetween. The specific processing flow of the program is described in detail below.

[1193] System Overview

[1194] The main components are as follows:

[1195] Wearable devices (terminals)

[1196] server

[1197] communication network

[1198] Terminal

[1199] The system is activated when the user puts on the wearable device. The device's camera captures objects within the user's visual field in real time. This video data is preprocessed by an internal processor, and features are extracted using an object detection algorithm. These features are then sent to a server via a communications network.

[1200] server

[1201] The server receives the feature data sent from the device. Based on the received data, generative artificial intelligence (generative AI) generates related information. The generative AI uses a deep learning model (e.g., CNN or RNN) to identify the type of object and its related information. The generated information is then sent back to the device via the communication network.

[1202] Information display

[1203] The device visually displays the received relevant information as augmented reality (AR), allowing the user to obtain augmented information within their field of vision in real time. The displayed information is overlaid at an appropriate size and angle based on the user's viewpoint and the object's position.

[1204] Specific examples

[1205] Example 1: Museum use

[1206] Consider a scenario in which a user is looking at "ancient statues" in a history museum.

[1207] The device's camera captures video of the statue and extracts features such as shape, color, and texture.

[1208] The terminal transmits these features to a server via a communication network.

[1209] The server analyzes the features and determines that "this is an ancient Greek statue from 500 BC," and the generation AI generates information such as the historical background, the origin and significance of the statue.

[1210] The device analyzes the information received from the server and displays text such as "500 BC Ancient Greek Statues: Their Historical Background and Origins" and related images on the statue as AR.

[1211] Example 2: Use in daily life

[1212] Consider a scenario where a user is looking at "product packaging" in a supermarket.

[1213] The device's camera captures images of the product packaging and extracts features from the barcode and label information.

[1214] The terminal transmits these features to a server via a communication network.

[1215] The server analyzes the features and determines that "this is an organic food and does not contain specific allergens," and the generation AI generates detailed product information, nutritional information, consumer reviews, etc.

[1216] The device analyzes the information received from the server and displays text such as "organic food, ingredient information, consumer reviews" and related images on the product packaging as AR.

[1217] This allows users to instantly acquire a wealth of knowledge and data based on visual information, improving the quality of their learning, research, and daily life.The system based on this invention aims to provide efficient and highly accurate information, significantly improving the user experience.

[1218] The processing flow will be explained below.

[1219] Step 1:

[1220] The user puts on the wearable device. The wearable device starts up and the camera begins capturing video data within the user's visual field. This video data is captured frame by frame and processed at 30 frames per second (FPS).

[1221] Step 2:

[1222] The device receives the captured video data and performs preprocessing, which includes removing noise from the video data and adjusting the resolution. It then uses object detection algorithms to detect objects and features within its visual range. Specifically, it extracts color, shape, texture, and identifiers such as barcodes and QR codes from the camera's video data.

[1223] Step 3:

[1224] The extracted feature data is converted into JSON format and sent to a server via a communication network, using Wi-Fi or mobile data communication.

[1225] Step 4:

[1226] The server receives the feature data sent from the device. The received data is analyzed by generative artificial intelligence (generative AI). The generative AI uses a deep learning model (e.g., CNN or RNN) to determine the type of object from the features.

[1227] Step 5:

[1228] The server generates relevant information based on the results of the judgment. The generation AI collects relevant information from databases and the Internet and generates that information in natural language. The generated information is then converted back into JSON format.

[1229] Step 6:

[1230] The server generates information and sends it to the terminal via a communication network. The transmitted data includes specific information about the object, related images, text, and so on.

[1231] Step 7:

[1232] The device parses the information received from the server and converts it into a format for display. The received data is parsed appropriately and formatted into a visual display format using an AR library (e.g., Unity or ARKit).

[1233] Step 8:

[1234] The device displays the analyzed information in the user's field of view as augmented reality (AR), overlaying text information and images on top of the visual data based on the object's position, angle, and size, allowing the user to obtain additional information about objects within their field of view in real time.

[1235] Step 9:

[1236] The device periodically sends user data to the server and receives updated information as needed. New video data is captured at regular intervals, and features are extracted again and sent to the server. The server continues to generate new information, and the device continues to receive this updated information, so that the latest information is always provided to the user.

[1237] In this way, users can instantly acquire a wealth of knowledge and data based on visual information, improving the quality of their learning, research, and daily life.

[1238] Example 1

[1239] 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."

[1240] Conventional wearable devices have limited the information that users can visually obtain, making it difficult to provide information in real time. Furthermore, analyzing acquired data, extracting features, and generating and displaying relevant information require significant time, which can detract from the user experience. Furthermore, they are limited to use in specific situations and environments, limiting their versatile use. Furthermore, conventional systems often lack the accuracy and relevance of the generated information, failing to provide useful information to users.

[1241] 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.

[1242] In this invention, the server includes means for acquiring information within the visual range of a device worn by a user, means for analyzing the acquired information and extracting features using a trained algorithm, means for transmitting the extracted features to a central processing unit via a communication network, means for generating related information based on the features received by the central processing unit using generative artificial intelligence, means for transmitting the generated information to the device via the communication network, and means for displaying the information received by the device as visual augmentation, thereby enabling users to expand the information they can visually obtain in real time and instantly acquire a wealth of knowledge and data.

[1243] "User" in this invention refers to an individual who wears and uses the device.

[1244] "Device" refers to a wearable device worn by a user that acquires and displays information within visual range.

[1245] "Visual information" refers to video and other data captured by a user's device using cameras and sensors.

