System

Abstract

A system is provided.SOLUTION: A system comprising: means for obtaining visual data; means for analyzing the visual data to extract visual information; artificial intelligence means for generating additional information based on the visual information; and means for providing the additional information to a user.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] In today's information-overloaded world, users need to instantly acquire the information they need in their daily lives and learning activities. However, current technology only provides limited methods for instantly acquiring information about objects and scenes within a user's field of vision, and there are no effective means to improve users' knowledge acquisition or learning efficiency. Furthermore, in marketing and promotional activities, it is difficult to provide appropriate information in real time based on the user's visual information. In these circumstances, a new system is needed that can instantly analyze information within a user's field of vision and provide the generated information. [Means for solving the problem]

[0005] The present invention provides a system including a means for acquiring visual data, a means for analyzing the visual data to extract visual information, an artificial intelligence means for generating additional information based on the visual information, and a means for providing the additional information to a user. Specifically, the system includes a camera that captures an image within the user's field of view, analyzes the visual data using an image analysis server, and generates the additional information using a generation AI. The generated additional information is provided to the user in an appropriate format, allowing the user to instantly gain knowledge about objects and scenes within the field of view. This aims to improve learning efficiency and quality of life, as well as enhance marketing effectiveness.

[0006] "Visual data" refers to information on images and videos of objects and scenes within the user's field of vision captured using a photographing device such as a camera.

[0007] "Visual information" refers to information such as the characteristics and positions of objects in images and videos, obtained by analyzing visual data.

[0008] "Artificial intelligence means" refers to technologies including machine learning models and natural language processing models for generating additional information based on visual information.

[0009] "Additional Information" refers to further explanations or related information about visual information that is generated by artificial intelligence means and provided to the user.

[0010] "User" refers to a person who utilizes the system to obtain visual data and obtain additional information.

[0011] A "camera" is a photographic device for capturing images and videos within the user's field of view.

[0012] The "image analysis server" is a server device that analyzes acquired visual data and extracts visual information.

[0013] "Generative AI" is an artificial intelligence model that generates text information and commentary based on visual information. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

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

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

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

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0029] 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.

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

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] The present invention relates to a system for acquiring and analyzing visual data to generate and provide additional information. This system includes a means for acquiring visual data, a means for analyzing the visual data to extract visual information, an artificial intelligence means for generating additional information based on the visual information, and a means for providing the additional information to a user.

[0036] Device behavior

[0037] The device has a built-in camera that captures objects and scenes within the user's field of view in real time. It captures the image the user sees through the device and sends it to the server as image data. The device then encodes the image data appropriately and sends it to the server's endpoint as an HTTP request.

[0038] Server Operation

[0039] The server receives image data sent from the device. The received image data is first analyzed by the image analysis server to extract visual information about objects and features in the image. The extracted visual information is sent to the generative AI means, which generates additional information. The generative AI means generates text information and explanations based on the visual information. A feedback loop is also implemented to ensure that the generated information is useful to the user.

[0040] Specific examples

[0041] As a specific example, consider a scenario in which a user is looking at a historical building at a tourist spot. The user is wearing a glasses-type device, which captures an image of the building. This image is sent from the device to a server. The server first analyzes the image using an image analysis server to identify the building's features and name. If the analysis results identify the "Eiffel Tower," the AI ​​generation means generates additional information such as "The Eiffel Tower is an iconic French building built in 1889, approximately 324 meters tall." The device displays this information in the user's field of view using AR, allowing the user to instantly learn about the Eiffel Tower.

[0042] User Experience

[0043] By simply wearing the glasses, users can receive rich information about objects and scenes in their field of vision in real time. This will greatly improve the learning experience when traveling, touring tourist spots, visiting museums, etc. It will also improve the quality of life in everyday life by allowing users to instantly obtain information about unfamiliar objects and new places.

[0044] The above is one example of a mode for carrying out the present invention, and the present invention is not limited to this specific example. The present invention includes all possible embodiments.

[0045] The processing flow will be explained below.

[0046] Step 1:

[0047] A user wears the glasses-type device and looks at an object within their field of view. At this time, the camera built into the device captures image data within the user's field of view. The captured image data is temporarily stored within the device.

[0048] Step 2:

[0049] The device encodes the captured image data and prepares it for sending to the server. Specifically, the image data is converted to JPEG format or other format and compiled into a sendable data format. Next, the image data is sent to the server endpoint as an HTTP POST request.

[0050] Step 3:

[0051] The server receives the image data sent from the terminal. The server checks the received data and prepares to start analyzing the image data. First, it checks the integrity of the data and makes sure there are no missing or damaged parts.

[0052] Step 4:

[0053] The server passes the image data to the image analysis server, which then uses machine learning models and algorithms to identify objects and features in the image, extracting visual information (e.g., the names and characteristics of specific buildings and objects).

[0054] Step 5:

[0055] The server receives the visual information obtained from the image analysis server, and converts this visual information into a data format that is prepared for use in the next step and passed to the generation AI means.

[0056] Step 6:

[0057] The server sends the visual information to the AI ​​generator, requesting it to generate additional information. The AI ​​generator then uses natural language processing technology to generate relevant text information and commentary based on the visual information. This process typically takes place within a few seconds.

[0058] Step 7:

[0059] The generated additional information is returned from the generation AI means to the server. The server checks the content of this additional information and prepares it for presentation to the user. Specifically, it converts the text information into an appropriate format and prepares it for transmission to the terminal.

[0060] Step 8:

[0061] The server sends the prepared additional information to the device. The device receives the additional information and notifies the user through a user interface (UI). When using AR technology, the device displays the information superimposed on the user's field of view.

[0062] Step 9:

[0063] Users receive additional information in real time through the glasses, allowing them to instantly gain detailed knowledge about objects and scenes within their field of view, improving the quality of their learning and daily life.

[0064] Example 1

[0065] 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."

[0066] Conventional visual information provision systems have made it difficult for users to obtain useful information from visual data in real time. Furthermore, analyzing visual data and generating additional information requires time and effort, limiting the improvement of user experience. To address this issue, a system that can efficiently analyze visual data and provide practical and immediate additional information is needed.

[0067] 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.

[0068] In this invention, the server includes a means for encoding visual data and transmitting it over a network, a means for analyzing the visual data to extract object features and visual information, and an artificial intelligence means for generating text information and explanations based on the visual information, thereby enabling analysis of the visual data and real-time generation and provision of additional information.

[0069] "Visual data" is image data that captures objects and scenes within a user's field of view using an optical device such as a camera.

[0070] "Encoding" is the process of converting a particular data format into another format, and in this invention refers to converting visual data into a format that can be transmitted over a network.

[0071] A "network" is a communications infrastructure that connects multiple computers and devices and is used in the present invention to send and receive visual data and additional information.

[0072] An "analysis device" is a device that analyzes visual data to identify objects and features in an image and extract visual information.

[0073] "Visual information" refers to the attributes and associated information of objects and features in the visual data, including, for example, the names and characteristics of objects.

[0074] "Artificial intelligence means" means means that use artificial intelligence techniques or algorithms to generate textual information or commentary based on visual information.

[0075] "Additional information" refers to textual information or explanations generated by artificial intelligence means based on the analyzed visual information, and is supplementary information that helps the user further understand the visual data.

[0076] An "optical device" is a device for capturing images, such as a camera.

[0077] "Real-time display" refers to the process of providing information acquired or generated by a terminal to a user immediately and without delay.

[0078] The present invention is a system for acquiring visual data, analyzing it, and generating and providing additional information. This system includes a "means for acquiring visual data," a "means for encoding the visual data and transmitting it over a network," a "means for analyzing the visual data and extracting object features and visual information," an "artificial intelligence means for generating text information and commentary based on the visual information," and a "means for encoding the additional information to a user, transmitting it, and displaying it." A specific embodiment for implementing this system will be described below.

[0079] Device behavior

[0080] The device uses its built-in camera to capture objects and scenes within the user's field of view in real time. For example, if a user wears a glasses-type device and is at a tourist spot, the device will capture images of the surrounding scenery and buildings. The captured visual data is encoded in JPEG or PNG format and sent to a server over the network. The device sends the visual data to the server using an HTTP request.

[0081] Server Operation

[0082] The server receives the visual data sent from the device. After receiving the data, it is first temporarily stored and then sent to the image analysis server. The image analysis server uses a deep learning model (e.g., a convolutional neural network) to perform a detailed analysis of the image data. As a result of the analysis, object features and visual information are extracted.

[0083] The extracted visual information is input into a generative AI model, which generates additional information in real time. This generative AI model receives prompts such as "Please tell me the name and information about this object" based on the visual information, and generates text information and explanations based on that. The generated information is sent to the device as an HTTP response.

[0084] Specific examples

[0085] Consider a scenario in which a user is looking at a historical building at a tourist spot. If the user is wearing a glasses-type device and looking at the Eiffel Tower, the device captures an image of the Eiffel Tower. This image data is sent from the device to a server, which uses an image analysis server to analyze the image and identify the building's features and name. If the analysis results identify the "Eiffel Tower," the generation AI generates information such as "The Eiffel Tower is an iconic French building built in 1889 and is approximately 324 meters tall." This additional information is sent to the device and displayed in AR in the user's field of view.

[0086] User Experience

[0087] By simply wearing the glasses, users can obtain a wealth of information from visual data in real time. This system will significantly improve the learning experience when traveling, touring tourist spots, visiting museums, etc. It will also improve the quality of life in everyday life by allowing users to instantly obtain information about unfamiliar objects and new places.

[0088] Example prompt sentence:

[0089] 1. "What is the name of this object and what are some details about it?"

[0090] 2. "Tell me about the building in front of you."

[0091] The above is one example of the mode for carrying out the present invention, and the present invention is not limited to this specific example and includes all modes.

[0092] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0093] Step 1:

[0094] The device acquires visual data using a built-in camera. The user wears a glasses-type device, which captures objects and scenes in the user's field of view in real time. The input is visual data (images) acquired by the camera, and the output is encoded image data.

[0095] Step 2:

[0096] The visual data acquired by the device is encoded in JPEG or PNG format and sent to the server via the network using an HTTP request. The input is the unencoded visual data stored in the device, and the output is the encoded visual data sent to the server.

[0097] Step 3:

[0098] The server receives the encoded visual data sent from the device. After receiving, the server temporarily stores this data and then sends it to the image analysis server. The input is the visual data received via the network, and the output is the stored image data.

[0099] Step 4:

[0100] The image analysis server analyzes the stored visual data. The image analysis server uses a deep learning model (e.g., a convolutional neural network) to extract object features and visual information from the image data. The input is the stored visual data, and the output is the extracted visual information.

[0101] Step 5:

[0102] The server receives the extracted visual information from the image analysis server and inputs it into a generative AI model. The generative AI model generates text information and explanations from the visual information based on a prompt such as "Please tell me the name and information about this object." The input is the extracted visual information and the prompt, and the output is the generated additional information in text format.

[0103] Step 6:

[0104] The server encodes the additional information created by the generative AI model and sends it to the terminal as an HTTP response. The input is the generated additional information, and the output is the encoded additional information.

[0105] Step 7:

[0106] The device receives the encoded additional information sent from the server. After receiving it, the device decodes this information and displays it in the user's field of view in AR. The input is the additional information received from the server, and the output is the explanation or information displayed in the user's field of view.

[0107] This series of processes allows the user to obtain useful information based on visual data in real time.

[0108] (Application example 1)

[0109] 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."

[0110] While there is a demand for improved quality control of products and parts and work efficiency in factories, conventional systems have difficulty in analyzing visual data in real time and providing immediate feedback, which has prevented them from fully achieving work efficiency and quality. Therefore, there is a need for a system that can efficiently analyze visual data and provide appropriate instructions on the spot.

[0111] 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.

[0112] In this invention, the server includes a means for receiving visual data, a means for analyzing the visual data to extract visual information, and an artificial intelligence means for generating instructions based on the visual information, thereby enabling the factory robot to instantly provide instructions for the next process or quality check based on the analysis results of the visual data acquired in real time.

[0113] "Visual data" refers to digital data of images and videos captured by factory robots and photography devices.

[0114] "Analysis" refers to the process of identifying objects and features from acquired visual data and extracting information based on them.

[0115] "Visual information" refers to information representing objects and features extracted from visual data through analysis.

[0116] "Additional information" refers to instructions or explanations regarding next steps or quality checks generated by the generative AI means based on the visual information.

[0117] "Artificial intelligence means" refers to machine learning models and algorithms that generate additional information based on visual information.

[0118] A "user" is a person or entity that operates a factory robot or uses a visual data analysis system.

[0119] "Server" refers to a central computing device for receiving and analyzing visual data.

[0120] "Display device" means a screen or monitor for visually presenting the additional generated information.

[0121] "Audio output device" refers to a speaker or earphone for providing additional information as audio.

[0122] This invention is a system for acquiring and analyzing visual data to generate and provide additional information. The system includes the following components:

[0123] 1. Hardware and Software Used

[0124] Hardware:

[0125] Camera: A high-resolution camera built into a factory robot, used to capture visual data in real time.

[0126] Display: A display device attached to the robot, used to visually present additional generated information.

[0127] Audio output device: A speaker built into the robot, used to provide additional information as audio.

[0128] software:

[0129] Image analysis: Identifying objects and features from visual data using Python's OpenCV library.

[0130] Generative AI model: OpenAI's GPT-4 is used to generate additional information based on visual information.

[0131] Data transmission and reception: Using the Python Requests library, visual data is sent to the server and analysis results are received.

[0132] 2. System Operation

[0133] Camera visual data acquisition:

[0134] High-resolution cameras built into factory robots capture real-time images of products and parts, which are then encoded into a suitable format on the device and sent to a server.

[0135] Image analysis by server:

[0136] The server receives image data sent from the device. The received image data is first analyzed by an image analysis function (using the OpenCV library) to extract visual information about objects and features. This visual information is then sent to a generative AI model (OpenAI GPT-4) to generate additional information.

[0137] Generate and provide additional information:

[0138] The generative AI model generates instructions for the next process or quality check based on the visual information. These instructions are provided to the factory robot's display and audio output device, and are displayed and communicated to the user visually or audibly.

[0139] 3. Specific Examples

[0140] For example, when a factory robot picks up a part, an image of the part is captured in real time. This image is sent to a server, which then performs image analysis to identify the part's characteristics. If the analysis results indicate that the part may be defective, the generative AI model generates instructions based on the following prompt:

[0141] Prompt Sentence Examples

[0142] Part analysis results: Possibly defective. Generate instructions for next steps and quality checks.

[0143] The generated instructions are provided to the user via the robot's display and voice output device, allowing for immediate action to be taken. For example, instructions such as "This part requires a quality check. Please re-inspect it before proceeding to the next process" are displayed.

[0144] In this way, the introduction of this system is expected to significantly improve work efficiency and product quality control within the factory.

[0145] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0146] Step 1:

[0147] A user operates a factory robot and captures images of an object (product or part) using the robot's built-in camera.

[0148] Input: Image of the object

[0149] Output: Captured image data

[0150] How it works: A high-resolution camera captures images of the object in real time.

[0151] Step 2:

[0152] The device encodes the captured image data into an appropriate format (for example, JPEG format) and sends it to the server as an HTTP request.

[0153] Input: Captured image data

[0154] Output: Encoded image data sent to the server

[0155] Specific operation: Image data is converted to JPEG format on the device, an HTTP request is constructed, and sent to the server endpoint.

[0156] Step 3:

[0157] The server receives the image data sent from the terminal and transfers it to the image analysis server for analysis.

[0158] Input: Encoded image data sent from the device

[0159] Output: Image data sent to the image analysis server

[0160] Specific operation: The server's receiving process receives the image data and transfers it to the image analysis server.

[0161] Step 4:

[0162] The image analysis server analyzes the image data and extracts objects and features in the image as visual information.

[0163] Input: Image data transferred to the image analysis server

[0164] Output: Extracted visual information (objects and features)

[0165] What it does: The image analysis server uses the OpenCV library to analyze images and identify objects and features.

[0166] Step 5:

[0167] The server provides the extracted visual information to the generative AI model and inputs prompt sentences to generate additional information.

[0168] Input: Extracted visual information

[0169] Output: Generated additional information (instructions for next steps and quality checks)

[0170] Specific operation: Based on visual information, the server inputs a prompt sentence into OpenAI's GPT-4 API and generates instructions.

[0171] Step 6:

[0172] The generated additional information is returned to the terminal and provided to the display or audio output device of the factory robot.

