System

Abstract

A system is provided.SOLUTION: Means for uploading an image by a user, means for extracting location information from Exif information of the uploaded image by a terminal, means for transmitting the location information extracted by the terminal to a server, means for acquiring address information by a reverse geocoder using the location information by the server, means for searching for landscape data related to an area based on the address information acquired by the server, means for generating an image generation AI model that learns the landscape data of the area by the server, means for generating an area-specific image by the server using the learned model, and means for transmitting the image generated by the server to the terminal. The system where the terminal includes means for displaying the transmitted image to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Current image generation AI systems have difficulty generating landscape images that accurately reflect specific regional information, resulting in the generation of "scenes that look like they've been seen somewhere before, but are nowhere." When users require realistic landscape images of a specific region, current technology is insufficient in a wide range of fields, including film production, travel promotion, and educational materials. Furthermore, the compatibility between the AI's training data and the generated images is low, often resulting in a lack of the region-specific information desired by the user. The present invention aims to solve these problems. [Means for solving the problem]

[0005] The present invention is a system that can generate realistic landscape images that accurately reflect region-specific information by using a means that includes: a means for a user to upload an image; a means for a terminal to extract Exif information from the image and obtain location information (latitude and longitude); a means for the server to obtain address information using a reverse geocoder based on the location information; a means for searching a database for landscape data related to the region based on the obtained address information; a means that includes an image generation AI model that learns the searched landscape data; a means for generating region-specific images using the learned AI model; a means for sending the generated images to the user's terminal; and a means for displaying the sent images to the user.

[0006] A "user" is a person who uses the system to upload images and generate landscape images specific to a region.

[0007] A "terminal" is a computing device through which a user uploads images, extracts Exif information, and transmits it to a server.

[0008] "Exif information" is data embedded in images taken with a digital camera or smartphone, and is metadata that includes, in particular, latitude and longitude information.

[0009] "Location information" refers to latitude and longitude data extracted from Exif information.

[0010] The "server" is a computer system that receives location information sent from a device, calls the reverse geocoder API to obtain address information, and searches and learns data related to the area.

[0011] A "reverse geocoder" is a system or API for converting latitude and longitude location information into address information.

[0012] "Address information" is a specific geographic address obtained from latitude and longitude using a reverse geocoder.

[0013] "Landscape data" is a dataset that contains images and visual features associated with a particular area.

[0014] An "image generation AI model" is an artificial intelligence model that learns landscape data from a specific region and generates landscape images specific to that region.

[0015] A "generated image" is a landscape image generated by an image generation AI model that reflects the unique characteristics of the region.

[0016] A "database" is a structured collection of information that allows the server to store and search regional landscape data. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0025] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0038] The present invention provides an image generation system that allows a user to generate a landscape image of a specific area. Specific embodiments for carrying out the invention will be described below.

[0039] ---

[0040] 1. User interaction and image upload

[0041] User

[0042] The user opens the image upload interface using a device (PC, smartphone, etc.), selects a photo file showing a scene from a specific area, and presses the upload button.

[0043] 2. Extracting and sending location information

[0044] Terminal

[0045] The device analyzes the Exif information from the photo file uploaded by the user to obtain latitude and longitude information. For example, for an image of Paris, the device extracts latitude "48.8566" and longitude "2.3522". The device converts this location information into JSON format and sends it to the server.

[0046] 3. Obtaining address information and searching area data

[0047] server

[0048] The server sends the latitude and longitude information received from the device to a reverse geocoder API (e.g., Google Maps API). The reverse geocoder API returns address information (e.g., "Paris, France") corresponding to the latitude and longitude information. The server then searches and retrieves local landscape data from a database based on the returned address information.

[0049] 4. Image generation AI model training and image generation

[0050] server

[0051] The server uses the acquired regional landscape data as input to train an image generation AI model. Through this training, the model understands the characteristics of Parisian landscapes and reflects these in the images it generates. After the model has completed training, the server generates landscape images specific to the Paris region based on the user's requests.

[0052] 5. Sending and displaying generated images

[0053] server

[0054] The server saves the generated image as an image file and sends it to the terminal as a response.

[0055] Terminal

[0056] The terminal receives the image file sent from the server and displays it on the user interface.

[0057] Specific examples

[0058] For example, consider the case where a user wants to generate a landscape image of Paris, Europe. The user uploads an image of a specific location in Paris to their device. The device extracts the latitude "48.8566" and longitude "2.3522" from the image and sends them to the server. The server uses a reverse geocoder API to obtain the address information "Paris, France" and retrieves landscape data related to Paris from a database. Based on this, the image generation AI model generates an image that recreates the Paris landscape. The generated image is sent to the user's device, where the user can view the realistic Paris landscape image that was generated.

[0059] ---

[0060] In this way, the present invention allows users to generate realistic landscape images of specific areas of their choice, allowing them to create high-quality content that can be used in film production, the travel industry, education, and other fields.

[0061] The processing flow will be explained below.

[0062] Step 1:

[0063] User

[0064] The user opens the image upload interface on the device, selects a photo file showing a scene from a specific area, and presses the upload button.

[0065] Step 2:

[0066] Terminal

[0067] The device analyzes the Exif information of the uploaded photo file and extracts the latitude and longitude information (e.g., latitude 48.8566, longitude 2.3522) from the Exif information.

[0068] Step 3:

[0069] Terminal

[0070] The terminal converts the extracted latitude and longitude information into JSON format and sends it to the server.

[0071] Step 4:

[0072] server

[0073] The server receives the latitude and longitude information from the device and sends it to the reverse geocoder API.

[0074] Step 5:

[0075] server

[0076] Receive the address information (e.g., Paris, France) returned by the reverse geocoder API.

[0077] Step 6:

[0078] server

[0079] The server references an internal database based on the address information and searches for and retrieves landscape data (photos and related feature data) for the relevant area.

[0080] Step 7:

[0081] server

[0082] The server inputs the landscape data of the area it has acquired into an image generation AI model, allowing the model to learn.

[0083] Preprocess the training data (e.g., normalization, data augmentation).

[0084] Formatting image and feature data as input to AI models.

[0085] Step 8:

[0086] server

[0087] The server uses a trained AI model to generate images that reflect the landscape characteristics of the specified area.

[0088] The generation task adds conditional inputs (e.g., season, day / night) to enable highly accurate generation.

[0089] Step 9:

[0090] server

[0091] The server saves the generated image as an image file and transmits it to the terminal as response data.

[0092] Step 10:

[0093] Terminal

[0094] The terminal obtains the response data received from the server, extracts the image file generated from the response data, and displays it on the user interface.

[0095] Step 11:

[0096] User

[0097] The user checks the displayed image and, if necessary, presses the download button to save the image file to their device.

[0098] ---

[0099] In this way, the system of the present invention generates realistic landscape images that reflect the unique characteristics of the area based on the location information of images uploaded by users, which can be used for a variety of purposes, such as filmmaking, travel guides, and educational materials.

[0100] Example 1

[0101] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0102] Conventional image generation systems require manual labor and complex processes to realistically recreate the scenery of a specific region. As a result, users are required to have a high level of technical knowledge and spend a lot of time, making it difficult to generate effective scenery images. Furthermore, existing systems do not fully automate the generation of realistic scenery images, and their accuracy is limited. To solve these problems, a system that allows users to easily generate realistic scenery images of specific regions is needed.

[0103] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0104] In this invention, the server includes: means for a user to upload images; means for a terminal to extract location information from metadata information of the uploaded images; means for the terminal to transmit the extracted location information to the server; means for the server to obtain address information using a reverse geocoder using the location information; means for the server to search for scenery data related to the region based on the obtained address information; means for the server to include an image generation artificial intelligence model that learns scenery data of the searched region; means for the server to generate region-specific images using the learned model; means for the server to transmit the generated images to the terminal; and means for the terminal to display the transmitted images to the user. This enables a user to easily and intuitively generate realistic scenery images of a specific region with high accuracy.

[0105] A "user" is a person or organization that uses the system to upload images and generate scenic images of a particular area.

[0106] A "terminal" is a hardware device, such as a computer or smartphone, used by a user to upload images, extract metadata information, transmit location information, and display generated images.

[0107] "Metadata information" is auxiliary information included in image files, such as Exif information. It records the location where the image was taken (latitude, longitude), the date and time of the photo, and the camera settings.

[0108] An "image generation artificial intelligence model" is a machine learning model trained to generate landscape images of a specific area, and uses deep learning technology to generate images that reflect the characteristics of the landscape.

[0109] A "reverse geocoder" is a tool or program for obtaining corresponding address information based on location information (latitude and longitude).

[0110] The "server" is a computer system that manages the entire system, processes data sent from terminals, performs reverse geocoding, searches for local landscape data, generates images using an image generation artificial intelligence model, and transmits the generated images.

[0111] "Landscape data" refers to images and other visual information related to a particular region that is used as training data for image generation.

[0112] "Address information" refers to a geographical address obtained based on specific location information (latitude and longitude), such as "Paris, France."

[0113] The present invention relates to an image generation system that enables a user to easily generate realistic landscape images of a specific area. Specific embodiments for carrying out the invention will be described below.

[0114] A user opens an image upload interface on their device (PC, smartphone, etc.). This interface is built using HTML and JavaScript. The user selects a photo file showing a scene from a specific area and presses the upload button. This action sends the image file from the device to the server as an HTTP POST request.

[0115] The device analyzes the metadata information (Exif information) from the uploaded photo file and extracts the latitude and longitude information. This analysis is performed using the Python ExifRead library. For example, in the case of an image of Paris, the extracted latitude and longitude information is latitude "48.8566" and longitude "2.3522". The acquired location information is converted to JSON format and sent to the server as an HTTP POST request.

[0116] The server uses the latitude and longitude information received from the device to send a request to a reverse geocoder API (for example, a map service API) and obtain the corresponding address information. The reverse geocoder API returns address information such as "Paris, France" based on the obtained location information. The server then uses this address information to search for and obtain scenery data for the corresponding area from a database. Database management uses MySQL or PostgreSQL.

[0117] The server then uses the acquired local landscape data to train an image-generating artificial intelligence model. Deep learning frameworks such as TensorFlow and PyTorch are used to train the model. Once training is complete, the model will understand the characteristics of Paris' landscapes and reflect them in the next image it generates. The server then generates new Paris landscape images based on user requests.

[0118] The generated image is sent from the server to the device as an HTTP response. Finally, the device displays the received image on the user interface. HTML and JavaScript technologies are used to display the generated image using the img tag.

[0119] For example, if a user executes the prompt "Prepare a landscape image of a specific location in Paris, and generate a landscape image of the corresponding area based on the latitude and longitude information extracted from the Exif information," the user uploads an image of a Paris landscape. The system then automatically executes the specified steps to generate a realistic landscape image of Paris and display it to the user.

[0120] In this way, the present invention enables users to easily generate realistic landscape images of specific areas with high accuracy, allowing users to efficiently create high-quality content that can be used in a variety of fields.

[0121] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0122] System program processing steps

[0123] Step 1: User uploads an image

[0124] The user opens an image upload interface on their device, which is built with HTML and JavaScript.

[0125] The user selects a photo file showing a scene from a specific area and presses the upload button.

[0126] Input: Photo files showing scenery from a specific area.

[0127] Output: Image data sent as an HTTP POST request.

[0128] Step 2: The device analyzes the image metadata and extracts the location information.

[0129] The device parses the metadata information (Exif information) from the uploaded photo file using the ExifRead library.

[0130] The acquired location information (latitude "48.8566", longitude "2.3522", etc.) is converted to JSON format.

[0131] Input: The uploaded image file.

[0132] Output: Geolocation data in JSON format.

[0133] Step 3: The device sends its location to the server

[0134] The device sends the extracted location information in JSON format to the server as an HTTP POST request.

[0135] Input: Geolocation data in JSON format.

[0136] Output: The HTTP POST request sent to the server.

[0137] Step 4: The server uses the location information to obtain the address information

[0138] The server analyzes the received location information and obtains the corresponding address information using a reverse geocoder API (map service API).

[0139] The requested API returns address information (e.g., "Paris, France").

[0140] Input: Geolocation data in JSON format.

[0141] Output: Address information (e.g., "Paris, France").

[0142] Step 5: The server searches for local landscape data based on the address information.

[0143] The server uses the acquired address information to search the database for scenery data for the corresponding area.

[0144] MySQL and PostgreSQL are used for database management.

[0145] Input: Address information.

[0146] Output: Landscape data related to the region.

[0147] Step 6: The server trains the image generation AI model

[0148] The server uses the acquired local landscape data as input to train an image generation artificial intelligence model using deep learning frameworks (TensorFlow and PyTorch).

[0149] Once trained, the model will understand the characteristics of the local landscape and incorporate them into the next image it generates.

[0150] Input: Regional landscape data.

[0151] Output: A trained image generation model.

[0152] Step 7: The server generates a region-specific landscape image

[0153] Using the learned image generation model, the server generates new landscape images based on user requests.

[0154] Input: A user request and a trained model.

[0155] Output: The generated landscape image.

[0156] Step 8: The server sends the generated image to the device

[0157] The generated image is sent from the server to the terminal as an HTTP response.

[0158] Input: Generated landscape images.

[0159] Output: Image data sent as an HTTP response.

[0160] Step 9: The terminal displays the generated image to the user

[0161] The device displays the received image file on the user interface using HTML and JavaScript technology, with the generated image displayed within an img tag.

[0162] Input: Received image data.

[0163] Output: The image displayed in the user interface.

[0164] Through the above steps, users can easily generate and view realistic landscape images of a specific area.

[0165] (Application example 1)

[0166] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0167] Conventional image generation systems can generate landscape images specific to a region based on images uploaded by users, but they have difficulty generating advertising content related to that region. Furthermore, manually creating region-specific advertising content requires significant time and cost. Therefore, there is a need for a system that allows users to automatically generate and efficiently provide advertising content related to a specific region.

[0168] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0169] In this invention, the server includes: means for a user to upload images; means for a terminal to extract location information from the Exif information of the uploaded images; means for the terminal to transmit the extracted location information to the server; means for the server to obtain address information using a reverse geocoder using the location information; means for the server to search for landscape data related to the region based on the obtained address information; means for the server to include an image generation AI model that learns the landscape data of the searched region; means for the server to generate region-specific images using the learned model; means for the server to transmit the generated images to the terminal; means for the terminal to display the transmitted images to the user; means for generating region-specific advertising content based on the images uploaded by the user; and means for providing the generated region-specific advertising content to the user. This enables users to automatically generate and efficiently use high-quality region-specific landscape images and advertising content based on the uploaded images.

[0170] "User" means a person or entity who utilizes the System to upload images and receive generated content.

[0171] A "terminal" is a device used by a user (e.g., a smartphone or PC) that has the function of uploading and displaying images.

[0172] "Exif information" is metadata contained in an image file, and includes information such as the date and time of shooting and location information.

[0173] "Location information" refers to a geographical location expressed in the form of latitude and longitude.

[0174] The term "server" refers to a computer system that processes data sent from a terminal via a network and executes a predetermined function.

[0175] A "reverse geocoder" is a system that has the function of obtaining address information by inputting latitude and longitude location information.

[0176] "Address information" refers to the specific place name or address corresponding to the location information.

[0177] "Landscape data" refers to data on scenery and features associated with a particular region.