[1246] "Trained algorithm" refers to the process of analyzing and extracting features using a machine learning model that has been trained on a large dataset in advance.

[1247] "Features" refers to attribute data such as shape, color, texture, barcode, and label information extracted from information within the visual range.

[1248] "Communication network" refers to the internet line or wireless communication technology (e.g., Wi-Fi, 5G, etc.) used to transmit the extracted feature data to the server.

[1249] "Central Processing Unit" refers to a computer system that functions as a server, receives and analyzes feature data, and generates and transmits related information.

[1250] "Generative artificial intelligence" refers to the process of using deep learning models (e.g., CNN, RNN) to generate relevant information based on received feature data.

[1251] "Related information" refers to information that is useful to the user, such as the type of generated object, its background information, history information, product information, and the like.

[1252] "Visual augmentation" refers to augmented reality (AR) technology that displays generated relevant information on a device to enhance a user's visual experience.

[1253] The present invention is embodied in a system including a wearable device worn by a user, a server, and a communication network connecting them. Specific configurations and processes for promoting the invention are described below.

[1254] System Configuration

[1255] 1. Wearable devices (terminals)

[1256] The wearable device worn by the user is equipped with a high-resolution camera and a built-in processor. The camera captures the user's visual field in real time, and the processor processes and pre-processes the video data. The wearable device also has a wireless communication module and communicates with a server via the Internet.

[1257] 2. Server

[1258] The server acts as a central processing unit, receiving and analyzing the feature data sent from the device. The server is equipped with hardware and software to run deep learning models (e.g., CNN, RNN). The generative AI uses this deep learning model to generate relevant information based on the feature data.

[1259] Data Processing and Flow

[1260] Video capture and pre-processing

[1261] The device's camera captures images within the user's visual field in real time, and the captured image data is pre-processed by a processor to remove noise and improve image quality.

[1262] Feature extraction

[1263] The preprocessed video data is then analyzed by an on-device trained algorithm (e.g., an object detection algorithm such as YOLO or SSD) to extract features (e.g., shape, color, texture, barcode, or label information) from the objects in the video.

[1264] Data transmission

[1265] The extracted feature data is sent to a server via a communication network using wireless communication such as Wi-Fi or 5G, and the data format used is a lightweight format such as JSON.

[1266] Server-side data analysis and information generation

[1267] The server receives the feature data sent from the device and generates relevant information using a deep learning model. For example, a CNN model can be used to identify an object in a video as an ancient Greek statue from 500 BC, and the AI ​​will generate information about its historical background, origin, significance, etc.

[1268] Information transmission and display

[1269] The generated related information is then sent from the server to the terminal via the communication network. The terminal analyzes the received information and displays it as an extension of the user's visual field. The information is overlaid at an appropriate size and position and presented visually to the user.

[1270] Specific examples

[1271] Example 1: Museum use

[1272] Consider a scenario in which a user is looking at ancient statues in a history museum.

[1273] The device's camera captures video of the statue and extracts its features.

[1274] The device transmits the extracted features to the server.

[1275] The server analyzes the features and determines that "this is an ancient Greek statue from 500 BC," and the generation AI generates information such as the historical background, origin, and significance of the statue.

[1276] The device displays the received information as a visual augmentation, and the user can see text such as "500 BC Ancient Greek Statue: Its Historical Background and Origin" on top of the statue in AR.

[1277] Example 2: Use in daily life

[1278] Consider a scenario where a user is looking at product packaging in a supermarket.

[1279] The device's camera captures images of the product packaging and extracts features from the barcode and label information.

[1280] The device transmits the extracted features to the server.

[1281] The server analyzes the features and determines that "this is an organic food and does not contain specific allergens," and the generation AI generates detailed product information, nutritional information, consumer reviews, etc.

[1282] The device displays the received information as a visual augmentation, and users can see text such as "Organic Food, Ingredient Information, Consumer Reviews" and related information on the product packaging in AR.

[1283] Prompt Sentence Examples

[1284] "Please tell me about the historical background, origins, and significance of ancient Greek statues."

[1285] "Based on the information on this product package, please tell me if it is organic, what ingredients it contains, and what consumer reviews it has."

[1286] In this way, the present invention provides a system that expands the information that users can visually obtain and allows them to instantly obtain a wealth of knowledge and data, thereby significantly improving the quality of their learning, research, and daily life.

[1287] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1288] Step 1: Booting the device

[1289] The wearable device worn by the user starts up automatically. At startup, various sensors inside the device begin to operate, and the camera and processor enter a ready state. The input is the user wearing the device, and the output is the device being ready. Specifically, the sensors detect that the user is wearing the device and prepare the environment for the entire system to operate.

[1290] Step 2: Capture footage

[1291] The device's camera captures objects within the user's visual field in real time. The input is the visual field image detected by the camera, and the output is the captured high-resolution video data. Specifically, the camera captures video at a rate of 30 frames per second or more and sends the data to a processor in either raw or compressed format.

[1292] Step 3: Preprocessing the video data

[1293] The processor inside the device receives the video data and performs preprocessing such as noise removal and image quality correction. The input is the captured video data, and the output is the preprocessed video data. Specifically, the processor performs noise removal using a Gaussian filter and contrast correction using histogram equalization.

[1294] Step 4: Feature extraction

[1295] A trained algorithm on the device extracts features from the preprocessed video data. The input is the preprocessed video data, and the output is object features (e.g., shape, color, texture, barcode, label information, etc.). Specifically, object detection algorithms such as YOLO and SSD are used to analyze important parts of the video and extract the necessary features as data.