[0173] Input: Generated additional information

[0174] Output: Additional information returned to the terminal

[0175] Specific operation: The server sends the generated instructions to the terminal, which receives them and displays them on the robot's display or outputs them as voice.

[0176] Step 7:

[0177] The user checks the additional information and performs the next process or quality check.

[0178] Input: Additional information provided by the robot's display or audio output device

[0179] Output: User performs work

[0180] Specific Action: The user follows the instructions provided, either visually or audibly, to perform the appropriate steps.

[0181] 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.

[0182] This invention combines a system that acquires and analyzes visual data to generate and provide additional information with an emotion engine that recognizes the user's emotions and optimizes the provision of information. This system includes "means for acquiring visual data," "means for analyzing the visual data and extracting visual information," "artificial intelligence means for generating additional information based on the visual information," and "means for providing additional information to the user," and further includes an "emotion engine that recognizes the user's emotions."

[0183] Device behavior

[0184] The device has a built-in camera that captures objects and scenes within the user's field of view in real time. It acquires the image the user sees through the device and sends it as image data to a server. It also uses an emotion engine to analyze the user's facial expressions and voice and recognize emotions. The recognized emotion data is also sent to the server.

[0185] Server Operation

[0186] The server receives image data and emotion data sent from the device. First, it analyzes the image data and extracts visual information. Next, the generation AI means generates related additional information based on this visual information. The generated additional information is adjusted based on the emotion data. For example, if the user is surprised, it generates additional information that explains the user in a gentle tone.

[0187] Specific examples

[0188] As a concrete example, imagine a scenario in which a user is surprised to see a new animal at the zoo. The user is wearing a glasses-type device, and the device captures an image of the animal. At the same time, the emotion engine recognizes the user's surprised expression. This image data and emotion data are sent from the device to the server. The server first analyzes the image and identifies the animal as a "koala." Next, the generative AI means generates information about the koala and creates a description such as, "Koalas are iconic Australian animals that usually live on eucalyptus trees." At the same time, the emotion engine takes the user's state of surprise into account and adjusts the description text to a gentler tone before sending it to the device. The device displays this information as AR in the user's field of view, allowing the user to instantly learn about koalas.

[0189] User Experience

[0190] By simply wearing the glasses, users can obtain rich information about objects and scenes in their field of view in real time. Furthermore, the device recognizes the user's emotions and adjusts the information accordingly, further personalizing the user's experience. For example, when a scene elicits surprise or interest, the device provides gentler, more detailed explanations, making it easier for the user to absorb the information. This further improves the learning experience and quality of life.

[0191] The above is a specific description of the embodiment for carrying out the present invention, and the invention can be practiced based on this embodiment. The present invention is not limited to this specific example, and various embodiments are intended to be considered.

[0192] The processing flow will be explained below.

[0193] Step 1:

[0194] A user wears the glasses-type device and looks at an object within their field of view. At this time, the camera built into the device captures image data within the user's field of view. The captured image data is temporarily stored within the device.

[0195] Step 2:

[0196] The device's emotion engine analyzes the user's facial expressions and voice in real time to recognize their emotions. For example, a facial expression recognition algorithm can be used to understand the user's state of surprise or interest. The recognized emotion data is also temporarily stored on the device.

[0197] Step 3:

[0198] The device encodes the captured image data and emotion data and prepares them for transmission to the server. Specifically, the image data is converted to JPEG format and the emotion data is converted to text format, compiling them into a transmittable data format. Next, the image data and emotion data are sent to the server endpoint as an HTTP POST request.

[0199] Step 4:

[0200] The server receives the image data and emotion data sent from the device. The server checks the received data and checks the consistency of the image data and emotion data. After checking for missing or damaged data, the server prepares to begin image analysis.

[0201] Step 5:

[0202] The server passes the image data to the image analysis server, which then performs image analysis. The image analysis server uses machine learning models and algorithms to identify objects and features in the image. For example, the names and features of animals and buildings in the image are extracted as visual information.

[0203] Step 6:

[0204] The server receives the visual information obtained from the image analysis server, and converts this visual information into a data format that is prepared for use in the next step and passed to the generation AI means.

[0205] Step 7:

[0206] The server sends visual information to the AI ​​generation means and requests it to generate additional information. Based on the visual information, the AI ​​generation means generates related text information and explanations using natural language processing technology.

[0207] Step 8:

[0208] The generated additional information is returned to the server from the generation AI means. The server combines this additional information with the emotion data and adjusts the additional information based on the user's emotion. For example, if the user is surprised, the tone of the explanation will be softened.

[0209] Step 9:

[0210] The server sends the prepared additional information to the device. The device receives the additional information and notifies the user through a user interface (UI). When using AR technology, the device displays the information superimposed on the user's field of view.

[0211] Step 10:

[0212] Users receive additional information in real time through the glasses, allowing them to instantly gain detailed knowledge about the objects and scenes in their field of view. Additionally, the emotion engine personalizes the information, enabling more effective learning and understanding.

[0213] Example 2

[0214] 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."

[0215] Conventional visual data acquisition and analysis systems simply provide visual information without considering the user's emotional state. This results in a uniform user experience, and the provision of non-personalized information can reduce user satisfaction and comprehension. The objective of this invention is to optimize the user experience and improve user satisfaction and comprehension by recognizing the user's emotions and providing information according to those emotions.

[0216] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0217] In this invention, the server includes means for acquiring visual data, means for analyzing the visual data and extracting visual information, artificial intelligence means for generating additional information based on the visual information, and an emotion engine for recognizing the user's emotions and optimizing the provision of information, thereby enabling the provision of personalized information according to the user's emotions.

[0218] "Visual data" is image information of objects and scenes that are within the user's field of view.

[0219] "Analysis" is the process of extracting useful visual information from visual data.

[0220] "Visual information" refers to information obtained through analysis regarding the identification and characteristics of an object.

[0221] "Artificial intelligence means" are machine learning models or algorithms for generating additional information based on visual information.

[0222] "Additional information" is information such as explanations or commentaries generated based on visual information.

[0223] The "means for providing" is a means for displaying the generated additional information to the user.

[0224] The "emotion engine" is a system that analyzes the user's facial expressions and voice to recognize their emotional state.

[0225] A "generative AI model" is an artificial intelligence model for generating appropriate additional information based on a prompt sentence.

[0226] A "prompt" is a textual instruction that is input to a generative AI model.

[0227] An "image analysis server" is a server that analyzes image data sent from a terminal and extracts visual information.

[0228] This invention combines a system that acquires and analyzes visual data to generate and provide additional information with an emotion engine that recognizes the user's emotions and optimizes the provision of information. This system includes "means for acquiring visual data," "means for analyzing the visual data and extracting visual information," "artificial intelligence means for generating additional information based on the visual information," and "means for providing additional information to the user," and further includes an "emotion engine that recognizes the user's emotions."

[0229] Device behavior

[0230] The device has a built-in camera that captures objects and scenes within the user's field of view in real time. It acquires the image the user sees through the device and sends it as image data to a server. It also uses an emotion engine to analyze the user's facial expressions and voice and recognize emotions. The recognized emotion data is also sent to the server.

[0231] Server Operation

[0232] The server receives image data and emotion data sent from the device. First, it analyzes the image data and extracts visual information. For image analysis, it uses image processing libraries such as TensorFlow and OpenCV. Next, based on this visual information, it generates related additional information using generative AI means (e.g., a generative AI model). The generated additional information is adjusted based on the emotion data. For example, if the user is surprised, it generates additional information that explains the user in a gentle tone. This adjustment is made using a natural language processing (NLP) algorithm.

[0233] Specific examples

[0234] Imagine a scenario in which a user is surprised to see a new animal at the zoo. The user is wearing a glasses-type device, and the device captures an image of the animal. At the same time, the emotion engine recognizes the user's surprised expression. This image data and emotion data are sent from the device to the server. The server first analyzes the image and identifies the animal as a "koala." Next, a generative AI means (generative AI model) generates information about the koala and creates a description such as, "Koalas are iconic Australian animals that usually live in eucalyptus trees." The emotion engine then takes the user's state of surprise into account and adjusts the description text to a gentler tone before sending it to the device. The device displays this information as AR in the user's field of view, allowing the user to instantly learn about koalas.

[0235] Prompt Sentence Examples

[0236] Here are some examples of prompts to input to a generative AI model:

[0237] A user is amazed to see a koala at the zoo. To explain this situation, create a gentle description of the koala.

[0238] User Experience

[0239] By simply wearing the glasses, users can obtain rich information about objects and scenes in their field of view in real time. Furthermore, the device recognizes the user's emotions and adjusts the information accordingly, further personalizing the user's experience. For example, when a scene elicits surprise or interest, the device provides gentler, more detailed explanations, making it easier for the user to absorb the information. This further improves the learning experience and quality of life.

[0240] The above is a specific description of the embodiment for carrying out the present invention, and the invention can be practiced based on this embodiment. The present invention is not limited to this specific example, and various embodiments are intended to be considered.

[0241] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0242] Step 1:

[0243] The device uses a camera to capture objects and scenes within the user's field of view in real time, thereby obtaining visual data (image data). Once this image data has been obtained, the device sends it to a server. The input is an image within the user's field of view, and the output is image data. Specifically, the camera continuously captures images, stores the data in the device's buffer, and transmits it to the server over the network.

[0244] Step 2:

[0245] The device's emotion engine analyzes the user's facial expressions and voice to obtain emotional data. The input is the user's facial and voice data, and the output is emotional data. This emotional data is sent to the server. Specifically, the microphone captures the voice, and the built-in emotion recognition algorithm analyzes it to identify the user's emotional state, and then sends the data to the server.

[0246] Step 3:

[0247] The server receives image data sent from the device and performs image analysis. This is done using image processing libraries such as TensorFlow and OpenCV. The input is image data and the output is visual information. Specific operations include the process in which the image analysis algorithm extracts animal features, identifies them, and generates specific visual information such as "koala."

[0248] Step 4:

[0249] The server generates a prompt sentence based on the visual information. Based on the generated prompt sentence, a generative AI model (e.g., a generative AI model) is used to generate related additional information. The input is visual information, and the output is the prompt sentence and additional information. Specifically, the server generates the following prompt sentence based on the visual information:

[0250] A user is amazed to see a koala at the zoo. To explain this situation, create a gentle description of the koala.

[0251] A generative AI model processes this prompt and generates an explanation.

[0252] Step 5:

[0253] The server adjusts the generated additional information based on the emotional data. The input is the additional information and the emotional data, and the output is the adjusted additional information. Specifically, the NLP algorithm analyzes the emotional data and adjusts the tone and content of the explanation based on the user's emotions.

[0254] Step 6:

[0255] The server sends the adjusted additional information to the terminal. This information is handled in real time. The input is the adjusted additional information, and the output is the data sent to the terminal.

[0256] Step 7:

[0257] The device overlays the received adjusted additional information onto the user's field of view, allowing the user to instantly obtain additional information based on the visual information. The input is the adjusted additional information, and the output is the user's visual display. Specific operations include the process of overlaying information onto the user's field of view using AR technology.

[0258] (Application example 2)

[0259] 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."

[0260] Conventional visual data analysis systems have the problem of not providing optimal information to users because they do not take into account the user's emotions. Also, because information is provided uniformly, it is difficult to provide a personalized experience that reflects the situation and emotions of each individual user. This makes it difficult to increase user satisfaction, especially in environments where real-time information provision is required.

[0261] 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.

[0262] In this invention, the server includes means for acquiring visual data, means for analyzing the visual data to extract visual information, artificial intelligence means for generating additional information based on the visual information, means for acquiring and analyzing emotional data, means for adjusting the additional information based on the emotional data, and means for providing the additional information to the user, thereby enabling personalized information provision that takes the user's emotions into consideration.

[0263] "Visual data" refers to information that can be visually confirmed by a user and is acquired by a camera or imaging device.

[0264] "Visual information" refers to information about objects, scenes, and situations extracted by analyzing the visual data.

[0265] "Artificial intelligence means" refers to algorithms, including machine learning and deep learning, for generating additional information based on visual information.

[0266] "Emotion data" is data that indicates emotions analyzed from the user's facial expressions, voice, etc.

[0267] An "emotion engine" is a system or software that acquires and analyzes emotional data and provides appropriate information based on the results of that analysis.

[0268] "Additional information" is information for the user that is generated based on visual information and further adjusted based on emotional data.

[0269] A "camera" is a photographic device for capturing images within a user's field of view.

[0270] An "image analysis server" is a server that analyzes acquired visual data and extracts visual information.

[0271] The "information providing means" refers to a device or method for displaying the generated additional information to the user.

[0272] MODE FOR CARRYING OUT THE INVENTION

[0273] The system for implementing the present invention acquires and analyzes visual and emotional data to provide additional personalized information to the user. This system mainly consists of the following main components:

[0274] 1. Device behavior:

[0275] Hardware: The device has a built-in camera that captures the user's visual data in real time, as well as a microphone that captures the user's facial expressions and voice.

[0276] Software: The device captures the user's visual data in real time and sends it to the server as image data. It also includes an emotion engine that recognizes the user's emotions. This emotion engine analyzes facial expressions and voice to extract emotional data and send it to the server.

[0277] 2. Server Operation:

[0278] Hardware: Servers are powerful computing devices with the processing power to perform large amounts of data analysis.

[0279] Software: The server receives image data and emotion data sent from the device. First, it uses an image analysis server for image analysis. It analyzes the visual data and extracts visual information through object recognition and scene recognition. Next, based on this visual information, a generative AI means generates related additional information. Furthermore, it uses an emotion engine to adjust the generated additional information based on the user's emotion data.

[0280] As a concrete example, consider a user shopping in a brick-and-mortar store. When the user puts on smart glasses and looks at a product on a shelf, the glasses capture the product in real time. At the same time, an emotion engine recognizes whether the user is interested or confused by the product. This visual and emotion data is sent from the device to a server. The server first performs image analysis to recognize the specific product (e.g., broccoli). Next, generative AI methods generate additional information about the broccoli (e.g., nutritional value, usage, current sales information, etc.). The emotion engine then adjusts the tone and level of detail of the information based on the user's emotions. For example, if the user is surprised, it generates a gentle explanation such as, "Broccoli is rich in vitamin C and helps boost your immune system. It's on sale this week, 10% off!"

[0281] This information is then sent to the device (smart glasses) and displayed as AR within the user's field of view, allowing the user to obtain detailed information about the product in real time.

[0282] Example prompt sentence:

[0283] Image data: Broccoli image

[0284] Emotion data: Surprise (Score = 0.85)

[0285] This system makes it possible to provide personalized services based on user emotions, which was difficult to achieve with conventional information provision systems, thereby increasing user satisfaction and providing a richer shopping experience.

[0286] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0287] Step 1:

[0288] The device uses a camera to acquire visual data of the user. Specifically, when the user looks at a store shelf or a specific product, the device captures the image data in real time. The visual data captured by the camera is treated as input and is sent to the server.

[0289] Step 2:

[0290] The device uses an emotion engine to obtain emotion data from the user's facial expressions and voice. Specifically, it analyzes the user's facial expressions and tone of voice to identify emotions such as surprise, interest, and confusion. The input is the user's facial expressions and voice data, and the output is sent to the server as emotion data.

[0291] Step 3:

[0292] The server receives the visual data sent from the device. It then uses an image analysis server to analyze the visual data and extract visual information. The input is the visual data, and the output is visual information about objects and scenes.

[0293] Step 4:

[0294] The server receives emotion data sent from the device. This data is analyzed by the emotion engine to indicate the user's current emotional state. The input is emotion data, and the output is the analysis result.

[0295] Step 5:

[0296] The server uses generative AI means to generate additional information based on the visual information, specifically, detailed information related to the objects or scenes recognized from the visual information (e.g., product descriptions, nutritional information, special offers, etc.). The input is the visual information, and the output is the generated additional information.

[0297] Step 6:

[0298] The server uses an emotion engine to adjust the additional information based on the emotion data. Specifically, the server changes the tone and level of detail of the information depending on the user's emotion. For example, a gentle tone and detailed explanation is provided to a surprised user. The input is the additional information and emotion data, and the output is the adjusted additional information.

[0299] Step 7:

[0300] The server sends the adjusted additional information to the device, which then displays the additional information on a display (such as smart glasses) within the user's field of view. The input is the adjusted additional information, and the output is the information displayed on the device's display.

[0301] Step 8:

[0302] Users can see additional information displayed within their field of view and get more information about the product in real time, which helps users better understand the product and make better purchasing decisions. The input is the additional information displayed, and the output is increased user purchasing behavior and interest.

