system

Abstract

We provide the system. [Solution] A means for analyzing image data received from a communication terminal and identifying identifiable information elements contained in the background, A means of modifying identified information elements and processing the background in a natural way using artificial intelligence, A means for transmitting processed image data to a communication terminal, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] When posting an image on an online platform such as SNS, there is a risk that identifiable information such as landmarks or addresses included in the background may be identified by others. Therefore, the privacy of the user is threatened, and there may be risks such as stalking and other security problems. There is a need for a technology that can solve this problem and share images safely.

Means for Solving the Problems

[0005] This invention provides a technology that receives image data from a communication terminal, identifies identifiable information elements contained in the background using artificial intelligence, and modifies these information elements in a natural manner. This technology detects information elements using an object detection algorithm and modifies the original image information in a natural way by processing the background of the image using a generative adversarial network. Furthermore, it constructs a system that transmits the processed image to the communication terminal, enabling users to safely post images to social media.

[0006] A "communication terminal" is a general term for devices that allow users to take pictures and send and receive data over a network.

[0007] "Image data" refers to visual information represented in digital format, and is usually stored as a collection of pixels.

[0008] "Artificial intelligence" is a general term for algorithms and technologies that computer systems use to emulate human intelligent activity.

[0009] "Identifiable information elements" refer to information within an image that has a specific meaning and is used to identify the location or object, such as specific shapes or text.

[0010] An "object detection algorithm" is a computational method for automatically recognizing specific objects or features from image data and determining their location.

[0011] A "generative adversarial network" is a type of neural network in which a network that generates data and a network that evaluates that data are in opposition, aiming to generate high-quality data. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2]This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, a processor with a reference numeral (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, a RAM (Random Access Memory) with a reference numeral is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, a storage with a reference numeral is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0018] In the following embodiments, a communication I / F (Interface) with a reference numeral is an interface including a communication processor and 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), or Bluetooth (registered trademark), and the like.

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This invention provides a system that enhances privacy protection by naturally altering identifiable information contained in the background of images shared by users on the internet. This system has the function of preventing others from determining the user's location by transmitting image data from the user's communication terminal to a server and altering specific background information in the process.

[0034] When a user selects an image on their device, the device sends the image to a server via the network. The server inputs the received image into an artificial intelligence system based on machine learning. This AI system uses object detection algorithms to recognize identifiable information elements in the image, such as landmarks and signs.

[0035] For identified informational elements, the server utilizes generative adversarial network (PAD) technology to process the background in a natural way. This process removes or alters privacy-related information from the original image while maintaining a visually natural appearance.

[0036] For example, if a user takes a photo at a famous tourist spot and a landmark is visible in the background, the server will transform that landmark into a more general building or landscape. During this process, visual elements such as color and lighting are also adjusted to maintain consistency.

[0037] The processed image is then sent back to the user's device, allowing the user to confidently post this image to social media or other platforms. As described above, the present invention provides users with a secure means of digital communication while reducing the privacy risks associated with image sharing.

[0038] The following describes the processing flow.

[0039] Step 1:

[0040] The device allows the user to select the image they want to post. The user chooses an image from their device's internal storage or camera app and prepares it for posting.

[0041] Step 2:

[0042] The terminal sends the selected image data to the server. HTTP or HTTPS is used as the communication protocol to securely transfer the image data.

[0043] Step 3:

[0044] The server inputs the received image data into an AI-based analysis engine for analysis. Here, object detection algorithms are used to automatically detect identifiable information elements within the image.

[0045] Step 4:

[0046] The server selects elements from the identified information that could lead to location identification and begins background processing to modify those elements. It utilizes generative adversarial networks to replace these elements in a natural way. For example, it can alter building shapes or textual information to make location identification more difficult.

[0047] Step 5:

[0048] The server generates a new, processed image. During this process, it also adjusts the overall color tone and lighting to maintain a consistent and natural appearance.

[0049] Step 6:

[0050] The server then sends the processed image back to the user's device. After transmission, the user makes a final check of the image, and it is ready to be posted to social media.

[0051] Step 7:

[0052] Users post edited images to social media and online platforms. This reduces the risk of location identification for third parties and allows content to be shared while protecting privacy.

[0053] (Example 1)

[0054] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0055] When visual data is shared over the internet, identifiable information contained in the background can pose a privacy risk. The challenge lies in developing technologies that modify information in a more natural way to reduce the risk of location information and personally identifiable elements being leaked.

[0056] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0057] In this invention, the server includes means for analyzing visual data received from an information processing device and identifying identifiable information elements contained in the background; means for generating commands to modify the identified information elements and processing the background in a natural manner using generative AI technology; and means for transmitting the processed visual data to the information processing device. This makes it possible to naturally modify information while protecting privacy when sharing visual data.

[0058] An "information processing device" is a general term for electronic devices that can receive and transmit data, and perform analysis and processing.

[0059] "Visual data" is a general term for data that contains information that can be displayed visually, such as still images and videos.

[0060] A "server" is a central device that communicates with information processing devices via a network and performs data analysis and processing.

[0061] "Identifiable information elements" are elements present in visual data that allow for the recognition of specific locations or objects.

[0062] "Generative AI technology" is a part of artificial intelligence technology and is a general term for methods that generate new data based on input data.

[0063] A "generative rival network" is a technique that aims to generate data naturally by constructing both a generative network and a discriminative network, and then training them in a rivalry.

[0064] This invention provides an embodiment for securely sharing visual data captured by users using an information processing device. Specifically, it realizes a system that protects privacy by detecting identifiable information elements contained in visual data and modifying them using generation AI technology.

[0065] Users select visual data on information processing devices such as smartphones and computers and send that visual data to a server via a network. This process is securely conducted via the HTTP or HTTPS protocol. The server analyzes the received visual data using object recognition methods that utilize deep learning frameworks such as TENSORFLOW® and PyTorch. These object recognition methods employ algorithms such as YOLO and Faster R-CNN to detect landmarks and identifiable information elements within the visual data.

[0066] For detected information elements, the server uses generative AI technology to form modification instructions. Specifically, generative counter-network (GAN) technology is used. The generative network proposes natural modifications to the visual data, and the discriminative network evaluates their naturalness. This process is repeated until the modified visual data is deemed natural.

[0067] For example, if a user takes an image at a specific tourist destination that includes a famous landmark, this invention can be used to replace that landmark with a more typical background landscape. The lighting conditions and colors are adjusted to match the original data, resulting in a natural-looking image without any noticeable inconsistencies.

[0068] The modified visual data is returned from the server to the information processing device, and the user can confidently post this data to digital platforms such as social media. An example of a prompt might be a command such as, "Naturally remove a specific landmark from this image and replace it with other common scenery." The generative AI model performs the modification via this prompt.

[0069] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0070] Step 1:

[0071] The user selects the visual data they want to modify on their device. This visual data is often captured with a digital camera or smartphone. After selection, the device sends this visual data to the server via the HTTP or HTTPS protocol. The input data is a raw visual file (e.g., JPEG, PNG format), and the output is the visual data securely transferred to the server.

[0072] Step 2:

[0073] The server analyzes the received visual data. Specifically, it inputs the visual data into an object recognition model based on TensorFlow or PyTorch. Using algorithms such as YOLO or Faster R-CNN, it identifies identifiable information elements such as landmarks and signs within the visual data. The input is the received visual data, and the output is a list of identifiable information elements.

[0074] Step 3:

[0075] The server generates instructions to modify the identified information elements. For example, it might generate a prompt such as, "Replace background landmarks with common scenery." This prompt is then used as input to the generative AI model. The input is a list of identified information elements, and the output is a prompt for the generative AI model.

[0076] Step 4:

[0077] The server uses a Generative Counter-Network (GAN) to modify visual data. The generative network proposes a new background, and the discriminative network evaluates its naturalness; this process is repeated. The input consists of modification instructions and the original visual data, and the output is visual data modified to appear natural. Through this process, landmarks and other elements are replaced with more typical landscapes.

[0078] Step 5:

[0079] The server sends the modified visual data back to the original device. Users can then confidently share this modified visual data on social media and other platforms. The input data is the modified visual data, and the output is the modified data securely sent back to the user's device. This process allows users to engage in digital communication with reduced privacy risks.

[0080] (Application Example 1)

[0081] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0082] Images shared on the internet may contain information related to the poster's location and privacy. This can threaten individual safety and privacy, so technologies to mitigate this risk are needed. Furthermore, methods are required to easily modify transmitted images and return them to the server in a visually accurate form.

[0083] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0084] In this invention, the server includes means for analyzing image data captured by a camera and identifying privacy-related information contained in the background; means for modifying the identified information and processing the background in a visually consistent manner using machine learning; and means for providing the processed image to a communication terminal and supporting user posting. This enables users to share images on the internet with peace of mind without the leakage of personal information.

[0085] "Photography equipment" refers to electronic devices used to acquire image data, mainly including smartphones and digital cameras.

[0086] "Image data" refers to a collection of visual information acquired using photographic equipment, which is stored or transmitted in digital format.

[0087] "Privacy-related information" refers to information that contains an individual's location or other identifiable information within image data, which may affect an individual's safety or privacy.

[0088] Machine learning is a technique that learns patterns from data and applies those patterns to new data. It is an artificial intelligence technology used in areas such as image recognition and object detection.

[0089] "Visually consistent form" refers to a state where the modification of an image is natural and the light and color characteristics of the original image are preserved.

[0090] A "communication terminal" is a device that sends and receives data over a network, and generally includes smartphones and tablets.

[0091] This invention begins with the user transmitting image data acquired using a camera to a server via a communication network. The server analyzes the received image data and identifies privacy-related information contained in the background. This employs image recognition techniques widely used as object recognition algorithms. Specifically, it uses machine learning libraries such as TensorFlow and OpenCV.

[0092] For privacy-related information identified by the server, machine learning is used to modify the background in a visually consistent manner. This modification utilizes generative AI models, such as TensorFlow and Keras. A specific example is a Generative Adversarial Network (GAN). This process allows for natural background changes without disrupting the user's intended content.

[0093] The processed image data is sent back to the communication terminal, allowing users to securely post these images to online platforms and communication services. Users can gain peace of mind knowing they can publish images taken at any location without their personal information being leaked. For example, when a user posts a photo of a product taken at home, the image can be processed so that the interior of their home is not visible in the background.

[0094] An example of a prompt message might be, "Detect any address-identifying information contained in the background and replace it with a generic wallpaper pattern." This allows for complete privacy protection while maintaining the image's appearance.

[0095] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0096] Step 1:

[0097] The user uses a camera to acquire image data and sends that image from the terminal to the server. This input image data includes information about the product and its background. The user selects images and specifies options for protecting privacy.

[0098] Step 2:

[0099] The server analyzes the received image data. At this stage, it applies image recognition algorithms to identify privacy-related information contained in the background. This process uses TensorFlow and OpenCV to detect image landmarks, text, etc., and considers them as privacy risks. The input is image data, and the output is a list of identified privacy-related information.

[0100] Step 3:

[0101] The server modifies the background using a generative AI model (such as a GAN) based on the identified privacy-related information. The generative AI model is given image data containing privacy information and its location information as input, and based on this, it masks the privacy-related information while maintaining a natural appearance. The output is the modified, visually consistent image data.