[1296] Step 5: Send feature data

[1297] The device transmits feature data to a central processing unit (server) via wireless communication (e.g., Wi-Fi, 5G). The input is the extracted feature data, and the output is the data transmitted via the communication network. Specifically, the feature data is converted to a format such as JSON, compressed, and transmitted via the wireless communication module.

[1298] Step 6: Data reception and analysis

[1299] The server receives and analyzes the feature data. The input is the feature data sent from the device, and the output is related information generated by the generative AI model. Specifically, the data is received in the execution environment of the deep learning model (e.g., CNN, RNN), and the analysis program analyzes the features and generates related information.

[1300] Step 7: Generate related information

[1301] The server uses generative AI to generate relevant information based on the received feature data. The input is the feature data obtained through analysis, and the output is relevant information (e.g., historical information, product information, etc.). Specifically, the deep learning model identifies the type of object, and the relevant information is generated using a natural language generation model. For example, background information about an ancient Greek statue and its significance are generated.

[1302] Step 8: Submit relevant information

[1303] The server transmits the generated related information to the terminal via a communication network. The input is the generated related information, and the output is the transmitted information. Specifically, the server converts the related information into an appropriate format and transmits it to the terminal via a wireless communication network.

[1304] Step 9: Displaying Information as a Visual Augmentation

[1305] The device analyzes the relevant information received and displays it as augmented reality (AR). The input is the relevant information sent from the server, and the output is the augmented reality information displayed within the user's visual field. Specifically, the relevant information is overlaid at an appropriate size and position to fit the user's visual environment. For example, text or images may be displayed on a statue, seamlessly integrating with the user's visual field.

[1306] (Application example 1)

[1307] 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."

[1308] At logistics centers, the ability to quickly and accurately pick and pack large quantities of products is a major challenge. However, conventional methods require workers to locate products using only visual information, which creates challenges in terms of work efficiency and accuracy. Furthermore, there are limitations to how much information workers can grasp manually, making errors more likely. Therefore, there is a need for a system that provides both visual and auditory support for work.

[1309] 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.

[1310] In this invention, the server includes: means for acquiring information within the visual range of a wearable device worn by a user; means for analyzing the acquired information and extracting features; means for transmitting the extracted features to the server via a communications network; means for generating related information based on the features received by the server using generative artificial intelligence; means for transmitting the generated information to the wearable device via the communications network; and means for visually displaying the received information as augmented reality on the wearable device, which is further worn by a worker to support work at a logistics center. This allows workers to obtain visual and auditory information in real time through the wearable device, enabling them to pick and pack products quickly and accurately.

[1311] A "wearable device" is an electronic device that can be worn by the user on the body. It is a terminal that has a built-in camera, display, and sensor and can acquire and display information.

[1312] "Information within visual range" refers to all information within the user's field of view that is captured by a camera attached to a wearable device.

[1313] "Features" refer to specific patterns, attributes, and data extracted from information within the visual field that are necessary to identify objects.

[1314] "Communications network" refers to the entire infrastructure for transmitting and receiving data between wearable devices and servers, and between multiple devices.

[1315] "Server" refers to the computer system that receives data sent from a wearable device and processes, analyzes, and generates information.

[1316] "Generative artificial intelligence" refers to AI that uses machine learning and deep learning algorithms based on large amounts of data to generate relevant information based on features.

[1317] "Augmented reality" refers to the technology of overlaying computer-generated information onto real-world visual information.

[1318] A "logistics center" refers to a facility where logistics operations such as collection, delivery, storage, sorting, packaging, and shipping of goods are carried out.

[1319] "Work support" refers to providing visual and auditory information to workers so that they can perform their work more efficiently and accurately.

[1320] The present invention provides a system that uses wearable devices, a server, and a communication network to improve work efficiency in a logistics center.

[1321] System Overview

[1322] The main components are as follows:

[1323] Wearable devices (e.g., smart glasses or smart eyeglasses)

[1324] server

[1325] Communication network (Wi-Fi or 5G)

[1326] Wearable devices

[1327] The system is activated when a worker puts on the wearable device. The device's built-in camera captures information within the worker's visual range (products, barcodes, QR codes, etc.) in real time. This video data is preprocessed by the device's processor, and feature values ​​are extracted. These feature values ​​are then sent to a server via a communications network.

[1328] server

[1329] The server receives the feature data sent from the device. Generative artificial intelligence (generative AI) analyzes this feature data and generates related product information and picking instructions. The generative AI analyzes the features using a deep learning model (e.g., CNN or RNN) and generates information. The generated information is then sent back to the wearable device via the communication network.

[1330] Augmented reality information display

[1331] The wearable device visually displays the received information as augmented reality (AR), allowing workers to see augmented information in real time within their field of vision. The displayed information is overlaid at the appropriate size and angle based on the worker's viewpoint and the location of the item.

[1332] Specific examples

[1333] Use at logistics centers

[1334] Consider a scenario where a worker is picking items at a logistics center.

[1335] The camera in the wearable device captures images of the shelves and extracts features such as barcodes, QR codes, and shapes.

[1336] The wearable device transmits these features to a server via a communication network.

[1337] The server analyzes the features and determines, "This is product A, and its shelf number is 12B," and the generation AI generates picking instructions and inventory information for this product.

[1338] The wearable device analyzes the information received from the server and displays text such as "Product A, shelf number 12B, quantity in stock 30" and related images, as well as audio guidance, on the shelf as AR.

[1339] Hardware and Software Description

[1340] Hardware:

[1341] Wearable devices (smart glasses, etc.)