[0178] An "image generation AI model" is an artificial intelligence model that learns the characteristics of a region and generates new images based on the specified region.

[0179] "Localized advertising content" refers to advertising content that is relevant to a specific region and includes information specific to that region.

[0180] "Advertising Content" means content in the form of images or text that contains information intended to promote a product or service.

[0181] A specific embodiment of the present invention will be described. As an application example, a location-specific advertisement generation application is assumed. This system has a function that allows a user to upload an image of a specific location and generates advertisement content related to that location.

[0182] 1. Uploading images and extracting location information

[0183] User

[0184] The user uses an interface to upload images to a device, such as a smartphone or PC. The user selects an image file showing a scene from a specific area and presses the upload button.

[0185] Terminal

[0186] The device analyzes the Exif information from the uploaded image file to obtain latitude and longitude information. For example, if the latitude and longitude of the image are "35.6895" and "139.6917," the device extracts these and converts them into JSON format before sending them to the server.

[0187] 2. Obtaining address information and searching area data

[0188] server

[0189] The server receives the latitude and longitude information sent from the device and sends this location information to a reverse geocoder API (e.g., Google Maps API). The reverse geocoder API returns the address information corresponding to the latitude and longitude information. The server then searches and retrieves local landscape data from a database based on the address information obtained.

[0190] 3. Training and running image generation AI models for generating advertising content

[0191] server

[0192] The server uses the acquired local landscape data to train an image generation AI model. Through this training, the model understands the characteristics of a specific region and reflects these in the images it generates next. To generate region-specific advertisements, the server also creates prompts based on the uploaded images and generates advertising content. The generated advertisement content includes information related to the specific region and is generated as a region-specific advertising image.

[0193] 4. Providing and displaying generated advertising content

[0194] server

[0195] The server saves the generated region-specific advertising content as an image file and transmits it to the terminal as a response.

[0196] Terminal

[0197] The terminal receives the advertisement image file sent from the server and displays it on the user interface, allowing the user to check the generated advertisement content.

[0198] Specific examples

[0199] Hardware and software used

[0200] Hardware: Smartphone or PC

[0201] Software: Python, Exif reading library (exifread), image processing library (PIL), reverse geocoder API (Google Maps API)

[0202] Examples:

[0203] Let's say a user uploads an image of a Tokyo landscape. The Exif information from this image is analyzed to extract the latitude "35.6895" and longitude "139.6917." The server uses the Google Maps API to obtain the address information "Tokyo, Japan" and searches the database for landscape data related to the area. The image generation AI model uses this data to generate advertising content specific to Tokyo and sends it to the user's device. The user can then view the generated advertising image.

[0204] Example prompt sentence:

[0205] "Generate an advertising banner linked to a tourist spot in Tokyo. For example, please use an image containing a view of Shiba Park in Minato Ward, Tokyo."

[0206] In this way, the system according to the present invention can automatically generate advertising content relevant to a specific region based on an image provided by the user, and efficiently provide it to the user.

[0207] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0208] Step 1:

[0209] A user uploads an image.

[0210] How it works: A user uses the application's interface to select an image file depicting a particular area and presses the upload button.

[0211] Input: An image file selected by the user.

[0212] Output: An image file is captured on the device.

[0213] Step 2:

[0214] The device extracts location information from the Exif information of the uploaded image.

[0215] How it works: The device parses the Exif information from the image to obtain latitude and longitude information, for example, by reading the GPS Latitude and GPS Longitude from the Exif information.

[0216] Input: User uploaded image file.

[0217] Output: The extracted latitude and longitude information (e.g. "35.6895, 139.6917").

[0218] Step 3:

[0219] The terminal transmits the extracted location information to the server.

[0220] Operation: The device converts the extracted latitude and longitude information into JSON format and sends it to the server.

[0221] Input: Extracted latitude and longitude information.

[0222] Output: JSON formatted location data sent to the server.

[0223] Step 4:

[0224] The server uses the location information to obtain address information using a reverse geocoder.

[0225] How it works: The server sends the received latitude and longitude information to a reverse geocoder API (e.g., Google Maps API) to obtain the corresponding address information (e.g., "Tokyo, Japan").

[0226] Input: Location data sent to the server in JSON format.

[0227] Output: Address information returned by the Reverse Geocoder API.

[0228] Step 5:

[0229] The server searches for landscape data related to the area based on the address information acquired.

[0230] Operation: The server searches the database for and retrieves landscape data related to the address information.

[0231] Input: Address information obtained from the reverse geocoder API.

[0232] Output: Landscape data related to the region.

[0233] Step 6:

[0234] The server uses an image generation AI model that learns landscape data from the searched area.

[0235] How it works: The server inputs local landscape data and trains the image generation AI model. The model learns the characteristics of a specific area and reflects them in the next image generation.

[0236] Input: Landscape data relevant to the region.

[0237] Output: An image generation AI model that has learned the characteristics of the area.

[0238] Step 7:

[0239] The server uses the trained model to generate region-specific advertising images.

[0240] How it works: The server uses a trained image generation AI model to generate localized ad content based on the image uploaded by the user. It also provides the prompt text to the generation AI model to generate ad content.

[0241] Input: A trained image generation AI model, an uploaded image, and a prompt.

[0242] Output: Region-specific advertising images.

[0243] Step 8:

[0244] The server transmits the generated advertisement image to the terminal.

[0245] How it works: The server saves the generated ad image file and sends it to the user's device as a response.

[0246] Input: The generated ad image.

[0247] Output: The ad image file sent to the device.

[0248] Step 9:

[0249] The terminal displays the transmitted advertisement image to the user.

[0250] Operation: The device displays the received advertisement image file on the user interface so that the user can check it.

[0251] Input: Ad image file sent from server.

[0252] Output: The ad image displayed in the user interface.

[0253] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0254] The present invention provides an image generation system that allows a user to generate a landscape image of a specific area. Furthermore, by combining an emotion engine that recognizes the user's emotions and adjusts the characteristics of the generated image, it is possible to generate a landscape image customized according to the user's emotions. Specific embodiments for implementing the invention are described below.

[0255] ---

[0256] 1. User interaction and image upload

[0257] User

[0258] The user opens the image upload interface using a device (PC, smartphone, etc.), selects a photo file showing a scene from a specific area, and presses the upload button.

[0259] 2. Extracting and sending location information

[0260] Terminal

[0261] The device analyzes the Exif information of the uploaded photo file to obtain latitude and longitude information. For example, for an image of Paris, the device extracts latitude "48.8566" and longitude "2.3522". The device converts this location information into JSON format and sends it to the server.

[0262] 3. Obtaining address information and searching area data

[0263] server

[0264] The server sends the latitude and longitude information received from the device to a reverse geocoder API (e.g., Google Maps API). The reverse geocoder API returns address information (e.g., "Paris, France") corresponding to the latitude and longitude information. The server then searches and retrieves local landscape data from a database based on the returned address information.

[0265] 4. Image generation AI model training and image generation

[0266] server

[0267] The server uses the local landscape data it acquires as input to train an image generation AI model. Through this training, the model understands the characteristics of Parisian landscapes and reflects this in the images it subsequently generates. After the model has completed training, the server generates landscape images specific to the Paris region based on the user's requests.

[0268] 5. Manipulating the Emotion Engine

[0269] server

[0270] The server is equipped with an emotion engine that recognizes the user's emotions. When the user operates the system, the emotion engine acquires the user's emotion data (e.g., happiness, sadness, excitement, etc.) in real time via, for example, a camera or microphone. The acquired emotion data is then analyzed.

[0271] 6. Image Adjustment Based on Emotion Data

[0272] server

[0273] The server adjusts the characteristics of the generated image (such as color tone, brightness, and contrast) based on the emotion data obtained from the emotion engine. For example, if the user's emotion is "happiness," it generates a landscape image of Paris with bright and vivid colors.

[0274] 7. Sending and displaying generated images

[0275] server

[0276] The server saves the generated image as an image file and sends it to the terminal as a response.

[0277] Terminal

[0278] The terminal receives the image file sent from the server and displays it on the user interface.

[0279] Specific examples

[0280] For example, consider the case where a user wants to generate a landscape image of Paris, Europe. The user uploads an image of a specific location in Paris to their device. The device extracts the latitude "48.8566" and longitude "2.3522" from the image and sends them to the server. The server uses a reverse geocoder API to obtain the address information "Paris, France" and retrieves landscape data related to Paris from a database. Based on this, the image generation AI model generates an image that recreates the Paris landscape. The emotion engine recognizes the user's emotions in real time, and if the user is recognized as "happy," an image with bright and vivid colors is generated. The generated image is sent to the user's device, where the user can view the realistic Paris landscape image that was generated.

[0281] ---

[0282] In this way, the system of the present invention not only generates images that reflect the unique characteristics of a region based on the location information of images uploaded by users, but also generates customized images based on the user's emotional data, allowing users to use more personalized, high-quality content for a variety of purposes.

[0283] The processing flow will be explained below.

[0284] Step 1:

[0285] User

[0286] The user opens the image upload interface on the device, selects a photo file showing a scene from a specific area, and presses the upload button.

[0287] Step 2:

[0288] Terminal

[0289] The device analyzes the Exif information of the uploaded photo file to obtain latitude and longitude information. For example, for an image of Paris, the latitude "48.8566" and longitude "2.3522" are extracted.

[0290] Step 3:

[0291] Terminal

[0292] The terminal converts the extracted latitude and longitude information into JSON format and sends it to the server.

[0293] Step 4:

[0294] server

[0295] The server receives the latitude and longitude information from the device and sends it to the reverse geocoder API to obtain the address information.

[0296] Step 5:

[0297] server

[0298] Receive the address information (e.g., Paris, France) returned from the reverse geocoder API and search the database to obtain landscape data for the corresponding area.

[0299] Step 6:

[0300] server

[0301] The server inputs the acquired local landscape data into an image generation AI model, allowing the AI ​​model to learn. The learning data is preprocessed and normalized, and then formatted as input for the AI ​​model.

[0302] Step 7:

[0303] server

[0304] The server uses a trained AI model to generate images that reflect the characteristics of the specified area. Depending on the generation task, conditional inputs (e.g., season, time of day, etc.) can be added to achieve high-precision generation.

[0305] Step 8:

[0306] server

[0307] The server's emotion engine acquires the user's emotion data, for example, by analyzing the user's facial expressions and voice in real time using a camera and microphone.

[0308] Step 9:

[0309] server

[0310] Based on the acquired emotional data, the system adjusts the characteristics of the generated image (color tone, brightness, contrast, etc.). For example, if the user is recognized as "happy," it generates an image with bright and vivid colors.

[0311] Step 10:

[0312] server

[0313] The server saves the generated image as an image file and transmits it to the terminal as response data.

[0314] Step 11:

[0315] Terminal

[0316] The terminal acquires the response data received from the server, extracts the image file generated from the response data, and displays it on the user interface.

[0317] Step 12:

[0318] User

[0319] The user checks the displayed image and, if necessary, presses the download button to save the image file to his / her terminal.

[0320] ---

[0321] In this way, the system of the present invention not only generates images that reflect the unique characteristics of a region based on the location information of images uploaded by users, but also generates customized images based on the user's emotional data, allowing users to use more personalized, high-quality content for a variety of purposes.

[0322] Example 2

[0323] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0324] Conventional image generation systems can generate landscape images that reflect the characteristics of a specific region from images uploaded by users, but they lack customization based on the user's emotions. Also, they have few interactive elements, so there is a need for technology to provide more personalized content.

[0325] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes emotion recognition means for acquiring and analyzing emotion data of the user, means for adjusting the characteristics of the generated image based on the acquired emotion data, and means including an image generation model that learns using landscape data of the searched area as input. This makes it possible to generate high-quality landscape images customized based on the user's emotions while reflecting the regional characteristics of the image uploaded by the user.

[0326] "Image file" means a file containing visual information stored in digital format.

[0327] A "terminal" is an electronic device operated by a user, and includes a personal computer, a smartphone, etc.

[0328] "Exif information" is metadata embedded in an image file, and includes information such as the date and time of the image being taken and its location.

[0329] "Location information" refers to latitude and longitude data that indicates a specific location.

[0330] A "server" refers to a computer system that provides services over a network.

[0331] "Reverse geocoding" refers to the process of obtaining corresponding address information from latitude and longitude information.

[0332] "Address information" refers to geographical description data that indicates a specific location.

[0333] "Landscape data" refers to digital images and information that show the scenery and features of a particular area.

[0334] An "image generation model" refers to a machine learning model that is trained to generate new images based on input data.

[0335] "Emotion recognition means" refers to technology for acquiring and analyzing a user's emotions in real time.

[0336] "Emotion data" refers to information that indicates the user's emotional state.

[0337] "Characteristics" refers to visual elements such as color, brightness, and contrast in images and data.

[0338] The present invention provides an image generation system that allows a user to generate a landscape image of a specific area. Furthermore, by combining an emotion engine that recognizes the user's emotions and adjusts the characteristics of the generated image, it is possible to generate a landscape image customized according to the user's emotions. Specific embodiments for implementing the invention are described below.

[0339] First, a user uploads an image using a device such as a PC or smartphone. The device analyzes the latitude and longitude from the Exif information in the uploaded image file, converts this location information into JSON format, and sends it to the server. The device then selects an image of a specific area, for example, and presses the "upload" button.

[0340] The server sends the received latitude and longitude information to a reverse geocoder API (e.g., Google Maps API) to obtain the corresponding address information. Based on this address information, the server searches and obtains the landscape data of the relevant area from the database.

[0341] The acquired landscape data of the area becomes input data for training an image generation AI model (e.g., Generative Adversarial Network: GAN) on the server. Through this training process, the AI ​​model will be able to recognize the characteristics of the area and reflect them in the next image generation.

[0342] Once the model has completed its training, the server generates a new landscape image with the unique characteristics of the region according to the user's request. This generated image is not left as is; rather, the emotion engine further adjusts the image's color tone, brightness, contrast, and other characteristics based on the results of acquiring and analyzing the user's emotional data.

[0343] Specifically, the system captures the user's emotions (e.g., happiness, sadness, excitement, etc.) in real time through a camera and microphone, and if the user is recognized as happy, for example, the image is adjusted to have brighter, more vivid colors.

[0344] Finally, the server sends the generated image to the terminal, which displays the received image file on the user interface, allowing the user to check the generated realistic landscape image.

[0345] Specific examples

[0346] For example, consider a case where a user wants to generate a landscape image of Paris, Europe. The user uploads an image of a specific location in Paris to their device. The device extracts the latitude "48.8566" and longitude "2.3522" from the image and sends them to the server. The server uses a reverse geocoder API to obtain the address information "Paris, France" and retrieves landscape data related to Paris from a database. An image generation AI model uses this information to generate an image that recreates the Paris landscape. The emotion engine recognizes the user's emotions in real time, and if it recognizes "happiness," it generates an image with bright, vivid colors. The generated image is sent to the user's device, where the user can view the realistic Paris landscape image.

[0347] Prompt Sentence Examples

[0348] "Upload a picture of Paris and sit back and relax while we analyze the sentiment of your image."

[0349] Through the above process, the system of the present invention can generate images that reflect the characteristics of a particular region based on the location information of images uploaded by users, as well as generate customized images based on the user's emotional data, allowing users to enjoy more personalized, high-quality content.