[0303] 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.

[0304] 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.

[0305] 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.

[0306] [Second embodiment]

[0307] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0308] 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.

[0309] 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).

[0310] 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.

[0311] 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.

[0312] 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).

[0313] 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.

[0314] 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.

[0315] 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.

[0316] 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.

[0317] 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.

[0318] 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."

[0319] The present invention relates to a system for acquiring and analyzing visual data to generate and provide additional information. This system includes a means for acquiring visual data, a means for analyzing the visual data to extract visual information, an artificial intelligence means for generating additional information based on the visual information, and a means for providing the additional information to a user.

[0320] Device behavior

[0321] The device has a built-in camera that captures objects and scenes within the user's field of view in real time. It captures the image the user sees through the device and sends it to the server as image data. The device then encodes the image data appropriately and sends it to the server's endpoint as an HTTP request.

[0322] Server Operation

[0323] The server receives image data sent from the device. The received image data is first analyzed by the image analysis server to extract visual information about objects and features in the image. The extracted visual information is sent to the generative AI means, which generates additional information. The generative AI means generates text information and explanations based on the visual information. A feedback loop is also implemented to ensure that the generated information is useful to the user.

[0324] Specific examples

[0325] As a specific example, consider a scenario in which a user is looking at a historical building at a tourist spot. The user is wearing a glasses-type device, which captures an image of the building. This image is sent from the device to a server. The server first analyzes the image using an image analysis server to identify the building's features and name. If the analysis results identify the "Eiffel Tower," the AI ​​generation means generates additional information such as "The Eiffel Tower is an iconic French building built in 1889, approximately 324 meters tall." The device displays this information in the user's field of view using AR, allowing the user to instantly learn about the Eiffel Tower.

[0326] User Experience

[0327] By simply wearing the glasses, users can receive rich information about objects and scenes in their field of vision in real time. This will greatly improve the learning experience when traveling, touring tourist spots, visiting museums, etc. It will also improve the quality of life in everyday life by allowing users to instantly obtain information about unfamiliar objects and new places.

[0328] The above is one example of a mode for carrying out the present invention, and the present invention is not limited to this specific example. The present invention includes all possible embodiments.

[0329] The processing flow will be explained below.

[0330] Step 1:

[0331] A user wears the glasses-type device and looks at an object within their field of view. At this time, the camera built into the device captures image data within the user's field of view. The captured image data is temporarily stored within the device.

[0332] Step 2:

[0333] The device encodes the captured image data and prepares it for sending to the server. Specifically, the image data is converted to JPEG format or other format and compiled into a sendable data format. Next, the image data is sent to the server endpoint as an HTTP POST request.

[0334] Step 3:

[0335] The server receives the image data sent from the terminal. The server checks the received data and prepares to start analyzing the image data. First, it checks the integrity of the data and makes sure there are no missing or damaged parts.

[0336] Step 4:

[0337] The server passes the image data to the image analysis server, which then uses machine learning models and algorithms to identify objects and features in the image, extracting visual information (e.g., the names and characteristics of specific buildings and objects).

[0338] Step 5:

[0339] The server receives the visual information obtained from the image analysis server, and converts this visual information into a data format that is prepared for use in the next step and passed to the generation AI means.

[0340] Step 6:

[0341] The server sends the visual information to the AI ​​generator, requesting it to generate additional information. The AI ​​generator then uses natural language processing technology to generate relevant text information and commentary based on the visual information. This process typically takes place within a few seconds.

[0342] Step 7:

[0343] The generated additional information is returned from the generation AI means to the server. The server checks the content of this additional information and prepares it for presentation to the user. Specifically, it converts the text information into an appropriate format and prepares it for transmission to the terminal.

[0344] Step 8:

[0345] The server sends the prepared additional information to the device. The device receives the additional information and notifies the user through a user interface (UI). When using AR technology, the device displays the information superimposed on the user's field of view.

[0346] Step 9:

[0347] Users receive additional information in real time through the glasses, allowing them to instantly gain detailed knowledge about objects and scenes within their field of view, improving the quality of their learning and daily life.

[0348] Example 1

[0349] 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."

[0350] Conventional visual information provision systems have made it difficult for users to obtain useful information from visual data in real time. Furthermore, analyzing visual data and generating additional information requires time and effort, limiting the improvement of user experience. To address this issue, a system that can efficiently analyze visual data and provide practical and immediate additional information is needed.

[0351] 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.

[0352] In this invention, the server includes a means for encoding visual data and transmitting it over a network, a means for analyzing the visual data to extract object features and visual information, and an artificial intelligence means for generating text information and explanations based on the visual information, thereby enabling analysis of the visual data and real-time generation and provision of additional information.

[0353] "Visual data" is image data that captures objects and scenes within a user's field of view using an optical device such as a camera.

[0354] "Encoding" is the process of converting a particular data format into another format, and in this invention refers to converting visual data into a format that can be transmitted over a network.

[0355] A "network" is a communications infrastructure that connects multiple computers and devices and is used in the present invention to send and receive visual data and additional information.

[0356] An "analysis device" is a device that analyzes visual data to identify objects and features in an image and extract visual information.

[0357] "Visual information" refers to the attributes and associated information of objects and features in the visual data, including, for example, the names and characteristics of objects.

[0358] "Artificial intelligence means" means means that use artificial intelligence techniques or algorithms to generate textual information or commentary based on visual information.

[0359] "Additional information" refers to textual information or explanations generated by artificial intelligence means based on the analyzed visual information, and is supplementary information that helps the user further understand the visual data.

[0360] An "optical device" is a device for capturing images, such as a camera.

[0361] "Real-time display" refers to the process of providing information acquired or generated by a terminal to a user immediately and without delay.

[0362] The present invention is a system for acquiring visual data, analyzing it, and generating and providing additional information. This system includes a "means for acquiring visual data," a "means for encoding the visual data and transmitting it over a network," a "means for analyzing the visual data and extracting object features and visual information," an "artificial intelligence means for generating text information and commentary based on the visual information," and a "means for encoding the additional information to a user, transmitting it, and displaying it." A specific embodiment for implementing this system will be described below.

[0363] Device behavior

[0364] The device uses its built-in camera to capture objects and scenes within the user's field of view in real time. For example, if a user wears a glasses-type device and is at a tourist spot, the device will capture images of the surrounding scenery and buildings. The captured visual data is encoded in JPEG or PNG format and sent to a server over the network. The device sends the visual data to the server using an HTTP request.

[0365] Server Operation

[0366] The server receives the visual data sent from the device. After receiving the data, it is first temporarily stored and then sent to the image analysis server. The image analysis server uses a deep learning model (e.g., a convolutional neural network) to perform a detailed analysis of the image data. As a result of the analysis, object features and visual information are extracted.

[0367] The extracted visual information is input into a generative AI model, which generates additional information in real time. This generative AI model receives prompts such as "Please tell me the name and information about this object" based on the visual information, and generates text information and explanations based on that. The generated information is sent to the device as an HTTP response.

[0368] Specific examples

[0369] Consider a scenario in which a user is looking at a historical building at a tourist spot. If the user is wearing a glasses-type device and looking at the Eiffel Tower, the device captures an image of the Eiffel Tower. This image data is sent from the device to a server, which uses an image analysis server to analyze the image and identify the building's features and name. If the analysis results identify the "Eiffel Tower," the generation AI generates information such as "The Eiffel Tower is an iconic French building built in 1889 and is approximately 324 meters tall." This additional information is sent to the device and displayed in AR in the user's field of view.

[0370] User Experience

[0371] By simply wearing the glasses, users can obtain a wealth of information from visual data in real time. This system will significantly improve the learning experience when traveling, touring tourist spots, visiting museums, etc. It will also improve the quality of life in everyday life by allowing users to instantly obtain information about unfamiliar objects and new places.

[0372] Example prompt sentence:

[0373] 1. "What is the name of this object and what are some details about it?"

[0374] 2. "Tell me about the building in front of you."

[0375] The above is one example of the mode for carrying out the present invention, and the present invention is not limited to this specific example and includes all modes.

[0376] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0377] Step 1:

[0378] The device acquires visual data using a built-in camera. The user wears a glasses-type device, which captures objects and scenes in the user's field of view in real time. The input is visual data (images) acquired by the camera, and the output is encoded image data.

[0379] Step 2:

[0380] The visual data acquired by the device is encoded in JPEG or PNG format and sent to the server via the network using an HTTP request. The input is the unencoded visual data stored in the device, and the output is the encoded visual data sent to the server.

[0381] Step 3:

[0382] The server receives the encoded visual data sent from the device. After receiving, the server temporarily stores this data and then sends it to the image analysis server. The input is the visual data received via the network, and the output is the stored image data.

[0383] Step 4:

[0384] The image analysis server analyzes the stored visual data. The image analysis server uses a deep learning model (e.g., a convolutional neural network) to extract object features and visual information from the image data. The input is the stored visual data, and the output is the extracted visual information.

[0385] Step 5:

[0386] The server receives the extracted visual information from the image analysis server and inputs it into a generative AI model. The generative AI model generates text information and explanations from the visual information based on a prompt such as "Please tell me the name and information about this object." The input is the extracted visual information and the prompt, and the output is the generated additional information in text format.

[0387] Step 6:

[0388] The server encodes the additional information created by the generative AI model and sends it to the terminal as an HTTP response. The input is the generated additional information, and the output is the encoded additional information.

[0389] Step 7:

[0390] The device receives the encoded additional information sent from the server. After receiving it, the device decodes this information and displays it in the user's field of view in AR. The input is the additional information received from the server, and the output is the explanation or information displayed in the user's field of view.

[0391] This series of processes allows the user to obtain useful information based on visual data in real time.

[0392] (Application example 1)

[0393] 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."

[0394] While there is a demand for improved quality control of products and parts and work efficiency in factories, conventional systems have difficulty in analyzing visual data in real time and providing immediate feedback, which has prevented them from fully achieving work efficiency and quality. Therefore, there is a need for a system that can efficiently analyze visual data and provide appropriate instructions on the spot.

[0395] 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.

[0396] In this invention, the server includes a means for receiving visual data, a means for analyzing the visual data to extract visual information, and an artificial intelligence means for generating instructions based on the visual information, thereby enabling the factory robot to instantly provide instructions for the next process or quality check based on the analysis results of the visual data acquired in real time.

[0397] "Visual data" refers to digital data of images and videos captured by factory robots and photography devices.

[0398] "Analysis" refers to the process of identifying objects and features from acquired visual data and extracting information based on them.

[0399] "Visual information" refers to information representing objects and features extracted from visual data through analysis.

[0400] "Additional information" refers to instructions or explanations regarding next steps or quality checks generated by the generative AI means based on the visual information.

[0401] "Artificial intelligence means" refers to machine learning models and algorithms that generate additional information based on visual information.

[0402] A "user" is a person or entity that operates a factory robot or uses a visual data analysis system.

[0403] "Server" refers to a central computing device for receiving and analyzing visual data.

[0404] "Display device" means a screen or monitor for visually presenting the additional generated information.

[0405] "Audio output device" refers to a speaker or earphone for providing additional information as audio.

[0406] This invention is a system for acquiring and analyzing visual data to generate and provide additional information. The system includes the following components:

[0407] 1. Hardware and Software Used

[0408] Hardware:

[0409] Camera: A high-resolution camera built into a factory robot, used to capture visual data in real time.

[0410] Display: A display device attached to the robot, used to visually present additional generated information.

[0411] Audio output device: A speaker built into the robot, used to provide additional information as audio.

[0412] software:

[0413] Image analysis: Identifying objects and features from visual data using Python's OpenCV library.

[0414] Generative AI model: OpenAI's GPT-4 is used to generate additional information based on visual information.

[0415] Data transmission and reception: Using the Python Requests library, visual data is sent to the server and analysis results are received.

[0416] 2. System Operation

[0417] Camera visual data acquisition:

[0418] High-resolution cameras built into factory robots capture real-time images of products and parts, which are then encoded into a suitable format on the device and sent to a server.

[0419] Image analysis by server:

[0420] The server receives image data sent from the device. The received image data is first analyzed by an image analysis function (using the OpenCV library) to extract visual information about objects and features. This visual information is then sent to a generative AI model (OpenAI GPT-4) to generate additional information.

[0421] Generate and provide additional information:

[0422] The generative AI model generates instructions for the next process or quality check based on the visual information. These instructions are provided to the factory robot's display and audio output device, and are displayed and communicated to the user visually or audibly.

[0423] 3. Specific Examples

[0424] For example, when a factory robot picks up a part, an image of the part is captured in real time. This image is sent to a server, which performs image analysis to identify the part's characteristics. If the analysis results indicate that the part may be defective, the generative AI model generates instructions based on the following prompt:

[0425] Prompt Sentence Examples

[0426] Part analysis results: Possibly defective. Generate instructions for next steps and quality checks.

[0427] The generated instructions are provided to the user via the robot's display and voice output device, allowing for immediate action to be taken. For example, instructions such as "This part requires a quality check. Please re-inspect it before proceeding to the next process" are displayed.

[0428] In this way, the introduction of this system is expected to significantly improve work efficiency and product quality control within the factory.

[0429] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0430] Step 1:

[0431] A user operates a factory robot and captures images of an object (product or part) using the robot's built-in camera.

[0432] Input: Image of the object

[0433] Output: Captured image data

[0434] How it works: A high-resolution camera captures images of the object in real time.

[0435] Step 2:

[0436] The device encodes the captured image data into an appropriate format (for example, JPEG format) and sends it to the server as an HTTP request.

[0437] Input: Captured image data

[0438] Output: Encoded image data sent to the server

[0439] Specific operation: Image data is converted to JPEG format on the device, an HTTP request is constructed, and sent to the server endpoint.

[0440] Step 3:

[0441] The server receives the image data sent from the terminal and transfers it to the image analysis server for analysis.

[0442] Input: Encoded image data sent from the device

[0443] Output: Image data sent to the image analysis server

[0444] Specific operation: The server's receiving process receives the image data and transfers it to the image analysis server.

[0445] Step 4:

[0446] The image analysis server analyzes the image data and extracts objects and features in the image as visual information.

[0447] Input: Image data transferred to the image analysis server

[0448] Output: Extracted visual information (objects and features)

[0449] What it does: The image analysis server uses the OpenCV library to analyze images and identify objects and features.

[0450] Step 5:

[0451] The server provides the extracted visual information to the generative AI model and inputs prompt sentences to generate additional information.

[0452] Input: Extracted visual information

[0453] Output: Generated additional information (instructions for next steps and quality checks)

[0454] Specific operation: Based on visual information, the server inputs a prompt sentence into OpenAI's GPT-4 API and generates instructions.

[0455] Step 6:

[0456] The generated additional information is returned to the terminal and provided to the display or audio output device of the factory robot.

[0457] Input: Generated additional information

[0458] Output: Additional information returned to the terminal

[0459] Specific operation: The server sends the generated instructions to the terminal, which receives them and displays them on the robot's display or outputs them as voice.

[0460] Step 7:

[0461] The user checks the additional information and performs the next process or quality check.

[0462] Input: Additional information provided by the robot's display or audio output device

[0463] Output: User performs work

[0464] Specific Action: The user follows the instructions provided, either visually or audibly, to perform the appropriate steps.

[0465] 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.

[0466] This invention combines a system that acquires and analyzes visual data to generate and provide additional information with an emotion engine that recognizes the user's emotions and optimizes the provision of information. This system includes "means for acquiring visual data," "means for analyzing the visual data and extracting visual information," "artificial intelligence means for generating additional information based on the visual information," and "means for providing additional information to the user," and further includes an "emotion engine that recognizes the user's emotions."

[0467] Device behavior

[0468] The device has a built-in camera that captures objects and scenes within the user's field of view in real time. It acquires the image the user sees through the device and sends it as image data to a server. It also uses an emotion engine to analyze the user's facial expressions and voice and recognize emotions. The recognized emotion data is also sent to the server.

[0469] Server Operation

[0470] The server receives image data and emotion data sent from the device. First, it analyzes the image data and extracts visual information. Next, the generation AI means generates related additional information based on this visual information. The generated additional information is adjusted based on the emotion data. For example, if the user is surprised, it generates additional information that explains the user in a gentle tone.