[0102] Step 4:

[0103] The processed image data is sent from the server to the terminal. The user reviews this modified image and makes further adjustments as needed. The final image data is ready for use on social media, online shopping review pages, etc. The input is the modified image data, and the output is the image after the user's final review.

[0104] Step 5:

[0105] Users can confidently post modified images to online platforms. In this step, users ensure their privacy is securely protected when publishing images and sharing content. The output is a published image, and the risk of privacy violations is reduced throughout this process.

[0106] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0107] This invention provides a system that enables more personalized image processing by naturally altering identifiable information contained in the background of images shared by users, and further reflecting the user's emotions. When a user selects an image using a communication terminal, the emotion engine analyzes the image along with the user's current emotional information. This emotion engine analyzes data indicating emotions, such as the user's facial expressions and tone of voice, to recognize the user's emotional state.

[0108] The device sends the selected image data to the server, along with the results of the emotion engine's analysis. The server inputs the image into an AI-based analysis system, which uses object detection algorithms to detect identifiable information elements in the background.

[0109] The server, having received emotional information from the emotion engine, incorporates this information when processing the background. Using a generative adversarial network, it modifies the recognized information elements, reflecting the user's emotions in terms of color scheme and design in the background. For example, if the user is expressing enjoyment, bright colors and friendly design elements can be adopted.

[0110] The edited image, with a personalized background reflecting the user's emotions, is sent back to the user's device. The user can then review this image and, if satisfied, safely post it to social media or other platforms.

[0111] This system not only protects users' privacy but also allows them to share unique images with visual effects that match their emotions, thereby improving the quality of digital communication.

[0112] The following describes the processing flow.

[0113] Step 1:

[0114] Users select images they want to post using their communication device. The device offers options to choose images from its camera app or gallery. After selecting an image, users can use the camera to record their current facial expressions and voice.

[0115] Step 2:

[0116] The device sends selected image data and user facial expression and voice data to the server. The HTTPS protocol is used for secure data transfer.

[0117] Step 3:

[0118] The server inputs the received image data into an AI analysis engine and uses an object detection algorithm to detect identifiable information elements within the image. These elements include specific landmarks and address information.

[0119] Step 4:

[0120] Simultaneously, the server inputs the received user's facial expressions and voice data into the emotion engine, which analyzes the user's emotional state. The emotion engine analyzes changes in facial expressions and tone of voice to identify the user's current emotion.

[0121] Step 5:

[0122] The server uses a generative adversarial network to process the background based on the identified information elements. During this process, emotional information obtained from the emotion engine is reflected in the background's color and design. For example, if the emotion of joy is recognized, the background will be constructed with bright colors.

[0123] Step 6:

[0124] The server generates a new image processed based on emotions and sends that data to the device. The generated image is adjusted to maintain a consistent and natural appearance.

[0125] Step 7:

[0126] The device displays the processed image to the user and prompts them for final confirmation. The user can review the image and make minor adjustments as needed.

[0127] Step 8:

[0128] Users then post the finalized images to social media and other online platforms. This ensures that users' privacy is protected and allows them to share images that reflect their emotions.

[0129] (Example 2)

[0130] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0131] In image sharing, there is a need to create visual data with unique and personalized visual effects that reflect users' emotions while protecting user privacy. However, conventional technologies have faced the challenge of making natural background modifications based on the emotions of individual users.

[0132] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0133] In this invention, the server includes means for analyzing visual data received from an information processing device and detecting identifiable information contained in the background; means for an emotion analysis engine to analyze the user's emotions based on the identified information; and means for modifying the identified information and altering the background in a natural way that incorporates the user's emotional information using a generative AI model. This makes it possible to naturally modify the background of the visual data in a way that is tailored to the individual user while reflecting the user's emotions.

[0134] An "information processing device" is an electronic device with communication functions operated by a user, which performs image selection and emotion analysis.

[0135] "Visual data" refers to all image data acquired by a user using an information processing device, and includes digital information such as backgrounds and identifiable information.

[0136] An "emotion analysis engine" is a collection of software and hardware used to analyze a user's emotional state from their facial expressions and tone of voice.

[0137] "Identifiable information" refers to objects or elements present in an image that can be identified or detected, including dynamic data located in the background.

[0138] A "generative AI model" is a collection of algorithms that use artificial intelligence technology to modify or generate data, and in particular refers to methods that include generative adversarial networks.

[0139] A "generative adversarial network" is a technique in which two networks, one for generating and the other for identifying, learn while competing with each other during image generation and modification, enabling the generation of more realistic images.

[0140] This invention is a system that uses visual data captured or selected by the user to naturally modify the background to match the user's personal feelings while protecting their privacy. Specifically, it is configured as follows:

[0141] The user uses an information processing device, which is a communication terminal, to select visual data from either the camera or storage. This visual data is analyzed by an emotion analysis engine built into the terminal to reflect the user's current emotional state. This emotion analysis engine is software that detects the user's facial expressions and tone of voice, and identifies the user's emotions through an analysis algorithm.

[0142] The analysis results and visual data are sent from the information processing device to the server. The server passes the visual data to an AI-based analysis system, which uses object recognition algorithms to extract identifiable information contained in the background. This includes identifiable objects and textual information.

[0143] Next, the server uses a generative AI model, particularly a generative adversarial network (GAN), to modify the extracted identifiable information based on the user's emotions. In this process, it references information from the emotion analysis engine and applies colors and designs to the background that match the user's emotions. For example, if the user is feeling happy, the background can reflect bright colors and a colorful design.

[0144] The modified visual data is sent back to the information processing device, where the user performs a final check. If the user is satisfied with the processing, they can share this personalized modified image on platforms such as social media.

[0145] As a concrete example, a text-based prompt such as "naturally enhance a smiling selfie and change the background to a brighter one" is input to the model. This system allows users to easily utilize visual effects optimized for their individual emotions to improve digital communication.

[0146] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0147] Step 1:

[0148] The user selects visual data on the information processing device. Specifically, the user operates the device's photo app and selects the visual data they want to process from their gallery or captured images by tapping it. The input for this operation is the user's instruction, and the output is the selected visual data.

[0149] Step 2:

[0150] The device analyzes the user's emotions using an emotion analysis engine. The device uses a camera and microphone to capture the user's facial expressions and voice, and the emotion analysis algorithm analyzes this data. Specifically, it uses image recognition technology to extract features such as smiles, wrinkles, and voice tone to identify the user's emotional state. The input to this module is the user's voice and video data, and the output is the analyzed emotion information.

[0151] Step 3:

[0152] The terminal sends the selected visual data and analyzed sentiment information to the server. Specifically, this involves packaging the data and sending it to the server via a secure communication protocol. The input is the selected visual data and sentiment information, and the output is the data received by the server.

[0153] Step 4:

[0154] The server inputs visual data into an AI-based analysis system to detect identifiable information. The server uses object recognition algorithms to extract identifiable elements such as text and landmarks from the image. The input is the received visual data, and the output is the detected identifiable information.

[0155] Step 5:

[0156] The server utilizes a Generative Adversarial Network (GAN) to modify visual data using detected information and sentiment data. Specifically, it uses GANs to add color and design to the background and generate visual effects that match the user's emotions. The input is detected identification information and sentiment data, and the output is the modified visual data.

[0157] Step 6:

[0158] The modified visual data is sent back to the terminal. The server then transmits the generated data again via a secure communication protocol, and the user is notified of the result on the terminal. The input is the modified visual data, and the output is the final visual data presented to the user on the terminal.

[0159] (Application Example 2)

[0160] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0161] In recent years, advertising displays and experiences based on the individual emotional states of visitors have begun to be emphasized in commercial facilities and retail settings. However, with current technology, it is difficult to accurately grasp visitors' emotions in real time and display personalized, dynamic advertising content accordingly. This presents a technical challenge in achieving emotionally resonant advertising displays for individual visitors.

[0162] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0163] In this invention, the server includes means for analyzing visual information received from a communication device and identifying identifiable information components contained in the background; means for modifying the identified information components and processing the background in a natural way using a machine learning algorithm; and means for analyzing the user's emotional state and personalizing the advertisement content and design based on the analysis results. This enables the display of dynamic and personalized advertisements that respond to the visitor's emotional state.

[0164] "Communication equipment" refers to hardware or software used to send and receive data from external sources.

[0165] "Visual information" refers to information that is perceived visually, such as image data.

[0166] "Analysis" refers to the process of breaking down data and information to understand their meaning and structure.

[0167] "Background" refers to the parts of an image or visual information other than the main subject.

[0168] "Identifiable information elements" refer to objects or features that can be identified within images or visual data.

[0169] A "machine learning algorithm" refers to a method for learning patterns from large amounts of data and predicting or classifying information.

[0170] "User's emotional state" refers to the emotions the user is experiencing at that moment, inferred from their facial expressions, voice, body language, etc.

[0171] "Personalization" refers to adjusting or customizing content to suit the individual user's characteristics and preferences.

[0172] "Advertising content and design" refers to the visuals and messages displayed to promote products or services to viewers.

[0173] The system for implementing this invention aims to analyze visual information in real time and personalize advertisements according to the user's emotional state. The system mainly consists of a communication device, a server, an emotion analysis engine, an image analysis system, and a generative adversarial network. The communication device is responsible for receiving data from external sources.

[0174] The server receives visual information transmitted from the communication device and uses object detection algorithms to identify identifiable informational elements contained in the background. It also utilizes machine learning algorithms to process the background in a natural way. Generative Adversarial Networks (GANs) are used to process the background, generating natural and engaging visuals.

[0175] Emotion analysis is performed based on the user's facial expressions and voice data, and is analyzed via an emotion engine. The emotion engine uses Microsoft® Azure® Emotion API and other tools to analyze the user's emotional state and personalize ad content and design to suit the user.

[0176] For example, if the server analyzes the visual information it receives and the user indicates positive emotions, the generated ad will be adjusted to include colorful and positive messages. This is to improve the user experience and enhance the appeal of the ad.

[0177] An example of a prompt would be, "This customer is currently in a happy emotional state. Generate an advertising image that attractively showcases the latest tennis shoes using bright colors and a positive atmosphere." This allows the generative AI model to generate appropriate visuals based on the user's emotional state.

[0178] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0179] Step 1:

[0180] The communication device acquires the user's visual and audio data. Using a camera and microphone, it records the user's facial expressions and voice tone, and transmits this data to the server. The input is visual and audio data, and the output is raw data transferred to the server.

[0181] Step 2:

[0182] The server analyzes the received visual information using an object detection algorithm to identify identifiable information elements in the background. The input is raw data, and digital elements are identified by an image analysis system (e.g., TensorFlow or OpenCV). The output is a dataset containing the identified identifiable information elements.

[0183] Step 3:

[0184] The server uses voice data from the user and an emotion engine to analyze the emotional state. This engine can utilize services such as the Microsoft Azure Emotion API. The input is voice data, and the output is information indicating the corresponding emotional state.

[0185] Step 4:

[0186] Based on the analysis results, the server modifies the identifiable informational elements of the background through machine learning algorithms. A generative adversarial network (GAN) is used to generate natural-looking visuals that are appropriate to the user's emotional state. The input is the analyzed dataset and emotional information, and the output is the processed image data.

[0187] Step 5:

[0188] The server personalizes the processed visual information into ad content that corresponds to the user's emotional state, generating the final ad visual. By inputting prompt text into the generating AI model, the ad image is adjusted to match the user's specific emotions. The input is processed visual information, and the output is a personalized ad visual.