[0350] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0351] Step 1:

[0352] User image upload

[0353] The user opens the image upload interface using a device (such as a PC or smartphone), selects a photo file showing a scene from a specific area, and presses the upload button.

[0354] Input: An image file selected by the user.

[0355] Output: Image file uploaded to the device

[0356] Specific operation: When the user selects an image file and clicks the "Upload" button, the image file is uploaded to the device.

[0357] Step 2:

[0358] Extracting location information

[0359] The device analyzes the Exif information of the uploaded image file and extracts the latitude and longitude information. For example, in the case of an image of Paris, the device extracts the latitude "48.8566" and longitude "2.3522".

[0360] Input: Image file containing Exif information

[0361] Output: Extracted latitude and longitude information (e.g., latitude "48.8566", longitude "2.3522")

[0362] What happens: The device parses the Exif metadata of the image file to read the latitude and longitude, which are then prepared for transmission to the server in the next step.

[0363] Step 3:

[0364] Sending location information

[0365] The device converts the acquired latitude and longitude information into JSON format and sends it to the server. This JSON data contains the necessary location information.

[0366] Input: Extracted latitude and longitude information

[0367] Output: Location information sent to the server in JSON format

[0368] Specific operation: The device converts the latitude and longitude information into JSON format and sends it to the server as an HTTP request.

[0369] Step 4:

[0370] Obtaining address information

[0371] The server sends the received latitude and longitude information to a reverse geocoder API (e.g., a geographic information API) to obtain the corresponding address information. This API returns the address information corresponding to the latitude and longitude information.

[0372] Input: JSON data containing latitude and longitude information

[0373] Output: The address information obtained (e.g., "Paris, France")

[0374] Specific operation: The server sends latitude and longitude information to the API and receives address information returned from the API.

[0375] Step 5:

[0376] Searching for geographical data

[0377] Based on the acquired address information, the server searches the database for landscape data for the area and retrieves the relevant data.

[0378] Input: Address information

[0379] Output: Landscape data of the relevant area

[0380] Specific operation: The server uses the address information as a search key in the database to retrieve landscape data for the corresponding area.

[0381] Step 6:

[0382] Learning an image generation AI model

[0383] The server uses the acquired local landscape data as input to train the image generation AI model. Through this training process, the model will be able to recognize the local characteristics.

[0384] Input: Regional landscape data

[0385] Output: Trained image generation AI model

[0386] How it works: The server feeds local landscape data to the AI ​​model and applies a learning algorithm to train the model.

[0387] Step 7:

[0388] Image generation

[0389] Using the image generation AI model that has completed training, the server generates new landscape images based on the user's requests.

[0390] Input: Trained image generation AI model, user request (prompt sentence)

[0391] Output: Generated landscape image

[0392] Specific operation: The server uses the trained AI model to perform the calculations necessary to generate a new landscape image and generate an image file.

[0393] Step 8:

[0394] Emotion recognition by emotion engine

[0395] The server has an emotion recognition unit that captures and analyzes the user's emotion data in real time. The server captures the user's emotions (e.g., happiness, sadness, excitement, etc.) through a camera and microphone.

[0396] Input: User emotion data acquired through camera and microphone

[0397] Output: Parsed user's emotional state

[0398] Specific operation: The server collects emotional data through the camera and microphone, and applies an emotion analysis algorithm to recognize the user's emotional state.

[0399] Step 9:

[0400] Image adjustment

[0401] The server adjusts the characteristics of the generated image based on information from the emotion recognition means, for example, if the user is recognized as "happy," it adjusts the color tone of the image to be brighter and more vivid.

[0402] Input: Generated landscape image, analyzed user's emotional state

[0403] Output: Adjusted landscape image

[0404] Specific behavior: The server adjusts the color tone, brightness, contrast, and other characteristics of the generated image based on the emotional state.

[0405] Step 10:

[0406] Sending generated images

[0407] The server saves the adjusted image as a file and transmits it to the terminal as response data.

[0408] Input: Adjusted landscape image

[0409] Output: The final generated image sent to the device.

[0410] Specific operation: The server sends the adjusted image to the device as an HTTP response.

[0411] Step 11:

[0412] Displaying the generated image

[0413] The terminal receives the image file sent from the server and displays it on the user interface.

[0414] Input: Image file received from the server

[0415] Output: The final generated image displayed in the user interface.

[0416] Specific behavior: The device receives the image file and displays it to the user in a browser or application.

[0417] Through the above specific processing, the system of the present invention can generate images that reflect the unique characteristics of a region based on the location information of images uploaded by users, and can also provide high-quality landscape images customized to match the user's emotional data.

[0418] (Application example 2)

[0419] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0420] Existing image generation systems can generate region-specific landscape images based on images uploaded by users, but they do not customize the images based on the user's emotions, making it difficult to provide an optimized experience for each individual user. Furthermore, applications such as virtual tourism require real-time landscape images that reflect the user's emotions, but no system exists that can meet this need. This limits the user experience and poses the challenge of being unable to provide a personalized tourism experience based on emotions.

[0421] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0422] In this invention, the server includes a means for training an image generation AI model, an emotion recognition means for recognizing a user's emotion, and a means for adjusting the characteristics of the generated image based on the emotion, thereby enabling the server to customize region-specific landscape images according to the user's emotion and provide a more personalized sightseeing experience.

[0423] An "image generation AI model" is an artificial intelligence algorithm that learns specific features and patterns based on input data and generates realistic images.

[0424] "Emotion recognition means" refers to technology including sensors and software for identifying a user's emotions in real time.

[0425] "Exif information" is metadata embedded in image files taken with a digital camera, and includes information such as the date and time the image was taken and its location.

[0426] A "reverse geocoder" is a technology or API for obtaining corresponding address information based on latitude and longitude information.

[0427] "Landscape data" is image data of scenery and buildings related to a specific area, and is data that reflects the characteristics of that area.

[0428] A "terminal" is a device used to upload or receive images, including smartphones and personal computers.

[0429] "Address information" is physical address data corresponding to a specific latitude and longitude obtained by a reverse geocoder.

[0430] "Location-specific imagery" is imagery that reflects the characteristics and visual elements of a particular geographic location and recreates the landscape of a particular region.

[0431] "Means for adjusting the characteristics of the generated image based on emotion" refers to a technology that analyzes the user's emotional data and dynamically changes the color tone, brightness, contrast, etc. of the generated image based on the results.

[0432] The present invention provides an image generation system that allows a user to generate landscape images of a specific area, and also provides a function that recognizes the user's emotions and adjusts the characteristics of the generated image. Specific embodiments of the invention are described below.

[0433] 1. User interaction and image upload

[0434] The user opens the image upload interface using a device (PC, smartphone, etc.), selects an image file showing a scene from a specific area, and presses the upload button. This uploaded image contains Exif information, which allows location information to be obtained.

[0435] 2. Extracting and sending location information

[0436] The device analyzes the Exif information of the uploaded image and obtains the latitude and longitude information. For example, for an image of Paris, the latitude "48.8566" and longitude "2.3522" are extracted. The device converts this location information into JSON format and sends it to the server.

[0437] 3. Obtaining address information and searching area data

[0438] The server uses the reverse geocoder API to obtain address information (e.g., "Paris, France") from the latitude and longitude information received from the device. Based on the returned address information, the server searches for and obtains landscape data for the corresponding area from a database.

[0439] 4. Image generation AI model training and image generation

[0440] The server uses the local landscape data it acquires as input to train an image generation AI model. Through this training, the model understands the characteristics of Paris' landscapes and reflects this in the images it subsequently generates. After the model has completed training, the server generates region-specific landscape images based on the user's requests.

[0441] 5. Manipulation of emotion recognition measures

[0442] The server is equipped with an emotion recognition means for recognizing the user's emotions. When the user operates the system, the emotion recognition means acquires the user's emotion data (e.g., happiness, sadness, excitement, etc.) in real time via, for example, a camera or microphone. The acquired emotion data is then analyzed.

[0443] 6. Image Adjustment Based on Emotion Data

[0444] The server adjusts the characteristics of the generated image (color tone, brightness, contrast, etc.) based on the emotion data acquired from the emotion recognition means. For example, if the user's emotion is "happiness," it generates a region-specific landscape image with bright, vivid colors.

[0445] 7. Sending and displaying generated images

[0446] The server saves the generated image as an image file and sends it to the terminal as a response. The terminal receives the image file sent from the server and displays it on the user interface.

[0447] Specific examples

[0448] For example, if a user uploads an image of the Eiffel Tower in Paris, the location information (latitude 48.8584, longitude 2.2945) is extracted. If emotion recognition detects "excitement," a colorful, dynamic image of the Eiffel Tower is generated.

[0449] Prompt Sentence Examples

[0450] "A user uploads an image of the Eiffel Tower. If emotion recognition detects excitement, generate a colorful, animated image of the Eiffel Tower."

[0451] In this way, the system of the present invention can generate images that reflect the characteristics of a particular region based on the location information of images uploaded by users, as well as generate customized images based on the user's emotional data, allowing users to use more personalized, high-quality content for a variety of purposes.

[0452] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0453] Step 1:

[0454] A user opens the image upload interface on a terminal, selects an image file showing a scene from a specific area, and presses the upload button. The input is the image file selected by the user. The output is the image file uploaded to the terminal.

[0455] Step 2:

[0456] The device analyzes the Exif information of the uploaded image and obtains the latitude and longitude information. The input is the image file. The data is processed by extracting the latitude and longitude from the Exif information. The output is location information such as latitude "48.8566" and longitude "2.3522".

[0457] Step 3:

[0458] The location information extracted by the device is converted to JSON format and sent to the server. The input is latitude and longitude information. The location information is converted to JSON format as data processing. The location information data in JSON format is sent to the server as output.

[0459] Step 4:

[0460] The server uses the reverse geocoder API to obtain address information from the latitude and longitude information received from the device. The input is location data in JSON format. For data calculation, the location information is sent to the reverse geocoder API and the corresponding address information is received. The output is address information such as "Paris, France."

[0461] Step 5:

[0462] Based on the address information acquired by the server, the landscape data for the relevant area is searched and acquired from the database. The input is the address information. A database search is performed as a data calculation. The landscape data for the relevant area is obtained as the output.

[0463] Step 6:

[0464] The server uses the landscape data of the area acquired as input to train an image generation AI model. The input is the landscape data of the area. The AI ​​model is trained as a data calculation. The trained image generation AI model is obtained as an output.

[0465] Step 7:

[0466] The server uses the trained image generation AI model to generate region-specific images. The input is the trained AI model and the user's request. The data is processed to generate a landscape image. The output is a region-specific image.

[0467] Step 8:

[0468] The server operates the emotion recognition means to recognize the user's emotions and acquires the user's emotion data. The input is the emotion data obtained when the user operates the device. The data is analyzed by the emotion recognition means as a data calculation. The output is the user's emotion data.

[0469] Step 9:

[0470] The server adjusts the characteristics (color tone, brightness, contrast, etc.) of the generated image based on the emotion data acquired from the emotion recognition means. The input is the emotion data and the generated image. The image characteristics are adjusted as part of the data processing. The adjusted image is obtained as the output.

[0471] Step 10:

[0472] The server saves the generated image as an image file and sends it to the terminal as a response. The input is the generated image. The image file is sent as a data calculation. The image file is sent to the terminal as an output.

[0473] Step 11:

[0474] The terminal receives the image file sent from the server and displays it on the user interface. The input is the image file sent from the server. The data is processed by converting the image into a display format. The output is the adjusted image displayed to the user.

[0475] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0476] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0477] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0478] [Second embodiment]

[0479] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0480] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0481] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0482] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0483] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0484] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0485] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0486] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0487] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0488] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0489] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0490] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0491] The present invention provides an image generation system that allows a user to generate a landscape image of a specific area. Specific embodiments for carrying out the invention will be described below.

[0492] ---

[0493] 1. User interaction and image upload

[0494] User

[0495] The user opens the image upload interface using a device (PC, smartphone, etc.), selects a photo file showing a scene from a specific area, and presses the upload button.

[0496] 2. Extracting and sending location information

[0497] Terminal

[0498] The device analyzes the Exif information from the photo file uploaded by the user to obtain latitude and longitude information. For example, for an image of Paris, the device extracts latitude "48.8566" and longitude "2.3522". The device converts this location information into JSON format and sends it to the server.

[0499] 3. Obtaining address information and searching area data

[0500] server

[0501] The server sends the latitude and longitude information received from the device to a reverse geocoder API (e.g., Google Maps API). The reverse geocoder API returns address information (e.g., "Paris, France") corresponding to the latitude and longitude information. The server then searches and retrieves local landscape data from a database based on the returned address information.

[0502] 4. Image generation AI model training and image generation

[0503] server

[0504] The server uses the acquired regional landscape data as input to train an image generation AI model. Through this training, the model understands the characteristics of Parisian landscapes and reflects these in the images it generates. After the model has completed training, the server generates landscape images specific to the Paris region based on the user's requests.

[0505] 5. Sending and displaying generated images

[0506] server

[0507] The server saves the generated image as an image file and sends it to the terminal as a response.

[0508] Terminal

[0509] The terminal receives the image file sent from the server and displays it on the user interface.

[0510] Specific examples

[0511] For example, consider the case where a user wants to generate a landscape image of Paris, Europe. The user uploads an image of a specific location in Paris to their device. The device extracts the latitude "48.8566" and longitude "2.3522" from the image and sends them to the server. The server uses a reverse geocoder API to obtain the address information "Paris, France" and retrieves landscape data related to Paris from a database. Based on this, the image generation AI model generates an image that recreates the Paris landscape. The generated image is sent to the user's device, where the user can view the realistic Paris landscape image that was generated.

[0512] ---

[0513] In this way, the present invention allows users to generate realistic landscape images of specific areas of their choice, allowing them to create high-quality content that can be used in film production, the travel industry, education, and other fields.

[0514] The processing flow will be explained below.

[0515] Step 1:

[0516] User

[0517] The user opens the image upload interface on the device, selects a photo file showing a scene from a specific area, and presses the upload button.

[0518] Step 2:

[0519] Terminal

[0520] The device analyzes the Exif information of the uploaded photo file and extracts the latitude and longitude information (e.g., latitude 48.8566, longitude 2.3522) from the Exif information.

[0521] Step 3:

[0522] Terminal

[0523] The terminal converts the extracted latitude and longitude information into JSON format and sends it to the server.

[0524] Step 4:

[0525] server

[0526] The server receives the latitude and longitude information from the device and sends it to the reverse geocoder API.

[0527] Step 5:

[0528] server

[0529] Receive the address information (e.g., Paris, France) returned by the reverse geocoder API.

[0530] Step 6:

[0531] server

[0532] The server references an internal database based on the address information and searches for and retrieves landscape data (photos and related feature data) for the relevant area.

[0533] Step 7:

[0534] server

[0535] The server inputs the landscape data of the area it has acquired into an image generation AI model, allowing the model to learn.

[0536] Preprocess the training data (e.g., normalization, data augmentation).

[0537] Formatting image and feature data as input to AI models.

[0538] Step 8:

[0539] server

[0540] The server uses a trained AI model to generate images that reflect the landscape characteristics of the specified area.

[0541] The generation task adds conditional inputs (e.g., season, day / night) to enable highly accurate generation.

[0542] Step 9:

[0543] server

[0544] The server saves the generated image as an image file and transmits it to the terminal as response data.