[1342] Camera (built into wearable device)

[1343] Communication networks (Wi-Fi, 5G)

[1344] software:

[1345] Python (image processing, running generative AI models)

[1346] OpenCV (image processing library)

[1347] Requests (HTTP communication library)

[1348] ARModule (AR display library)

[1349] Examples of prompt statements

[1350] Imagine a scenario in which a worker wearing smart glasses at a distribution center is searching for an item in a picking area. An example prompt is as follows:

[1351] "Analyze product information from the video data and generate the information to be displayed. For example, if the product shown in the video is 'Product A', generate and respond with its name, stock quantity, and shelf number as 'Product A, stock quantity 30, shelf number 12B'."

[1352] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1353] Step 1:

[1354] The user puts on the wearable device and begins work in the logistics center.

[1355] Input: Visual information from a wearable device worn by the user

[1356] How it works: A camera built into the wearable device captures information in real time that comes within the user's visual field.

[1357] Output: Captured video data

[1358] Step 2:

[1359] The device analyzes the video data and extracts features.

[1360] Input: Captured video data

[1361] How it works: The device's processor processes the video data and uses an image recognition algorithm (e.g., OpenCV) to extract features such as product shelves, barcodes, and QR codes.

[1362] Output: Extracted feature data

[1363] Step 3:

[1364] The terminal transmits the feature data to the server via a communication network.

[1365] Input: Extracted feature data

[1366] Action: The device formats the feature data and sends it to the server using an HTTP communication library (e.g., Requests).

[1367] Output: Feature data received by the server

[1368] Step 4:

[1369] The server generates related information using artificial intelligence based on the received feature data.

[1370] Input: Feature data sent from the device

[1371] Operation: The generative AI model runs on the server, analyzes feature data using deep learning algorithms (CNN or RNN), and generates related product information, picking instructions, inventory information, etc.

[1372] Output: Related information generated

[1373] Step 5:

[1374] The server transmits the generated related information to the terminal via a communication network.

[1375] Input: Generated related information

[1376] How it works: The server formats the relevant information and sends it to the device using an HTTP communication library.

[1377] Output: Relevant information received by the device

[1378] Step 6:

[1379] The device analyzes the relevant information received and displays it visually as augmented reality (AR).

[1380] Input: Relevant information received by the device

[1381] Operation: Using an AR library (e.g., ARModule), the device overlays relevant information received with an appropriate position and size based on the user's viewpoint and the location of the item. Audio guidance is also integrated to provide voice instructions to the worker.

[1382] Output: The information the user receives visually and audibly.

[1383] Step 7:

[1384] Picking and packing are carried out quickly and accurately based on information provided by the user through the wearable device.

[1385] Input: AR and related information provided as audio guide

[1386] Action: The user uses visual and auditory information to pick the specified item and transport or pack it to the appropriate location.

[1387] Output: Users working efficiently and accurately

[1388] 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.

[1389] This invention is implemented using a system including a wearable device worn by a user, a server, and a network for communication between them. In particular, by combining it with an emotion engine that recognizes the user's emotions, it is possible to provide more personalized information. The specific processing flow of the program is described in detail below.

[1390] System Overview

[1391] The main components are as follows:

[1392] Wearable devices (terminals)

[1393] server

[1394] communication network

[1395] Emotion Engine

[1396] Terminal

[1397] The system is activated when the user puts on the wearable device. The device's camera captures objects within the user's visual field in real time. This video data is preprocessed by an internal processor, and features are extracted using an object detection algorithm. These features are then sent to a server via a communications network.

[1398] Emotion Engine

[1399] The device is equipped with an emotion engine that recognizes the user's emotions from their facial expressions and voice. The emotion engine analyzes camera footage and audio data to identify the user's emotional state (e.g., joy, surprise, sadness, anger, etc.). The detected emotion data, along with the feature values, is also sent to a server via a communication network.

[1400] server

[1401] The server receives the feature data and emotion data sent from the device. Based on the received data, generative artificial intelligence (generative AI) generates relevant information. The generative AI uses a deep learning model (e.g., CNN or RNN) to determine the type of object from the feature data and combines it with emotion data to generate information that best suits the user's current state. The generated information is then sent back to the device via the communications network.

[1402] Information display

[1403] The device visually displays the received relevant information as augmented reality (AR), allowing users to obtain augmented information within their field of vision in real time. The displayed information is overlaid at an appropriate size and angle based on the user's viewpoint and the object's position. Furthermore, the content and format of the information are personalized based on emotional data.

[1404] Specific examples

[1405] Example 1: Museum use

[1406] Consider a scenario in which a user is looking at "ancient statues" in a history museum.

[1407] The device's camera captures video of the statue and extracts features such as shape, color, and texture.

[1408] The terminal transmits these features to a server via a communication network.

[1409] The device's emotion engine analyzes the user's facial expression and determines that the user is expressing surprise.

[1410] The server analyzes both pieces of data and generates a summary that says, "This is an ancient Greek statue from 500 BC, and provides context and origins, as well as additional facts that may surprise the user."

[1411] The device analyzes the information received from the server and displays text and related images such as "500 BC Ancient Greek Statues: Their Historical Background and Amazing Facts" on the statue as AR.

[1412] Example 2: Use in daily life

[1413] Consider a scenario where a user is looking at "product packaging" in a supermarket.

[1414] The device's camera captures images of the product packaging and extracts features from the barcode and label information.

[1415] The terminal transmits these features to a server via a communication network.

[1416] The device's emotion engine analyzes the user's voice and determines whether the user is happy.