[0471] Specific examples

[0472] As a concrete example, imagine a scenario in which a user is surprised to see a new animal at the zoo. The user is wearing a glasses-type device, and the device captures an image of the animal. At the same time, the emotion engine recognizes the user's surprised expression. This image data and emotion data are sent from the device to the server. The server first analyzes the image and identifies the animal as a "koala." Next, the generative AI means generates information about the koala and creates a description such as, "Koalas are iconic Australian animals that usually live on eucalyptus trees." At the same time, the emotion engine takes the user's state of surprise into account and adjusts the description text to a gentler tone before sending it to the device. The device displays this information as AR in the user's field of view, allowing the user to instantly learn about koalas.

[0473] User Experience

[0474] By simply wearing the glasses, users can obtain rich information about objects and scenes in their field of view in real time. Furthermore, the device recognizes the user's emotions and adjusts the information accordingly, further personalizing the user's experience. For example, when a scene elicits surprise or interest, the device provides gentler, more detailed explanations, making it easier for the user to absorb the information. This further improves the learning experience and quality of life.

[0475] The above is a specific description of the embodiment for carrying out the present invention, and the invention can be practiced based on this embodiment. The present invention is not limited to this specific example, and various embodiments are intended to be considered.

[0476] The processing flow will be explained below.

[0477] Step 1:

[0478] A user wears the glasses-type device and looks at an object within their field of view. At this time, the camera built into the device captures image data within the user's field of view. The captured image data is temporarily stored within the device.

[0479] Step 2:

[0480] The device's emotion engine analyzes the user's facial expressions and voice in real time to recognize their emotions. For example, a facial expression recognition algorithm can be used to understand the user's state of surprise or interest. The recognized emotion data is also temporarily stored on the device.

[0481] Step 3:

[0482] The device encodes the captured image data and emotion data and prepares them for transmission to the server. Specifically, the image data is converted to JPEG format and the emotion data is converted to text format, compiling them into a transmittable data format. Next, the image data and emotion data are sent to the server endpoint as an HTTP POST request.

[0483] Step 4:

[0484] The server receives the image data and emotion data sent from the device. The server checks the received data and checks the consistency of the image data and emotion data. After checking for missing or damaged data, the server prepares to begin image analysis.

[0485] Step 5:

[0486] The server passes the image data to the image analysis server, which then performs image analysis. The image analysis server uses machine learning models and algorithms to identify objects and features in the image. For example, the names and features of animals and buildings in the image are extracted as visual information.

[0487] Step 6:

[0488] The server receives the visual information obtained from the image analysis server, and converts this visual information into a data format that is prepared for use in the next step and passed to the generation AI means.

[0489] Step 7:

[0490] The server sends visual information to the AI ​​generation means and requests it to generate additional information. Based on the visual information, the AI ​​generation means generates related text information and explanations using natural language processing technology.

[0491] Step 8:

[0492] The generated additional information is returned to the server from the generation AI means. The server combines this additional information with the emotion data and adjusts the additional information based on the user's emotion. For example, if the user is surprised, the tone of the explanation will be softened.

[0493] Step 9:

[0494] The server sends the prepared additional information to the device. The device receives the additional information and notifies the user through a user interface (UI). When using AR technology, the device displays the information superimposed on the user's field of view.

[0495] Step 10:

[0496] Users receive additional information in real time through the glasses, allowing them to instantly gain detailed knowledge about the objects and scenes in their field of view. Additionally, the emotion engine personalizes the information, enabling more effective learning and understanding.

[0497] Example 2

[0498] 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."

[0499] Conventional visual data acquisition and analysis systems simply provide visual information without considering the user's emotional state. This results in a uniform user experience, and the provision of non-personalized information can reduce user satisfaction and comprehension. The objective of this invention is to optimize the user experience and improve user satisfaction and comprehension by recognizing the user's emotions and providing information according to those emotions.

[0500] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0501] In this invention, the server includes means for acquiring visual data, means for analyzing the visual data and extracting visual information, artificial intelligence means for generating additional information based on the visual information, and an emotion engine for recognizing the user's emotions and optimizing the provision of information, thereby enabling the provision of personalized information according to the user's emotions.

[0502] "Visual data" is image information of objects and scenes that are within the user's field of view.

[0503] "Analysis" is the process of extracting useful visual information from visual data.

[0504] "Visual information" refers to information obtained through analysis regarding the identification and characteristics of an object.

[0505] "Artificial intelligence means" are machine learning models or algorithms for generating additional information based on visual information.

[0506] "Additional information" is information such as explanations or commentaries generated based on visual information.

[0507] The "means for providing" is a means for displaying the generated additional information to the user.

[0508] The "emotion engine" is a system that analyzes the user's facial expressions and voice to recognize their emotional state.

[0509] A "generative AI model" is an artificial intelligence model for generating appropriate additional information based on a prompt sentence.

[0510] A "prompt" is a textual instruction that is input to a generative AI model.

[0511] An "image analysis server" is a server that analyzes image data sent from a terminal and extracts visual information.

[0512] This invention combines a system that acquires and analyzes visual data to generate and provide additional information with an emotion engine that recognizes the user's emotions and optimizes the provision of information. This system includes "means for acquiring visual data," "means for analyzing the visual data and extracting visual information," "artificial intelligence means for generating additional information based on the visual information," and "means for providing additional information to the user," and further includes an "emotion engine that recognizes the user's emotions."

[0513] Device behavior

[0514] The device has a built-in camera that captures objects and scenes within the user's field of view in real time. It acquires the image the user sees through the device and sends it as image data to a server. It also uses an emotion engine to analyze the user's facial expressions and voice and recognize emotions. The recognized emotion data is also sent to the server.

[0515] Server Operation

[0516] The server receives image data and emotion data sent from the device. First, it analyzes the image data and extracts visual information. For image analysis, it uses image processing libraries such as TensorFlow and OpenCV. Next, based on this visual information, it generates related additional information using generative AI means (e.g., a generative AI model). The generated additional information is adjusted based on the emotion data. For example, if the user is surprised, it generates additional information that explains the user in a gentle tone. This adjustment is made using a natural language processing (NLP) algorithm.

[0517] Specific examples

[0518] Imagine a scenario in which a user is surprised to see a new animal at the zoo. The user is wearing a glasses-type device, and the device captures an image of the animal. At the same time, the emotion engine recognizes the user's surprised expression. This image data and emotion data are sent from the device to the server. The server first analyzes the image and identifies the animal as a "koala." Next, a generative AI means (generative AI model) generates information about the koala and creates a description such as, "Koalas are iconic Australian animals that usually live in eucalyptus trees." The emotion engine then takes the user's state of surprise into account and adjusts the description text to a gentler tone before sending it to the device. The device displays this information as AR in the user's field of view, allowing the user to instantly learn about koalas.

[0519] Prompt Sentence Examples

[0520] Here are some examples of prompts to input to a generative AI model:

[0521] A user is amazed to see a koala at the zoo. To explain this situation, create a gentle description of the koala.

[0522] User Experience

[0523] By simply wearing the glasses, users can obtain rich information about objects and scenes in their field of view in real time. Furthermore, the device recognizes the user's emotions and adjusts the information accordingly, further personalizing the user's experience. For example, when a scene elicits surprise or interest, the device provides gentler, more detailed explanations, making it easier for the user to absorb the information. This further improves the learning experience and quality of life.

[0524] The above is a specific description of the embodiment for carrying out the present invention, and the invention can be practiced based on this embodiment. The present invention is not limited to this specific example, and various embodiments are intended to be considered.

[0525] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0526] Step 1:

[0527] The device uses a camera to capture objects and scenes within the user's field of view in real time, thereby obtaining visual data (image data). Once this image data has been obtained, the device sends it to a server. The input is an image within the user's field of view, and the output is image data. Specifically, the camera continuously captures images, stores the data in the device's buffer, and transmits it to the server over the network.

[0528] Step 2:

[0529] The device's emotion engine analyzes the user's facial expressions and voice to obtain emotional data. The input is the user's facial and voice data, and the output is emotional data. This emotional data is sent to the server. Specifically, the microphone captures the voice, and the built-in emotion recognition algorithm analyzes it to identify the user's emotional state, and then sends the data to the server.

[0530] Step 3:

[0531] The server receives image data sent from the device and performs image analysis. This is done using image processing libraries such as TensorFlow and OpenCV. The input is image data and the output is visual information. Specific operations include the process in which the image analysis algorithm extracts animal features, identifies them, and generates specific visual information such as "koala."

[0532] Step 4:

[0533] The server generates a prompt sentence based on the visual information. Based on the generated prompt sentence, a generative AI model (e.g., a generative AI model) is used to generate related additional information. The input is visual information, and the output is the prompt sentence and additional information. Specifically, the server generates the following prompt sentence based on the visual information:

[0534] A user is amazed to see a koala at the zoo. To explain this situation, create a gentle description of the koala.

[0535] A generative AI model processes this prompt and generates an explanation.

[0536] Step 5:

[0537] The server adjusts the generated additional information based on the emotional data. The input is the additional information and the emotional data, and the output is the adjusted additional information. Specifically, the NLP algorithm analyzes the emotional data and adjusts the tone and content of the explanation based on the user's emotions.

[0538] Step 6:

[0539] The server sends the adjusted additional information to the terminal. This information is handled in real time. The input is the adjusted additional information, and the output is the data sent to the terminal.

[0540] Step 7:

[0541] The device overlays the received adjusted additional information onto the user's field of view, allowing the user to instantly obtain additional information based on the visual information. The input is the adjusted additional information, and the output is the user's visual display. Specific operations include the process of overlaying information onto the user's field of view using AR technology.

[0542] (Application example 2)

[0543] 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."

[0544] Conventional visual data analysis systems have the problem of not providing optimal information to users because they do not take into account the user's emotions. Also, because information is provided uniformly, it is difficult to provide a personalized experience that reflects the situation and emotions of each individual user. This makes it difficult to increase user satisfaction, especially in environments where real-time information provision is required.

[0545] 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.

[0546] In this invention, the server includes means for acquiring visual data, means for analyzing the visual data to extract visual information, artificial intelligence means for generating additional information based on the visual information, means for acquiring and analyzing emotional data, means for adjusting the additional information based on the emotional data, and means for providing the additional information to the user, thereby enabling personalized information provision that takes the user's emotions into consideration.

[0547] "Visual data" refers to information that can be visually confirmed by a user and is acquired by a camera or imaging device.

[0548] "Visual information" refers to information about objects, scenes, and situations extracted by analyzing the visual data.

[0549] "Artificial intelligence means" refers to algorithms, including machine learning and deep learning, for generating additional information based on visual information.

[0550] "Emotion data" is data that indicates emotions analyzed from the user's facial expressions, voice, etc.

[0551] An "emotion engine" is a system or software that acquires and analyzes emotional data and provides appropriate information based on the results of that analysis.

[0552] "Additional information" is information for the user that is generated based on visual information and further adjusted based on emotional data.

[0553] A "camera" is a photographic device for capturing images within a user's field of view.

[0554] An "image analysis server" is a server that analyzes acquired visual data and extracts visual information.

[0555] The "information providing means" refers to a device or method for displaying the generated additional information to the user.

[0556] MODE FOR CARRYING OUT THE INVENTION

[0557] The system for implementing the present invention acquires and analyzes visual and emotional data to provide additional personalized information to the user. This system mainly consists of the following main components:

[0558] 1. Device operation:

[0559] Hardware: The device has a built-in camera that captures the user's visual data in real time, as well as a microphone that captures the user's facial expressions and voice.

[0560] Software: The device captures the user's visual data in real time and sends it to the server as image data. It also includes an emotion engine that recognizes the user's emotions. This emotion engine analyzes facial expressions and voice to extract emotional data and send it to the server.

[0561] 2. Server Operation:

[0562] Hardware: Servers are powerful computing devices with the processing power to perform large amounts of data analysis.

[0563] Software: The server receives image data and emotion data sent from the device. First, it uses an image analysis server for image analysis. It analyzes the visual data and extracts visual information through object recognition and scene recognition. Next, based on this visual information, a generative AI means generates related additional information. Furthermore, it uses an emotion engine to adjust the generated additional information based on the user's emotion data.

[0564] As a concrete example, consider a user shopping in a brick-and-mortar store. When the user puts on smart glasses and looks at a product on a shelf, the glasses capture the product in real time. At the same time, an emotion engine recognizes whether the user is interested or confused by the product. This visual and emotion data is sent from the device to a server. The server first performs image analysis to recognize the specific product (e.g., broccoli). Next, generative AI methods generate additional information about the broccoli (e.g., nutritional value, usage, current sales information, etc.). The emotion engine then adjusts the tone and level of detail of the information based on the user's emotions. For example, if the user is surprised, it generates a gentle explanation such as, "Broccoli is rich in vitamin C and helps boost your immune system. It's on sale this week, 10% off!"

[0565] This information is then sent to the device (smart glasses) and displayed as AR within the user's field of view, allowing the user to obtain detailed information about the product in real time.

[0566] Example prompt sentence:

[0567] Image data: Broccoli image

[0568] Emotion data: Surprise (Score = 0.85)

[0569] This system makes it possible to provide personalized services based on user emotions, which was difficult to achieve with conventional information provision systems, thereby increasing user satisfaction and providing a richer shopping experience.

[0570] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0571] Step 1:

[0572] The device uses a camera to acquire visual data of the user. Specifically, when the user looks at a store shelf or a specific product, the device captures the image data in real time. The visual data captured by the camera is treated as input and is sent to the server.

[0573] Step 2:

[0574] The device uses an emotion engine to obtain emotion data from the user's facial expressions and voice. Specifically, it analyzes the user's facial expressions and tone of voice to identify emotions such as surprise, interest, and confusion. The input is the user's facial expressions and voice data, and the output is sent to the server as emotion data.

[0575] Step 3:

[0576] The server receives the visual data sent from the device. It then uses an image analysis server to analyze the visual data and extract visual information. The input is the visual data, and the output is visual information about objects and scenes.

[0577] Step 4:

[0578] The server receives emotion data sent from the device. This data is analyzed by the emotion engine to indicate the user's current emotional state. The input is emotion data, and the output is the analysis result.

[0579] Step 5:

[0580] The server uses generative AI means to generate additional information based on the visual information, specifically, detailed information related to the objects or scenes recognized from the visual information (e.g., product descriptions, nutritional information, special offers, etc.). The input is the visual information, and the output is the generated additional information.

[0581] Step 6:

[0582] The server uses an emotion engine to adjust the additional information based on the emotion data. Specifically, the server changes the tone and level of detail of the information depending on the user's emotion. For example, a gentle tone and detailed explanation is provided to a surprised user. The input is the additional information and emotion data, and the output is the adjusted additional information.

[0583] Step 7:

[0584] The server sends the adjusted additional information to the device, which then displays the additional information on a display (such as smart glasses) within the user's field of view. The input is the adjusted additional information, and the output is the information displayed on the device's display.

[0585] Step 8:

[0586] Users can see additional information displayed within their field of view and get more information about the product in real time, which helps users better understand the product and make better purchasing decisions. The input is the additional information displayed, and the output is increased user purchasing behavior and interest.

[0587] 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.

[0588] 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.

[0589] 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.

[0590] [Third embodiment]

[0591] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0592] 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.

[0593] 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).

[0594] 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.

[0595] 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.

[0596] 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).

[0597] 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.

[0598] 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.

[0599] 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.

[0600] 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.

[0601] 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.

[0602] 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."

[0603] The present invention relates to a system for acquiring and analyzing visual data to generate and provide additional information. This system includes a means for acquiring visual data, a means for analyzing the visual data to extract visual information, an artificial intelligence means for generating additional information based on the visual information, and a means for providing the additional information to a user.

[0604] Device behavior

[0605] The device has a built-in camera that captures objects and scenes within the user's field of view in real time. It captures the image the user sees through the device and sends it to the server as image data. The device then encodes the image data appropriately and sends it to the server's endpoint as an HTTP request.

[0606] Server Operation

[0607] The server receives image data sent from the device. The received image data is first analyzed by the image analysis server to extract visual information about objects and features in the image. The extracted visual information is sent to the generative AI means, which generates additional information. The generative AI means generates text information and explanations based on the visual information. A feedback loop is also implemented to ensure that the generated information is useful to the user.

[0608] Specific examples

[0609] As a specific example, consider a scenario in which a user is looking at a historical building at a tourist spot. The user is wearing a glasses-type device, which captures an image of the building. This image is sent from the device to a server. The server first analyzes the image using an image analysis server to identify the building's features and name. If the analysis results identify the "Eiffel Tower," the AI ​​generation means generates additional information such as "The Eiffel Tower is an iconic French building built in 1889, approximately 324 meters tall." The device displays this information in the user's field of view using AR, allowing the user to instantly learn about the Eiffel Tower.