[0545] Step 10:

[0546] Terminal

[0547] The terminal obtains the response data received from the server, extracts the image file generated from the response data, and displays it on the user interface.

[0548] Step 11:

[0549] User

[0550] The user checks the displayed image and, if necessary, presses the download button to save the image file to their device.

[0551] ---

[0552] In this way, the system of the present invention generates realistic landscape images that reflect the unique characteristics of the area based on the location information of images uploaded by users, which can be used for a variety of purposes, such as filmmaking, travel guides, and educational materials.

[0553] Example 1

[0554] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0555] Conventional image generation systems require manual labor and complex processes to realistically recreate the scenery of a specific region. As a result, users are required to have a high level of technical knowledge and spend a lot of time, making it difficult to generate effective scenery images. Furthermore, existing systems do not fully automate the generation of realistic scenery images, and their accuracy is limited. To solve these problems, a system that allows users to easily generate realistic scenery images of specific regions is needed.

[0556] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0557] In this invention, the server includes: means for a user to upload images; means for a terminal to extract location information from metadata information of the uploaded images; means for the terminal to transmit the extracted location information to the server; means for the server to obtain address information using a reverse geocoder using the location information; means for the server to search for scenery data related to the region based on the obtained address information; means for the server to include an image generation artificial intelligence model that learns scenery data of the searched region; means for the server to generate region-specific images using the learned model; means for the server to transmit the generated images to the terminal; and means for the terminal to display the transmitted images to the user. This enables a user to easily and intuitively generate realistic scenery images of a specific region with high accuracy.

[0558] A "user" is a person or organization that uses the system to upload images and generate scenic images of a particular area.

[0559] A "terminal" is a hardware device, such as a computer or smartphone, used by a user to upload images, extract metadata information, transmit location information, and display generated images.

[0560] "Metadata information" is auxiliary information included in image files, such as Exif information. It records the location where the image was taken (latitude, longitude), the date and time of the photo, and the camera settings.

[0561] An "image generation artificial intelligence model" is a machine learning model trained to generate landscape images of a specific area, and uses deep learning technology to generate images that reflect the characteristics of the landscape.

[0562] A "reverse geocoder" is a tool or program for obtaining corresponding address information based on location information (latitude and longitude).

[0563] The "server" is a computer system that manages the entire system, processes data sent from terminals, performs reverse geocoding, searches for local landscape data, generates images using an image generation artificial intelligence model, and transmits the generated images.

[0564] "Landscape data" refers to images and other visual information related to a particular region that is used as training data for image generation.

[0565] "Address information" refers to a geographical address obtained based on specific location information (latitude and longitude), such as "Paris, France."

[0566] The present invention relates to an image generation system that enables a user to easily generate realistic landscape images of a specific area. Specific embodiments for carrying out the invention will be described below.

[0567] A user opens an image upload interface on their device (PC, smartphone, etc.). This interface is built using HTML and JavaScript. The user selects a photo file showing a scene from a specific area and presses the upload button. This action sends the image file from the device to the server as an HTTP POST request.

[0568] The device analyzes the metadata information (Exif information) from the uploaded photo file and extracts the latitude and longitude information. This analysis is performed using the Python ExifRead library. For example, in the case of an image of Paris, the extracted latitude and longitude information is latitude "48.8566" and longitude "2.3522". The acquired location information is converted to JSON format and sent to the server as an HTTP POST request.

[0569] The server uses the latitude and longitude information received from the device to send a request to a reverse geocoder API (for example, a map service API) and obtain the corresponding address information. The reverse geocoder API returns address information such as "Paris, France" based on the obtained location information. The server then uses this address information to search for and obtain scenery data for the corresponding area from a database. Database management uses MySQL or PostgreSQL.

[0570] The server then uses the acquired local landscape data to train an image-generating artificial intelligence model. Deep learning frameworks such as TensorFlow and PyTorch are used to train the model. Once training is complete, the model will understand the characteristics of Paris' landscapes and reflect them in the next image it generates. The server then generates new Paris landscape images based on user requests.

[0571] The generated image is sent from the server to the device as an HTTP response. Finally, the device displays the received image on the user interface. HTML and JavaScript technologies are used to display the generated image using the img tag.

[0572] For example, if a user executes the prompt "Prepare a landscape image of a specific location in Paris, and generate a landscape image of the corresponding area based on the latitude and longitude information extracted from the Exif information," the user uploads an image of a Paris landscape. The system then automatically executes the specified steps to generate a realistic landscape image of Paris and display it to the user.

[0573] In this way, the present invention enables users to easily generate realistic landscape images of specific areas with high accuracy, allowing users to efficiently create high-quality content that can be used in a variety of fields.

[0574] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0575] System program processing steps

[0576] Step 1: User uploads an image

[0577] The user opens an image upload interface on their device, which is built with HTML and JavaScript.

[0578] The user selects a photo file showing a scene from a specific area and presses the upload button.

[0579] Input: Photo files showing scenery from a specific area.

[0580] Output: Image data sent as an HTTP POST request.

[0581] Step 2: The device analyzes the image metadata and extracts the location information.

[0582] The device parses the metadata information (Exif information) from the uploaded photo file using the ExifRead library.

[0583] The acquired location information (latitude "48.8566", longitude "2.3522", etc.) is converted to JSON format.

[0584] Input: The uploaded image file.

[0585] Output: Geolocation data in JSON format.

[0586] Step 3: The device sends its location to the server

[0587] The device sends the extracted location information in JSON format to the server as an HTTP POST request.

[0588] Input: Geolocation data in JSON format.

[0589] Output: The HTTP POST request sent to the server.

[0590] Step 4: The server uses the location information to obtain the address information

[0591] The server analyzes the received location information and obtains the corresponding address information using a reverse geocoder API (map service API).

[0592] The requested API returns address information (e.g., "Paris, France").

[0593] Input: Geolocation data in JSON format.

[0594] Output: Address information (e.g., "Paris, France").

[0595] Step 5: The server searches for local landscape data based on the address information.

[0596] The server uses the acquired address information to search the database for scenery data for the corresponding area.

[0597] MySQL and PostgreSQL are used for database management.

[0598] Input: Address information.

[0599] Output: Landscape data related to the region.

[0600] Step 6: The server trains the image generation AI model

[0601] The server uses the acquired local landscape data as input to train an image generation artificial intelligence model using deep learning frameworks (TensorFlow and PyTorch).

[0602] Once trained, the model will understand the characteristics of the local landscape and incorporate them into the next image it generates.

[0603] Input: Regional landscape data.

[0604] Output: A trained image generation model.

[0605] Step 7: The server generates a region-specific landscape image

[0606] Using the learned image generation model, the server generates new landscape images based on user requests.

[0607] Input: A user request and a trained model.

[0608] Output: The generated landscape image.

[0609] Step 8: The server sends the generated image to the device

[0610] The generated image is sent from the server to the terminal as an HTTP response.

[0611] Input: Generated landscape images.

[0612] Output: Image data sent as an HTTP response.

[0613] Step 9: The terminal displays the generated image to the user

[0614] The device displays the received image file on the user interface using HTML and JavaScript technology, with the generated image displayed within an img tag.

[0615] Input: Received image data.

[0616] Output: The image displayed in the user interface.

[0617] Through the above steps, users can easily generate and view realistic landscape images of a specific area.

[0618] (Application example 1)

[0619] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0620] Conventional image generation systems can generate landscape images specific to a region based on images uploaded by users, but they have difficulty generating advertising content related to that region. Furthermore, manually creating region-specific advertising content requires significant time and cost. Therefore, there is a need for a system that allows users to automatically generate and efficiently provide advertising content related to a specific region.

[0621] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0622] In this invention, the server includes: means for a user to upload images; means for a terminal to extract location information from the Exif information of the uploaded images; means for the terminal to transmit the extracted location information to the server; means for the server to obtain address information using a reverse geocoder using the location information; means for the server to search for landscape data related to the region based on the obtained address information; means for the server to include an image generation AI model that learns the landscape data of the searched region; means for the server to generate region-specific images using the learned model; means for the server to transmit the generated images to the terminal; means for the terminal to display the transmitted images to the user; means for generating region-specific advertising content based on the images uploaded by the user; and means for providing the generated region-specific advertising content to the user. This enables users to automatically generate and efficiently use high-quality region-specific landscape images and advertising content based on the uploaded images.

[0623] "User" means a person or entity who utilizes the System to upload images and receive generated content.

[0624] A "terminal" is a device used by a user (e.g., a smartphone or PC) that has the function of uploading and displaying images.

[0625] "Exif information" is metadata contained in an image file, and includes information such as the date and time of shooting and location information.

[0626] "Location information" refers to a geographical location expressed in the form of latitude and longitude.

[0627] The term "server" refers to a computer system that processes data sent from a terminal via a network and executes a predetermined function.

[0628] A "reverse geocoder" is a system that has the function of obtaining address information by inputting latitude and longitude location information.

[0629] "Address information" refers to the specific place name or address corresponding to the location information.

[0630] "Landscape data" refers to data on scenery and features associated with a particular region.

[0631] An "image generation AI model" is an artificial intelligence model that learns the characteristics of a region and generates new images based on the specified region.

[0632] "Localized advertising content" refers to advertising content that is relevant to a specific region and includes information specific to that region.

[0633] "Advertising Content" means content in the form of images or text that contains information intended to promote a product or service.

[0634] A specific embodiment of the present invention will be described. As an application example, a location-specific advertisement generation application is assumed. This system has a function that allows a user to upload an image of a specific location and generates advertisement content related to that location.

[0635] 1. Uploading images and extracting location information

[0636] User

[0637] The user uses an interface to upload images to a device, such as a smartphone or PC. The user selects an image file showing a scene from a specific area and presses the upload button.

[0638] Terminal

[0639] The device analyzes the Exif information from the uploaded image file to obtain latitude and longitude information. For example, if the latitude and longitude of the image are "35.6895" and "139.6917," the device extracts these and converts them into JSON format before sending them to the server.

[0640] 2. Obtaining address information and searching area data

[0641] server

[0642] The server receives the latitude and longitude information sent from the device and sends this location information to a reverse geocoder API (e.g., Google Maps API). The reverse geocoder API returns the address information corresponding to the latitude and longitude information. The server then searches and retrieves local landscape data from a database based on the address information obtained.

[0643] 3. Training and running image generation AI models for generating advertising content

[0644] server

[0645] The server uses the acquired local landscape data to train an image generation AI model. Through this training, the model understands the characteristics of a specific region and reflects these in the images it generates next. To generate region-specific advertisements, the server also creates prompts based on the uploaded images and generates advertising content. The generated advertisement content includes information related to the specific region and is generated as a region-specific advertising image.

[0646] 4. Providing and displaying generated advertising content

[0647] server

[0648] The server saves the generated region-specific advertising content as an image file and transmits it to the terminal as a response.

[0649] Terminal

[0650] The terminal receives the advertisement image file sent from the server and displays it on the user interface, allowing the user to check the generated advertisement content.

[0651] Specific examples

[0652] Hardware and software used

[0653] Hardware: Smartphone or PC

[0654] Software: Python, Exif reading library (exifread), image processing library (PIL), reverse geocoder API (Google Maps API)

[0655] Examples:

[0656] Let's say a user uploads an image of a Tokyo landscape. The Exif information from this image is analyzed to extract the latitude "35.6895" and longitude "139.6917." The server uses the Google Maps API to obtain the address information "Tokyo, Japan" and searches the database for landscape data related to the area. The image generation AI model uses this data to generate advertising content specific to Tokyo and sends it to the user's device. The user can then view the generated advertising image.

[0657] Example prompt sentence:

[0658] "Generate an advertising banner linked to a tourist spot in Tokyo. For example, please use an image containing a view of Shiba Park in Minato Ward, Tokyo."

[0659] In this way, the system according to the present invention can automatically generate advertising content relevant to a specific region based on an image provided by the user, and efficiently provide it to the user.

[0660] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0661] Step 1:

[0662] A user uploads an image.

[0663] How it works: A user uses the application's interface to select an image file depicting a particular area and presses the upload button.

[0664] Input: An image file selected by the user.

[0665] Output: An image file is captured on the device.

[0666] Step 2:

[0667] The device extracts location information from the Exif information of the uploaded image.

[0668] How it works: The device parses the Exif information from the image to obtain latitude and longitude information, for example, by reading the GPS Latitude and GPS Longitude from the Exif information.

[0669] Input: User uploaded image file.

[0670] Output: The extracted latitude and longitude information (e.g. "35.6895, 139.6917").

[0671] Step 3:

[0672] The terminal transmits the extracted location information to the server.

[0673] Operation: The device converts the extracted latitude and longitude information into JSON format and sends it to the server.

[0674] Input: Extracted latitude and longitude information.

[0675] Output: JSON formatted location data sent to the server.

[0676] Step 4:

[0677] The server uses the location information to obtain address information using a reverse geocoder.

[0678] How it works: The server sends the received latitude and longitude information to a reverse geocoder API (e.g., Google Maps API) to obtain the corresponding address information (e.g., "Tokyo, Japan").

[0679] Input: Location data sent to the server in JSON format.

[0680] Output: Address information returned by the Reverse Geocoder API.

[0681] Step 5:

[0682] The server searches for landscape data related to the area based on the address information acquired.

[0683] Operation: The server searches the database for and retrieves landscape data related to the address information.

[0684] Input: Address information obtained from the reverse geocoder API.

[0685] Output: Landscape data related to the region.

[0686] Step 6:

[0687] The server uses an image generation AI model that learns landscape data from the searched area.

[0688] How it works: The server inputs local landscape data and trains the image generation AI model. The model learns the characteristics of a specific area and reflects them in the next image generation.

[0689] Input: Landscape data relevant to the region.

[0690] Output: An image generation AI model that has learned the characteristics of the area.

[0691] Step 7:

[0692] The server uses the trained model to generate region-specific advertising images.

[0693] How it works: The server uses a trained image generation AI model to generate localized ad content based on the image uploaded by the user. It also provides the prompt text to the generation AI model to generate ad content.

[0694] Input: A trained image generation AI model, an uploaded image, and a prompt.

[0695] Output: Region-specific advertising images.

[0696] Step 8:

[0697] The server transmits the generated advertisement image to the terminal.

[0698] How it works: The server saves the generated ad image file and sends it to the user's device as a response.

[0699] Input: The generated ad image.

[0700] Output: The ad image file sent to the device.

[0701] Step 9:

[0702] The terminal displays the transmitted advertisement image to the user.

[0703] Operation: The device displays the received advertisement image file on the user interface so that the user can check it.

[0704] Input: Ad image file sent from server.

[0705] Output: The ad image displayed in the user interface.

[0706] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0707] The present invention provides an image generation system that allows a user to generate a landscape image of a specific area. Furthermore, by combining an emotion engine that recognizes the user's emotions and adjusts the characteristics of the generated image, it is possible to generate a landscape image customized according to the user's emotions. Specific embodiments for implementing the invention are described below.

[0708] ---

[0709] 1. User interaction and image upload

[0710] User

[0711] The user opens the image upload interface using a device (PC, smartphone, etc.), selects a photo file showing a scene from a specific area, and presses the upload button.

[0712] 2. Extracting and sending location information

[0713] Terminal

[0714] The device analyzes the Exif information of the uploaded photo file to obtain latitude and longitude information. For example, for an image of Paris, the device extracts latitude "48.8566" and longitude "2.3522". The device converts this location information into JSON format and sends it to the server.