[1417] The server analyzes both sets of data and generates encouraging information about the food, including that it's organic, that it's free of certain allergens, and its health benefits.

[1418] The device analyzes the information received from the server and displays text such as "organic food, allergen information, health benefits" and related images as AR on the product packaging.

[1419] In this way, users can instantly acquire a wealth of knowledge and data based on visual information, and by receiving personalized information based on their emotions, the quality of their learning, research, and daily life can be further improved.

[1420] The processing flow will be explained below.

[1421] Step 1:

[1422] The user puts on the wearable device. The wearable device starts up and the camera begins capturing video data within the user's visual field. This video data is captured frame by frame and processed at 30 frames per second (FPS).

[1423] Step 2:

[1424] The device receives the captured video data and performs preprocessing, which includes removing noise from the video data and adjusting the resolution. It then uses object detection algorithms to detect objects and features within its visual range. Specifically, it extracts color, shape, texture, and identifiers such as barcodes and QR codes from the camera's video data.

[1425] Step 3:

[1426] The device's emotion engine analyzes the user's facial expressions and voice to determine their emotional state. The emotion engine uses facial recognition and voice analysis algorithms to determine whether the user is happy, surprised, sad, angry, or other emotions.

[1427] Step 4:

[1428] The extracted feature data and emotion data are converted into JSON format and sent to a server via a communication network, using Wi-Fi or mobile data.

[1429] Step 5:

[1430] The server receives the feature data and emotion data sent from the device. The received data is analyzed by generative artificial intelligence (generative AI). The generative AI uses a deep learning model (e.g., CNN or RNN) to determine the type of object from the feature data and generate related information taking emotion data into account.

[1431] Step 6:

[1432] The server generates relevant information based on the judgment results and emotion data. The generation AI collects relevant information from databases and the internet, generates that information in natural language, and personalizes the information to match the user's emotions. The generated information is then converted back into JSON format.

[1433] Step 7:

[1434] The server generates information and sends it to the terminal via a communication network. The transmitted data includes specific information about the object, related images, text, and so on.

[1435] Step 8:

[1436] The device parses the information received from the server and converts it into a format for display. The received data is parsed appropriately and formatted into a visual display format using an AR library (e.g., Unity or ARKit).

[1437] Step 9:

[1438] The device displays the analyzed information as augmented reality (AR) within the user's field of view. Specifically, text information and images are overlaid on top of the visual data based on the object's position, angle, and size. Furthermore, the content and format of the information are personalized based on the user's emotional data, providing information that corresponds to the user's emotions.

[1439] Step 10:

[1440] The device periodically sends user data to the server and receives updated information as needed. New video data is captured at regular intervals, and feature and emotion data are extracted again and sent to the server. The server continues to generate new information, and the device receives this updated information, always providing the user with the latest information.

[1441] In this way, users can instantly acquire a wealth of knowledge and data based on visual information, and by receiving personalized information based on their emotions, the quality of their learning, research, and daily life can be further improved.

[1442] Example 2

[1443] 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."

[1444] Current information provision systems using wearable devices are limited to acquiring and displaying information within the user's visual field, and do not adequately provide personalized information that takes into account the user's emotional state. This limits the quality of the user experience and makes it difficult to display appropriate information according to the usage scenario.

[1445] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for acquiring information within the visual range of a wearable device worn by a user; means for analyzing the acquired information and extracting features; means for analyzing the user's facial expressions and voice to acquire emotional data; means for transmitting the extracted features and emotional data to the server via a communication network; means for generating related information based on the features and emotional data received by the server using artificial intelligence; means for transmitting the generated information to the wearable device via the communication network; and means for visually displaying the information received by the wearable device as augmented reality. This enables the provision of personalized information according to the user's emotional state. Furthermore, combining visually acquired information with emotional data can improve the quality of the user experience and provide more appropriate information.

[1446] A "wearable device" is a terminal device with computing functions that is worn on the user's body.

[1447] "Visual range" refers to the area that a user can see through a wearable device.

[1448] "Means for acquiring information" refers to devices or methods that use cameras or sensors installed in wearable devices to collect images and data within the visual range.

[1449] "Means for extracting features" refers to algorithms or devices that analyze and extract characteristic data such as the shape, color, and texture of objects from images and data acquired by cameras or sensors.

[1450] A "communications network" is a system that provides an infrastructure for transmitting and receiving data, and includes wired or wireless networks.

[1451] "Server" refers to a computer system that processes and stores data over a network and provides services to client devices.

[1452] "Emotion data" refers to information obtained by analyzing data that represents the emotional state of a user, such as facial expressions and voice.

[1453] "Generative artificial intelligence" refers to technology that uses machine learning and deep learning models to analyze data and generate new information.

[1454] "Augmented reality" refers to a technology that displays computer-generated visual information overlaid on a real-world environment.

[1455] This invention is a system that uses a wearable device worn by a user to analyze information within the user's visual field and provide related information. This system is realized mainly by a wearable device, a server, a communication network, and an emotion engine.

[1456] Hardware and Software Configuration

[1457] A wearable device includes the following elements:

[1458] Camera: Captures objects within its visual range.

[1459] Microphone: Captures user voice.

[1460] Processor: Performs data preprocessing.

[1461] Communication module: Sends and receives data.

[1462] A server is a computer system with high-performance computing power that includes the following elements:

[1463] Generative AI models (e.g., CNNs and RNNs): Analyze data and generate information.

[1464] Database: Stores the acquired and generated data.