[0610] User Experience

[0611] By simply wearing the glasses, users can receive rich information about objects and scenes in their field of vision in real time. This will greatly improve the learning experience when traveling, touring tourist spots, visiting museums, etc. It will also improve the quality of life in everyday life by allowing users to instantly obtain information about unfamiliar objects and new places.

[0612] The above is one example of a mode for carrying out the present invention, and the present invention is not limited to this specific example. The present invention includes all possible embodiments.

[0613] The processing flow will be explained below.

[0614] Step 1:

[0615] A user wears the glasses-type device and looks at an object within their field of view. At this time, the camera built into the device captures image data within the user's field of view. The captured image data is temporarily stored within the device.

[0616] Step 2:

[0617] The device encodes the captured image data and prepares it for sending to the server. Specifically, the image data is converted to JPEG format or other format and compiled into a sendable data format. Next, the image data is sent to the server endpoint as an HTTP POST request.

[0618] Step 3:

[0619] The server receives the image data sent from the terminal. The server checks the received data and prepares to start analyzing the image data. First, it checks the integrity of the data and makes sure there are no missing or damaged parts.

[0620] Step 4:

[0621] The server passes the image data to the image analysis server, which then uses machine learning models and algorithms to identify objects and features in the image, extracting visual information (e.g., the names and characteristics of specific buildings and objects).

[0622] Step 5:

[0623] The server receives the visual information obtained from the image analysis server, and converts this visual information into a data format that is prepared for use in the next step and passed to the generation AI means.

[0624] Step 6:

[0625] The server sends the visual information to the AI ​​generator, requesting it to generate additional information. The AI ​​generator then uses natural language processing technology to generate relevant text information and commentary based on the visual information. This process typically takes place within a few seconds.

[0626] Step 7:

[0627] The generated additional information is returned from the generation AI means to the server. The server checks the content of this additional information and prepares it for presentation to the user. Specifically, it converts the text information into an appropriate format and prepares it for transmission to the terminal.

[0628] Step 8:

[0629] The server sends the prepared additional information to the device. The device receives the additional information and notifies the user through a user interface (UI). When using AR technology, the device displays the information superimposed on the user's field of view.

[0630] Step 9:

[0631] Users receive additional information in real time through the glasses, allowing them to instantly gain detailed knowledge about objects and scenes within their field of view, improving the quality of their learning and daily life.

[0632] Example 1

[0633] 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."

[0634] Conventional visual information provision systems have made it difficult for users to obtain useful information from visual data in real time. Furthermore, analyzing visual data and generating additional information requires time and effort, limiting the improvement of user experience. To address this issue, a system that can efficiently analyze visual data and provide practical and immediate additional information is needed.

[0635] 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.

[0636] In this invention, the server includes a means for encoding visual data and transmitting it over a network, a means for analyzing the visual data to extract object features and visual information, and an artificial intelligence means for generating text information and explanations based on the visual information, thereby enabling analysis of the visual data and real-time generation and provision of additional information.

[0637] "Visual data" is image data that captures objects and scenes within a user's field of view using an optical device such as a camera.

[0638] "Encoding" is the process of converting a particular data format into another format, and in this invention refers to converting visual data into a format that can be transmitted over a network.

[0639] A "network" is a communications infrastructure that connects multiple computers and devices and is used in the present invention to send and receive visual data and additional information.

[0640] An "analysis device" is a device that analyzes visual data to identify objects and features in an image and extract visual information.

[0641] "Visual information" refers to the attributes and associated information of objects and features in the visual data, including, for example, the names and characteristics of objects.

[0642] "Artificial intelligence means" means means that use artificial intelligence techniques or algorithms to generate textual information or commentary based on visual information.

[0643] "Additional information" refers to textual information or explanations generated by artificial intelligence means based on the analyzed visual information, and is supplementary information that helps the user further understand the visual data.

[0644] An "optical device" is a device for capturing images, such as a camera.

[0645] "Real-time display" refers to the process of providing information acquired or generated by a terminal to a user immediately and without delay.

[0646] The present invention is a system for acquiring visual data, analyzing it, and generating and providing additional information. This system includes a "means for acquiring visual data," a "means for encoding the visual data and transmitting it over a network," a "means for analyzing the visual data and extracting object features and visual information," an "artificial intelligence means for generating text information and commentary based on the visual information," and a "means for encoding the additional information to a user, transmitting it, and displaying it." A specific embodiment for implementing this system will be described below.

[0647] Device behavior

[0648] The device uses its built-in camera to capture objects and scenes within the user's field of view in real time. For example, if a user wears a glasses-type device and is at a tourist spot, the device will capture images of the surrounding scenery and buildings. The captured visual data is encoded in JPEG or PNG format and sent to a server over the network. The device sends the visual data to the server using an HTTP request.

[0649] Server Operation

[0650] The server receives the visual data sent from the device. After receiving the data, it is first temporarily stored and then sent to the image analysis server. The image analysis server uses a deep learning model (e.g., a convolutional neural network) to perform a detailed analysis of the image data. As a result of the analysis, object features and visual information are extracted.

[0651] The extracted visual information is input into a generative AI model, which generates additional information in real time. This generative AI model receives prompts such as "Please tell me the name and information about this object" based on the visual information, and generates text information and explanations based on that. The generated information is sent to the device as an HTTP response.

[0652] Specific examples

[0653] Consider a scenario in which a user is looking at a historical building at a tourist spot. If the user is wearing a glasses-type device and looking at the Eiffel Tower, the device captures an image of the Eiffel Tower. This image data is sent from the device to a server, which uses an image analysis server to analyze the image and identify the building's features and name. If the analysis results identify the "Eiffel Tower," the generation AI generates information such as "The Eiffel Tower is an iconic French building built in 1889 and is approximately 324 meters tall." This additional information is sent to the device and displayed in AR in the user's field of view.

[0654] User Experience

[0655] By simply wearing the glasses, users can obtain a wealth of information from visual data in real time. This system will significantly improve the learning experience when traveling, touring tourist spots, visiting museums, etc. It will also improve the quality of life in everyday life by allowing users to instantly obtain information about unfamiliar objects and new places.

[0656] Example prompt sentence:

[0657] 1. "What is the name of this object and what are some details about it?"

[0658] 2. "Tell me about the building in front of you."

[0659] The above is one example of the mode for carrying out the present invention, and the present invention is not limited to this specific example and includes all modes.

[0660] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0661] Step 1:

[0662] The device acquires visual data using a built-in camera. The user wears a glasses-type device, which captures objects and scenes in the user's field of view in real time. The input is visual data (images) acquired by the camera, and the output is encoded image data.

[0663] Step 2:

[0664] The visual data acquired by the device is encoded in JPEG or PNG format and sent to the server via the network using an HTTP request. The input is the unencoded visual data stored in the device, and the output is the encoded visual data sent to the server.

[0665] Step 3:

[0666] The server receives the encoded visual data sent from the device. After receiving, the server temporarily stores this data and then sends it to the image analysis server. The input is the visual data received via the network, and the output is the stored image data.

[0667] Step 4:

[0668] The image analysis server analyzes the stored visual data. The image analysis server uses a deep learning model (e.g., a convolutional neural network) to extract object features and visual information from the image data. The input is the stored visual data, and the output is the extracted visual information.

[0669] Step 5:

[0670] The server receives the extracted visual information from the image analysis server and inputs it into a generative AI model. The generative AI model generates text information and explanations from the visual information based on a prompt such as "Please tell me the name and information about this object." The input is the extracted visual information and the prompt, and the output is the generated additional information in text format.

[0671] Step 6:

[0672] The server encodes the additional information created by the generative AI model and sends it to the terminal as an HTTP response. The input is the generated additional information, and the output is the encoded additional information.

[0673] Step 7:

[0674] The device receives the encoded additional information sent from the server. After receiving it, the device decodes this information and displays it in the user's field of view in AR. The input is the additional information received from the server, and the output is the explanation or information displayed in the user's field of view.

[0675] This series of processes allows the user to obtain useful information based on visual data in real time.

[0676] (Application example 1)

[0677] 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."

[0678] While there is a demand for improved quality control of products and parts and work efficiency in factories, conventional systems have difficulty in analyzing visual data in real time and providing immediate feedback, which has prevented them from fully achieving work efficiency and quality. Therefore, there is a need for a system that can efficiently analyze visual data and provide appropriate instructions on the spot.

[0679] 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.

[0680] In this invention, the server includes a means for receiving visual data, a means for analyzing the visual data to extract visual information, and an artificial intelligence means for generating instructions based on the visual information, thereby enabling the factory robot to instantly provide instructions for the next process or quality check based on the analysis results of the visual data acquired in real time.

[0681] "Visual data" refers to digital data of images and videos captured by factory robots and photography devices.

[0682] "Analysis" refers to the process of identifying objects and features from acquired visual data and extracting information based on them.

[0683] "Visual information" refers to information representing objects and features extracted from visual data through analysis.

[0684] "Additional information" refers to instructions or explanations regarding next steps or quality checks generated by the generative AI means based on the visual information.

[0685] "Artificial intelligence means" refers to machine learning models and algorithms that generate additional information based on visual information.

[0686] A "user" is a person or entity that operates a factory robot or uses a visual data analysis system.

[0687] "Server" refers to a central computing device for receiving and analyzing visual data.

[0688] "Display device" means a screen or monitor for visually presenting the additional generated information.

[0689] "Audio output device" refers to a speaker or earphone for providing additional information as audio.

[0690] This invention is a system for acquiring and analyzing visual data to generate and provide additional information. The system includes the following components:

[0691] 1. Hardware and Software Used

[0692] Hardware:

[0693] Camera: A high-resolution camera built into a factory robot, used to capture visual data in real time.

[0694] Display: A display device attached to the robot, used to visually present additional generated information.

[0695] Audio output device: A speaker built into the robot, used to provide additional information as audio.

[0696] software:

[0697] Image analysis: Identifying objects and features from visual data using Python's OpenCV library.

[0698] Generative AI model: OpenAI's GPT-4 is used to generate additional information based on visual information.

[0699] Data transmission and reception: Using the Python Requests library, visual data is sent to the server and analysis results are received.

[0700] 2. System Operation

[0701] Camera visual data acquisition:

[0702] High-resolution cameras built into factory robots capture real-time images of products and parts, which are then encoded into a suitable format on the device and sent to a server.

[0703] Image analysis by server:

[0704] The server receives image data sent from the device. The received image data is first analyzed by an image analysis function (using the OpenCV library) to extract visual information about objects and features. This visual information is then sent to a generative AI model (OpenAI GPT-4) to generate additional information.

[0705] Generate and provide additional information:

[0706] The generative AI model generates instructions for the next process or quality check based on the visual information. These instructions are provided to the factory robot's display and audio output device, and are displayed and communicated to the user visually or audibly.

[0707] 3. Specific Examples

[0708] For example, when a factory robot picks up a part, an image of the part is captured in real time. This image is sent to a server, which performs image analysis to identify the part's characteristics. If the analysis results indicate that the part may be defective, the generative AI model generates instructions based on the following prompt:

[0709] Prompt Sentence Examples

[0710] Part analysis results: Possibly defective. Generate instructions for next steps and quality checks.

[0711] The generated instructions are provided to the user via the robot's display and voice output device, allowing for immediate action to be taken. For example, instructions such as "This part requires a quality check. Please re-inspect it before proceeding to the next process" are displayed.

[0712] In this way, the introduction of this system is expected to significantly improve work efficiency and product quality control within the factory.

[0713] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0714] Step 1:

[0715] A user operates a factory robot and captures images of an object (product or part) using the robot's built-in camera.

[0716] Input: Image of the object

[0717] Output: Captured image data

[0718] How it works: A high-resolution camera captures images of the object in real time.

[0719] Step 2:

[0720] The device encodes the captured image data into an appropriate format (for example, JPEG format) and sends it to the server as an HTTP request.

[0721] Input: Captured image data

[0722] Output: Encoded image data sent to the server

[0723] Specific operation: Image data is converted to JPEG format on the device, an HTTP request is constructed, and sent to the server endpoint.

[0724] Step 3:

[0725] The server receives the image data sent from the terminal and transfers it to the image analysis server for analysis.

[0726] Input: Encoded image data sent from the device

[0727] Output: Image data sent to the image analysis server

[0728] Specific operation: The server's receiving process receives the image data and transfers it to the image analysis server.

[0729] Step 4:

[0730] The image analysis server analyzes the image data and extracts objects and features in the image as visual information.

[0731] Input: Image data transferred to the image analysis server

[0732] Output: Extracted visual information (objects and features)

[0733] What it does: The image analysis server uses the OpenCV library to analyze images and identify objects and features.

[0734] Step 5:

[0735] The server provides the extracted visual information to the generative AI model and inputs prompt sentences to generate additional information.

[0736] Input: Extracted visual information

[0737] Output: Generated additional information (instructions for next steps and quality checks)

[0738] Specific operation: Based on visual information, the server inputs a prompt sentence into OpenAI's GPT-4 API and generates instructions.

[0739] Step 6:

[0740] The generated additional information is returned to the terminal and provided to the display or audio output device of the factory robot.

[0741] Input: Generated additional information

[0742] Output: Additional information returned to the terminal

[0743] Specific operation: The server sends the generated instructions to the terminal, which receives them and displays them on the robot's display or outputs them as voice.

[0744] Step 7:

[0745] The user checks the additional information and performs the next process or quality check.

[0746] Input: Additional information provided by the robot's display or audio output device

[0747] Output: User performs work

[0748] Specific Action: The user follows the instructions provided, either visually or audibly, to perform the appropriate steps.

[0749] 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.

[0750] This invention combines a system that acquires and analyzes visual data to generate and provide additional information with an emotion engine that recognizes the user's emotions and optimizes the provision of information. This system includes "means for acquiring visual data," "means for analyzing the visual data and extracting visual information," "artificial intelligence means for generating additional information based on the visual information," and "means for providing additional information to the user," and further includes an "emotion engine that recognizes the user's emotions."

[0751] Device behavior

[0752] The device has a built-in camera that captures objects and scenes within the user's field of view in real time. It acquires the image the user sees through the device and sends it as image data to a server. It also uses an emotion engine to analyze the user's facial expressions and voice and recognize emotions. The recognized emotion data is also sent to the server.

[0753] Server Operation

[0754] The server receives image data and emotion data sent from the device. First, it analyzes the image data and extracts visual information. Next, the generation AI means generates related additional information based on this visual information. The generated additional information is adjusted based on the emotion data. For example, if the user is surprised, it generates additional information that explains the user in a gentle tone.

[0755] Specific examples

[0756] As a concrete example, imagine a scenario in which a user is surprised to see a new animal at the zoo. The user is wearing a glasses-type device, and the device captures an image of the animal. At the same time, the emotion engine recognizes the user's surprised expression. This image data and emotion data are sent from the device to the server. The server first analyzes the image and identifies the animal as a "koala." Next, the generative AI means generates information about the koala and creates a description such as, "Koalas are iconic Australian animals that usually live on eucalyptus trees." At the same time, the emotion engine takes the user's state of surprise into account and adjusts the description text to a gentler tone before sending it to the device. The device displays this information as AR in the user's field of view, allowing the user to instantly learn about koalas.

[0757] User Experience

[0758] By simply wearing the glasses, users can obtain rich information about objects and scenes in their field of view in real time. Furthermore, the device recognizes the user's emotions and adjusts the information accordingly, further personalizing the user's experience. For example, when a scene elicits surprise or interest, the device provides gentler, more detailed explanations, making it easier for the user to absorb the information. This further improves the learning experience and quality of life.

[0759] The above is a specific description of the embodiment for carrying out the present invention, and the invention can be practiced based on this embodiment. The present invention is not limited to this specific example, and various embodiments are intended to be considered.

[0760] The processing flow will be explained below.

[0761] Step 1:

[0762] A user wears the glasses-type device and looks at an object within their field of view. At this time, the camera built into the device captures image data within the user's field of view. The captured image data is temporarily stored within the device.

[0763] Step 2:

[0764] The device's emotion engine analyzes the user's facial expressions and voice in real time to recognize their emotions. For example, a facial expression recognition algorithm can be used to understand the user's state of surprise or interest. The recognized emotion data is also temporarily stored on the device.