[0715] 3. Obtaining address information and searching area data

[0716] server

[0717] The server sends the latitude and longitude information received from the device to a reverse geocoder API (e.g., Google Maps API). The reverse geocoder API returns address information (e.g., "Paris, France") corresponding to the latitude and longitude information. The server then searches and retrieves local landscape data from a database based on the returned address information.

[0718] 4. Image generation AI model training and image generation

[0719] server

[0720] The server uses the local landscape data it acquires as input to train an image generation AI model. Through this training, the model understands the characteristics of Parisian landscapes and reflects this in the images it subsequently generates. After the model has completed training, the server generates landscape images specific to the Paris region based on the user's requests.

[0721] 5. Manipulating the Emotion Engine

[0722] server

[0723] The server is equipped with an emotion engine that recognizes the user's emotions. When the user operates the system, the emotion engine acquires the user's emotion data (e.g., happiness, sadness, excitement, etc.) in real time via, for example, a camera or microphone. The acquired emotion data is then analyzed.

[0724] 6. Image Adjustment Based on Emotion Data

[0725] server

[0726] The server adjusts the characteristics of the generated image (such as color tone, brightness, and contrast) based on the emotion data obtained from the emotion engine. For example, if the user's emotion is "happiness," it generates a landscape image of Paris with bright and vivid colors.

[0727] 7. Sending and displaying generated images

[0728] server

[0729] The server saves the generated image as an image file and sends it to the terminal as a response.

[0730] Terminal

[0731] The terminal receives the image file sent from the server and displays it on the user interface.

[0732] Specific examples

[0733] For example, consider the case where a user wants to generate a landscape image of Paris, Europe. The user uploads an image of a specific location in Paris to their device. The device extracts the latitude "48.8566" and longitude "2.3522" from the image and sends them to the server. The server uses a reverse geocoder API to obtain the address information "Paris, France" and retrieves landscape data related to Paris from a database. Based on this, the image generation AI model generates an image that recreates the Paris landscape. The emotion engine recognizes the user's emotions in real time, and if the user is recognized as "happy," an image with bright and vivid colors is generated. The generated image is sent to the user's device, where the user can view the realistic Paris landscape image that was generated.

[0734] ---

[0735] In this way, the system of the present invention not only generates images that reflect the unique characteristics of a region based on the location information of images uploaded by users, but also generates customized images based on the user's emotional data, allowing users to use more personalized, high-quality content for a variety of purposes.

[0736] The processing flow will be explained below.

[0737] Step 1:

[0738] User

[0739] The user opens the image upload interface on the device, selects a photo file showing a scene from a specific area, and presses the upload button.

[0740] Step 2:

[0741] Terminal

[0742] The device analyzes the Exif information of the uploaded photo file to obtain latitude and longitude information. For example, for an image of Paris, the latitude "48.8566" and longitude "2.3522" are extracted.

[0743] Step 3:

[0744] Terminal

[0745] The terminal converts the extracted latitude and longitude information into JSON format and sends it to the server.

[0746] Step 4:

[0747] server

[0748] The server receives the latitude and longitude information from the device and sends it to the reverse geocoder API to obtain the address information.

[0749] Step 5:

[0750] server

[0751] Receive the address information (e.g., Paris, France) returned from the reverse geocoder API and search the database to obtain landscape data for the corresponding area.

[0752] Step 6:

[0753] server

[0754] The server inputs the acquired local landscape data into an image generation AI model, allowing the AI ​​model to learn. The learning data is preprocessed and normalized, and then formatted as input for the AI ​​model.

[0755] Step 7:

[0756] server

[0757] The server uses a trained AI model to generate images that reflect the characteristics of the specified area. Depending on the generation task, conditional inputs (e.g., season, time of day, etc.) can be added to achieve high-precision generation.

[0758] Step 8:

[0759] server

[0760] The server's emotion engine acquires the user's emotion data, for example, by analyzing the user's facial expressions and voice in real time using a camera and microphone.

[0761] Step 9:

[0762] server

[0763] Based on the acquired emotional data, the system adjusts the characteristics of the generated image (color tone, brightness, contrast, etc.). For example, if the user is recognized as "happy," it generates an image with bright and vivid colors.

[0764] Step 10:

[0765] server

[0766] The server saves the generated image as an image file and transmits it to the terminal as response data.

[0767] Step 11:

[0768] Terminal

[0769] The terminal acquires the response data received from the server, extracts the image file generated from the response data, and displays it on the user interface.

[0770] Step 12:

[0771] User

[0772] The user checks the displayed image and, if necessary, presses the download button to save the image file to his / her terminal.

[0773] ---

[0774] In this way, the system of the present invention not only generates images that reflect the unique characteristics of a region based on the location information of images uploaded by users, but also generates customized images based on the user's emotional data, allowing users to use more personalized, high-quality content for a variety of purposes.

[0775] Example 2

[0776] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0777] Conventional image generation systems can generate landscape images that reflect the characteristics of a specific region from images uploaded by users, but they lack customization based on the user's emotions. Also, they have few interactive elements, so there is a need for technology to provide more personalized content.

[0778] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes emotion recognition means for acquiring and analyzing emotion data of the user, means for adjusting the characteristics of the generated image based on the acquired emotion data, and means including an image generation model that learns using landscape data of the searched area as input. This makes it possible to generate high-quality landscape images customized based on the user's emotions while reflecting the regional characteristics of the image uploaded by the user.

[0779] "Image file" means a file containing visual information stored in digital format.

[0780] A "terminal" is an electronic device operated by a user, and includes a personal computer, a smartphone, etc.

[0781] "Exif information" is metadata embedded in an image file, and includes information such as the date and time of the image being taken and its location.

[0782] "Location information" refers to latitude and longitude data that indicates a specific location.

[0783] A "server" refers to a computer system that provides services over a network.

[0784] "Reverse geocoding" refers to the process of obtaining corresponding address information from latitude and longitude information.

[0785] "Address information" refers to geographical description data that indicates a specific location.

[0786] "Landscape data" refers to digital images and information that show the scenery and features of a particular area.

[0787] An "image generation model" refers to a machine learning model that is trained to generate new images based on input data.

[0788] "Emotion recognition means" refers to technology for acquiring and analyzing a user's emotions in real time.

[0789] "Emotion data" refers to information that indicates the user's emotional state.

[0790] "Characteristics" refers to visual elements such as color, brightness, and contrast in images and data.

[0791] The present invention provides an image generation system that allows a user to generate a landscape image of a specific area. Furthermore, by combining an emotion engine that recognizes the user's emotions and adjusts the characteristics of the generated image, it is possible to generate a landscape image customized according to the user's emotions. Specific embodiments for implementing the invention are described below.

[0792] First, a user uploads an image using a device such as a PC or smartphone. The device analyzes the latitude and longitude from the Exif information in the uploaded image file, converts this location information into JSON format, and sends it to the server. The device then selects an image of a specific area, for example, and presses the "upload" button.

[0793] The server sends the received latitude and longitude information to a reverse geocoder API (e.g., Google Maps API) to obtain the corresponding address information. Based on this address information, the server searches and obtains the landscape data of the relevant area from the database.

[0794] The acquired landscape data of the area becomes input data for training an image generation AI model (e.g., Generative Adversarial Network: GAN) on the server. Through this training process, the AI ​​model will be able to recognize the characteristics of the area and reflect them in the next image generation.

[0795] Once the model has completed its training, the server generates a new landscape image with the unique characteristics of the region according to the user's request. This generated image is not left as is; rather, the emotion engine further adjusts the image's color tone, brightness, contrast, and other characteristics based on the results of acquiring and analyzing the user's emotional data.

[0796] Specifically, the system captures the user's emotions (e.g., happiness, sadness, excitement, etc.) in real time through a camera and microphone, and if the user is recognized as happy, for example, the image is adjusted to have brighter, more vivid colors.

[0797] Finally, the server sends the generated image to the terminal, which displays the received image file on the user interface, allowing the user to check the generated realistic landscape image.

[0798] Specific examples

[0799] For example, consider a case where a user wants to generate a landscape image of Paris, Europe. The user uploads an image of a specific location in Paris to their device. The device extracts the latitude "48.8566" and longitude "2.3522" from the image and sends them to the server. The server uses a reverse geocoder API to obtain the address information "Paris, France" and retrieves landscape data related to Paris from a database. An image generation AI model uses this information to generate an image that recreates the Paris landscape. The emotion engine recognizes the user's emotions in real time, and if it recognizes "happiness," it generates an image with bright, vivid colors. The generated image is sent to the user's device, where the user can view the realistic Paris landscape image.

[0800] Prompt Sentence Examples

[0801] "Upload a picture of Paris and sit back and relax while we analyze the sentiment of your image."

[0802] Through the above process, the system of the present invention can generate images that reflect the characteristics of a particular region based on the location information of images uploaded by users, as well as generate customized images based on the user's emotional data, allowing users to enjoy more personalized, high-quality content.

[0803] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0804] Step 1:

[0805] User image upload

[0806] The user opens the image upload interface using a device (such as a PC or smartphone), selects a photo file showing a scene from a specific area, and presses the upload button.

[0807] Input: An image file selected by the user.

[0808] Output: Image file uploaded to the device

[0809] Specific operation: When the user selects an image file and clicks the "Upload" button, the image file is uploaded to the device.

[0810] Step 2:

[0811] Extracting location information

[0812] The device analyzes the Exif information of the uploaded image file and extracts the latitude and longitude information. For example, in the case of an image of Paris, the device extracts the latitude "48.8566" and longitude "2.3522".

[0813] Input: Image file containing Exif information

[0814] Output: Extracted latitude and longitude information (e.g., latitude "48.8566", longitude "2.3522")

[0815] What happens: The device parses the Exif metadata of the image file to read the latitude and longitude, which are then prepared for transmission to the server in the next step.

[0816] Step 3:

[0817] Sending location information

[0818] The device converts the acquired latitude and longitude information into JSON format and sends it to the server. This JSON data contains the necessary location information.

[0819] Input: Extracted latitude and longitude information

[0820] Output: Location information sent to the server in JSON format

[0821] Specific operation: The device converts the latitude and longitude information into JSON format and sends it to the server as an HTTP request.

[0822] Step 4:

[0823] Obtaining address information

[0824] The server sends the received latitude and longitude information to a reverse geocoder API (e.g., a geographic information API) to obtain the corresponding address information. This API returns the address information corresponding to the latitude and longitude information.

[0825] Input: JSON data containing latitude and longitude information

[0826] Output: The address information obtained (e.g., "Paris, France")

[0827] Specific operation: The server sends latitude and longitude information to the API and receives address information returned from the API.

[0828] Step 5:

[0829] Searching for geographical data

[0830] Based on the acquired address information, the server searches the database for landscape data for the area and retrieves the relevant data.

[0831] Input: Address information

[0832] Output: Landscape data of the relevant area

[0833] Specific operation: The server uses the address information as a search key in the database to retrieve landscape data for the corresponding area.

[0834] Step 6:

[0835] Learning an image generation AI model

[0836] The server uses the acquired local landscape data as input to train the image generation AI model. Through this training process, the model will be able to recognize the local characteristics.

[0837] Input: Regional landscape data

[0838] Output: Trained image generation AI model

[0839] How it works: The server feeds local landscape data to the AI ​​model and applies a learning algorithm to train the model.

[0840] Step 7:

[0841] Image generation

[0842] Using the image generation AI model that has completed training, the server generates new landscape images based on the user's requests.

[0843] Input: Trained image generation AI model, user request (prompt sentence)

[0844] Output: Generated landscape image

[0845] Specific operation: The server uses the trained AI model to perform the calculations necessary to generate a new landscape image and generate an image file.

[0846] Step 8:

[0847] Emotion recognition by emotion engine

[0848] The server has an emotion recognition unit that captures and analyzes the user's emotion data in real time. The server captures the user's emotions (e.g., happiness, sadness, excitement, etc.) through a camera and microphone.

[0849] Input: User emotion data acquired through camera and microphone

[0850] Output: Parsed user's emotional state

[0851] Specific operation: The server collects emotional data through the camera and microphone, and applies an emotion analysis algorithm to recognize the user's emotional state.

[0852] Step 9:

[0853] Image adjustment

[0854] The server adjusts the characteristics of the generated image based on information from the emotion recognition means, for example, adjusting the color tone of the image to be brighter and more vivid if the user is recognized as "happy."

[0855] Input: Generated landscape image, analyzed user's emotional state

[0856] Output: Adjusted landscape image

[0857] Specific behavior: The server adjusts the color tone, brightness, contrast, and other characteristics of the generated image based on the emotional state.

[0858] Step 10:

[0859] Sending generated images

[0860] The server saves the adjusted image as a file and transmits it to the terminal as response data.

[0861] Input: Adjusted landscape image

[0862] Output: The final generated image sent to the device.

[0863] Specific operation: The server sends the adjusted image to the device as an HTTP response.

[0864] Step 11:

[0865] Displaying the generated image

[0866] The terminal receives the image file sent from the server and displays it on the user interface.

[0867] Input: Image file received from the server

[0868] Output: The final generated image displayed in the user interface.

[0869] Specific behavior: The device receives the image file and displays it to the user in a browser or application.

[0870] Through the above specific processing, the system of the present invention can generate images that reflect the unique characteristics of a region based on the location information of images uploaded by users, and can also provide high-quality landscape images customized to match the user's emotional data.

[0871] (Application example 2)

[0872] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0873] Existing image generation systems can generate region-specific landscape images based on images uploaded by users, but they do not customize the images based on the user's emotions, making it difficult to provide an optimized experience for each individual user. Furthermore, applications such as virtual tourism require real-time landscape images that reflect the user's emotions, but no system exists that can meet this need. This limits the user experience and poses the challenge of being unable to provide a personalized tourism experience based on emotions.

[0874] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0875] In this invention, the server includes a means for training an image generation AI model, an emotion recognition means for recognizing a user's emotion, and a means for adjusting the characteristics of the generated image based on the emotion, thereby enabling the server to customize region-specific landscape images according to the user's emotion and provide a more personalized sightseeing experience.

[0876] An "image generation AI model" is an artificial intelligence algorithm that learns specific features and patterns based on input data and generates realistic images.

[0877] "Emotion recognition means" refers to technology including sensors and software for identifying a user's emotions in real time.

[0878] "Exif information" is metadata embedded in image files taken with a digital camera, and includes information such as the date and time the image was taken and its location.

[0879] A "reverse geocoder" is a technology or API for obtaining corresponding address information based on latitude and longitude information.

[0880] "Landscape data" is image data of scenery and buildings related to a specific area, and is data that reflects the characteristics of that area.

[0881] A "terminal" is a device used to upload or receive images, including smartphones and personal computers.

[0882] "Address information" is physical address data corresponding to a specific latitude and longitude obtained by a reverse geocoder.

[0883] "Location-specific imagery" is imagery that reflects the characteristics and visual elements of a particular geographic location and recreates the landscape of a particular region.

[0884] "Means for adjusting the characteristics of the generated image based on emotion" refers to a technology that analyzes the user's emotional data and dynamically changes the color tone, brightness, contrast, etc. of the generated image based on the results.

[0885] The present invention provides an image generation system that allows a user to generate landscape images of a specific area, and also provides a function that recognizes the user's emotions and adjusts the characteristics of the generated image. Specific embodiments of the invention are described below.