[0189] Step 6:

[0190] The server transmits personalized advertising visuals to the communication device. The input is the personalized advertising visual, and the output is the final advertising image displayed on the communication device.

[0191] This series of processes generates personalized advertisements in real time that respond to the user's emotions, providing an optimal visual experience.

[0192] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0193] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0194] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0195] [Second Embodiment]

[0196] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0197] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0198] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0199] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0200] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0201] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0202] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0203] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0204] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0205] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0206] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0207] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0208] This invention provides a system that enhances privacy protection by naturally altering identifiable information contained in the background of images shared by users on the internet. This system has the function of preventing others from determining the user's location by transmitting image data from the user's communication terminal to a server and altering specific background information in the process.

[0209] When a user selects an image on their device, the device sends the image to a server via the network. The server inputs the received image into an artificial intelligence system based on machine learning. This AI system uses object detection algorithms to recognize identifiable information elements in the image, such as landmarks and signs.

[0210] For identified informational elements, the server utilizes generative adversarial network (PAD) technology to process the background in a natural way. This process removes or alters privacy-related information from the original image while maintaining a visually natural appearance.

[0211] For example, if a user takes a photo at a famous tourist spot and a landmark is visible in the background, the server will transform that landmark into a more general building or landscape. During this process, visual elements such as color and lighting are also adjusted to maintain consistency.

[0212] The processed image is then sent back to the user's device, allowing the user to confidently post this image to social media or other platforms. As described above, the present invention provides users with a secure means of digital communication while reducing the privacy risks associated with image sharing.

[0213] The following describes the processing flow.

[0214] Step 1:

[0215] The device allows the user to select the image they want to post. The user chooses an image from their device's internal storage or camera app and prepares it for posting.

[0216] Step 2:

[0217] The terminal sends the selected image data to the server. HTTP or HTTPS is used as the communication protocol to securely transfer the image data.

[0218] Step 3:

[0219] The server inputs the received image data into an AI-based analysis engine for analysis. Here, object detection algorithms are used to automatically detect identifiable information elements within the image.

[0220] Step 4:

[0221] The server selects elements from the identified information that could lead to location identification and begins background processing to modify those elements. It utilizes generative adversarial networks to replace these elements in a natural way. For example, it can alter building shapes or textual information to make location identification more difficult.

[0222] Step 5:

[0223] The server generates a new, processed image. During this process, it also adjusts the overall color tone and lighting to maintain a consistent and natural appearance.

[0224] Step 6:

[0225] The server then sends the processed image back to the user's device. After transmission, the user makes a final check of the image, and it is ready to be posted to social media.

[0226] Step 7:

[0227] Users post edited images to social media and online platforms. This reduces the risk of location identification for third parties and allows content to be shared while protecting privacy.

[0228] (Example 1)

[0229] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0230] When visual data is shared over the internet, identifiable information contained in the background can pose a privacy risk. The challenge lies in developing technologies that modify information in a more natural way to reduce the risk of location information and personally identifiable elements being leaked.

[0231] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0232] In this invention, the server includes means for analyzing visual data received from an information processing device and identifying identifiable information elements contained in the background; means for generating commands to modify the identified information elements and processing the background in a natural manner using generative AI technology; and means for transmitting the processed visual data to the information processing device. This makes it possible to naturally modify information while protecting privacy when sharing visual data.

[0233] An "information processing device" is a general term for electronic devices that can receive and transmit data, and perform analysis and processing.

[0234] "Visual data" is a general term for data that contains information that can be displayed visually, such as still images and videos.

[0235] A "server" is a central device that communicates with information processing devices via a network and performs data analysis and processing.

[0236] "Identifiable information elements" are elements present in visual data that allow for the recognition of specific locations or objects.

[0237] "Generative AI technology" is a part of artificial intelligence technology and is a general term for methods that generate new data based on input data.

[0238] A "generative rival network" is a technique that aims to generate data naturally by constructing both a generative network and a discriminative network, and then training them in a rivalry.

[0239] This invention provides an embodiment for securely sharing visual data captured by users using an information processing device. Specifically, it realizes a system that protects privacy by detecting identifiable information elements contained in visual data and modifying them using generation AI technology.

[0240] Users select visual data on information processing devices such as smartphones and computers and send that visual data to a server over a network. This process is securely conducted via the HTTP or HTTPS protocol. The server analyzes the received visual data using object recognition methods that utilize deep learning frameworks such as TensorFlow and PyTorch. These object recognition methods employ algorithms such as YOLO and Faster R-CNN to detect landmarks and identifiable information elements within the visual data.

[0241] For detected information elements, the server uses generative AI technology to form modification instructions. Specifically, generative counter-network (GAN) technology is used. The generative network proposes natural modifications to the visual data, and the discriminative network evaluates their naturalness. This process is repeated until the modified visual data is deemed natural.

[0242] For example, if a user takes an image at a specific tourist destination that includes a famous landmark, this invention can be used to replace that landmark with a more typical background landscape. The lighting conditions and colors are adjusted to match the original data, resulting in a natural-looking image without any noticeable inconsistencies.

[0243] The modified visual data is returned from the server to the information processing device, and the user can confidently post this data to digital platforms such as social media. An example of a prompt might be a command such as, "Naturally remove a specific landmark from this image and replace it with other common scenery." The generative AI model performs the modification via this prompt.

[0244] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0245] Step 1:

[0246] The user selects the visual data they want to modify on their device. This visual data is often captured with a digital camera or smartphone. After selection, the device sends this visual data to the server via the HTTP or HTTPS protocol. The input data is a raw visual file (e.g., JPEG, PNG format), and the output is the visual data securely transferred to the server.

[0247] Step 2:

[0248] The server analyzes the received visual data. Specifically, it inputs the visual data into an object recognition model based on TensorFlow or PyTorch. Using algorithms such as YOLO or Faster R-CNN, it identifies identifiable information elements such as landmarks and signs within the visual data. The input is the received visual data, and the output is a list of identifiable information elements.

[0249] Step 3:

[0250] The server generates instructions to modify the identified information elements. For example, it might generate a prompt such as, "Replace background landmarks with common scenery." This prompt is then used as input to the generative AI model. The input is a list of identified information elements, and the output is a prompt for the generative AI model.

[0251] Step 4:

[0252] The server uses a Generative Counter-Network (GAN) to modify visual data. The generative network proposes a new background, and the discriminative network evaluates its naturalness; this process is repeated. The input consists of modification instructions and the original visual data, and the output is visual data modified to appear natural. Through this process, landmarks and other elements are replaced with more typical landscapes.

[0253] Step 5:

[0254] The server sends the modified visual data back to the original device. Users can then confidently share this modified visual data on social media and other platforms. The input data is the modified visual data, and the output is the modified data securely sent back to the user's device. This process allows users to engage in digital communication with reduced privacy risks.

[0255] (Application Example 1)

[0256] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0257] Images shared on the internet may contain information related to the poster's location and privacy. This can threaten individual safety and privacy, so technologies to mitigate this risk are needed. Furthermore, methods are required to easily modify transmitted images and return them to the server in a visually accurate form.

[0258] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0259] In this invention, the server includes means for analyzing image data captured by a camera and identifying privacy-related information contained in the background; means for modifying the identified information and processing the background in a visually consistent manner using machine learning; and means for providing the processed image to a communication terminal and supporting user posting. This enables users to share images on the internet with peace of mind without the leakage of personal information.

[0260] "Photography equipment" refers to electronic devices used to acquire image data, mainly including smartphones and digital cameras.

[0261] "Image data" refers to a collection of visual information acquired using photographic equipment, which is stored or transmitted in digital format.

[0262] "Privacy-related information" refers to information that contains an individual's location or other identifiable information within image data, which may affect an individual's safety or privacy.

[0263] Machine learning is a technique that learns patterns from data and applies those patterns to new data. It is an artificial intelligence technology used in areas such as image recognition and object detection.

[0264] "Visually consistent form" refers to a state where the modification of an image is natural and the light and color characteristics of the original image are preserved.

[0265] A "communication terminal" is a device that sends and receives data over a network, and generally includes smartphones and tablets.

[0266] This invention begins with the user transmitting image data acquired using a camera to a server via a communication network. The server analyzes the received image data and identifies privacy-related information contained in the background. This employs image recognition techniques widely used as object recognition algorithms. Specifically, it uses machine learning libraries such as TensorFlow and OpenCV.

[0267] For privacy-related information identified by the server, machine learning is used to modify the background in a visually consistent manner. This modification utilizes generative AI models, such as TensorFlow and Keras. A specific example is a Generative Adversarial Network (GAN). This process allows for natural background changes without disrupting the user's intended content.

[0268] The processed image data is sent back to the communication terminal, allowing users to securely post these images to online platforms and communication services. Users can gain peace of mind knowing they can publish images taken at any location without their personal information being leaked. For example, when a user posts a photo of a product taken at home, the image can be processed so that the interior of their home is not visible in the background.

[0269] An example of a prompt message might be, "Detect any address-identifying information contained in the background and replace it with a generic wallpaper pattern." This allows for complete privacy protection while maintaining the image's appearance.

[0270] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0271] Step 1:

[0272] The user uses a camera to acquire image data and sends that image from the terminal to the server. This input image data includes information about the product and its background. The user selects images and specifies options for protecting privacy.

[0273] Step 2:

[0274] The server analyzes the received image data. At this stage, it applies image recognition algorithms to identify privacy-related information contained in the background. This process uses TensorFlow and OpenCV to detect image landmarks, text, etc., and considers them as privacy risks. The input is image data, and the output is a list of identified privacy-related information.

[0275] Step 3:

[0276] The server modifies the background using a generative AI model (such as a GAN) based on the identified privacy-related information. The generative AI model is given image data containing privacy information and its location information as input, and based on this, it masks the privacy-related information while maintaining a natural appearance. The output is the modified, visually consistent image data.

[0277] Step 4:

[0278] The processed image data is sent from the server to the terminal. The user reviews this modified image and makes further adjustments as needed. The final image data is ready for use on social media, online shopping review pages, etc. The input is the modified image data, and the output is the image after the user's final review.

[0279] Step 5:

[0280] The user can safely post the modified image on the online platform. At this step, the user can confirm that the image can be publicly released with privacy securely protected and share the content. The output is the publicly released image, and the risk of privacy infringement is reduced in this process.

[0281] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion recognition model 59 and perform specific processing using the user's emotion.

[0282] The present invention provides a system that realizes more personalized image processing by naturally modifying identifiable information included in the background and further reflecting the user's emotion when sharing an image taken by the user. When the user selects an image using the communication terminal, the emotion engine analyzes the current emotion information of the user together with the image. This emotion engine analyzes data indicating emotions such as the user's expression and voice tone and recognizes the user's emotional state.

[0283] The terminal transmits the selected image data to the server, and at the same time, the result analyzed by the emotion engine is also sent to the server. The server inputs the image into an AI-based analysis system and uses an object detection algorithm to detect identifiable information elements included in the background.

[0284] The server that receives the emotion information from the emotion engine incorporates this emotion information when performing background processing. Using a generative adversarial network, the recognized information elements are changed, and at that time, the color tone and design along with the user's emotion are reflected in the background. For example, when the user shows a happy emotion, bright color tones and friendly design elements can be adopted.