[0765] Step 3:

[0766] The device encodes the captured image data and emotion data and prepares them for transmission to the server. Specifically, the image data is converted to JPEG format and the emotion data is converted to text format, compiling them into a transmittable data format. Next, the image data and emotion data are sent to the server endpoint as an HTTP POST request.

[0767] Step 4:

[0768] The server receives the image data and emotion data sent from the device. The server checks the received data and checks the consistency of the image data and emotion data. After checking for missing or damaged data, the server prepares to begin image analysis.

[0769] Step 5:

[0770] The server passes the image data to the image analysis server, which then performs image analysis. The image analysis server uses machine learning models and algorithms to identify objects and features in the image. For example, the names and features of animals and buildings in the image are extracted as visual information.

[0771] Step 6:

[0772] The server receives the visual information obtained from the image analysis server, and converts this visual information into a data format that is prepared for use in the next step and passed to the generation AI means.

[0773] Step 7:

[0774] The server sends visual information to the AI ​​generation means and requests it to generate additional information. Based on the visual information, the AI ​​generation means generates related text information and explanations using natural language processing technology.

[0775] Step 8:

[0776] The generated additional information is returned to the server from the generation AI means. The server combines this additional information with the emotion data and adjusts the additional information based on the user's emotion. For example, if the user is surprised, the tone of the explanation will be softened.

[0777] Step 9:

[0778] The server sends the prepared additional information to the device. The device receives the additional information and notifies the user through a user interface (UI). When using AR technology, the device displays the information superimposed on the user's field of view.

[0779] Step 10:

[0780] Users receive additional information in real time through the glasses, allowing them to instantly gain detailed knowledge about the objects and scenes in their field of view. Additionally, the emotion engine personalizes the information, enabling more effective learning and understanding.

[0781] Example 2

[0782] 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."

[0783] Conventional visual data acquisition and analysis systems simply provide visual information without considering the user's emotional state. This results in a uniform user experience, and the provision of non-personalized information can reduce user satisfaction and comprehension. The objective of this invention is to optimize the user experience and improve user satisfaction and comprehension by recognizing the user's emotions and providing information according to those emotions.

[0784] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0785] In this invention, the server includes means for acquiring visual data, means for analyzing the visual data and extracting visual information, artificial intelligence means for generating additional information based on the visual information, and an emotion engine for recognizing the user's emotions and optimizing the provision of information, thereby enabling the provision of personalized information according to the user's emotions.

[0786] "Visual data" is image information of objects and scenes that are within the user's field of view.

[0787] "Analysis" is the process of extracting useful visual information from visual data.

[0788] "Visual information" refers to information obtained through analysis regarding the identification and characteristics of an object.

[0789] "Artificial intelligence means" are machine learning models or algorithms for generating additional information based on visual information.

[0790] "Additional information" is information such as explanations or commentaries generated based on visual information.

[0791] The "means for providing" is a means for displaying the generated additional information to the user.

[0792] The "emotion engine" is a system that analyzes the user's facial expressions and voice to recognize their emotional state.

[0793] A "generative AI model" is an artificial intelligence model for generating appropriate additional information based on a prompt sentence.

[0794] A "prompt" is a textual instruction that is input to a generative AI model.

[0795] An "image analysis server" is a server that analyzes image data sent from a terminal and extracts visual information.

[0796] This invention combines a system that acquires and analyzes visual data to generate and provide additional information with an emotion engine that recognizes the user's emotions and optimizes the provision of information. This system includes "means for acquiring visual data," "means for analyzing the visual data and extracting visual information," "artificial intelligence means for generating additional information based on the visual information," and "means for providing additional information to the user," and further includes an "emotion engine that recognizes the user's emotions."

[0797] Device behavior

[0798] The device has a built-in camera that captures objects and scenes within the user's field of view in real time. It acquires the image the user sees through the device and sends it as image data to a server. It also uses an emotion engine to analyze the user's facial expressions and voice and recognize emotions. The recognized emotion data is also sent to the server.

[0799] Server Operation

[0800] The server receives image data and emotion data sent from the device. First, it analyzes the image data and extracts visual information. For image analysis, it uses image processing libraries such as TensorFlow and OpenCV. Next, based on this visual information, it generates related additional information using generative AI means (e.g., a generative AI model). The generated additional information is adjusted based on the emotion data. For example, if the user is surprised, it generates additional information that explains the user in a gentle tone. This adjustment is made using a natural language processing (NLP) algorithm.

[0801] Specific examples

[0802] Imagine a scenario in which a user is surprised to see a new animal at the zoo. The user is wearing a glasses-type device, and the device captures an image of the animal. At the same time, the emotion engine recognizes the user's surprised expression. This image data and emotion data are sent from the device to the server. The server first analyzes the image and identifies the animal as a "koala." Next, a generative AI means (generative AI model) generates information about the koala and creates a description such as, "Koalas are iconic Australian animals that usually live in eucalyptus trees." The emotion engine then takes the user's state of surprise into account and adjusts the description text to a gentler tone before sending it to the device. The device displays this information as AR in the user's field of view, allowing the user to instantly learn about koalas.

[0803] Prompt Sentence Examples

[0804] Here are some examples of prompts to input to a generative AI model:

[0805] A user is amazed to see a koala at the zoo. To explain this situation, create a gentle description of the koala.

[0806] User Experience

[0807] By simply wearing the glasses, users can obtain rich information about objects and scenes in their field of view in real time. Furthermore, the device recognizes the user's emotions and adjusts the information accordingly, further personalizing the user's experience. For example, when a scene elicits surprise or interest, the device provides gentler, more detailed explanations, making it easier for the user to absorb the information. This further improves the learning experience and quality of life.

[0808] The above is a specific description of the embodiment for carrying out the present invention, and the invention can be practiced based on this embodiment. The present invention is not limited to this specific example, and various embodiments are intended to be considered.

[0809] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0810] Step 1:

[0811] The device uses a camera to capture objects and scenes within the user's field of view in real time, thereby obtaining visual data (image data). Once this image data has been obtained, the device sends it to a server. The input is an image within the user's field of view, and the output is image data. Specifically, the camera continuously captures images, stores the data in the device's buffer, and transmits it to the server over the network.

[0812] Step 2:

[0813] The device's emotion engine analyzes the user's facial expressions and voice to obtain emotional data. The input is the user's facial and voice data, and the output is emotional data. This emotional data is sent to the server. Specifically, the microphone captures the voice, and the built-in emotion recognition algorithm analyzes it to identify the user's emotional state, and then sends the data to the server.

[0814] Step 3:

[0815] The server receives image data sent from the device and performs image analysis. This is done using image processing libraries such as TensorFlow and OpenCV. The input is image data and the output is visual information. Specific operations include the process in which the image analysis algorithm extracts animal features, identifies them, and generates specific visual information such as "koala."

[0816] Step 4:

[0817] The server generates a prompt sentence based on the visual information. Based on the generated prompt sentence, a generative AI model (e.g., a generative AI model) is used to generate related additional information. The input is visual information, and the output is the prompt sentence and additional information. Specifically, the server generates the following prompt sentence based on the visual information:

[0818] A user is amazed to see a koala at the zoo. To explain this situation, create a gentle description of the koala.

[0819] A generative AI model processes this prompt and generates an explanation.

[0820] Step 5:

[0821] The server adjusts the generated additional information based on the emotional data. The input is the additional information and the emotional data, and the output is the adjusted additional information. Specifically, the NLP algorithm analyzes the emotional data and adjusts the tone and content of the explanation based on the user's emotions.

[0822] Step 6:

[0823] The server sends the adjusted additional information to the terminal. This information is handled in real time. The input is the adjusted additional information, and the output is the data sent to the terminal.

[0824] Step 7:

[0825] The device overlays the received adjusted additional information onto the user's field of view, allowing the user to instantly obtain additional information based on the visual information. The input is the adjusted additional information, and the output is the user's visual display. Specific operations include the process of overlaying information onto the user's field of view using AR technology.

[0826] (Application example 2)

[0827] 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."

[0828] Conventional visual data analysis systems have the problem of not providing optimal information to users because they do not take into account the user's emotions. Also, because information is provided uniformly, it is difficult to provide a personalized experience that reflects the situation and emotions of each individual user. This makes it difficult to increase user satisfaction, especially in environments where real-time information provision is required.

[0829] 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.

[0830] In this invention, the server includes means for acquiring visual data, means for analyzing the visual data to extract visual information, artificial intelligence means for generating additional information based on the visual information, means for acquiring and analyzing emotional data, means for adjusting the additional information based on the emotional data, and means for providing the additional information to the user, thereby enabling personalized information provision that takes the user's emotions into consideration.

[0831] "Visual data" refers to information that can be visually confirmed by a user and is acquired by a camera or imaging device.

[0832] "Visual information" refers to information about objects, scenes, and situations extracted by analyzing the visual data.

[0833] "Artificial intelligence means" refers to algorithms, including machine learning and deep learning, for generating additional information based on visual information.

[0834] "Emotion data" is data that indicates emotions analyzed from the user's facial expressions, voice, etc.

[0835] An "emotion engine" is a system or software that acquires and analyzes emotional data and provides appropriate information based on the results of that analysis.

[0836] "Additional information" is information for the user that is generated based on visual information and further adjusted based on emotional data.

[0837] A "camera" is a photographic device for capturing images within a user's field of view.

[0838] An "image analysis server" is a server that analyzes acquired visual data and extracts visual information.

[0839] The "information providing means" refers to a device or method for displaying the generated additional information to the user.

[0840] MODE FOR CARRYING OUT THE INVENTION

[0841] The system for implementing the present invention acquires and analyzes visual and emotional data to provide additional personalized information to the user. This system mainly consists of the following main components:

[0842] 1. Device operation:

[0843] Hardware: The device has a built-in camera that captures the user's visual data in real time, as well as a microphone that captures the user's facial expressions and voice.

[0844] Software: The device captures the user's visual data in real time and sends it to the server as image data. It also includes an emotion engine that recognizes the user's emotions. This emotion engine analyzes facial expressions and voice to extract emotional data and send it to the server.

[0845] 2. Server Operation:

[0846] Hardware: Servers are powerful computing devices with the processing power to perform large amounts of data analysis.

[0847] Software: The server receives image data and emotion data sent from the device. First, it uses an image analysis server for image analysis. It analyzes the visual data and extracts visual information through object recognition and scene recognition. Next, based on this visual information, a generative AI means generates related additional information. Furthermore, it uses an emotion engine to adjust the generated additional information based on the user's emotion data.

[0848] As a concrete example, consider a user shopping in a brick-and-mortar store. When the user puts on smart glasses and looks at a product on a shelf, the glasses capture the product in real time. At the same time, an emotion engine recognizes whether the user is interested or confused by the product. This visual and emotion data is sent from the device to a server. The server first performs image analysis to recognize the specific product (e.g., broccoli). Next, generative AI methods generate additional information about the broccoli (e.g., nutritional value, usage, current sales information, etc.). The emotion engine then adjusts the tone and level of detail of the information based on the user's emotions. For example, if the user is surprised, it generates a gentle explanation such as, "Broccoli is rich in vitamin C and helps boost your immune system. It's on sale this week, 10% off!"

[0849] This information is then sent to the device (smart glasses) and displayed as AR within the user's field of view, allowing the user to obtain detailed information about the product in real time.

[0850] Example prompt sentence:

[0851] Image data: Broccoli image

[0852] Emotion data: Surprise (Score = 0.85)

[0853] This system makes it possible to provide personalized services based on user emotions, which was difficult to achieve with conventional information provision systems, thereby increasing user satisfaction and providing a richer shopping experience.

[0854] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0855] Step 1:

[0856] The device uses a camera to acquire visual data of the user. Specifically, when the user looks at a store shelf or a specific product, the device captures the image data in real time. The visual data captured by the camera is treated as input and is sent to the server.

[0857] Step 2:

[0858] The device uses an emotion engine to obtain emotion data from the user's facial expressions and voice. Specifically, it analyzes the user's facial expressions and tone of voice to identify emotions such as surprise, interest, and confusion. The input is the user's facial expressions and voice data, and the output is sent to the server as emotion data.

[0859] Step 3:

[0860] The server receives the visual data sent from the device. It then uses an image analysis server to analyze the visual data and extract visual information. The input is the visual data, and the output is visual information about objects and scenes.

[0861] Step 4:

[0862] The server receives emotion data sent from the device. This data is analyzed by the emotion engine to indicate the user's current emotional state. The input is emotion data, and the output is the analysis result.

[0863] Step 5:

[0864] The server uses generative AI means to generate additional information based on the visual information, specifically, detailed information related to the objects or scenes recognized from the visual information (e.g., product descriptions, nutritional information, special offers, etc.). The input is the visual information, and the output is the generated additional information.

[0865] Step 6:

[0866] The server uses an emotion engine to adjust the additional information based on the emotion data. Specifically, the server changes the tone and level of detail of the information depending on the user's emotion. For example, a gentle tone and detailed explanation is provided to a surprised user. The input is the additional information and emotion data, and the output is the adjusted additional information.

[0867] Step 7:

[0868] The server sends the adjusted additional information to the device, which then displays the additional information on a display (such as smart glasses) within the user's field of view. The input is the adjusted additional information, and the output is the information displayed on the device's display.

[0869] Step 8:

[0870] Users can see additional information displayed within their field of view and get more information about the product in real time, which helps users better understand the product and make better purchasing decisions. The input is the additional information displayed, and the output is increased user purchasing behavior and interest.

[0871] 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.

[0872] 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.

[0873] 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.

[0874] [Fourth embodiment]

[0875] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0876] 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.

[0877] 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).

[0878] 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.

[0879] 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.

[0880] 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).

[0881] 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.

[0882] 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.

[0883] 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.

[0884] 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.

[0885] 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.

[0886] 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.

[0887] 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."

[0888] The present invention relates to a system for acquiring and analyzing visual data to generate and provide additional information. This system includes a means for acquiring visual data, a means for analyzing the visual data to extract visual information, an artificial intelligence means for generating additional information based on the visual information, and a means for providing the additional information to a user.

[0889] Device behavior

[0890] The device has a built-in camera that captures objects and scenes within the user's field of view in real time. It captures the image the user sees through the device and sends it to the server as image data. The device then encodes the image data appropriately and sends it to the server's endpoint as an HTTP request.

[0891] Server Operation

[0892] The server receives image data sent from the device. The received image data is first analyzed by the image analysis server to extract visual information about objects and features in the image. The extracted visual information is sent to the generative AI means, which generates additional information. The generative AI means generates text information and explanations based on the visual information. A feedback loop is also implemented to ensure that the generated information is useful to the user.

[0893] Specific examples

[0894] As a specific example, consider a scenario in which a user is looking at a historical building at a tourist spot. The user is wearing a glasses-type device, which captures an image of the building. This image is sent from the device to a server. The server first analyzes the image using an image analysis server to identify the building's features and name. If the analysis results identify the "Eiffel Tower," the AI ​​generation means generates additional information such as "The Eiffel Tower is an iconic French building built in 1889, approximately 324 meters tall." The device displays this information in the user's field of view using AR, allowing the user to instantly learn about the Eiffel Tower.

[0895] User Experience

[0896] By simply wearing the glasses, users can receive rich information about objects and scenes in their field of vision in real time. This will greatly improve the learning experience when traveling, touring tourist spots, visiting museums, etc. It will also improve the quality of life in everyday life by allowing users to instantly obtain information about unfamiliar objects and new places.

[0897] The above is one example of a mode for carrying out the present invention, and the present invention is not limited to this specific example. The present invention includes all possible embodiments.

[0898] The processing flow will be explained below.

[0899] Step 1:

[0900] A user wears the glasses-type device and looks at an object within their field of view. At this time, the camera built into the device captures image data within the user's field of view. The captured image data is temporarily stored within the device.

[0901] Step 2:

[0902] The device encodes the captured image data and prepares it for sending to the server. Specifically, the image data is converted to JPEG format or other format and compiled into a sendable data format. Next, the image data is sent to the server endpoint as an HTTP POST request.

[0903] Step 3:

[0904] The server receives the image data sent from the terminal. The server checks the received data and prepares to start analyzing the image data. First, it checks the integrity of the data and makes sure there are no missing or damaged parts.

[0905] Step 4:

[0906] The server passes the image data to the image analysis server, which then uses machine learning models and algorithms to identify objects and features in the image, extracting visual information (e.g., the names and characteristics of specific buildings and objects).

[0907] Step 5:

[0908] The server receives the visual information obtained from the image analysis server, and converts this visual information into a data format that is prepared for use in the next step and passed to the generation AI means.