[0886] 1. User interaction and image upload

[0887] The user opens the image upload interface using a device (PC, smartphone, etc.), selects an image file showing a scene from a specific area, and presses the upload button. This uploaded image contains Exif information, which allows location information to be obtained.

[0888] 2. Extracting and sending location information

[0889] The device analyzes the Exif information of the uploaded image and obtains the latitude and longitude information. For example, for an image of Paris, the latitude "48.8566" and longitude "2.3522" are extracted. The device converts this location information into JSON format and sends it to the server.

[0890] 3. Obtaining address information and searching area data

[0891] The server uses the reverse geocoder API to obtain address information (e.g., "Paris, France") from the latitude and longitude information received from the device. Based on the returned address information, the server searches for and obtains landscape data for the corresponding area from a database.

[0892] 4. Image generation AI model training and image generation

[0893] The server uses the local landscape data it acquires as input to train an image generation AI model. Through this training, the model understands the characteristics of Paris' landscapes and reflects this in the images it subsequently generates. After the model has completed training, the server generates region-specific landscape images based on the user's requests.

[0894] 5. Manipulation of emotion recognition measures

[0895] The server is equipped with an emotion recognition means for recognizing the user's emotions. When the user operates the system, the emotion recognition means acquires the user's emotion data (e.g., happiness, sadness, excitement, etc.) in real time via, for example, a camera or microphone. The acquired emotion data is then analyzed.

[0896] 6. Image Adjustment Based on Emotion Data

[0897] The server adjusts the characteristics of the generated image (color tone, brightness, contrast, etc.) based on the emotion data acquired from the emotion recognition means. For example, if the user's emotion is "happiness," it generates a region-specific landscape image with bright, vivid colors.

[0898] 7. Sending and displaying generated images

[0899] The server saves the generated image as an image file and sends it to the terminal as a response. The terminal receives the image file sent from the server and displays it on the user interface.

[0900] Specific examples

[0901] For example, if a user uploads an image of the Eiffel Tower in Paris, the location information (latitude 48.8584, longitude 2.2945) is extracted. If emotion recognition detects "excitement," a colorful, dynamic image of the Eiffel Tower is generated.

[0902] Prompt Sentence Examples

[0903] "A user uploads an image of the Eiffel Tower. If emotion recognition detects excitement, generate a colorful, animated image of the Eiffel Tower."

[0904] In this way, the system of the present invention can generate images that reflect the characteristics of a particular region based on the location information of images uploaded by users, as well as generate customized images based on the user's emotional data, allowing users to use more personalized, high-quality content for a variety of purposes.

[0905] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0906] Step 1:

[0907] A user opens the image upload interface on a terminal, selects an image file showing a scene from a specific area, and presses the upload button. The input is the image file selected by the user. The output is the image file uploaded to the terminal.

[0908] Step 2:

[0909] The device analyzes the Exif information of the uploaded image and obtains the latitude and longitude information. The input is the image file. The data is processed by extracting the latitude and longitude from the Exif information. The output is location information such as latitude "48.8566" and longitude "2.3522".

[0910] Step 3:

[0911] The location information extracted by the device is converted to JSON format and sent to the server. The input is latitude and longitude information. The location information is converted to JSON format as data processing. The location information data in JSON format is sent to the server as output.

[0912] Step 4:

[0913] The server uses the reverse geocoder API to obtain address information from the latitude and longitude information received from the device. The input is location data in JSON format. For data calculation, the location information is sent to the reverse geocoder API and the corresponding address information is received. The output is address information such as "Paris, France."

[0914] Step 5:

[0915] Based on the address information acquired by the server, the landscape data for the relevant area is searched and acquired from the database. The input is the address information. A database search is performed as a data calculation. The landscape data for the relevant area is obtained as the output.

[0916] Step 6:

[0917] The server uses the landscape data of the area acquired as input to train an image generation AI model. The input is the landscape data of the area. The AI ​​model is trained as a data calculation. The trained image generation AI model is obtained as an output.

[0918] Step 7:

[0919] The server uses the trained image generation AI model to generate region-specific images. The input is the trained AI model and the user's request. The data is processed to generate a landscape image. The output is a region-specific image.

[0920] Step 8:

[0921] The server operates the emotion recognition means to recognize the user's emotions and acquires the user's emotion data. The input is the emotion data obtained when the user operates the device. The data is analyzed by the emotion recognition means as a data calculation. The output is the user's emotion data.

[0922] Step 9:

[0923] The server adjusts the characteristics (color tone, brightness, contrast, etc.) of the generated image based on the emotion data acquired from the emotion recognition means. The input is the emotion data and the generated image. The image characteristics are adjusted as part of the data processing. The adjusted image is obtained as the output.

[0924] Step 10:

[0925] The server saves the generated image as an image file and sends it to the terminal as a response. The input is the generated image. The image file is sent as a data calculation. The image file is sent to the terminal as an output.

[0926] Step 11:

[0927] The terminal receives the image file sent from the server and displays it on the user interface. The input is the image file sent from the server. The data is processed by converting the image into a display format. The output is the adjusted image displayed to the user.

[0928] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0929] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0930] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0931] [Third embodiment]

[0932] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0933] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0934] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0935] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0936] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0937] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0938] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0939] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0940] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0941] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0942] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0943] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0944] The present invention provides an image generation system that allows a user to generate a landscape image of a specific area. Specific embodiments for carrying out the invention will be described below.

[0945] ---

[0946] 1. User interaction and image upload

[0947] User

[0948] The user opens the image upload interface using a device (PC, smartphone, etc.), selects a photo file showing a scene from a specific area, and presses the upload button.

[0949] 2. Extracting and sending location information

[0950] Terminal

[0951] The device analyzes the Exif information from the photo file uploaded by the user to obtain latitude and longitude information. For example, for an image of Paris, the device extracts latitude "48.8566" and longitude "2.3522". The device converts this location information into JSON format and sends it to the server.

[0952] 3. Obtaining address information and searching area data

[0953] server

[0954] The server sends the latitude and longitude information received from the device to a reverse geocoder API (e.g., Google Maps API). The reverse geocoder API returns address information (e.g., "Paris, France") corresponding to the latitude and longitude information. The server then searches and retrieves local landscape data from a database based on the returned address information.

[0955] 4. Image generation AI model training and image generation

[0956] server

[0957] The server uses the acquired regional landscape data as input to train an image generation AI model. Through this training, the model understands the characteristics of Parisian landscapes and reflects these in the images it generates. After the model has completed training, the server generates landscape images specific to the Paris region based on the user's requests.

[0958] 5. Sending and displaying generated images

[0959] server

[0960] The server saves the generated image as an image file and sends it to the terminal as a response.

[0961] Terminal

[0962] The terminal receives the image file sent from the server and displays it on the user interface.

[0963] Specific examples

[0964] For example, consider the case where a user wants to generate a landscape image of Paris, Europe. The user uploads an image of a specific location in Paris to their device. The device extracts the latitude "48.8566" and longitude "2.3522" from the image and sends them to the server. The server uses a reverse geocoder API to obtain the address information "Paris, France" and retrieves landscape data related to Paris from a database. Based on this, the image generation AI model generates an image that recreates the Paris landscape. The generated image is sent to the user's device, where the user can view the realistic Paris landscape image that was generated.

[0965] ---

[0966] In this way, the present invention allows users to generate realistic landscape images of specific areas of their choice, allowing them to create high-quality content that can be used in film production, the travel industry, education, and other fields.

[0967] The processing flow will be explained below.

[0968] Step 1:

[0969] User

[0970] The user opens the image upload interface on the device, selects a photo file showing a scene from a specific area, and presses the upload button.

[0971] Step 2:

[0972] Terminal

[0973] The device analyzes the Exif information of the uploaded photo file and extracts the latitude and longitude information (e.g., latitude 48.8566, longitude 2.3522) from the Exif information.

[0974] Step 3:

[0975] Terminal

[0976] The terminal converts the extracted latitude and longitude information into JSON format and sends it to the server.

[0977] Step 4:

[0978] server

[0979] The server receives the latitude and longitude information from the device and sends it to the reverse geocoder API.

[0980] Step 5:

[0981] server

[0982] Receive the address information (e.g., Paris, France) returned by the reverse geocoder API.

[0983] Step 6:

[0984] server

[0985] The server references an internal database based on the address information and searches for and retrieves landscape data (photos and related feature data) for the relevant area.

[0986] Step 7:

[0987] server

[0988] The server inputs the landscape data of the area it has acquired into an image generation AI model, allowing the model to learn.

[0989] Preprocess the training data (e.g., normalization, data augmentation).

[0990] Formatting image and feature data as input to AI models.

[0991] Step 8:

[0992] server

[0993] The server uses a trained AI model to generate images that reflect the landscape characteristics of the specified area.

[0994] The generation task adds conditional inputs (e.g., season, day / night) to enable highly accurate generation.

[0995] Step 9:

[0996] server

[0997] The server saves the generated image as an image file and transmits it to the terminal as response data.

[0998] Step 10:

[0999] Terminal

[1000] The terminal obtains the response data received from the server, extracts the image file generated from the response data, and displays it on the user interface.

[1001] Step 11:

[1002] User

[1003] The user checks the displayed image and, if necessary, presses the download button to save the image file to their device.

[1004] ---

[1005] In this way, the system of the present invention generates realistic landscape images that reflect the unique characteristics of the area based on the location information of images uploaded by users, which can be used for a variety of purposes, such as filmmaking, travel guides, and educational materials.

[1006] Example 1

[1007] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1008] Conventional image generation systems require manual labor and complex processes to realistically recreate the scenery of a specific region. As a result, users are required to have a high level of technical knowledge and spend a lot of time, making it difficult to generate effective scenery images. Furthermore, existing systems do not fully automate the generation of realistic scenery images, and their accuracy is limited. To solve these problems, a system that allows users to easily generate realistic scenery images of specific regions is needed.

[1009] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1010] In this invention, the server includes: means for a user to upload images; means for a terminal to extract location information from metadata information of the uploaded images; means for the terminal to transmit the extracted location information to the server; means for the server to obtain address information using a reverse geocoder using the location information; means for the server to search for scenery data related to the region based on the obtained address information; means for the server to include an image generation artificial intelligence model that learns scenery data of the searched region; means for the server to generate region-specific images using the learned model; means for the server to transmit the generated images to the terminal; and means for the terminal to display the transmitted images to the user. This enables a user to easily and intuitively generate realistic scenery images of a specific region with high accuracy.

[1011] A "user" is a person or organization that uses the system to upload images and generate scenic images of a particular area.

[1012] A "terminal" is a hardware device, such as a computer or smartphone, used by a user to upload images, extract metadata information, transmit location information, and display generated images.

[1013] "Metadata information" is auxiliary information included in image files, such as Exif information. It records the location where the image was taken (latitude, longitude), the date and time of the photo, and the camera settings.

[1014] An "image generation artificial intelligence model" is a machine learning model trained to generate landscape images of a specific area, and uses deep learning technology to generate images that reflect the characteristics of the landscape.

[1015] A "reverse geocoder" is a tool or program for obtaining corresponding address information based on location information (latitude and longitude).

[1016] The "server" is a computer system that manages the entire system, processes data sent from terminals, performs reverse geocoding, searches for local landscape data, generates images using an image generation artificial intelligence model, and transmits the generated images.

[1017] "Landscape data" refers to images and other visual information related to a particular region that is used as training data for image generation.

[1018] "Address information" refers to a geographical address obtained based on specific location information (latitude and longitude), such as "Paris, France."

[1019] The present invention relates to an image generation system that enables a user to easily generate realistic landscape images of a specific area. Specific embodiments for carrying out the invention will be described below.

[1020] A user opens an image upload interface on their device (PC, smartphone, etc.). This interface is built using HTML and JavaScript. The user selects a photo file showing a scene from a specific area and presses the upload button. This action sends the image file from the device to the server as an HTTP POST request.

[1021] The device analyzes the metadata information (Exif information) from the uploaded photo file and extracts the latitude and longitude information. This analysis is performed using the Python ExifRead library. For example, in the case of an image of Paris, the extracted latitude and longitude information is latitude "48.8566" and longitude "2.3522". The acquired location information is converted to JSON format and sent to the server as an HTTP POST request.

[1022] The server uses the latitude and longitude information received from the device to send a request to a reverse geocoder API (for example, a map service API) and obtain the corresponding address information. The reverse geocoder API returns address information such as "Paris, France" based on the obtained location information. The server then uses this address information to search for and obtain scenery data for the corresponding area from a database. Database management uses MySQL or PostgreSQL.

[1023] The server then uses the acquired local landscape data to train an image-generating artificial intelligence model. Deep learning frameworks such as TensorFlow and PyTorch are used to train the model. Once training is complete, the model will understand the characteristics of Paris' landscapes and reflect them in the next image it generates. The server then generates new Paris landscape images based on user requests.

[1024] The generated image is sent from the server to the device as an HTTP response. Finally, the device displays the received image on the user interface. HTML and JavaScript technologies are used to display the generated image using the img tag.

[1025] For example, if a user executes the prompt "Prepare a landscape image of a specific location in Paris, and generate a landscape image of the corresponding area based on the latitude and longitude information extracted from the Exif information," the user uploads an image of a Paris landscape. The system then automatically executes the specified steps to generate a realistic landscape image of Paris and display it to the user.

[1026] In this way, the present invention enables users to easily generate realistic landscape images of specific areas with high accuracy, allowing users to efficiently create high-quality content that can be used in a variety of fields.

[1027] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1028] System program processing steps

[1029] Step 1: User uploads an image

[1030] The user opens an image upload interface on their device, which is built with HTML and JavaScript.

[1031] The user selects a photo file showing a scene from a specific area and presses the upload button.

[1032] Input: Photo files showing scenery from a specific area.

[1033] Output: Image data sent as an HTTP POST request.

[1034] Step 2: The device analyzes the image metadata and extracts the location information.

[1035] The device parses the metadata information (Exif information) from the uploaded photo file using the ExifRead library.

[1036] The acquired location information (latitude "48.8566", longitude "2.3522", etc.) is converted to JSON format.

[1037] Input: The uploaded image file.

[1038] Output: Geolocation data in JSON format.

[1039] Step 3: The device sends its location to the server

[1040] The device sends the extracted location information in JSON format to the server as an HTTP POST request.

[1041] Input: Geolocation data in JSON format.

[1042] Output: The HTTP POST request sent to the server.

[1043] Step 4: The server uses the location information to obtain the address information

[1044] The server analyzes the received location information and obtains the corresponding address information using a reverse geocoder API (map service API).

[1045] The requested API returns address information (e.g., "Paris, France").

[1046] Input: Geolocation data in JSON format.

[1047] Output: Address information (e.g., "Paris, France").

[1048] Step 5: The server searches for local landscape data based on the address information.

[1049] The server uses the acquired address information to search the database for scenery data for the corresponding area.

[1050] MySQL and PostgreSQL are used for database management.

[1051] Input: Address information.

[1052] Output: Landscape data related to the region.

[1053] Step 6: The server trains the image generation AI model

[1054] The server uses the acquired local landscape data as input to train an image generation artificial intelligence model using deep learning frameworks (TensorFlow and PyTorch).

[1055] Once trained, the model will understand the characteristics of the local landscape and incorporate them into the next image it generates.