[1465] The emotion engine is a software component that analyzes emotions from the user's facial expressions and voice.

[1466] A communications network is the infrastructure that enables data communication over the web.

[1467] Operation explanation

[1468] When a user puts on the wearable device, the system is activated. The camera captures objects within the user's visual field in real time, and the processor analyzes the video data to extract features. These features are then sent to a server via a communication network.

[1469] The emotion engine installed in the wearable device analyzes the captured video and audio data to identify the user's emotional state, which is then transmitted to a server via a communication network.

[1470] The server analyzes the received feature data and emotion data and generates relevant information using a generative AI model (e.g., CNN or RNN). This generated information is personalized and best suited to the type of object and the user's emotional state. The generated information is then sent back to the wearable device via the communication network.

[1471] Specific examples

[1472] Example 1: Museum use

[1473] Consider a case where a user is looking at an "ancient statue" in a history museum. The device's camera captures video of the statue and extracts features such as shape, color, and texture. The device then sends these features to a server via a communications network. The device's emotion engine analyzes the user's facial expression and determines that the user is expressing surprise. The server analyzes both sets of data and generates content that explains, "This is an ancient Greek statue from 500 BC, and provides its historical background and origin, as well as additional facts that may surprise the user." The device then analyzes the information received from the server and displays text such as "500 BC Ancient Greek statue, its historical background, and surprising facts" and related images on top of the statue as AR.

[1474] Example 2: Use in daily life

[1475] Consider a case where a user is looking at a "product package" in a supermarket. The device's camera captures an image of the product package and extracts features from the barcode and label information. The device then sends these features to a server via a communications network. The device's emotion engine analyzes the user's voice and determines that the user is happy. The server analyzes both sets of data and generates encouraging information about "this is organic food, does not contain specific allergens, and its health benefits." The device analyzes the information received from the server and displays text such as "organic food, allergen information, health benefits" and related images on the product package as AR.

[1476] Examples of prompt statements

[1477] 1. "A user looks surprised while looking at an ancient statue in a museum. The statue's features are: Shape: 'Cylindrical', Color: 'Gray', Texture: 'Rough'. Generate historical information about this statue."

[1478] 2. "A user is looking at a product package in a supermarket and exclaims with delight. The product is organic and has barcode: '123456789'. Please generate more information about this."

[1479] This system allows users to obtain visual information in real time and enjoy personalized content that responds to their emotions.

[1480] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1481] Step 1:

[1482] The user puts on the wearable device and the system is started. The input can be a gesture of putting on the device or a voice command. The output can be the activation of each component of the wearable device (camera, microphone, processor, communication module).

[1483] Step 2:

[1484] The device's camera captures objects within the user's field of vision in real time. The input is video data from the camera, and the output is the captured video data. The processor receives the video data and performs preprocessing, specifically image processing such as noise reduction and color filtering.

[1485] Step 3:

[1486] The device applies an object detection algorithm (such as YOLO or SSD) to the preprocessed video data to extract features such as the shape, color, and texture of the object. The input is the preprocessed video data, and the output is the extracted feature data. Specifically, the extracted features include the statue's shape being "cylindrical," its color being "gray," and its texture being "rough."

[1487] Step 4:

[1488] The device's emotion engine analyzes camera footage and microphone audio to identify the user's emotional state. The input is camera footage and microphone audio, and the output is emotion data. Specifically, it analyzes the user's facial expressions and tone of voice to identify emotions such as "surprise" or "joy."

[1489] Step 5:

[1490] The device transmits the extracted feature data and emotion data to a server via a communication network. The input is the feature data and emotion data, and the output is the data transmitted to the server. Specifically, the feature data (shape: 'cylindrical', color: 'gray', texture: 'rough') and emotion data (surprise) are transmitted to the server.

[1491] Step 6:

[1492] The server receives feature data and emotion data sent from the device. The input is the data sent from the device, and the output is the received data. The server inputs the received data into a generative AI model (e.g., CNN or RNN) to generate related information. Specifically, historical information and additional facts about ancient Greek statues are generated.

[1493] Step 7:

[1494] The server transmits the generated related information to the terminal via a communication network. The input is the generated information, and the output is the information transmitted to the terminal. The terminal receives and analyzes this information.

[1495] Step 8:

[1496] Based on the received information, the device visually displays the information on top of the object as augmented reality (AR). The input is the information received from the server, and the output is the AR information displayed within the user's field of vision. Specifically, text such as "500 BC Ancient Greek Statues: Their Historical Background and Amazing Facts" and related images are displayed on top of the statue.

[1497] This allows users to get real-time personalized information related to objects within their field of vision.

[1498] (Application example 2)

[1499] 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."

[1500] Conventional factory robots and assistance systems have difficulty monitoring the operator's condition in real time and providing assistance information at the appropriate time. Furthermore, few systems recognize the operator's emotions and provide work assistance, and they have not adequately improved work efficiency or prevented errors. This has led to problems such as reduced work efficiency and an increased risk of errors.

[1501] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1502] means for transmitting emotion data to a server;

[1503] means for generating related information based on the features received by the server using a generating artificial intelligence;

[1504] means for transmitting the generated information to a wearable device via a communication network;

[1505] This includes:

[1506] It is possible to detect the user's emotions in real time and provide personalized work support information and advice based on that, thereby improving the operator's work efficiency.

[1507] A "wearable device" is an electronic device that can be worn by a user and has the ability to acquire, analyze, and display information in real time.

[1508] An "emotion engine" is a software or hardware system that recognizes and analyzes emotions from a user's facial expressions and voice.