[0909] Step 6:

[0910] The server sends the visual information to the AI ​​generator, requesting it to generate additional information. The AI ​​generator then uses natural language processing technology to generate relevant text information and commentary based on the visual information. This process typically takes place within a few seconds.

[0911] Step 7:

[0912] The generated additional information is returned from the generation AI means to the server. The server checks the content of this additional information and prepares it for presentation to the user. Specifically, it converts the text information into an appropriate format and prepares it for transmission to the terminal.

[0913] Step 8:

[0914] The server sends the prepared additional information to the device. The device receives the additional information and notifies the user through a user interface (UI). When using AR technology, the device displays the information superimposed on the user's field of view.

[0915] Step 9:

[0916] Users receive additional information in real time through the glasses, allowing them to instantly gain detailed knowledge about objects and scenes within their field of view, improving the quality of their learning and daily life.

[0917] Example 1

[0918] 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."

[0919] Conventional visual information provision systems have made it difficult for users to obtain useful information from visual data in real time. Furthermore, analyzing visual data and generating additional information requires time and effort, limiting the improvement of user experience. To address this issue, a system that can efficiently analyze visual data and provide practical and immediate additional information is needed.

[0920] 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.

[0921] In this invention, the server includes a means for encoding visual data and transmitting it over a network, a means for analyzing the visual data to extract object features and visual information, and an artificial intelligence means for generating text information and explanations based on the visual information, thereby enabling analysis of the visual data and real-time generation and provision of additional information.

[0922] "Visual data" is image data that captures objects and scenes within a user's field of view using an optical device such as a camera.

[0923] "Encoding" is the process of converting a particular data format into another format, and in this invention refers to converting visual data into a format that can be transmitted over a network.

[0924] A "network" is a communications infrastructure that connects multiple computers and devices and is used in the present invention to send and receive visual data and additional information.

[0925] An "analysis device" is a device that analyzes visual data to identify objects and features in an image and extract visual information.

[0926] "Visual information" refers to the attributes and associated information of objects and features in the visual data, including, for example, the names and characteristics of objects.

[0927] "Artificial intelligence means" means means that use artificial intelligence techniques or algorithms to generate textual information or commentary based on visual information.

[0928] "Additional information" refers to textual information or explanations generated by artificial intelligence means based on the analyzed visual information, and is supplementary information that helps the user further understand the visual data.

[0929] An "optical device" is a device for capturing images, such as a camera.

[0930] "Real-time display" refers to the process of providing information acquired or generated by a terminal to a user immediately and without delay.

[0931] The present invention is a system for acquiring visual data, analyzing it, and generating and providing additional information. This system includes a "means for acquiring visual data," a "means for encoding the visual data and transmitting it over a network," a "means for analyzing the visual data and extracting object features and visual information," an "artificial intelligence means for generating text information and commentary based on the visual information," and a "means for encoding the additional information to a user, transmitting it, and displaying it." A specific embodiment for implementing this system will be described below.

[0932] Device behavior

[0933] The device uses its built-in camera to capture objects and scenes within the user's field of view in real time. For example, if a user wears a glasses-type device and is at a tourist spot, the device will capture images of the surrounding scenery and buildings. The captured visual data is encoded in JPEG or PNG format and sent to a server over the network. The device sends the visual data to the server using an HTTP request.

[0934] Server Operation

[0935] The server receives the visual data sent from the device. After receiving the data, it is first temporarily stored and then sent to the image analysis server. The image analysis server uses a deep learning model (e.g., a convolutional neural network) to perform a detailed analysis of the image data. As a result of the analysis, object features and visual information are extracted.

[0936] The extracted visual information is input into a generative AI model, which generates additional information in real time. This generative AI model receives prompts such as "Please tell me the name and information about this object" based on the visual information, and generates text information and explanations based on that. The generated information is sent to the device as an HTTP response.

[0937] Specific examples

[0938] Consider a scenario in which a user is looking at a historical building at a tourist spot. If the user is wearing a glasses-type device and looking at the Eiffel Tower, the device captures an image of the Eiffel Tower. This image data is sent from the device to a server, which uses an image analysis server to analyze the image and identify the building's features and name. If the analysis results identify the "Eiffel Tower," the generation AI generates information such as "The Eiffel Tower is an iconic French building built in 1889 and is approximately 324 meters tall." This additional information is sent to the device and displayed in AR in the user's field of view.

[0939] User Experience

[0940] By simply wearing the glasses, users can obtain a wealth of information from visual data in real time. This system will significantly improve the learning experience when traveling, touring tourist spots, visiting museums, etc. It will also improve the quality of life in everyday life by allowing users to instantly obtain information about unfamiliar objects and new places.

[0941] Example prompt sentence:

[0942] 1. "What is the name of this object and what are some details about it?"

[0943] 2. "Tell me about the building in front of you."

[0944] The above is one example of the mode for carrying out the present invention, and the present invention is not limited to this specific example and includes all modes.

[0945] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0946] Step 1:

[0947] The device acquires visual data using a built-in camera. The user wears a glasses-type device, which captures objects and scenes in the user's field of view in real time. The input is visual data (images) acquired by the camera, and the output is encoded image data.

[0948] Step 2:

[0949] The visual data acquired by the device is encoded in JPEG or PNG format and sent to the server via the network using an HTTP request. The input is the unencoded visual data stored in the device, and the output is the encoded visual data sent to the server.

[0950] Step 3:

[0951] The server receives the encoded visual data sent from the device. After receiving, the server temporarily stores this data and then sends it to the image analysis server. The input is the visual data received via the network, and the output is the stored image data.

[0952] Step 4:

[0953] The image analysis server analyzes the stored visual data. The image analysis server uses a deep learning model (e.g., a convolutional neural network) to extract object features and visual information from the image data. The input is the stored visual data, and the output is the extracted visual information.

[0954] Step 5:

[0955] The server receives the extracted visual information from the image analysis server and inputs it into a generative AI model. The generative AI model generates text information and explanations from the visual information based on a prompt such as "Please tell me the name and information about this object." The input is the extracted visual information and the prompt, and the output is the generated additional information in text format.

[0956] Step 6:

[0957] The server encodes the additional information created by the generative AI model and sends it to the terminal as an HTTP response. The input is the generated additional information, and the output is the encoded additional information.

[0958] Step 7:

[0959] The device receives the encoded additional information sent from the server. After receiving it, the device decodes this information and displays it in the user's field of view in AR. The input is the additional information received from the server, and the output is the explanation or information displayed in the user's field of view.

[0960] This series of processes allows the user to obtain useful information based on visual data in real time.

[0961] (Application example 1)

[0962] 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."

[0963] While there is a demand for improved quality control of products and parts and work efficiency in factories, conventional systems have difficulty in analyzing visual data in real time and providing immediate feedback, which has prevented them from fully achieving work efficiency and quality. Therefore, there is a need for a system that can efficiently analyze visual data and provide appropriate instructions on the spot.

[0964] 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.

[0965] In this invention, the server includes a means for receiving visual data, a means for analyzing the visual data to extract visual information, and an artificial intelligence means for generating instructions based on the visual information, thereby enabling the factory robot to instantly provide instructions for the next process or quality check based on the analysis results of the visual data acquired in real time.

[0966] "Visual data" refers to digital data of images and videos captured by factory robots and photography devices.

[0967] "Analysis" refers to the process of identifying objects and features from acquired visual data and extracting information based on them.

[0968] "Visual information" refers to information representing objects and features extracted from visual data through analysis.

[0969] "Additional information" refers to instructions or explanations regarding next steps or quality checks generated by the generative AI means based on the visual information.

[0970] "Artificial intelligence means" refers to machine learning models and algorithms that generate additional information based on visual information.

[0971] A "user" is a person or entity that operates a factory robot or uses a visual data analysis system.

[0972] "Server" refers to a central computing device for receiving and analyzing visual data.

[0973] "Display device" means a screen or monitor for visually presenting the additional generated information.

[0974] "Audio output device" refers to a speaker or earphone for providing additional information as audio.

[0975] This invention is a system for acquiring and analyzing visual data to generate and provide additional information. The system includes the following components:

[0976] 1. Hardware and Software Used

[0977] Hardware:

[0978] Camera: A high-resolution camera built into a factory robot, used to capture visual data in real time.

[0979] Display: A display device attached to the robot, used to visually present additional generated information.

[0980] Audio output device: A speaker built into the robot, used to provide additional information as audio.

[0981] software:

[0982] Image analysis: Identifying objects and features from visual data using Python's OpenCV library.

[0983] Generative AI model: OpenAI's GPT-4 is used to generate additional information based on visual information.

[0984] Data transmission and reception: Using the Python Requests library, visual data is sent to the server and analysis results are received.

[0985] 2. System Operation

[0986] Camera visual data acquisition:

[0987] High-resolution cameras built into factory robots capture real-time images of products and parts, which are then encoded into a suitable format on the device and sent to a server.

[0988] Image analysis by server:

[0989] The server receives image data sent from the device. The received image data is first analyzed by an image analysis function (using the OpenCV library) to extract visual information about objects and features. This visual information is then sent to a generative AI model (OpenAI GPT-4) to generate additional information.

[0990] Generate and provide additional information:

[0991] The generative AI model generates instructions for the next process or quality check based on the visual information. These instructions are provided to the factory robot's display and audio output device, and are displayed and communicated to the user visually or audibly.

[0992] 3. Specific Examples

[0993] For example, when a factory robot picks up a part, an image of the part is captured in real time. This image is sent to a server, which performs image analysis to identify the part's characteristics. If the analysis results indicate that the part may be defective, the generative AI model generates instructions based on the following prompt:

[0994] Prompt Sentence Examples

[0995] Part analysis results: Possibly defective. Generate instructions for next steps and quality checks.

[0996] The generated instructions are provided to the user via the robot's display and voice output device, allowing for immediate action to be taken. For example, instructions such as "This part requires a quality check. Please re-inspect it before proceeding to the next process" are displayed.

[0997] In this way, the introduction of this system is expected to significantly improve work efficiency and product quality control within the factory.

[0998] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0999] Step 1:

[1000] A user operates a factory robot and captures images of an object (product or part) using the robot's built-in camera.

[1001] Input: Image of the object

[1002] Output: Captured image data

[1003] How it works: A high-resolution camera captures images of the object in real time.

[1004] Step 2:

[1005] The device encodes the captured image data into an appropriate format (for example, JPEG format) and sends it to the server as an HTTP request.

[1006] Input: Captured image data

[1007] Output: Encoded image data sent to the server

[1008] Specific operation: Image data is converted to JPEG format on the device, an HTTP request is constructed, and sent to the server endpoint.

[1009] Step 3:

[1010] The server receives the image data sent from the terminal and transfers it to the image analysis server for analysis.

[1011] Input: Encoded image data sent from the device

[1012] Output: Image data sent to the image analysis server

[1013] Specific operation: The server's receiving process receives the image data and transfers it to the image analysis server.

[1014] Step 4:

[1015] The image analysis server analyzes the image data and extracts objects and features in the image as visual information.

[1016] Input: Image data transferred to the image analysis server

[1017] Output: Extracted visual information (objects and features)

[1018] What it does: The image analysis server uses the OpenCV library to analyze images and identify objects and features.

[1019] Step 5:

[1020] The server provides the extracted visual information to the generative AI model and inputs prompt sentences to generate additional information.

[1021] Input: Extracted visual information

[1022] Output: Generated additional information (instructions for next steps and quality checks)

[1023] Specific operation: Based on visual information, the server inputs a prompt sentence into OpenAI's GPT-4 API and generates instructions.

[1024] Step 6:

[1025] The generated additional information is returned to the terminal and provided to the display or audio output device of the factory robot.

[1026] Input: Generated additional information

[1027] Output: Additional information returned to the terminal

[1028] Specific operation: The server sends the generated instructions to the terminal, which receives them and displays them on the robot's display or outputs them as voice.

[1029] Step 7:

[1030] The user checks the additional information and performs the next process or quality check.

[1031] Input: Additional information provided by the robot's display or audio output device

[1032] Output: User performs work

[1033] Specific Action: The user follows the instructions provided, either visually or audibly, to perform the appropriate steps.

[1034] 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.

[1035] This invention combines a system that acquires and analyzes visual data to generate and provide additional information with an emotion engine that recognizes the user's emotions and optimizes the provision of information. This system includes "means for acquiring visual data," "means for analyzing the visual data and extracting visual information," "artificial intelligence means for generating additional information based on the visual information," and "means for providing additional information to the user," and further includes an "emotion engine that recognizes the user's emotions."

[1036] Device behavior

[1037] The device has a built-in camera that captures objects and scenes within the user's field of view in real time. It acquires the image the user sees through the device and sends it as image data to a server. It also uses an emotion engine to analyze the user's facial expressions and voice and recognize emotions. The recognized emotion data is also sent to the server.

[1038] Server Operation

[1039] The server receives image data and emotion data sent from the device. First, it analyzes the image data and extracts visual information. Next, the generation AI means generates related additional information based on this visual information. The generated additional information is adjusted based on the emotion data. For example, if the user is surprised, it generates additional information that explains the user in a gentle tone.

[1040] Specific examples

[1041] As a concrete example, imagine a scenario in which a user is surprised to see a new animal at the zoo. The user is wearing a glasses-type device, and the device captures an image of the animal. At the same time, the emotion engine recognizes the user's surprised expression. This image data and emotion data are sent from the device to the server. The server first analyzes the image and identifies the animal as a "koala." Next, the generative AI means generates information about the koala and creates a description such as, "Koalas are iconic Australian animals that usually live on eucalyptus trees." At the same time, the emotion engine takes the user's state of surprise into account and adjusts the description text to a gentler tone before sending it to the device. The device displays this information as AR in the user's field of view, allowing the user to instantly learn about koalas.

[1042] User Experience

[1043] By simply wearing the glasses, users can obtain rich information about objects and scenes in their field of view in real time. Furthermore, the device recognizes the user's emotions and adjusts the information accordingly, further personalizing the user's experience. For example, when a scene elicits surprise or interest, the device provides gentler, more detailed explanations, making it easier for the user to absorb the information. This further improves the learning experience and quality of life.

[1044] The above is a specific description of the embodiment for carrying out the present invention, and the invention can be practiced based on this embodiment. The present invention is not limited to this specific example, and various embodiments are intended to be considered.

[1045] The processing flow will be explained below.

[1046] Step 1:

[1047] A user wears the glasses-type device and looks at an object within their field of view. At this time, the camera built into the device captures image data within the user's field of view. The captured image data is temporarily stored within the device.

[1048] Step 2:

[1049] The device's emotion engine analyzes the user's facial expressions and voice in real time to recognize their emotions. For example, a facial expression recognition algorithm can be used to understand the user's state of surprise or interest. The recognized emotion data is also temporarily stored on the device.

[1050] Step 3:

[1051] The device encodes the captured image data and emotion data and prepares them for transmission to the server. Specifically, the image data is converted to JPEG format and the emotion data is converted to text format, compiling them into a transmittable data format. Next, the image data and emotion data are sent to the server endpoint as an HTTP POST request.

[1052] Step 4:

[1053] The server receives the image data and emotion data sent from the device. The server checks the received data and checks the consistency of the image data and emotion data. After checking for missing or damaged data, the server prepares to begin image analysis.

[1054] Step 5:

[1055] The server passes the image data to the image analysis server, which then performs image analysis. The image analysis server uses machine learning models and algorithms to identify objects and features in the image. For example, the names and features of animals and buildings in the image are extracted as visual information.

[1056] Step 6:

[1057] The server receives the visual information obtained from the image analysis server, and converts this visual information into a data format that is prepared for use in the next step and passed to the generation AI means.

[1058] Step 7:

[1059] The server sends visual information to the AI ​​generation means and requests it to generate additional information. Based on the visual information, the AI ​​generation means generates related text information and explanations using natural language processing technology.

[1060] Step 8:

[1061] The generated additional information is returned to the server from the generation AI means. The server combines this additional information with the emotion data and adjusts the additional information based on the user's emotion. For example, if the user is surprised, the tone of the explanation will be softened.

[1062] Step 9:

[1063] The server sends the prepared additional information to the device. The device receives the additional information and notifies the user through a user interface (UI). When using AR technology, the device displays the information superimposed on the user's field of view.

[1064] Step 10:

[1065] Users receive additional information in real time through the glasses, allowing them to instantly gain detailed knowledge about the objects and scenes in their field of view. Additionally, the emotion engine personalizes the information, enabling more effective learning and understanding.

[1066] Example 2

[1067] 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."