[0285] The processed image has a personalized background that reflects the user's emotions and is sent back to the user's terminal again. The user can perform a final check on this image and, if satisfied, safely post it on SNS or other platforms.

[0286] With this system, not only is the user's privacy protected, but they can also share a unique image with a visual effect that matches their emotions, improving the quality of digital communication.

[0287] The processing flow will be described below.

[0288] Step 1:

[0289] The user selects an image to post using a communication terminal. At this time, the terminal has options to select an image from the camera app or gallery. After selection, the user can use the camera to record their current expression and voice.

[0290] Step 2:

[0291] The terminal sends the selected image data and the user's expression and voice data to the server. The HTTPS protocol is used for communication to transfer data securely.

[0292] Step 3:

[0293] The server inputs the received image data into an AI analysis engine and uses an object detection algorithm to detect identifiable information elements in the image. These elements include specific landmarks, address displays, etc.

[0294] Step 4:

[0295] At the same time, the server inputs the received user expression and voice data into an emotion engine to analyze the user's emotional state. The emotion engine analyzes changes in expression and tone of voice to identify the current emotion.

[0296] Step 5:

[0297] The server uses a generative adversarial network to process the background based on the identified information elements. During this process, emotional information obtained from the emotion engine is reflected in the background's color and design. For example, if the emotion of joy is recognized, the background will be constructed with bright colors.

[0298] Step 6:

[0299] The server generates a new image processed based on emotions and sends that data to the device. The generated image is adjusted to maintain a consistent and natural appearance.

[0300] Step 7:

[0301] The device displays the processed image to the user and prompts them for final confirmation. The user can review the image and make minor adjustments as needed.

[0302] Step 8:

[0303] Users then post the finalized images to social media and other online platforms. This ensures that users' privacy is protected and allows them to share images that reflect their emotions.

[0304] (Example 2)

[0305] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0306] In image sharing, there is a need to create visual data with unique and personalized visual effects that reflect users' emotions while protecting user privacy. However, conventional technologies have faced the challenge of making natural background modifications based on the emotions of individual users.

[0307] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Example 2 is realized by the following means.

[0308] In this invention, the server includes means for analyzing visual data received from an information processing device and detecting identifiable information included in the background, means for the emotion analysis engine to analyze the user's emotion based on the identified information, and means for using a generative AI model to modify the identified information and modify the background in a natural form incorporating the user's emotion information. Thereby, it becomes possible to naturally modify the background of the visual data in a form specialized for the user while reflecting the user's emotion.

[0309] The "information processing device" is an electronic device having a communication function operated by the user, and is a device that selects images and analyzes emotions.

[0310] The "visual data" refers to all image data acquired by the user using an information processing device, and is digital information including the background and identifiable information.

[0311] The "emotion analysis engine" is an aggregate of software and hardware used to analyze the emotional state from the user's expression and voice tone.

[0312] The "identifiable information" refers to objects or elements existing in the image that can be identified or detected, and includes dynamic data located in the background.

[0313] The "generative AI model" is a collection of algorithms for modifying and generating data using artificial intelligence technology, and particularly refers to a method including a generative adversarial network etc.

[0314] The "generative adversarial network" is a method in which two networks, a generator and a discriminator, learn while competing in image generation and modification, and is a technology that enables more realistic image generation.

[0315] This invention is a system that uses visual data captured or selected by the user to naturally modify the background to match the user's personal feelings while protecting their privacy. Specifically, it is configured as follows:

[0316] The user uses an information processing device, which is a communication terminal, to select visual data from either the camera or storage. This visual data is analyzed by an emotion analysis engine built into the terminal to reflect the user's current emotional state. This emotion analysis engine is software that detects the user's facial expressions and tone of voice, and identifies the user's emotions through an analysis algorithm.

[0317] The analysis results and visual data are sent from the information processing device to the server. The server passes the visual data to an AI-based analysis system, which uses object recognition algorithms to extract identifiable information contained in the background. This includes identifiable objects and textual information.

[0318] Next, the server uses a generative AI model, particularly a generative adversarial network (GAN), to modify the extracted identifiable information based on the user's emotions. In this process, it references information from the emotion analysis engine and applies colors and designs to the background that match the user's emotions. For example, if the user is feeling happy, the background can reflect bright colors and a colorful design.

[0319] The modified visual data is sent back to the information processing device, where the user performs a final check. If the user is satisfied with the processing, they can share this personalized modified image on platforms such as social media.

[0320] As a concrete example, a text-based prompt such as "naturally enhance a smiling selfie and change the background to a brighter one" is input to the model. This system allows users to easily utilize visual effects optimized for their individual emotions to improve digital communication.

[0321] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0322] Step 1:

[0323] The user selects visual data on the information processing device. Specifically, the user operates the device's photo app and selects the visual data they want to process from their gallery or captured images by tapping it. The input for this operation is the user's instruction, and the output is the selected visual data.

[0324] Step 2:

[0325] The device analyzes the user's emotions using an emotion analysis engine. The device uses a camera and microphone to capture the user's facial expressions and voice, and the emotion analysis algorithm analyzes this data. Specifically, it uses image recognition technology to extract features such as smiles, wrinkles, and voice tone to identify the user's emotional state. The input to this module is the user's voice and video data, and the output is the analyzed emotion information.

[0326] Step 3:

[0327] The terminal sends the selected visual data and analyzed sentiment information to the server. Specifically, this involves packaging the data and sending it to the server via a secure communication protocol. The input is the selected visual data and sentiment information, and the output is the data received by the server.

[0328] Step 4:

[0329] The server inputs visual data into an AI-based analysis system to detect identifiable information. The server uses object recognition algorithms to extract identifiable elements such as text and landmarks from the image. The input is the received visual data, and the output is the detected identifiable information.

[0330] Step 5:

[0331] The server utilizes a Generative Adversarial Network (GAN) to modify visual data using detected information and sentiment data. Specifically, it uses GANs to add color and design to the background and generate visual effects that match the user's emotions. The input is detected identification information and sentiment data, and the output is the modified visual data.

[0332] Step 6:

[0333] The modified visual data is sent back to the terminal. The server then transmits the generated data again via a secure communication protocol, and the user is notified of the result on the terminal. The input is the modified visual data, and the output is the final visual data presented to the user on the terminal.

[0334] (Application Example 2)

[0335] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0336] In recent years, advertising displays and experiences based on the individual emotional states of visitors have begun to be emphasized in commercial facilities and retail settings. However, with current technology, it is difficult to accurately grasp visitors' emotions in real time and display personalized, dynamic advertising content accordingly. This presents a technical challenge in achieving emotionally resonant advertising displays for individual visitors.

[0337] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0338] In this invention, the server includes means for analyzing visual information received from a communication device and identifying identifiable information components contained in the background; means for modifying the identified information components and processing the background in a natural way using a machine learning algorithm; and means for analyzing the user's emotional state and personalizing the advertisement content and design based on the analysis results. This enables the display of dynamic and personalized advertisements that respond to the visitor's emotional state.

[0339] "Communication equipment" refers to hardware or software used to send and receive data from external sources.

[0340] "Visual information" refers to information that is perceived visually, such as image data.

[0341] "Analysis" refers to the process of breaking down data and information to understand their meaning and structure.

[0342] "Background" refers to the parts of an image or visual information other than the main subject.

[0343] "Identifiable information elements" refer to objects or features that can be identified within images or visual data.

[0344] A "machine learning algorithm" refers to a method for learning patterns from large amounts of data and predicting or classifying information.

[0345] "User's emotional state" refers to the emotions the user is experiencing at that moment, inferred from their facial expressions, voice, body language, etc.

[0346] "Personalization" refers to adjusting or customizing content to suit the individual user's characteristics and preferences.

[0347] "Advertising content and design" refers to the visuals and messages displayed to promote products or services to viewers.

[0348] The system for implementing this invention aims to analyze visual information in real time and personalize advertisements according to the user's emotional state. The system mainly consists of a communication device, a server, an emotion analysis engine, an image analysis system, and a generative adversarial network. The communication device is responsible for receiving data from external sources.

[0349] The server receives visual information transmitted from the communication device and uses object detection algorithms to identify identifiable informational elements contained in the background. It also utilizes machine learning algorithms to process the background in a natural way. Generative Adversarial Networks (GANs) are used to process the background, generating natural and engaging visuals.

[0350] Emotion analysis is performed based on the user's facial expressions and voice data, and is analyzed via an emotion engine. The emotion engine uses tools such as the Microsoft Azure Emotion API to analyze the user's emotional state and personalize ad content and design to suit the user.

[0351] For example, if the server analyzes the visual information it receives and the user indicates positive emotions, the generated ad will be adjusted to include colorful and positive messages. This is to improve the user experience and enhance the appeal of the ad.

[0352] An example of a prompt would be, "This customer is currently in a happy emotional state. Generate an advertising image that attractively showcases the latest tennis shoes using bright colors and a positive atmosphere." This allows the generative AI model to generate appropriate visuals based on the user's emotional state.

[0353] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0354] Step 1:

[0355] The communication device acquires the user's visual and audio data. Using a camera and microphone, it records the user's facial expressions and voice tone, and transmits this data to the server. The input is visual and audio data, and the output is raw data transferred to the server.

[0356] Step 2:

[0357] The server analyzes the received visual information using an object detection algorithm to identify identifiable information elements in the background. The input is raw data, and digital elements are identified by an image analysis system (e.g., TensorFlow or OpenCV). The output is a dataset containing the identified identifiable information elements.

[0358] Step 3:

[0359] The server uses voice data from the user and an emotion engine to analyze the emotional state. This engine can utilize services such as the Microsoft Azure Emotion API. The input is voice data, and the output is information indicating the corresponding emotional state.

[0360] Step 4:

[0361] Based on the analysis results, the server modifies the identifiable informational elements of the background through machine learning algorithms. A generative adversarial network (GAN) is used to generate natural-looking visuals that are appropriate to the user's emotional state. The input is the analyzed dataset and emotional information, and the output is the processed image data.

[0362] Step 5:

[0363] The server personalizes the processed visual information into ad content that corresponds to the user's emotional state, generating the final ad visual. By inputting prompt text into the generating AI model, the ad image is adjusted to match the user's specific emotions. The input is processed visual information, and the output is a personalized ad visual.

[0364] Step 6:

[0365] The server transmits personalized advertising visuals to the communication device. The input is the personalized advertising visual, and the output is the final advertising image displayed on the communication device.

[0366] This series of processes generates personalized advertisements in real time that respond to the user's emotions, providing an optimal visual experience.

[0367] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0368] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0369] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0370] [Third Embodiment]

[0371] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0372] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0373] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0374] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0375] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0376] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0377] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0378] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0379] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0380] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0381] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0382] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0383] This invention provides a system that enhances privacy protection by naturally altering identifiable information contained in the background of images shared by users on the internet. This system has the function of preventing others from determining the user's location by transmitting image data from the user's communication terminal to a server and altering specific background information in the process.

[0384] When a user selects an image on their device, the device sends the image to a server via the network. The server inputs the received image into an artificial intelligence system based on machine learning. This AI system uses object detection algorithms to recognize identifiable information elements in the image, such as landmarks and signs.

[0385] For identified informational elements, the server utilizes generative adversarial network (PAD) technology to process the background in a natural way. This process removes or alters privacy-related information from the original image while maintaining a visually natural appearance.