[1056] Input: Regional landscape data.

[1057] Output: A trained image generation model.

[1058] Step 7: The server generates a region-specific landscape image

[1059] Using the learned image generation model, the server generates new landscape images based on user requests.

[1060] Input: A user request and a trained model.

[1061] Output: The generated landscape image.

[1062] Step 8: The server sends the generated image to the device

[1063] The generated image is sent from the server to the terminal as an HTTP response.

[1064] Input: Generated landscape images.

[1065] Output: Image data sent as an HTTP response.

[1066] Step 9: The terminal displays the generated image to the user

[1067] The device displays the received image file on the user interface using HTML and JavaScript technology, with the generated image displayed within an img tag.

[1068] Input: Received image data.

[1069] Output: The image displayed in the user interface.

[1070] Through the above steps, users can easily generate and view realistic landscape images of a specific area.

[1071] (Application example 1)

[1072] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1073] Conventional image generation systems can generate landscape images specific to a region based on images uploaded by users, but they have difficulty generating advertising content related to that region. Furthermore, manually creating region-specific advertising content requires significant time and cost. Therefore, there is a need for a system that allows users to automatically generate and efficiently provide advertising content related to a specific region.

[1074] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1075] In this invention, the server includes: means for a user to upload images; means for a terminal to extract location information from the Exif information of the uploaded images; means for the terminal to transmit the extracted location information to the server; means for the server to obtain address information using a reverse geocoder using the location information; means for the server to search for landscape data related to the region based on the obtained address information; means for the server to include an image generation AI model that learns the landscape data of the searched region; means for the server to generate region-specific images using the learned model; means for the server to transmit the generated images to the terminal; means for the terminal to display the transmitted images to the user; means for generating region-specific advertising content based on the images uploaded by the user; and means for providing the generated region-specific advertising content to the user. This enables users to automatically generate and efficiently use high-quality region-specific landscape images and advertising content based on the uploaded images.

[1076] "User" means a person or entity who utilizes the System to upload images and receive generated content.

[1077] A "terminal" is a device used by a user (e.g., a smartphone or PC) that has the function of uploading and displaying images.

[1078] "Exif information" is metadata contained in an image file, and includes information such as the date and time of shooting and location information.

[1079] "Location information" refers to a geographical location expressed in the form of latitude and longitude.

[1080] The term "server" refers to a computer system that processes data sent from a terminal via a network and executes a predetermined function.

[1081] A "reverse geocoder" is a system that has the function of obtaining address information by inputting latitude and longitude location information.

[1082] "Address information" refers to the specific place name or address corresponding to the location information.

[1083] "Landscape data" refers to data on scenery and features associated with a particular region.

[1084] An "image generation AI model" is an artificial intelligence model that learns the characteristics of a region and generates new images based on the specified region.

[1085] "Localized advertising content" refers to advertising content that is relevant to a specific region and includes information specific to that region.

[1086] "Advertising Content" means content in the form of images or text that contains information intended to promote a product or service.

[1087] A specific embodiment of the present invention will be described. As an application example, a location-specific advertisement generation application is assumed. This system has a function that allows a user to upload an image of a specific location and generates advertisement content related to that location.

[1088] 1. Uploading images and extracting location information

[1089] User

[1090] The user uses an interface to upload images to a device, such as a smartphone or PC. The user selects an image file showing a scene from a specific area and presses the upload button.

[1091] Terminal

[1092] The device analyzes the Exif information from the uploaded image file to obtain latitude and longitude information. For example, if the latitude and longitude of the image are "35.6895" and "139.6917," the device extracts these and converts them into JSON format before sending them to the server.

[1093] 2. Obtaining address information and searching area data

[1094] server

[1095] The server receives the latitude and longitude information sent from the device and sends this location information to a reverse geocoder API (e.g., Google Maps API). The reverse geocoder API returns the address information corresponding to the latitude and longitude information. The server then searches and retrieves local landscape data from a database based on the address information obtained.

[1096] 3. Training and running image generation AI models for generating advertising content

[1097] server

[1098] The server uses the acquired local landscape data to train an image generation AI model. Through this training, the model understands the characteristics of a specific region and reflects these in the images it generates next. To generate region-specific advertisements, the server also creates prompts based on the uploaded images and generates advertising content. The generated advertisement content includes information related to the specific region and is generated as a region-specific advertising image.

[1099] 4. Providing and displaying generated advertising content

[1100] server

[1101] The server saves the generated region-specific advertising content as an image file and transmits it to the terminal as a response.

[1102] Terminal

[1103] The terminal receives the advertisement image file sent from the server and displays it on the user interface, allowing the user to check the generated advertisement content.

[1104] Specific examples

[1105] Hardware and software used

[1106] Hardware: Smartphone or PC

[1107] Software: Python, Exif reading library (exifread), image processing library (PIL), reverse geocoder API (Google Maps API)

[1108] Examples:

[1109] Let's say a user uploads an image of a Tokyo landscape. The Exif information from this image is analyzed to extract the latitude "35.6895" and longitude "139.6917." The server uses the Google Maps API to obtain the address information "Tokyo, Japan" and searches the database for landscape data related to the area. The image generation AI model uses this data to generate advertising content specific to Tokyo and sends it to the user's device. The user can then view the generated advertising image.

[1110] Example prompt sentence:

[1111] "Generate an advertising banner linked to a tourist spot in Tokyo. For example, please use an image containing a view of Shiba Park in Minato Ward, Tokyo."

[1112] In this way, the system according to the present invention can automatically generate advertising content relevant to a specific region based on an image provided by the user, and efficiently provide it to the user.

[1113] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1114] Step 1:

[1115] A user uploads an image.

[1116] How it works: A user uses the application's interface to select an image file depicting a particular area and presses the upload button.

[1117] Input: An image file selected by the user.

[1118] Output: An image file is captured on the device.

[1119] Step 2:

[1120] The device extracts location information from the Exif information of the uploaded image.

[1121] How it works: The device parses the Exif information from the image to obtain latitude and longitude information, for example, by reading the GPS Latitude and GPS Longitude from the Exif information.

[1122] Input: User uploaded image file.

[1123] Output: The extracted latitude and longitude information (e.g. "35.6895, 139.6917").

[1124] Step 3:

[1125] The terminal transmits the extracted location information to the server.

[1126] Operation: The device converts the extracted latitude and longitude information into JSON format and sends it to the server.

[1127] Input: Extracted latitude and longitude information.

[1128] Output: JSON formatted location data sent to the server.

[1129] Step 4:

[1130] The server uses the location information to obtain address information using a reverse geocoder.

[1131] How it works: The server sends the received latitude and longitude information to a reverse geocoder API (e.g., Google Maps API) to obtain the corresponding address information (e.g., "Tokyo, Japan").

[1132] Input: Location data sent to the server in JSON format.

[1133] Output: Address information returned by the Reverse Geocoder API.

[1134] Step 5:

[1135] The server searches for landscape data related to the area based on the address information acquired.

[1136] Operation: The server searches the database for and retrieves landscape data related to the address information.

[1137] Input: Address information obtained from the reverse geocoder API.

[1138] Output: Landscape data related to the region.

[1139] Step 6:

[1140] The server uses an image generation AI model that learns landscape data from the searched area.

[1141] How it works: The server inputs local landscape data and trains the image generation AI model. The model learns the characteristics of a specific area and reflects them in the next image generation.

[1142] Input: Landscape data relevant to the region.

[1143] Output: An image generation AI model that has learned the characteristics of the area.

[1144] Step 7:

[1145] The server uses the trained model to generate region-specific advertising images.

[1146] How it works: The server uses a trained image generation AI model to generate localized ad content based on the image uploaded by the user. It also provides the prompt text to the generation AI model to generate ad content.

[1147] Input: A trained image generation AI model, an uploaded image, and a prompt.

[1148] Output: Region-specific advertising images.

[1149] Step 8:

[1150] The server transmits the generated advertisement image to the terminal.

[1151] How it works: The server saves the generated ad image file and sends it to the user's device as a response.

[1152] Input: The generated ad image.

[1153] Output: The ad image file sent to the device.

[1154] Step 9:

[1155] The terminal displays the transmitted advertisement image to the user.

[1156] Operation: The device displays the received advertising image file on the user interface so that the user can check it.

[1157] Input: Ad image file sent from server.

[1158] Output: The ad image displayed in the user interface.

[1159] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1160] The present invention provides an image generation system that allows a user to generate a landscape image of a specific area. Furthermore, by combining an emotion engine that recognizes the user's emotions and adjusts the characteristics of the generated image, it is possible to generate a landscape image customized according to the user's emotions. Specific embodiments for implementing the invention are described below.

[1161] ---

[1162] 1. User interaction and image upload

[1163] User

[1164] The user opens the image upload interface using a device (PC, smartphone, etc.), selects a photo file showing a scene from a specific area, and presses the upload button.

[1165] 2. Extracting and sending location information

[1166] Terminal

[1167] The device analyzes the Exif information of the uploaded photo file to obtain latitude and longitude information. For example, for an image of Paris, the device extracts latitude "48.8566" and longitude "2.3522". The device converts this location information into JSON format and sends it to the server.

[1168] 3. Obtaining address information and searching area data

[1169] server

[1170] The server sends the latitude and longitude information received from the device to a reverse geocoder API (e.g., Google Maps API). The reverse geocoder API returns address information (e.g., "Paris, France") corresponding to the latitude and longitude information. The server then searches and retrieves local landscape data from a database based on the returned address information.

[1171] 4. Image generation AI model training and image generation

[1172] server

[1173] The server uses the local landscape data it acquires as input to train an image generation AI model. Through this training, the model understands the characteristics of Parisian landscapes and reflects this in the images it subsequently generates. After the model has completed training, the server generates landscape images specific to the Paris region based on the user's requests.

[1174] 5. Manipulating the Emotion Engine

[1175] server

[1176] The server is equipped with an emotion engine that recognizes the user's emotions. When the user operates the system, the emotion engine acquires the user's emotion data (e.g., happiness, sadness, excitement, etc.) in real time via, for example, a camera or microphone. The acquired emotion data is then analyzed.

[1177] 6. Image Adjustment Based on Emotion Data

[1178] server

[1179] The server adjusts the characteristics of the generated image (such as color tone, brightness, and contrast) based on the emotion data obtained from the emotion engine. For example, if the user's emotion is "happiness," it generates a landscape image of Paris with bright and vivid colors.

[1180] 7. Sending and displaying generated images

[1181] server

[1182] The server saves the generated image as an image file and sends it to the terminal as a response.

[1183] Terminal

[1184] The terminal receives the image file sent from the server and displays it on the user interface.

[1185] Specific examples

[1186] For example, consider the case where a user wants to generate a landscape image of Paris, Europe. The user uploads an image of a specific location in Paris to their device. The device extracts the latitude "48.8566" and longitude "2.3522" from the image and sends them to the server. The server uses a reverse geocoder API to obtain the address information "Paris, France" and retrieves landscape data related to Paris from a database. Based on this, the image generation AI model generates an image that recreates the Paris landscape. The emotion engine recognizes the user's emotions in real time, and if the user is recognized as "happy," an image with bright and vivid colors is generated. The generated image is sent to the user's device, where the user can view the realistic Paris landscape image that was generated.

[1187] ---

[1188] In this way, the system of the present invention not only generates images that reflect the unique characteristics of a region based on the location information of images uploaded by users, but also generates customized images based on the user's emotional data, allowing users to use more personalized, high-quality content for a variety of purposes.

[1189] The processing flow will be explained below.

[1190] Step 1:

[1191] User

[1192] The user opens the image upload interface on the device, selects a photo file showing a scene from a specific area, and presses the upload button.

[1193] Step 2:

[1194] Terminal

[1195] The device analyzes the Exif information of the uploaded photo file to obtain latitude and longitude information. For example, for an image of Paris, the latitude "48.8566" and longitude "2.3522" are extracted.

[1196] Step 3:

[1197] Terminal

[1198] The terminal converts the extracted latitude and longitude information into JSON format and sends it to the server.

[1199] Step 4:

[1200] server

[1201] The server receives the latitude and longitude information from the device and sends it to the reverse geocoder API to obtain the address information.

[1202] Step 5:

[1203] server

[1204] Receive the address information (e.g., Paris, France) returned from the reverse geocoder API and search the database to obtain landscape data for the corresponding area.

[1205] Step 6:

[1206] server

[1207] The server inputs the acquired local landscape data into an image generation AI model, allowing the AI ​​model to learn. The learning data is preprocessed and normalized, and then formatted as input for the AI ​​model.

[1208] Step 7:

[1209] server

[1210] The server uses a trained AI model to generate images that reflect the characteristics of the specified area. Depending on the generation task, conditional inputs (e.g., season, time of day, etc.) can be added to achieve high-precision generation.

[1211] Step 8:

[1212] server

[1213] The server's emotion engine acquires the user's emotion data, for example, by analyzing the user's facial expressions and voice in real time using a camera and microphone.

[1214] Step 9:

[1215] server

[1216] Based on the acquired emotional data, the system adjusts the characteristics of the generated image (color tone, brightness, contrast, etc.). For example, if the user is recognized as "happy," it generates an image with bright and vivid colors.

[1217] Step 10:

[1218] server

[1219] The server saves the generated image as an image file and transmits it to the terminal as response data.

[1220] Step 11:

[1221] Terminal

[1222] The terminal acquires the response data received from the server, extracts the image file generated from the response data, and displays it on the user interface.

[1223] Step 12:

[1224] User

[1225] The user checks the displayed image and, if necessary, presses the download button to save the image file to his / her terminal.

[1226] ---

[1227] In this way, the system of the present invention not only generates images that reflect the unique characteristics of a region based on the location information of images uploaded by users, but also generates customized images based on the user's emotional data, allowing users to use more personalized, high-quality content for a variety of purposes.

[1228] Example 2

[1229] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1230] Conventional image generation systems can generate landscape images that reflect the characteristics of a specific region from images uploaded by users, but they lack customization based on the user's emotions. Also, they have few interactive elements, so there is a need for technology to provide more personalized content.

[1231] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes emotion recognition means for acquiring and analyzing emotion data of the user, means for adjusting the characteristics of the generated image based on the acquired emotion data, and means including an image generation model that learns using landscape data of the searched area as input. This makes it possible to generate high-quality landscape images customized based on the user's emotions while reflecting the regional characteristics of the image uploaded by the user.

[1232] "Image file" means a file containing visual information stored in digital format.

[1233] A "terminal" is an electronic device operated by a user, and includes a personal computer, a smartphone, etc.

[1234] "Exif information" is metadata embedded in an image file, and includes information such as the date and time of the image being taken and its location.

[1235] "Location information" refers to latitude and longitude data that indicates a specific location.

[1236] A "server" refers to a computer system that provides services over a network.

[1237] "Reverse geocoding" refers to the process of obtaining corresponding address information from latitude and longitude information.

[1238] "Address information" refers to geographical description data that indicates a specific location.

[1239] "Landscape data" refers to digital images and information that show the scenery and features of a particular area.

[1240] An "image generation model" refers to a machine learning model that is trained to generate new images based on input data.

[1241] "Emotion recognition means" refers to technology for acquiring and analyzing a user's emotions in real time.

[1242] "Emotion data" refers to information that indicates the user's emotional state.

[1243] "Characteristics" refers to visual elements such as color, brightness, and contrast in images and data.