[1068] Conventional visual data acquisition and analysis systems simply provide visual information without considering the user's emotional state. This results in a uniform user experience, and the provision of non-personalized information can reduce user satisfaction and comprehension. The objective of this invention is to optimize the user experience and improve user satisfaction and comprehension by recognizing the user's emotions and providing information according to those emotions.

[1069] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1070] In this invention, the server includes means for acquiring visual data, means for analyzing the visual data and extracting visual information, artificial intelligence means for generating additional information based on the visual information, and an emotion engine for recognizing the user's emotions and optimizing the provision of information, thereby enabling the provision of personalized information according to the user's emotions.

[1071] "Visual data" is image information of objects and scenes that are within the user's field of view.

[1072] "Analysis" is the process of extracting useful visual information from visual data.

[1073] "Visual information" refers to information obtained through analysis regarding the identification and characteristics of an object.

[1074] "Artificial intelligence means" are machine learning models or algorithms for generating additional information based on visual information.

[1075] "Additional information" is information such as explanations or commentaries generated based on visual information.

[1076] The "means for providing" is a means for displaying the generated additional information to the user.

[1077] The "emotion engine" is a system that analyzes the user's facial expressions and voice to recognize their emotional state.

[1078] A "generative AI model" is an artificial intelligence model for generating appropriate additional information based on a prompt sentence.

[1079] A "prompt" is a textual instruction that is input to a generative AI model.

[1080] An "image analysis server" is a server that analyzes image data sent from a terminal and extracts visual information.

[1081] This invention combines a system that acquires and analyzes visual data to generate and provide additional information with an emotion engine that recognizes the user's emotions and optimizes the provision of information. This system includes "means for acquiring visual data," "means for analyzing the visual data and extracting visual information," "artificial intelligence means for generating additional information based on the visual information," and "means for providing additional information to the user," and further includes an "emotion engine that recognizes the user's emotions."

[1082] Device behavior

[1083] The device has a built-in camera that captures objects and scenes within the user's field of view in real time. It acquires the image the user sees through the device and sends it as image data to a server. It also uses an emotion engine to analyze the user's facial expressions and voice and recognize emotions. The recognized emotion data is also sent to the server.

[1084] Server Operation

[1085] The server receives image data and emotion data sent from the device. First, it analyzes the image data and extracts visual information. For image analysis, it uses image processing libraries such as TensorFlow and OpenCV. Next, based on this visual information, it generates related additional information using generative AI means (e.g., a generative AI model). The generated additional information is adjusted based on the emotion data. For example, if the user is surprised, it generates additional information that explains the user in a gentle tone. This adjustment is made using a natural language processing (NLP) algorithm.

[1086] Specific examples

[1087] Imagine a scenario in which a user is surprised to see a new animal at the zoo. The user is wearing a glasses-type device, and the device captures an image of the animal. At the same time, the emotion engine recognizes the user's surprised expression. This image data and emotion data are sent from the device to the server. The server first analyzes the image and identifies the animal as a "koala." Next, a generative AI means (generative AI model) generates information about the koala and creates a description such as, "Koalas are iconic Australian animals that usually live in eucalyptus trees." The emotion engine then takes the user's state of surprise into account and adjusts the description text to a gentler tone before sending it to the device. The device displays this information as AR in the user's field of view, allowing the user to instantly learn about koalas.

[1088] Prompt Sentence Examples

[1089] Here are some examples of prompts to input to a generative AI model:

[1090] A user is amazed to see a koala at the zoo. To explain this situation, create a gentle description of the koala.

[1091] User Experience

[1092] By simply wearing the glasses, users can obtain rich information about objects and scenes in their field of view in real time. Furthermore, the device recognizes the user's emotions and adjusts the information accordingly, further personalizing the user's experience. For example, when a scene elicits surprise or interest, the device provides gentler, more detailed explanations, making it easier for the user to absorb the information. This further improves the learning experience and quality of life.

[1093] The above is a specific description of the embodiment for carrying out the present invention, and the invention can be practiced based on this embodiment. The present invention is not limited to this specific example, and various embodiments are intended to be considered.

[1094] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1095] Step 1:

[1096] The device uses a camera to capture objects and scenes within the user's field of view in real time, thereby obtaining visual data (image data). Once this image data has been obtained, the device sends it to a server. The input is an image within the user's field of view, and the output is image data. Specifically, the camera continuously captures images, stores the data in the device's buffer, and transmits it to the server over the network.

[1097] Step 2:

[1098] The device's emotion engine analyzes the user's facial expressions and voice to obtain emotional data. The input is the user's facial and voice data, and the output is emotional data. This emotional data is sent to the server. Specifically, the microphone captures the voice, and the built-in emotion recognition algorithm analyzes it to identify the user's emotional state, and then sends the data to the server.

[1099] Step 3:

[1100] The server receives image data sent from the device and performs image analysis. This is done using image processing libraries such as TensorFlow and OpenCV. The input is image data and the output is visual information. Specific operations include the process in which the image analysis algorithm extracts animal features, identifies them, and generates specific visual information such as "koala."

[1101] Step 4:

[1102] The server generates a prompt sentence based on the visual information. Based on the generated prompt sentence, a generative AI model (e.g., a generative AI model) is used to generate related additional information. The input is visual information, and the output is the prompt sentence and additional information. Specifically, the server generates the following prompt sentence based on the visual information:

[1103] A user is amazed to see a koala at the zoo. To explain this situation, create a gentle description of the koala.

[1104] A generative AI model processes this prompt and generates an explanation.

[1105] Step 5:

[1106] The server adjusts the generated additional information based on the emotional data. The input is the additional information and the emotional data, and the output is the adjusted additional information. Specifically, the NLP algorithm analyzes the emotional data and adjusts the tone and content of the explanation based on the user's emotions.

[1107] Step 6:

[1108] The server sends the adjusted additional information to the terminal. This information is handled in real time. The input is the adjusted additional information, and the output is the data sent to the terminal.

[1109] Step 7:

[1110] The device overlays the received adjusted additional information onto the user's field of view, allowing the user to instantly obtain additional information based on the visual information. The input is the adjusted additional information, and the output is the user's visual display. Specific operations include the process of overlaying information onto the user's field of view using AR technology.

[1111] (Application example 2)

[1112] 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."

[1113] Conventional visual data analysis systems have the problem of not providing optimal information to users because they do not take into account the user's emotions. Also, because information is provided uniformly, it is difficult to provide a personalized experience that reflects the situation and emotions of each individual user. This makes it difficult to increase user satisfaction, especially in environments where real-time information provision is required.

[1114] 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.

[1115] In this invention, the server includes means for acquiring visual data, means for analyzing the visual data to extract visual information, artificial intelligence means for generating additional information based on the visual information, means for acquiring and analyzing emotional data, means for adjusting the additional information based on the emotional data, and means for providing the additional information to the user, thereby enabling personalized information provision that takes the user's emotions into consideration.

[1116] "Visual data" refers to information that can be visually confirmed by a user and is acquired by a camera or imaging device.

[1117] "Visual information" refers to information about objects, scenes, and situations extracted by analyzing the visual data.

[1118] "Artificial intelligence means" refers to algorithms, including machine learning and deep learning, for generating additional information based on visual information.

[1119] "Emotion data" is data that indicates emotions analyzed from the user's facial expressions, voice, etc.

[1120] An "emotion engine" is a system or software that acquires and analyzes emotional data and provides appropriate information based on the results of that analysis.

[1121] "Additional information" is information for the user that is generated based on visual information and further adjusted based on emotional data.

[1122] A "camera" is a photographic device for capturing images within a user's field of view.

[1123] An "image analysis server" is a server that analyzes acquired visual data and extracts visual information.

[1124] The "information providing means" refers to a device or method for displaying the generated additional information to the user.

[1125] MODE FOR CARRYING OUT THE INVENTION

[1126] The system for implementing the present invention acquires and analyzes visual and emotional data to provide additional personalized information to the user. This system mainly consists of the following main components:

[1127] 1. Device operation:

[1128] Hardware: The device has a built-in camera that captures the user's visual data in real time, as well as a microphone that captures the user's facial expressions and voice.

[1129] Software: The device captures the user's visual data in real time and sends it to the server as image data. It also includes an emotion engine that recognizes the user's emotions. This emotion engine analyzes facial expressions and voice to extract emotional data and send it to the server.

[1130] 2. Server Operation:

[1131] Hardware: Servers are powerful computing devices with the processing power to perform large amounts of data analysis.

[1132] Software: The server receives image data and emotion data sent from the device. First, it uses an image analysis server for image analysis. It analyzes the visual data and extracts visual information through object recognition and scene recognition. Next, based on this visual information, a generative AI means generates related additional information. Furthermore, it uses an emotion engine to adjust the generated additional information based on the user's emotion data.

[1133] As a concrete example, consider a user shopping in a brick-and-mortar store. When the user puts on smart glasses and looks at a product on a shelf, the glasses capture the product in real time. At the same time, an emotion engine recognizes whether the user is interested or confused by the product. This visual and emotion data is sent from the device to a server. The server first performs image analysis to recognize the specific product (e.g., broccoli). Next, generative AI methods generate additional information about the broccoli (e.g., nutritional value, usage, current sales information, etc.). The emotion engine then adjusts the tone and level of detail of the information based on the user's emotions. For example, if the user is surprised, it generates a gentle explanation such as, "Broccoli is rich in vitamin C and helps boost your immune system. It's on sale this week, 10% off!"

[1134] This information is then sent to the device (smart glasses) and displayed as AR within the user's field of view, allowing the user to obtain detailed information about the product in real time.

[1135] Example prompt sentence:

[1136] Image data: Broccoli image

[1137] Emotion data: Surprise (Score = 0.85)

[1138] This system makes it possible to provide personalized services based on user emotions, which was difficult to achieve with conventional information provision systems, thereby increasing user satisfaction and providing a richer shopping experience.

[1139] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1140] Step 1:

[1141] The device uses a camera to acquire visual data of the user. Specifically, when the user looks at a store shelf or a specific product, the device captures the image data in real time. The visual data captured by the camera is treated as input and is sent to the server.

[1142] Step 2:

[1143] The device uses an emotion engine to obtain emotion data from the user's facial expressions and voice. Specifically, it analyzes the user's facial expressions and tone of voice to identify emotions such as surprise, interest, and confusion. The input is the user's facial expressions and voice data, and the output is sent to the server as emotion data.

[1144] Step 3:

[1145] The server receives the visual data sent from the device. It then uses an image analysis server to analyze the visual data and extract visual information. The input is the visual data, and the output is visual information about objects and scenes.

[1146] Step 4:

[1147] The server receives emotion data sent from the device. This data is analyzed by the emotion engine to indicate the user's current emotional state. The input is emotion data, and the output is the analysis result.

[1148] Step 5:

[1149] The server uses generative AI means to generate additional information based on the visual information, specifically, detailed information related to the objects or scenes recognized from the visual information (e.g., product descriptions, nutritional information, special offers, etc.). The input is the visual information, and the output is the generated additional information.

[1150] Step 6:

[1151] The server uses an emotion engine to adjust the additional information based on the emotion data. Specifically, the server changes the tone and level of detail of the information depending on the user's emotion. For example, a gentle tone and detailed explanation is provided to a surprised user. The input is the additional information and emotion data, and the output is the adjusted additional information.

[1152] Step 7:

[1153] The server sends the adjusted additional information to the device, which then displays the additional information on a display (such as smart glasses) within the user's field of view. The input is the adjusted additional information, and the output is the information displayed on the device's display.

[1154] Step 8:

[1155] Users can see additional information displayed within their field of view and get more information about the product in real time, which helps users better understand the product and make better purchasing decisions. The input is the additional information displayed, and the output is increased user purchasing behavior and interest.

[1156] 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.

[1157] 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.

[1158] 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.

[1159] 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.

[1160] FIG. 9 is a diagram illustrating 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 actions 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.

[1161] 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.

[1162] 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).

[1163] 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.

[1164] 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."

[1165] 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.

[1166] 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).

[1167] 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.

[1168] 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.

[1169] 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.

[1170] 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.

[1171] 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.

[1172] 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.

[1173] 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.

[1174] 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.

[1175] 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.

[1176] 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.

[1177] The following is further disclosed regarding the above embodiment.

[1178] (Claim 1)

[1179] a means for acquiring visual data;

[1180] means for analyzing the visual data to extract visual information;

[1181] artificial intelligence means for generating additional information based on said visual information;

[1182] means for providing said additional information to a user;

[1183] A system including:

[1184] (Claim 2)

[1185] 10. The system of claim 1, wherein the means for obtaining visual data includes a camera that captures an image within the user's field of view.

[1186] (Claim 3)

[1187] 10. The system of claim 1, wherein the means for analyzing and extracting visual information comprises an image analysis server.

[1188] "Example 1"

[1189] (Claim 1)

[1190] a means for acquiring visual data;

[1191] means for encoding and transmitting said visual data over a network;

[1192] means for analyzing the visual data to extract features and visual information of an object;

[1193] an artificial intelligence means for generating text information and explanations based on the visual information;

[1194] means for encoding and transmitting the additional information to a user for display;

[1195] A system including:

[1196] (Claim 2)

[1197] 10. The system of claim 1, wherein the means for obtaining visual data includes an optical device that captures an image within the user's field of view.

[1198] (Claim 3)

[1199] 10. The system of claim 1, wherein the means for analyzing and extracting visual information comprises an analysis device.

[1200] "Application Example 1"

[1201] (Claim 1)

[1202] a means for acquiring visual data;

[1203] means for analyzing the visual data to extract visual information;

[1204] artificial intelligence means for generating additional information based on said visual information;

[1205] means for providing said additional information to a user;

[1206] means for transmitting the visual data to a server;

[1207] means for the server to analyze the visual data and generate instructions for next steps and quality checks;

[1208] means for providing said instructions to a display or audio output device of the robot;

[1209] A system including:

[1210] (Claim 2)

[1211] 10. The system of claim 1, wherein the means for obtaining visual data includes a camera that captures an image within the user's field of view.

[1212] (Claim 3)

[1213] 10. The system of claim 1, wherein the means for analyzing and extracting visual information comprises an image analysis server.

[1214] "Example 2: Combining Emotion Engines"

[1215] (Claim 1)

[1216] a means for acquiring visual data;

[1217] means for analyzing the visual data to extract visual information;

[1218] artificial intelligence means for generating additional information based on said visual information;

[1219] means for providing said additional information to a user;

[1220] An emotion engine that recognizes the user's emotions and optimizes the information provided;

[1221] A system including:

[1222] (Claim 2)

[1223] 10. The system of claim 1, wherein the means for obtaining visual data includes a camera that captures an image within the user's field of view.

[1224] (Claim 3)

[1225] 10. The system of claim 1, wherein the means for analyzing and extracting visual information comprises an image analysis server.

[1226] (Claim 4)

[1227] 10. The system of claim 1, wherein the artificial intelligence means generates the additional information using a generative AI model.

[1228] (Claim 5)

[1229] 2. The system according to claim 1, wherein the emotion engine generates emotion data by analyzing a user's facial expression and voice.

[1230] (Claim 6)

[1231] 10. The system of claim 1, wherein the additional information is adjusted based on emotion data and is provided in different tones depending on the user's emotion.

[1232] (Claim 7)

[1233] 5. The system of claim 4, wherein the prompt sentence to be input to the generative AI model is generated based on visual information and emotional data.

[1234] "Application example 2 when combining emotion engines"

[1235] (Claim 1)

[1236] a means for acquiring visual data;

[1237] means for analyzing the visual data to extract visual information;

[1238] artificial intelligence means for generating additional information based on said visual information;

[1239] a means for acquiring and analyzing emotion data;

[1240] means for adjusting the additional information based on the emotion data;

[1241] means for providing said additional information to a user;

[1242] A system including:

[1243] (Claim 2)

[1244] 10. The system of claim 1, wherein the means for obtaining visual data includes a camera that captures an image within the user's field of view.

[1245] (Claim 3)

[1246] 10. The system of claim 1, wherein the means for analyzing and extracting visual information includes a processor for analyzing images. [Explanation of symbols]

[1247] 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 visual data; means for analyzing the visual data to extract visual information; artificial intelligence means for generating additional information based on said visual information; means for providing said additional information to a user; A system including:

2. 2. The system of claim 1, wherein the means for obtaining visual data includes a camera that captures an image within the user's field of view.

3. The system of claim 1 , wherein the means for analyzing and extracting visual information comprises an image analysis server.

Images