[0386] For example, if a user takes a photo at a famous tourist spot and a landmark is visible in the background, the server will transform that landmark into a more general building or landscape. During this process, visual elements such as color and lighting are also adjusted to maintain consistency.

[0387] The processed image is then sent back to the user's device, allowing the user to confidently post this image to social media or other platforms. As described above, the present invention provides users with a secure means of digital communication while reducing the privacy risks associated with image sharing.

[0388] The following describes the processing flow.

[0389] Step 1:

[0390] The device allows the user to select the image they want to post. The user chooses an image from their device's internal storage or camera app and prepares it for posting.

[0391] Step 2:

[0392] The terminal sends the selected image data to the server. HTTP or HTTPS is used as the communication protocol to securely transfer the image data.

[0393] Step 3:

[0394] The server inputs the received image data into an AI-based analysis engine for analysis. Here, object detection algorithms are used to automatically detect identifiable information elements within the image.

[0395] Step 4:

[0396] The server selects elements from the identified information that could lead to location identification and begins background processing to modify those elements. It utilizes generative adversarial networks to replace these elements in a natural way. For example, it can alter building shapes or textual information to make location identification more difficult.

[0397] Step 5:

[0398] The server generates a new, processed image. During this process, it also adjusts the overall color tone and lighting to maintain a consistent and natural appearance.

[0399] Step 6:

[0400] The server then sends the processed image back to the user's device. After transmission, the user makes a final check of the image, and it is ready to be posted to social media.

[0401] Step 7:

[0402] Users post edited images to social media and online platforms. This reduces the risk of location identification for third parties and allows content to be shared while protecting privacy.

[0403] (Example 1)

[0404] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0405] When visual data is shared over the internet, identifiable information contained in the background can pose a privacy risk. The challenge lies in developing technologies that modify information in a more natural way to reduce the risk of location information and personally identifiable elements being leaked.

[0406] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0407] In this invention, the server includes means for analyzing visual data received from an information processing device and identifying identifiable information elements contained in the background; means for generating commands to modify the identified information elements and processing the background in a natural manner using generative AI technology; and means for transmitting the processed visual data to the information processing device. This makes it possible to naturally modify information while protecting privacy when sharing visual data.

[0408] An "information processing device" is a general term for electronic devices that can receive and transmit data, and perform analysis and processing.

[0409] "Visual data" is a general term for data that contains information that can be displayed visually, such as still images and videos.

[0410] A "server" is a central device that communicates with information processing devices via a network and performs data analysis and processing.

[0411] "Identifiable information elements" are elements present in visual data that allow for the recognition of specific locations or objects.

[0412] "Generative AI technology" is a part of artificial intelligence technology and is a general term for methods that generate new data based on input data.

[0413] A "generative rival network" is a technique that aims to generate data naturally by constructing both a generative network and a discriminative network, and then training them in a rivalry.

[0414] This invention provides an embodiment for securely sharing visual data captured by users using an information processing device. Specifically, it realizes a system that protects privacy by detecting identifiable information elements contained in visual data and modifying them using generation AI technology.

[0415] Users select visual data on information processing devices such as smartphones and computers and send that visual data to a server over a network. This process is securely conducted via the HTTP or HTTPS protocol. The server analyzes the received visual data using object recognition methods that utilize deep learning frameworks such as TensorFlow and PyTorch. These object recognition methods employ algorithms such as YOLO and Faster R-CNN to detect landmarks and identifiable information elements within the visual data.

[0416] For detected information elements, the server uses generative AI technology to form modification instructions. Specifically, generative counter-network (GAN) technology is used. The generative network proposes natural modifications to the visual data, and the discriminative network evaluates their naturalness. This process is repeated until the modified visual data is deemed natural.

[0417] For example, if a user takes an image at a specific tourist destination that includes a famous landmark, this invention can be used to replace that landmark with a more typical background landscape. The lighting conditions and colors are adjusted to match the original data, resulting in a natural-looking image without any noticeable inconsistencies.

[0418] The modified visual data is returned from the server to the information processing device, and the user can confidently post this data to digital platforms such as social media. An example of a prompt might be a command such as, "Naturally remove a specific landmark from this image and replace it with other common scenery." The generative AI model performs the modification via this prompt.

[0419] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0420] Step 1:

[0421] The user selects the visual data they want to modify on their device. This visual data is often captured with a digital camera or smartphone. After selection, the device sends this visual data to the server via the HTTP or HTTPS protocol. The input data is a raw visual file (e.g., JPEG, PNG format), and the output is the visual data securely transferred to the server.

[0422] Step 2:

[0423] The server analyzes the received visual data. Specifically, it inputs the visual data into an object recognition model based on TensorFlow or PyTorch. Using algorithms such as YOLO or Faster R-CNN, it identifies identifiable information elements such as landmarks and signs within the visual data. The input is the received visual data, and the output is a list of identifiable information elements.

[0424] Step 3:

[0425] The server generates instructions to modify the identified information elements. For example, it might generate a prompt such as, "Replace background landmarks with common scenery." This prompt is then used as input to the generative AI model. The input is a list of identified information elements, and the output is a prompt for the generative AI model.

[0426] Step 4:

[0427] The server uses a Generative Counter-Network (GAN) to modify visual data. The generative network proposes a new background, and the discriminative network evaluates its naturalness; this process is repeated. The input consists of modification instructions and the original visual data, and the output is visual data modified to appear natural. Through this process, landmarks and other elements are replaced with more typical landscapes.

[0428] Step 5:

[0429] The server sends the modified visual data back to the original device. Users can then confidently share this modified visual data on social media and other platforms. The input data is the modified visual data, and the output is the modified data securely sent back to the user's device. This process allows users to engage in digital communication with reduced privacy risks.

[0430] (Application Example 1)

[0431] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0432] Images shared on the internet may contain information related to the poster's location and privacy. This can threaten individual safety and privacy, so technologies to mitigate this risk are needed. Furthermore, methods are required to easily modify transmitted images and return them to the server in a visually accurate form.

[0433] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0434] In this invention, the server includes means for analyzing image data captured by a camera and identifying privacy-related information contained in the background; means for modifying the identified information and processing the background in a visually consistent manner using machine learning; and means for providing the processed image to a communication terminal and supporting user posting. This enables users to share images on the internet with peace of mind without the leakage of personal information.

[0435] "Photography equipment" refers to electronic devices used to acquire image data, mainly including smartphones and digital cameras.

[0436] "Image data" refers to a collection of visual information acquired using photographic equipment, which is stored or transmitted in digital format.

[0437] "Privacy-related information" refers to information that contains an individual's location or other identifiable information within image data, which may affect an individual's safety or privacy.

[0438] Machine learning is a technique that learns patterns from data and applies those patterns to new data. It is an artificial intelligence technology used in areas such as image recognition and object detection.

[0439] "Visually consistent form" refers to a state where the modification of an image is natural and the light and color characteristics of the original image are preserved.

[0440] A "communication terminal" is a device that sends and receives data over a network, and generally includes smartphones and tablets.

[0441] This invention begins with the user transmitting image data acquired using a camera to a server via a communication network. The server analyzes the received image data and identifies privacy-related information contained in the background. This employs image recognition techniques widely used as object recognition algorithms. Specifically, it uses machine learning libraries such as TensorFlow and OpenCV.

[0442] For privacy-related information identified by the server, machine learning is used to modify the background in a visually consistent manner. This modification utilizes generative AI models, such as TensorFlow and Keras. A specific example is a Generative Adversarial Network (GAN). This process allows for natural background changes without disrupting the user's intended content.

[0443] The processed image data is sent back to the communication terminal, allowing users to securely post these images to online platforms and communication services. Users can gain peace of mind knowing they can publish images taken at any location without their personal information being leaked. For example, when a user posts a photo of a product taken at home, the image can be processed so that the interior of their home is not visible in the background.

[0444] An example of a prompt message might be, "Detect any address-identifying information contained in the background and replace it with a generic wallpaper pattern." This allows for complete privacy protection while maintaining the image's appearance.

[0445] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0446] Step 1:

[0447] The user uses a camera to acquire image data and sends that image from the terminal to the server. This input image data includes information about the product and its background. The user selects images and specifies options for protecting privacy.

[0448] Step 2:

[0449] The server analyzes the received image data. At this stage, it applies image recognition algorithms to identify privacy-related information contained in the background. This process uses TensorFlow and OpenCV to detect image landmarks, text, etc., and considers them as privacy risks. The input is image data, and the output is a list of identified privacy-related information.

[0450] Step 3:

[0451] The server modifies the background using a generative AI model (such as a GAN) based on the identified privacy-related information. The generative AI model is given image data containing privacy information and its location information as input, and based on this, it masks the privacy-related information while maintaining a natural appearance. The output is the modified, visually consistent image data.

[0452] Step 4:

[0453] The processed image data is sent from the server to the terminal. The user reviews this modified image and makes further adjustments as needed. The final image data is ready for use on social media, online shopping review pages, etc. The input is the modified image data, and the output is the image after the user's final review.

[0454] Step 5:

[0455] Users can confidently post modified images to online platforms. In this step, users ensure their privacy is securely protected when publishing images and sharing content. The output is a published image, and the risk of privacy violations is reduced throughout this process.

[0456] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0457] This invention provides a system that enables more personalized image processing by naturally altering identifiable information contained in the background of images shared by users, and further reflecting the user's emotions. When a user selects an image using a communication terminal, the emotion engine analyzes the image along with the user's current emotional information. This emotion engine analyzes data indicating emotions, such as the user's facial expressions and tone of voice, to recognize the user's emotional state.

[0458] The device sends the selected image data to the server, along with the results of the emotion engine's analysis. The server inputs the image into an AI-based analysis system, which uses object detection algorithms to detect identifiable information elements in the background.

[0459] The server, having received emotional information from the emotion engine, incorporates this information when processing the background. Using a generative adversarial network, it modifies the recognized information elements, reflecting the user's emotions in terms of color scheme and design in the background. For example, if the user is expressing enjoyment, bright colors and friendly design elements can be adopted.

[0460] The edited image, with a personalized background reflecting the user's emotions, is sent back to the user's device. The user can then review this image and, if satisfied, safely post it to social media or other platforms.

[0461] This system not only protects users' privacy but also allows them to share unique images with visual effects that match their emotions, thereby improving the quality of digital communication.

[0462] The following describes the processing flow.

[0463] Step 1:

[0464] Users select images they want to post using their communication device. The device offers options to choose images from its camera app or gallery. After selecting an image, users can use the camera to record their current facial expressions and voice.

[0465] Step 2:

[0466] The device sends selected image data and user facial expression and voice data to the server. The HTTPS protocol is used for secure data transfer.

[0467] Step 3:

[0468] The server inputs the received image data into an AI analysis engine and uses an object detection algorithm to detect identifiable information elements within the image. These elements include specific landmarks and address information.

[0469] Step 4:

[0470] Simultaneously, the server inputs the received user's facial expressions and voice data into the emotion engine, which analyzes the user's emotional state. The emotion engine analyzes changes in facial expressions and tone of voice to identify the user's current emotion.

[0471] Step 5:

[0472] The server uses a generative adversarial network to process the background based on the identified information elements. During this process, emotional information obtained from the emotion engine is reflected in the background's color and design. For example, if the emotion of joy is recognized, the background will be constructed with bright colors.

[0473] Step 6:

[0474] The server generates a new image processed based on emotions and sends that data to the device. The generated image is adjusted to maintain a consistent and natural appearance.