[1509] A "communications network" is an infrastructure for transmitting and receiving data, including the Internet and dedicated data communication lines.

[1510] A "server" is a computing resource that receives data transmitted from wearable devices over a network and generates analysis and related information.

[1511] "Generative artificial intelligence" refers to algorithms and models that generate information from data using techniques such as machine learning and deep learning.

[1512] "Features" are numerical data used to analyze information such as objects within the visual range and the emotional state of the user.

[1513] "Augmented reality" is a technology that displays digital information overlaid on real-world visual information, providing users with a richer information environment.

[1514] "Personalized information" is information that is specifically tailored to a user's emotional state and individual needs.

[1515] An "operator" is a human user who operates machinery or equipment in a factory or work environment.

[1516] "Work support information" is information that includes guidelines and advice for operators to perform work safely and efficiently.

[1517] This invention is implemented in a system that uses a wearable device worn by an operator in a factory or work environment, a server, and a network for communication between them. In particular, by combining it with an emotion engine that recognizes the operator's emotions, it is possible to provide more personalized work support information in real time.

[1518] System Overview

[1519] The main components are as follows:

[1520] Wearable device (terminal): A device worn by the operator that captures video, recognizes emotions, and displays AR.

[1521] Server: Analyzes the received data and generates relevant information using generation AI.

[1522] Communications network: The infrastructure through which devices and servers send and receive data.

[1523] Terminal

[1524] The wearable device is worn by the operator, and the camera captures images within the visual range in real time. This image data is preprocessed by an internal processor, and features are extracted using an object detection algorithm. In addition, an emotion engine analyzes the operator's facial expressions and voice to generate emotion data. This data is sent to a server via a communication network.

[1525] Emotion Engine

[1526] The wearable device is equipped with an emotion engine that analyzes the operator's emotional state in real time. The emotion engine identifies the operator's emotions (e.g., stress, joy, anxiety, etc.) based on camera footage and audio data. The analyzed emotion data is sent to a server along with feature data.

[1527] server

[1528] The server receives the feature data and emotion data sent from the device and generates relevant information using a generative AI model. The generated information uses a deep learning model (e.g., CNN or RNN) to adapt to the operator's current emotional state and work context. This information is then sent back to the wearable device via the communication network.

[1529] Information display

[1530] The wearable device visually displays the work support information received from the server as augmented reality (AR), allowing the operator to obtain augmented information within their visual range in real time. The displayed information is overlaid at an appropriate size and angle based on the operator's viewpoint and work situation. Furthermore, the content and format of the information are personalized based on emotional data.

[1531] Specific examples

[1532] Example: Factory use

[1533] Consider an operator picking up a part on an assembly line.

[1534] The device's camera captures images of the parts and extracts features such as shape, color, and texture.

[1535] The terminal transmits these features to a server via a communication network.

[1536] The device's emotion engine analyzes the operator's facial expressions and voice to determine if the operator is confused.

[1537] The server analyzes both sets of data and generates "This part is used on XYZ machine, and its assembly instructions and common error countermeasures."

[1538] The device analyzes the information received from the server and displays text such as "XYZ machine assembly procedure common error countermeasures" and related images on top of the part as AR.

[1539] Prompt Sentence Examples

[1540] "Build an application that recognizes an operator's emotions in real time and provides assembly assistance information based on his / her psychological state. The specific steps are as follows:"

[1541] "If an operator is confused, think about what information you should provide and display it in AR."

[1542] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1543] Step 1:

[1544] The terminal uses the camera of the wearable device worn by the operator to capture images within its visual range in real time. The input is the camera image, and the output is the captured image data. Specifically, the camera captures images at a constant frame rate and stores them in an internal buffer.

[1545] Step 2:

[1546] The device preprocesses the captured video data and extracts features using an object detection algorithm (e.g., YOLO or SSD). The input is the captured video data, and the output is the extracted features. Specific operations include noise removal, resizing, and filtering to enhance features in the video data.

[1547] Step 3:

[1548] The terminal uses an emotion engine to analyze emotions from the operator's facial expressions and voice data. The input is facial expression data and voice data, and the output is analyzed emotion data. Specific operations include extracting face areas from camera footage and performing spectrum analysis of voice data.

[1549] Step 4:

[1550] The device transmits the extracted feature data and emotion data to a server via a communication network. The input is the feature data and emotion data, and the output is a data packet transmitted over the network. Specifically, the data is serialized and packetized according to the network protocol.

[1551] Step 5:

[1552] The server analyzes the received feature data and emotion data and generates related information using a generative AI model. The input is feature data and emotion data, and the output is the generated related information. Specifically, the server analyzes the feature data using a convolutional neural network (CNN) and the emotion data using a recurrent neural network (RNN) to generate appropriate assistance information.

[1553] Step 6:

[1554] The server transmits the generated related information to the terminal via a communication network. The input is the generated related information, and the output is a data packet transmitted via the network. Specific operations include serializing the information and packetizing it into data packets.

[1555] Step 7:

[1556] The device interprets the received related information and visually displays it as augmented reality (AR). The input is the received related information, and the output is the AR content displayed on the display of the wearable device. Specifically, the related information is overlaid on the video data as an overlay and displayed in the appropriate position and size.

[1557] Step 8:

[1558] The user performs tasks based on personalized work support information displayed as augmented reality. The input is the visually displayed support information, and the output is the user's work results. Specifically, the user follows the guidelines provided through AR to properly progress through the task.

[1559] 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.

[1560] 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.

[1561] 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 robot 414.

[1562] 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.

[1563] 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.

[1564] 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.