[0475] Step 7:

[0476] The device displays the processed image to the user and prompts them for final confirmation. The user can review the image and make minor adjustments as needed.

[0477] Step 8:

[0478] Users then post the finalized images to social media and other online platforms. This ensures that users' privacy is protected and allows them to share images that reflect their emotions.

[0479] (Example 2)

[0480] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0481] In image sharing, there is a need to create visual data with unique and personalized visual effects that reflect users' emotions while protecting user privacy. However, conventional technologies have faced the challenge of making natural background modifications based on the emotions of individual users.

[0482] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0483] In this invention, the server includes means for analyzing visual data received from an information processing device and detecting identifiable information contained in the background; means for an emotion analysis engine to analyze the user's emotions based on the identified information; and means for modifying the identified information and altering the background in a natural way that incorporates the user's emotional information using a generative AI model. This makes it possible to naturally modify the background of the visual data in a way that is tailored to the individual user while reflecting the user's emotions.

[0484] An "information processing device" is an electronic device with communication functions operated by a user, which performs image selection and emotion analysis.

[0485] "Visual data" refers to all image data acquired by a user using an information processing device, and includes digital information such as backgrounds and identifiable information.

[0486] An "emotion analysis engine" is a collection of software and hardware used to analyze a user's emotional state from their facial expressions and tone of voice.

[0487] "Identifiable information" refers to objects or elements present in an image that can be identified or detected, including dynamic data located in the background.

[0488] A "generative AI model" is a collection of algorithms that use artificial intelligence technology to modify or generate data, and in particular refers to methods that include generative adversarial networks.

[0489] A "generative adversarial network" is a technique in which two networks, one for generating and the other for identifying, learn while competing with each other during image generation and modification, enabling the generation of more realistic images.

[0490] This invention is a system that uses visual data captured or selected by the user to naturally modify the background to match the user's personal feelings while protecting their privacy. Specifically, it is configured as follows:

[0491] The user uses an information processing device, which is a communication terminal, to select visual data from either the camera or storage. This visual data is analyzed by an emotion analysis engine built into the terminal to reflect the user's current emotional state. This emotion analysis engine is software that detects the user's facial expressions and tone of voice, and identifies the user's emotions through an analysis algorithm.

[0492] The analysis results and visual data are sent from the information processing device to the server. The server passes the visual data to an AI-based analysis system, which uses object recognition algorithms to extract identifiable information contained in the background. This includes identifiable objects and textual information.

[0493] Next, the server uses a generative AI model, particularly a generative adversarial network (GAN), to modify the extracted identifiable information based on the user's emotions. In this process, it references information from the emotion analysis engine and applies colors and designs to the background that match the user's emotions. For example, if the user is feeling happy, the background can reflect bright colors and a colorful design.

[0494] The modified visual data is sent back to the information processing device, where the user performs a final check. If the user is satisfied with the processing, they can share this personalized modified image on platforms such as social media.

[0495] As a concrete example, a text-based prompt such as "naturally enhance a smiling selfie and change the background to a brighter one" is input to the model. This system allows users to easily utilize visual effects optimized for their individual emotions to improve digital communication.

[0496] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0497] Step 1:

[0498] The user selects visual data on the information processing device. Specifically, the user operates the device's photo app and selects the visual data they want to process from their gallery or captured images by tapping it. The input for this operation is the user's instruction, and the output is the selected visual data.

[0499] Step 2:

[0500] The device analyzes the user's emotions using an emotion analysis engine. The device uses a camera and microphone to capture the user's facial expressions and voice, and the emotion analysis algorithm analyzes this data. Specifically, it uses image recognition technology to extract features such as smiles, wrinkles, and voice tone to identify the user's emotional state. The input to this module is the user's voice and video data, and the output is the analyzed emotion information.

[0501] Step 3:

[0502] The terminal sends the selected visual data and analyzed sentiment information to the server. Specifically, this involves packaging the data and sending it to the server via a secure communication protocol. The input is the selected visual data and sentiment information, and the output is the data received by the server.

[0503] Step 4:

[0504] The server inputs visual data into an AI-based analysis system to detect identifiable information. The server uses object recognition algorithms to extract identifiable elements such as text and landmarks from the image. The input is the received visual data, and the output is the detected identifiable information.

[0505] Step 5:

[0506] The server utilizes a Generative Adversarial Network (GAN) to modify visual data using detected information and sentiment data. Specifically, it uses GANs to add color and design to the background and generate visual effects that match the user's emotions. The input is detected identification information and sentiment data, and the output is the modified visual data.

[0507] Step 6:

[0508] The modified visual data is sent back to the terminal. The server then transmits the generated data again via a secure communication protocol, and the user is notified of the result on the terminal. The input is the modified visual data, and the output is the final visual data presented to the user on the terminal.

[0509] (Application Example 2)

[0510] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0511] In recent years, advertising displays and experiences based on the individual emotional states of visitors have begun to be emphasized in commercial facilities and retail settings. However, with current technology, it is difficult to accurately grasp visitors' emotions in real time and display personalized, dynamic advertising content accordingly. This presents a technical challenge in achieving emotionally resonant advertising displays for individual visitors.

[0512] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0513] In this invention, the server includes means for analyzing visual information received from a communication device and identifying identifiable information components contained in the background; means for modifying the identified information components and processing the background in a natural way using a machine learning algorithm; and means for analyzing the user's emotional state and personalizing the advertisement content and design based on the analysis results. This enables the display of dynamic and personalized advertisements that respond to the visitor's emotional state.

[0514] "Communication equipment" refers to hardware or software used to send and receive data from external sources.

[0515] "Visual information" refers to information that is perceived visually, such as image data.

[0516] "Analysis" refers to the process of breaking down data and information to understand their meaning and structure.

[0517] "Background" refers to the parts of an image or visual information other than the main subject.

[0518] "Identifiable information elements" refer to objects or features that can be identified within images or visual data.

[0519] A "machine learning algorithm" refers to a method for learning patterns from large amounts of data and predicting or classifying information.

[0520] "User's emotional state" refers to the emotions the user is experiencing at that moment, inferred from their facial expressions, voice, body language, etc.

[0521] "Personalization" refers to adjusting or customizing content to suit the individual user's characteristics and preferences.

[0522] "Advertising content and design" refers to the visuals and messages displayed to promote products or services to viewers.

[0523] The system for implementing this invention aims to analyze visual information in real time and personalize advertisements according to the user's emotional state. The system mainly consists of a communication device, a server, an emotion analysis engine, an image analysis system, and a generative adversarial network. The communication device is responsible for receiving data from external sources.

[0524] The server receives visual information transmitted from the communication device and uses object detection algorithms to identify identifiable informational elements contained in the background. It also utilizes machine learning algorithms to process the background in a natural way. Generative Adversarial Networks (GANs) are used to process the background, generating natural and engaging visuals.

[0525] Emotion analysis is performed based on the user's facial expressions and voice data, and is analyzed via an emotion engine. The emotion engine uses tools such as the Microsoft Azure Emotion API to analyze the user's emotional state and personalize ad content and design to suit the user.

[0526] For example, if the server analyzes the visual information it receives and the user indicates positive emotions, the generated ad will be adjusted to include colorful and positive messages. This is to improve the user experience and enhance the appeal of the ad.

[0527] An example of a prompt would be, "This customer is currently in a happy emotional state. Generate an advertising image that attractively showcases the latest tennis shoes using bright colors and a positive atmosphere." This allows the generative AI model to generate appropriate visuals based on the user's emotional state.

[0528] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0529] Step 1:

[0530] The communication device acquires the user's visual and audio data. Using a camera and microphone, it records the user's facial expressions and voice tone, and transmits this data to the server. The input is visual and audio data, and the output is raw data transferred to the server.

[0531] Step 2:

[0532] The server analyzes the received visual information using an object detection algorithm to identify identifiable information elements in the background. The input is raw data, and digital elements are identified by an image analysis system (e.g., TensorFlow or OpenCV). The output is a dataset containing the identified identifiable information elements.

[0533] Step 3:

[0534] The server uses voice data from the user and an emotion engine to analyze the emotional state. This engine can utilize services such as the Microsoft Azure Emotion API. The input is voice data, and the output is information indicating the corresponding emotional state.

[0535] Step 4:

[0536] Based on the analysis results, the server modifies the identifiable informational elements of the background through machine learning algorithms. A generative adversarial network (GAN) is used to generate natural-looking visuals that are appropriate to the user's emotional state. The input is the analyzed dataset and emotional information, and the output is the processed image data.

[0537] Step 5:

[0538] The server personalizes the processed visual information into ad content that corresponds to the user's emotional state, generating the final ad visual. By inputting prompt text into the generating AI model, the ad image is adjusted to match the user's specific emotions. The input is processed visual information, and the output is a personalized ad visual.

[0539] Step 6:

[0540] The server transmits personalized advertising visuals to the communication device. The input is the personalized advertising visual, and the output is the final advertising image displayed on the communication device.

[0541] This series of processes generates personalized advertisements in real time that respond to the user's emotions, providing an optimal visual experience.

[0542] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0543] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0544] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0545] [Fourth Embodiment]

[0546] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0547] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0548] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0549] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0550] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0551] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0552] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0553] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0554] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0555] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0556] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0557] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0558] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0559] This invention provides a system that enhances privacy protection by naturally altering identifiable information contained in the background of images shared by users on the internet. This system has the function of preventing others from determining the user's location by transmitting image data from the user's communication terminal to a server and altering specific background information in the process.

[0560] When a user selects an image on their device, the device sends the image to a server via the network. The server inputs the received image into an artificial intelligence system based on machine learning. This AI system uses object detection algorithms to recognize identifiable information elements in the image, such as landmarks and signs.

[0561] For identified informational elements, the server utilizes generative adversarial network (PAD) technology to process the background in a natural way. This process removes or alters privacy-related information from the original image while maintaining a visually natural appearance.

[0562] For example, if a user takes a photo at a famous tourist spot and a landmark is visible in the background, the server will transform that landmark into a more general building or landscape. During this process, visual elements such as color and lighting are also adjusted to maintain consistency.

[0563] The processed image is then sent back to the user's device, allowing the user to confidently post this image to social media or other platforms. As described above, the present invention provides users with a secure means of digital communication while reducing the privacy risks associated with image sharing.

[0564] The following describes the processing flow.

[0565] Step 1:

[0566] The device allows the user to select the image they want to post. The user chooses an image from their device's internal storage or camera app and prepares it for posting.

[0567] Step 2:

[0568] The terminal sends the selected image data to the server. HTTP or HTTPS is used as the communication protocol to securely transfer the image data.

[0569] Step 3:

[0570] The server inputs the received image data into an AI-based analysis engine for analysis. Here, object detection algorithms are used to automatically detect identifiable information elements within the image.

[0571] Step 4:

[0572] The server selects elements from the identified information that could lead to location identification and begins background processing to modify those elements. It utilizes generative adversarial networks to replace these elements in a natural way. For example, it can alter building shapes or textual information to make location identification more difficult.

[0573] Step 5:

[0574] The server generates a new, processed image. During this process, it also adjusts the overall color tone and lighting to maintain a consistent and natural appearance.

[0575] Step 6:

[0576] The server then sends the processed image back to the user's device. After transmission, the user makes a final check of the image, and it is ready to be posted to social media.

[0577] Step 7:

[0578] Users post edited images to social media and online platforms. This reduces the risk of location identification for third parties and allows content to be shared while protecting privacy.

[0579] (Example 1)

[0580] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0581] When visual data is shared over the internet, identifiable information contained in the background can pose a privacy risk. The challenge lies in developing technologies that modify information in a more natural way to reduce the risk of location information and personally identifiable elements being leaked.

[0582] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0583] In this invention, the server includes means for analyzing visual data received from an information processing device and identifying identifiable information elements contained in the background; means for generating commands to modify the identified information elements and processing the background in a natural manner using generative AI technology; and means for transmitting the processed visual data to the information processing device. This makes it possible to naturally modify information while protecting privacy when sharing visual data.

[0584] An "information processing device" is a general term for electronic devices that can receive and transmit data, and perform analysis and processing.

[0585] "Visual data" is a general term for data that contains information that can be displayed visually, such as still images and videos.

[0586] A "server" is a central device that communicates with information processing devices via a network and performs data analysis and processing.

[0587] "Identifiable information elements" are elements present in visual data that allow for the recognition of specific locations or objects.

[0588] "Generative AI technology" is a part of artificial intelligence technology and is a general term for methods that generate new data based on input data.

[0589] A "generative rival network" is a technique that aims to generate data naturally by constructing both a generative network and a discriminative network, and then training them in a rivalry.

[0590] This invention provides an embodiment for securely sharing visual data captured by users using an information processing device. Specifically, it realizes a system that protects privacy by detecting identifiable information elements contained in visual data and modifying them using generation AI technology.

[0591] Users select visual data on information processing devices such as smartphones and computers and send that visual data to a server over a network. This process is securely conducted via the HTTP or HTTPS protocol. The server analyzes the received visual data using object recognition methods that utilize deep learning frameworks such as TensorFlow and PyTorch. These object recognition methods employ algorithms such as YOLO and Faster R-CNN to detect landmarks and identifiable information elements within the visual data.

[0592] For detected information elements, the server uses generative AI technology to form modification instructions. Specifically, generative counter-network (GAN) technology is used. The generative network proposes natural modifications to the visual data, and the discriminative network evaluates their naturalness. This process is repeated until the modified visual data is deemed natural.

[0593] For example, if a user takes an image at a specific tourist destination that includes a famous landmark, this invention can be used to replace that landmark with a more typical background landscape. The lighting conditions and colors are adjusted to match the original data, resulting in a natural-looking image without any noticeable inconsistencies.

[0594] The modified visual data is returned from the server to the information processing device, and the user can confidently post this data to digital platforms such as social media. An example of a prompt might be a command such as, "Naturally remove a specific landmark from this image and replace it with other common scenery." The generative AI model performs the modification via this prompt.

[0595] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0596] Step 1:

[0597] The user selects the visual data they want to modify on their device. This visual data is often captured with a digital camera or smartphone. After selection, the device sends this visual data to the server via the HTTP or HTTPS protocol. The input data is a raw visual file (e.g., JPEG, PNG format), and the output is the visual data securely transferred to the server.

[0598] Step 2:

[0599] The server analyzes the received visual data. Specifically, it inputs the visual data into an object recognition model based on TensorFlow or PyTorch. Using algorithms such as YOLO or Faster R-CNN, it identifies identifiable information elements such as landmarks and signs within the visual data. The input is the received visual data, and the output is a list of identifiable information elements.

[0600] Step 3:

[0601] The server generates instructions to modify the identified information elements. For example, it might generate a prompt such as, "Replace background landmarks with common scenery." This prompt is then used as input to the generative AI model. The input is a list of identified information elements, and the output is a prompt for the generative AI model.

[0602] Step 4:

[0603] The server uses a Generative Counter-Network (GAN) to modify visual data. The generative network proposes a new background, and the discriminative network evaluates its naturalness; this process is repeated. The input consists of modification instructions and the original visual data, and the output is visual data modified to appear natural. Through this process, landmarks and other elements are replaced with more typical landscapes.

[0604] Step 5:

[0605] The server sends the modified visual data back to the original device. Users can then confidently share this modified visual data on social media and other platforms. The input data is the modified visual data, and the output is the modified data securely sent back to the user's device. This process allows users to engage in digital communication with reduced privacy risks.

[0606] (Application Example 1)

[0607] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0608] Images shared on the internet may contain information related to the poster's location and privacy. This can threaten individual safety and privacy, so technologies to mitigate this risk are needed. Furthermore, methods are required to easily modify transmitted images and return them to the server in a visually accurate form.

[0609] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0610] In this invention, the server includes means for analyzing image data captured by a camera and identifying privacy-related information contained in the background; means for modifying the identified information and processing the background in a visually consistent manner using machine learning; and means for providing the processed image to a communication terminal and supporting user posting. This enables users to share images on the internet with peace of mind without the leakage of personal information.

[0611] "Photography equipment" refers to electronic devices used to acquire image data, mainly including smartphones and digital cameras.

[0612] "Image data" refers to a collection of visual information acquired using photographic equipment, which is stored or transmitted in digital format.

[0613] "Privacy-related information" refers to information that contains an individual's location or other identifiable information within image data, which may affect an individual's safety or privacy.

[0614] Machine learning is a technique that learns patterns from data and applies those patterns to new data. It is an artificial intelligence technology used in areas such as image recognition and object detection.

[0615] "Visually consistent form" refers to a state where the modification of an image is natural and the light and color characteristics of the original image are preserved.

[0616] A "communication terminal" is a device that sends and receives data over a network, and generally includes smartphones and tablets.

[0617] This invention begins with the user transmitting image data acquired using a camera to a server via a communication network. The server analyzes the received image data and identifies privacy-related information contained in the background. This employs image recognition techniques widely used as object recognition algorithms. Specifically, it uses machine learning libraries such as TensorFlow and OpenCV.

[0618] For privacy-related information identified by the server, machine learning is used to modify the background in a visually consistent manner. This modification utilizes generative AI models, such as TensorFlow and Keras. A specific example is a Generative Adversarial Network (GAN). This process allows for natural background changes without disrupting the user's intended content.

[0619] The processed image data is sent back to the communication terminal, allowing users to securely post these images to online platforms and communication services. Users can gain peace of mind knowing they can publish images taken at any location without their personal information being leaked. For example, when a user posts a photo of a product taken at home, the image can be processed so that the interior of their home is not visible in the background.

[0620] An example of a prompt message might be, "Detect any address-identifying information contained in the background and replace it with a generic wallpaper pattern." This allows for complete privacy protection while maintaining the image's appearance.

[0621] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0622] Step 1:

[0623] The user uses a camera to acquire image data and sends that image from the terminal to the server. This input image data includes information about the product and its background. The user selects images and specifies options for protecting privacy.

[0624] Step 2:

[0625] The server analyzes the received image data. At this stage, it applies image recognition algorithms to identify privacy-related information contained in the background. This process uses TensorFlow and OpenCV to detect image landmarks, text, etc., and considers them as privacy risks. The input is image data, and the output is a list of identified privacy-related information.

[0626] Step 3:

[0627] The server modifies the background using a generative AI model (such as a GAN) based on the identified privacy-related information. The generative AI model is given image data containing privacy information and its location information as input, and based on this, it masks the privacy-related information while maintaining a natural appearance. The output is the modified, visually consistent image data.

[0628] Step 4:

[0629] The processed image data is sent from the server to the terminal. The user reviews this modified image and makes further adjustments as needed. The final image data is ready for use on social media, online shopping review pages, etc. The input is the modified image data, and the output is the image after the user's final review.

[0630] Step 5:

[0631] Users can confidently post modified images to online platforms. In this step, users ensure their privacy is securely protected when publishing images and sharing content. The output is a published image, and the risk of privacy violations is reduced throughout this process.

[0632] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0633] This invention provides a system that enables more personalized image processing by naturally altering identifiable information contained in the background of images shared by users, and further reflecting the user's emotions. When a user selects an image using a communication terminal, the emotion engine analyzes the image along with the user's current emotional information. This emotion engine analyzes data indicating emotions, such as the user's facial expressions and tone of voice, to recognize the user's emotional state.

[0634] The device sends the selected image data to the server, along with the results of the emotion engine's analysis. The server inputs the image into an AI-based analysis system, which uses object detection algorithms to detect identifiable information elements in the background.

[0635] The server, having received emotional information from the emotion engine, incorporates this information when processing the background. Using a generative adversarial network, it modifies the recognized information elements, reflecting the user's emotions in terms of color scheme and design in the background. For example, if the user is expressing enjoyment, bright colors and friendly design elements can be adopted.

[0636] The edited image, with a personalized background reflecting the user's emotions, is sent back to the user's device. The user can then review this image and, if satisfied, safely post it to social media or other platforms.

[0637] This system not only protects users' privacy but also allows them to share unique images with visual effects that match their emotions, thereby improving the quality of digital communication.

[0638] The following describes the processing flow.

[0639] Step 1:

[0640] Users select images they want to post using their communication device. The device offers options to choose images from its camera app or gallery. After selecting an image, users can use the camera to record their current facial expressions and voice.

[0641] Step 2:

[0642] The device sends selected image data and user facial expression and voice data to the server. The HTTPS protocol is used for secure data transfer.

[0643] Step 3:

[0644] The server inputs the received image data into an AI analysis engine and uses an object detection algorithm to detect identifiable information elements within the image. These elements include specific landmarks and address information.

[0645] Step 4:

[0646] Simultaneously, the server inputs the received user's facial expressions and voice data into the emotion engine, which analyzes the user's emotional state. The emotion engine analyzes changes in facial expressions and tone of voice to identify the user's current emotion.

[0647] Step 5:

[0648] The server uses a generative adversarial network to process the background based on the identified information elements. During this process, emotional information obtained from the emotion engine is reflected in the background's color and design. For example, if the emotion of joy is recognized, the background will be constructed with bright colors.

[0649] Step 6:

[0650] The server generates a new image processed based on emotions and sends that data to the device. The generated image is adjusted to maintain a consistent and natural appearance.

[0651] Step 7:

[0652] The device displays the processed image to the user and prompts them for final confirmation. The user can review the image and make minor adjustments as needed.

[0653] Step 8:

[0654] Users then post the finalized images to social media and other online platforms. This ensures that users' privacy is protected and allows them to share images that reflect their emotions.

[0655] (Example 2)

[0656] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0657] In image sharing, there is a need to create visual data with unique and personalized visual effects that reflect users' emotions while protecting user privacy. However, conventional technologies have faced the challenge of making natural background modifications based on the emotions of individual users.

[0658] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0659] In this invention, the server includes means for analyzing visual data received from an information processing device and detecting identifiable information contained in the background; means for an emotion analysis engine to analyze the user's emotions based on the identified information; and means for modifying the identified information and altering the background in a natural way that incorporates the user's emotional information using a generative AI model. This makes it possible to naturally modify the background of the visual data in a way that is tailored to the individual user while reflecting the user's emotions.

[0660] An "information processing device" is an electronic device with communication functions operated by a user, which performs image selection and emotion analysis.

[0661] "Visual data" refers to all image data acquired by a user using an information processing device, and includes digital information such as backgrounds and identifiable information.

[0662] An "emotion analysis engine" is a collection of software and hardware used to analyze a user's emotional state from their facial expressions and tone of voice.