[1565] 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).

[1566] 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.

[1567] 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."

[1568] 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.

[1569] 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).

[1570] 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.

[1571] 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.

[1572] 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.

[1573] 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.

[1574] 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.

[1575] 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.

[1576] 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.

[1577] 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.

[1578] 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.

[1579] 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.

[1580] The following is further disclosed regarding the above embodiment.

[1581] (Claim 1)

[1582] A means for acquiring information within the visual range of a wearable device worn by a user;

[1583] A means for analyzing the acquired information and extracting features;

[1584] means for transmitting the extracted features to a server via a communication network;

[1585] means for generating related information based on the features received by the server using a generating artificial intelligence;

[1586] means for transmitting the generated information to a wearable device via a communication network;

[1587] a means for visually displaying the information received by the wearable device as augmented reality;

[1588] A system including:

[1589] (Claim 2)

[1590] 10. The system of claim 1, further comprising means for periodically transmitting user data to the server and receiving updates from the server as needed.

[1591] (Claim 3)

[1592] 10. The system of claim 1, further comprising means for capturing video data within a visual field using a camera and extracting features using an object detection algorithm.

[1593] "Example 1"

[1594] (Claim 1)

[1595] means for acquiring information within the visual range of a device worn by a user;

[1596] A means for analyzing the acquired information and extracting features using a trained algorithm;

[1597] means for transmitting the extracted features to a central processing unit via a communication network;

[1598] means for generating relevant information based on the features received by the central processing unit using a generative artificial intelligence;

[1599] means for transmitting the generated information to a device via a communications network;

[1600] means for displaying the information received by the device as a visual augmentation;

[1601] A system including:

[1602] (Claim 2)

[1603] 10. The system of claim 1, further comprising means for periodically transmitting user data to the central processing unit and receiving updates from the central processing unit as needed.

[1604] (Claim 3)

[1605] 10. The system of claim 1, further comprising means for acquiring video data within a visual field using an image capture device and extracting features using an object recognition algorithm.

[1606] "Application Example 1"

[1607] (Claim 1)

[1608] A means for acquiring information within the visual range of a wearable device worn by a user;

[1609] A means for analyzing the acquired information and extracting features;

[1610] means for transmitting the extracted features to a server via a communication network;

[1611] means for generating related information based on the features received by the server using a generating artificial intelligence;

[1612] means for transmitting the generated information to a wearable device via a communication network;

[1613] a means for visually displaying the information received by the wearable device as augmented reality;

[1614] A means worn by workers to support work at a logistics center;

[1615] A system including:

[1616] (Claim 2)

[1617] 10. The system of claim 1, further comprising means for periodically transmitting user data to the server and receiving updates from the server as needed.

[1618] (Claim 3)

[1619] 10. The system of claim 1, further comprising means for capturing video data within a visual field using a camera and extracting features using an object detection algorithm.

[1620] "Example 2: Combining Emotion Engines"

[1621] (Claim 1)

[1622] A means for acquiring information within the visual range of a wearable device worn by a user;

[1623] A means for analyzing the acquired information and extracting features;

[1624] means for transmitting the extracted features to a server via a communication network;

[1625] A means for acquiring emotion data by analyzing a user's facial expressions and voice;

[1626] means for transmitting emotion data to a server via a communication network;

[1627] a means for generating related information based on the feature and emotion data received by the server using a generative artificial intelligence;

[1628] means for transmitting the generated information to a wearable device via a communication network;

[1629] a means for visually displaying the information received by the wearable device as augmented reality;

[1630] A system including:

[1631] (Claim 2)

[1632] 10. The system of claim 1, further comprising means for periodically transmitting user data to the server and receiving updates from the server as needed.

[1633] (Claim 3)

[1634] 10. The system of claim 1, further comprising means for capturing video data within a visual field using a camera and extracting features using an object detection algorithm.

[1635] "Application example 2 when combining emotion engines"

[1636] (Claim 1)

[1637] A means for acquiring information within the visual range of a wearable device worn by a user;

[1638] A means for analyzing the acquired information and extracting features;

[1639] means for transmitting the extracted features to a server via a communication network;

[1640] means for generating related information based on the features received by the server using a generating artificial intelligence;

[1641] means for transmitting the generated information to a wearable device via a communication network;

[1642] a means for visually displaying the information received by the wearable device as augmented reality;

[1643] Equipped with an emotion engine to recognize and analyze user emotions,

[1644] means for transmitting the recognized emotion data to a server;

[1645] means for displaying personalized information generated based on the emotion data;

[1646] a means for providing work support information in response to the emotion of the operator;

[1647] A system including:

[1648] (Claim 2)

[1649] 10. The system of claim 1, further comprising means for periodically transmitting user data to the server and receiving updates from the server as needed.

[1650] (Claim 3)

[1651] 10. The system of claim 1, further comprising means for capturing video data within a visual field using a camera and extracting features using an object detection algorithm. [Explanation of symbols]

[1652] 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. A means for acquiring information within the visual range of a wearable device worn by a user; A means for analyzing the acquired information and extracting features; means for transmitting the extracted features to a server via a communication network; means for generating related information based on the features received by the server using a generating artificial intelligence; means for transmitting the generated information to a wearable device via a communication network; a means for visually displaying the information received by the wearable device as augmented reality; A system including:

2. 2. The system of claim 1, further comprising means for periodically transmitting user data to the server and receiving updates from the server as needed.

3. 10. The system of claim 1, further comprising means for capturing video data within a visual field using a camera and extracting features using an object detection algorithm.

Images