[0663] "Identifiable information" refers to objects or elements present in an image that can be identified or detected, including dynamic data located in the background.

[0664] A "generative AI model" is a collection of algorithms that use artificial intelligence technology to modify or generate data, and in particular refers to methods that include generative adversarial networks.

[0665] A "generative adversarial network" is a technique in which two networks, one for generating and the other for identifying, learn while competing with each other during image generation and modification, enabling the generation of more realistic images.

[0666] This invention is a system that uses visual data captured or selected by the user to naturally modify the background to match the user's personal feelings while protecting their privacy. Specifically, it is configured as follows:

[0667] The user uses an information processing device, which is a communication terminal, to select visual data from either the camera or storage. This visual data is analyzed by an emotion analysis engine built into the terminal to reflect the user's current emotional state. This emotion analysis engine is software that detects the user's facial expressions and tone of voice, and identifies the user's emotions through an analysis algorithm.

[0668] The analysis results and visual data are sent from the information processing device to the server. The server passes the visual data to an AI-based analysis system, which uses object recognition algorithms to extract identifiable information contained in the background. This includes identifiable objects and textual information.

[0669] Next, the server uses a generative AI model, particularly a generative adversarial network (GAN), to modify the extracted identifiable information based on the user's emotions. In this process, it references information from the emotion analysis engine and applies colors and designs to the background that match the user's emotions. For example, if the user is feeling happy, the background can reflect bright colors and a colorful design.

[0670] The modified visual data is sent back to the information processing device, where the user performs a final check. If the user is satisfied with the processing, they can share this personalized modified image on platforms such as social media.

[0671] As a concrete example, a text-based prompt such as "naturally enhance a smiling selfie and change the background to a brighter one" is input to the model. This system allows users to easily utilize visual effects optimized for their individual emotions to improve digital communication.

[0672] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0673] Step 1:

[0674] The user selects visual data on the information processing device. Specifically, the user operates the device's photo app and selects the visual data they want to process from their gallery or captured images by tapping it. The input for this operation is the user's instruction, and the output is the selected visual data.

[0675] Step 2:

[0676] The device analyzes the user's emotions using an emotion analysis engine. The device uses a camera and microphone to capture the user's facial expressions and voice, and the emotion analysis algorithm analyzes this data. Specifically, it uses image recognition technology to extract features such as smiles, wrinkles, and voice tone to identify the user's emotional state. The input to this module is the user's voice and video data, and the output is the analyzed emotion information.

[0677] Step 3:

[0678] The terminal sends the selected visual data and analyzed sentiment information to the server. Specifically, this involves packaging the data and sending it to the server via a secure communication protocol. The input is the selected visual data and sentiment information, and the output is the data received by the server.

[0679] Step 4:

[0680] The server inputs visual data into an AI-based analysis system to detect identifiable information. The server uses object recognition algorithms to extract identifiable elements such as text and landmarks from the image. The input is the received visual data, and the output is the detected identifiable information.

[0681] Step 5:

[0682] The server utilizes a Generative Adversarial Network (GAN) to modify visual data using detected information and sentiment data. Specifically, it uses GANs to add color and design to the background and generate visual effects that match the user's emotions. The input is detected identification information and sentiment data, and the output is the modified visual data.

[0683] Step 6:

[0684] The modified visual data is sent back to the terminal. The server then transmits the generated data again via a secure communication protocol, and the user is notified of the result on the terminal. The input is the modified visual data, and the output is the final visual data presented to the user on the terminal.

[0685] (Application Example 2)

[0686] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0687] In recent years, advertising displays and experiences based on the individual emotional states of visitors have begun to be emphasized in commercial facilities and retail settings. However, with current technology, it is difficult to accurately grasp visitors' emotions in real time and display personalized, dynamic advertising content accordingly. This presents a technical challenge in achieving emotionally resonant advertising displays for individual visitors.

[0688] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0689] In this invention, the server includes means for analyzing visual information received from a communication device and identifying identifiable information components contained in the background; means for modifying the identified information components and processing the background in a natural way using a machine learning algorithm; and means for analyzing the user's emotional state and personalizing the advertisement content and design based on the analysis results. This enables the display of dynamic and personalized advertisements that respond to the visitor's emotional state.

[0690] "Communication equipment" refers to hardware or software used to send and receive data from external sources.

[0691] "Visual information" refers to information that is perceived visually, such as image data.

[0692] "Analysis" refers to the process of breaking down data and information to understand their meaning and structure.

[0693] "Background" refers to the parts of an image or visual information other than the main subject.

[0694] "Identifiable information elements" refer to objects or features that can be identified within images or visual data.

[0695] A "machine learning algorithm" refers to a method for learning patterns from large amounts of data and predicting or classifying information.

[0696] "User's emotional state" refers to the emotions the user is experiencing at that moment, inferred from their facial expressions, voice, body language, etc.

[0697] "Personalization" refers to adjusting or customizing content to suit the individual user's characteristics and preferences.

[0698] "Advertising content and design" refers to the visuals and messages displayed to promote products or services to viewers.

[0699] The system for implementing this invention aims to analyze visual information in real time and personalize advertisements according to the user's emotional state. The system mainly consists of a communication device, a server, an emotion analysis engine, an image analysis system, and a generative adversarial network. The communication device is responsible for receiving data from external sources.

[0700] The server receives visual information transmitted from the communication device and uses object detection algorithms to identify identifiable informational elements contained in the background. It also utilizes machine learning algorithms to process the background in a natural way. Generative Adversarial Networks (GANs) are used to process the background, generating natural and engaging visuals.

[0701] Emotion analysis is performed based on the user's facial expressions and voice data, and is analyzed via an emotion engine. The emotion engine uses tools such as the Microsoft Azure Emotion API to analyze the user's emotional state and personalize ad content and design to suit the user.

[0702] For example, if the server analyzes the visual information it receives and the user indicates positive emotions, the generated ad will be adjusted to include colorful and positive messages. This is to improve the user experience and enhance the appeal of the ad.

[0703] An example of a prompt would be, "This customer is currently in a happy emotional state. Generate an advertising image that attractively showcases the latest tennis shoes using bright colors and a positive atmosphere." This allows the generative AI model to generate appropriate visuals based on the user's emotional state.

[0704] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0705] Step 1:

[0706] The communication device acquires the user's visual and audio data. Using a camera and microphone, it records the user's facial expressions and voice tone, and transmits this data to the server. The input is visual and audio data, and the output is raw data transferred to the server.

[0707] Step 2:

[0708] The server analyzes the received visual information using an object detection algorithm to identify identifiable information elements in the background. The input is raw data, and digital elements are identified by an image analysis system (e.g., TensorFlow or OpenCV). The output is a dataset containing the identified identifiable information elements.

[0709] Step 3:

[0710] The server uses voice data from the user and an emotion engine to analyze the emotional state. This engine can utilize services such as the Microsoft Azure Emotion API. The input is voice data, and the output is information indicating the corresponding emotional state.

[0711] Step 4:

[0712] Based on the analysis results, the server modifies the identifiable informational elements of the background through machine learning algorithms. A generative adversarial network (GAN) is used to generate natural-looking visuals that are appropriate to the user's emotional state. The input is the analyzed dataset and emotional information, and the output is the processed image data.

[0713] Step 5:

[0714] The server personalizes the processed visual information into ad content that corresponds to the user's emotional state, generating the final ad visual. By inputting prompt text into the generating AI model, the ad image is adjusted to match the user's specific emotions. The input is processed visual information, and the output is a personalized ad visual.

[0715] Step 6:

[0716] The server transmits personalized advertising visuals to the communication device. The input is the personalized advertising visual, and the output is the final advertising image displayed on the communication device.

[0717] This series of processes generates personalized advertisements in real time that respond to the user's emotions, providing an optimal visual experience.

[0718] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0719] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0720] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0721] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0722] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0723] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0724] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0725] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0726] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0727] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0728] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0729] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0730] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0731] 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.

[0732] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0733] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0734] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0735] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0736] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0737] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0738] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0739] The following is further disclosed regarding the embodiments described above.

[0740] (Claim 1)

[0741] A means for analyzing image data received from a communication terminal and identifying identifiable information elements contained in the background,

[0742] A means of modifying identified information elements and processing the background in a natural way using artificial intelligence,

[0743] A means for transmitting processed image data to a communication terminal,

[0744] A system that includes this.

[0745] (Claim 2)

[0746] The system according to claim 1, which uses an object detection algorithm when identifying information elements.

[0747] (Claim 3)

[0748] The system according to claim 1, which uses a generative adversarial network when processing the background.

[0749] "Example 1"

[0750] (Claim 1)

[0751] A means for analyzing visual data received from an information processing device and identifying identifiable information elements contained in the background,

[0752] A means for generating instructions to modify identified information elements and processing the background in a natural way using generative AI technology,

[0753] A means for transmitting processed visual data to an information processing device,

[0754] A system that includes this.

[0755] (Claim 2)

[0756] The system according to claim 1, which uses an object recognition method when identifying information elements.

[0757] (Claim 3)

[0758] The system according to claim 1, which uses a generative counter-network when processing the background.

[0759] "Application Example 1"

[0760] (Claim 1)

[0761] A means of analyzing image data captured by a camera to identify privacy-related information contained in the background,

[0762] A method for modifying identified information and processing the background in a visually consistent manner using machine learning,

[0763] A means of providing processed images to communication terminals to support user submissions,

[0764] A system that includes this.

[0765] (Claim 2)

[0766] The system according to claim 1, which uses an image recognition algorithm when identifying privacy-related information.

[0767] (Claim 3)

[0768] The system according to claim 1, which uses a generative model when processing the background in a visually consistent manner.

[0769] "Example 2 of combining an emotion engine"

[0770] (Claim 1)

[0771] A means for analyzing visual data received from an information processing device and detecting identifiable information contained in the background,

[0772] Based on the identified information, the emotion analysis engine provides a means for analyzing the user's emotions,

[0773] A means of modifying the background in a natural way by changing identified information and incorporating the user's emotional information using a generative AI model,

[0774] Means for transmitting modified visual data to an information processing device,

[0775] A system that includes this.

[0776] (Claim 2)

[0777] The system according to claim 1, which applies an object recognition algorithm when identifying information.

[0778] (Claim 3)

[0779] The system according to claim 1, which utilizes a generated adversarial network when modifying the background.

[0780] "Application example 2 when combining with an emotional engine"

[0781] (Claim 1)

[0782] A means for analyzing visual information received from a communication device and identifying identifiable information components contained in the background,

[0783] A means of modifying identified informational elements and processing the background in a natural way using a machine learning algorithm,

[0784] A means of analyzing the user's emotional state and personalizing ad content and design based on the analysis results,

[0785] Means for transmitting processed and personalized visual information to a communication device,

[0786] A system that includes this.

[0787] (Claim 2)

[0788] The system according to claim 1, which uses an object detection algorithm when identifying information components.

[0789] (Claim 3)

[0790] The system according to claim 1, which uses a generative adversarial network when processing the background. [Explanation of symbols]

[0791] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for analyzing image data received from a communication terminal and identifying identifiable information elements contained in the background, A means of modifying identified information elements and processing the background in a natural way using artificial intelligence, A means for transmitting processed image data to a communication terminal, A system that includes this.

2. The system according to claim 1, which uses an object detection algorithm when identifying information elements.

3. The system according to claim 1, which uses a generative adversarial network when processing the background.

Images