[1244] The present invention provides an image generation system that allows a user to generate a landscape image of a specific area. Furthermore, by combining an emotion engine that recognizes the user's emotions and adjusts the characteristics of the generated image, it is possible to generate a landscape image customized according to the user's emotions. Specific embodiments for implementing the invention are described below.

[1245] First, a user uploads an image using a device such as a PC or smartphone. The device analyzes the latitude and longitude from the Exif information in the uploaded image file, converts this location information into JSON format, and sends it to the server. The device then selects an image of a specific area, for example, and presses the "upload" button.

[1246] The server sends the received latitude and longitude information to a reverse geocoder API (e.g., Google Maps API) to obtain the corresponding address information. Based on this address information, the server searches and obtains the landscape data of the relevant area from the database.

[1247] The acquired landscape data of the area becomes input data for training an image generation AI model (e.g., Generative Adversarial Network: GAN) on the server. Through this training process, the AI ​​model will be able to recognize the characteristics of the area and reflect them in the next image generation.

[1248] Once the model has completed its training, the server generates a new landscape image with the unique characteristics of the region according to the user's request. This generated image is not left as is; rather, the emotion engine further adjusts the image's color tone, brightness, contrast, and other characteristics based on the results of acquiring and analyzing the user's emotional data.

[1249] Specifically, the system captures the user's emotions (e.g., happiness, sadness, excitement, etc.) in real time through a camera and microphone, and if the user is recognized as happy, for example, the image is adjusted to have brighter, more vivid colors.

[1250] Finally, the server sends the generated image to the terminal, which displays the received image file on the user interface, allowing the user to check the generated realistic landscape image.

[1251] Specific examples

[1252] For example, consider a case where a user wants to generate a landscape image of Paris, Europe. The user uploads an image of a specific location in Paris to their device. The device extracts the latitude "48.8566" and longitude "2.3522" from the image and sends them to the server. The server uses a reverse geocoder API to obtain the address information "Paris, France" and retrieves landscape data related to Paris from a database. An image generation AI model uses this information to generate an image that recreates the Paris landscape. The emotion engine recognizes the user's emotions in real time, and if it recognizes "happiness," it generates an image with bright, vivid colors. The generated image is sent to the user's device, where the user can view the realistic Paris landscape image.

[1253] Prompt Sentence Examples

[1254] "Upload a picture of Paris and sit back and relax while we analyze the sentiment of your image."

[1255] Through the above process, the system of the present invention can generate images that reflect the characteristics of a particular region based on the location information of images uploaded by users, as well as generate customized images based on the user's emotional data, allowing users to enjoy more personalized, high-quality content.

[1256] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1257] Step 1:

[1258] User image upload

[1259] The user opens the image upload interface using a device (such as a PC or smartphone), selects a photo file showing a scene from a specific area, and presses the upload button.

[1260] Input: An image file selected by the user.

[1261] Output: Image file uploaded to the device

[1262] Specific operation: When the user selects an image file and clicks the "Upload" button, the image file is uploaded to the device.

[1263] Step 2:

[1264] Extracting location information

[1265] The device analyzes the Exif information of the uploaded image file and extracts the latitude and longitude information. For example, in the case of an image of Paris, the device extracts the latitude "48.8566" and longitude "2.3522".

[1266] Input: Image file containing Exif information

[1267] Output: Extracted latitude and longitude information (e.g., latitude "48.8566", longitude "2.3522")

[1268] What happens: The device parses the Exif metadata of the image file to read the latitude and longitude, which are then prepared for transmission to the server in the next step.

[1269] Step 3:

[1270] Sending location information

[1271] The device converts the acquired latitude and longitude information into JSON format and sends it to the server. This JSON data contains the necessary location information.

[1272] Input: Extracted latitude and longitude information

[1273] Output: Location information sent to the server in JSON format

[1274] Specific operation: The device converts the latitude and longitude information into JSON format and sends it to the server as an HTTP request.

[1275] Step 4:

[1276] Obtaining address information

[1277] The server sends the received latitude and longitude information to a reverse geocoder API (e.g., a geographic information API) to obtain the corresponding address information. This API returns the address information corresponding to the latitude and longitude information.

[1278] Input: JSON data containing latitude and longitude information

[1279] Output: The address information obtained (e.g., "Paris, France")

[1280] Specific operation: The server sends latitude and longitude information to the API and receives address information returned from the API.

[1281] Step 5:

[1282] Searching for geographical data

[1283] Based on the acquired address information, the server searches the database for landscape data for the area and retrieves the relevant data.

[1284] Input: Address information

[1285] Output: Landscape data of the relevant area

[1286] Specific operation: The server uses the address information as a search key in the database to retrieve landscape data for the corresponding area.

[1287] Step 6:

[1288] Learning an image generation AI model

[1289] The server uses the acquired local landscape data as input to train the image generation AI model. Through this training process, the model will be able to recognize the local characteristics.

[1290] Input: Regional landscape data

[1291] Output: Trained image generation AI model

[1292] How it works: The server feeds local landscape data to the AI ​​model and applies a learning algorithm to train the model.

[1293] Step 7:

[1294] Image generation

[1295] Using the image generation AI model that has completed training, the server generates new landscape images based on the user's requests.

[1296] Input: Trained image generation AI model, user request (prompt sentence)

[1297] Output: Generated landscape image

[1298] Specific operation: The server uses the trained AI model to perform the calculations necessary to generate a new landscape image and generate an image file.

[1299] Step 8:

[1300] Emotion recognition by emotion engine

[1301] The server has an emotion recognition unit that captures and analyzes the user's emotion data in real time. The server captures the user's emotions (e.g., happiness, sadness, excitement, etc.) through a camera and microphone.

[1302] Input: User emotion data acquired through camera and microphone

[1303] Output: Parsed user's emotional state

[1304] Specific operation: The server collects emotional data through the camera and microphone, and applies an emotion analysis algorithm to recognize the user's emotional state.

[1305] Step 9:

[1306] Image adjustment

[1307] The server adjusts the characteristics of the generated image based on information from the emotion recognition means, for example, if the user is recognized as "happy," it adjusts the color tone of the image to be brighter and more vivid.

[1308] Input: Generated landscape image, analyzed user's emotional state

[1309] Output: Adjusted landscape image

[1310] Specific behavior: The server adjusts the color tone, brightness, contrast, and other characteristics of the generated image based on the emotional state.

[1311] Step 10:

[1312] Sending generated images

[1313] The server saves the adjusted image as a file and transmits it to the terminal as response data.

[1314] Input: Adjusted landscape image

[1315] Output: The final generated image sent to the device.

[1316] Specific operation: The server sends the adjusted image to the device as an HTTP response.

[1317] Step 11:

[1318] Displaying the generated image

[1319] The terminal receives the image file sent from the server and displays it on the user interface.

[1320] Input: Image file received from the server

[1321] Output: The final generated image displayed in the user interface.

[1322] Specific behavior: The device receives the image file and displays it to the user in a browser or application.

[1323] Through the above specific processing, the system of the present invention can generate images that reflect the unique characteristics of a region based on the location information of images uploaded by users, and can also provide high-quality landscape images customized to match the user's emotional data.

[1324] (Application example 2)

[1325] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1326] Existing image generation systems can generate region-specific landscape images based on images uploaded by users, but they do not customize the images based on the user's emotions, making it difficult to provide an optimized experience for each individual user. Furthermore, applications such as virtual tourism require real-time landscape images that reflect the user's emotions, but no system exists that can meet this need. This limits the user experience and poses the challenge of being unable to provide a personalized tourism experience based on emotions.

[1327] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1328] In this invention, the server includes a means for training an image generation AI model, an emotion recognition means for recognizing a user's emotion, and a means for adjusting the characteristics of the generated image based on the emotion, thereby enabling the server to customize region-specific landscape images according to the user's emotion and provide a more personalized sightseeing experience.

[1329] An "image generation AI model" is an artificial intelligence algorithm that learns specific features and patterns based on input data and generates realistic images.

[1330] "Emotion recognition means" refers to technology including sensors and software for identifying a user's emotions in real time.

[1331] "Exif information" is metadata embedded in image files taken with a digital camera, and includes information such as the date and time the image was taken and its location.

[1332] A "reverse geocoder" is a technology or API for obtaining corresponding address information based on latitude and longitude information.

[1333] "Landscape data" is image data of scenery and buildings related to a specific area, and is data that reflects the characteristics of that area.

[1334] A "terminal" is a device used to upload or receive images, including smartphones and personal computers.

[1335] "Address information" is physical address data corresponding to a specific latitude and longitude obtained by a reverse geocoder.

[1336] "Location-specific imagery" is imagery that reflects the characteristics and visual elements of a particular geographic location and recreates the landscape of a particular region.

[1337] "Means for adjusting the characteristics of the generated image based on emotion" refers to a technology that analyzes the user's emotional data and dynamically changes the color tone, brightness, contrast, etc. of the generated image based on the results.

[1338] The present invention provides an image generation system that allows a user to generate landscape images of a specific area, and also provides a function that recognizes the user's emotions and adjusts the characteristics of the generated image. Specific embodiments of the invention are described below.

[1339] 1. User interaction and image upload

[1340] The user opens the image upload interface using a device (PC, smartphone, etc.), selects an image file showing a scene from a specific area, and presses the upload button. This uploaded image contains Exif information, which allows location information to be obtained.

[1341] 2. Extracting and sending location information

[1342] The device analyzes the Exif information of the uploaded image and obtains the latitude and longitude information. For example, for an image of Paris, the latitude "48.8566" and longitude "2.3522" are extracted. The device converts this location information into JSON format and sends it to the server.

[1343] 3. Obtaining address information and searching area data

[1344] The server uses the reverse geocoder API to obtain address information (e.g., "Paris, France") from the latitude and longitude information received from the device. Based on the returned address information, the server searches for and obtains landscape data for the corresponding area from a database.

[1345] 4. Image generation AI model training and image generation

[1346] The server uses the local landscape data it acquires as input to train an image generation AI model. Through this training, the model understands the characteristics of Paris' landscapes and reflects this in the images it subsequently generates. After the model has completed training, the server generates region-specific landscape images based on the user's requests.

[1347] 5. Manipulation of emotion recognition measures

[1348] The server is equipped with an emotion recognition means for recognizing the user's emotions. When the user operates the system, the emotion recognition means acquires the user's emotion data (e.g., happiness, sadness, excitement, etc.) in real time via, for example, a camera or microphone. The acquired emotion data is then analyzed.

[1349] 6. Image Adjustment Based on Emotion Data

[1350] The server adjusts the characteristics of the generated image (color tone, brightness, contrast, etc.) based on the emotion data acquired from the emotion recognition means. For example, if the user's emotion is "happiness," it generates a region-specific landscape image with bright, vivid colors.

[1351] 7. Sending and displaying generated images

[1352] The server saves the generated image as an image file and sends it to the terminal as a response. The terminal receives the image file sent from the server and displays it on the user interface.

[1353] Specific examples

[1354] For example, if a user uploads an image of the Eiffel Tower in Paris, the location information (latitude 48.8584, longitude 2.2945) is extracted. If emotion recognition detects "excitement," a colorful, dynamic image of the Eiffel Tower is generated.

[1355] Prompt Sentence Examples

[1356] "A user uploads an image of the Eiffel Tower. If emotion recognition detects excitement, generate a colorful, animated image of the Eiffel Tower."

[1357] In this way, the system of the present invention can generate images that reflect the characteristics of a particular region based on the location information of images uploaded by users, as well as generate customized images based on the user's emotional data, allowing users to use more personalized, high-quality content for a variety of purposes.

[1358] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1359] Step 1:

[1360] A user opens the image upload interface on a terminal, selects an image file showing a scene from a specific area, and presses the upload button. The input is the image file selected by the user. The output is the image file uploaded to the terminal.

[1361] Step 2:

[1362] The device analyzes the Exif information of the uploaded image and obtains the latitude and longitude information. The input is the image file. The data is processed by extracting the latitude and longitude from the Exif information. The output is location information such as latitude "48.8566" and longitude "2.3522".

[1363] Step 3:

[1364] The location information extracted by the device is converted to JSON format and sent to the server. The input is latitude and longitude information. The location information is converted to JSON format as data processing. The location information data in JSON format is sent to the server as output.

[1365] Step 4:

[1366] The server uses the reverse geocoder API to obtain address information from the latitude and longitude information received from the device. The input is location data in JSON format. For data calculation, the location information is sent to the reverse geocoder API and the corresponding address information is received. The output is address information such as "Paris, France."

[1367] Step 5:

[1368] Based on the address information acquired by the server, the landscape data for the relevant area is searched and acquired from the database. The input is the address information. A database search is performed as a data calculation. The landscape data for the relevant area is obtained as the output.

[1369] Step 6:

[1370] The server uses the landscape data of the area acquired as input to train an image generation AI model. The input is the landscape data of the area. The AI ​​model is trained as a data calculation. The trained image generation AI model is obtained as an output.

[1371] Step 7:

[1372] The server uses the trained image generation AI model to generate region-specific images. The input is the trained AI model and the user's request. The data is processed to generate a landscape image. The output is a region-specific image.

[1373] Step 8:

[1374] The server operates the emotion recognition means to recognize the user's emotions and acquires the user's emotion data. The input is the emotion data obtained when the user operates the device. The data is analyzed by the emotion recognition means as a data calculation. The output is the user's emotion data.

[1375] Step 9:

[1376] The server adjusts the characteristics (color tone, brightness, contrast, etc.) of the generated image based on the emotion data acquired from the emotion recognition means. The input is the emotion data and the generated image. The image characteristics are adjusted as part of the data processing. The adjusted image is obtained as the output.

[1377] Step 10:

[1378] The server saves the generated image as an image file and sends it to the terminal as a response. The input is the generated image. The image file is sent as a data calculation. The image file is sent to the terminal as an output.

[1379] Step 11:

[1380] The terminal receives the image file sent from the server and displays it on the user interface. The input is the image file sent from the server. The data is processed by converting the image into a display format. The output is the adjusted image displayed to the user.

[1381] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1382] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1383] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1384] [Fourth embodiment]

[1385] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1386] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1387] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1388] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1389] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1390] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1391] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1392] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1393] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1394] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1395] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1396] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1397] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1398] The present invention provides an image generation system that allows a user to generate a landscape image of a specific area. Specific embodiments for carrying out the invention will be described below.

[1399] ---

[1400] 1. User interaction and image upload

[1401] User

[1402] The user opens the image upload interface using a device (PC, smartphone, etc.), selects a photo file showing a scene from a specific area, and presses the upload button.

[1403] 2. Extracting and sending location information

[1404] Terminal

[1405] The device analyzes the Exif information from the photo file uploaded by the user to obtain latitude and longitude information. For example, for an image of Paris, the device extracts latitude "48.8566" and longitude "2.3522". The device converts this location information into JSON format and sends it to the server.

[1406] 3. Obtaining address information and searching area data

[1407] server

[1408] The server sends the latitude and longitude information received from the device to a reverse geocoder API (e.g., Google Maps API). The reverse geocoder API returns address information (e.g., "Paris, France") corresponding to the latitude and longitude information. The server then searches and retrieves local landscape data from a database based on the returned address information.

[1409] 4. Image generation AI model training and image generation

[1410] server

[1411] The server uses the acquired regional landscape data as input to train an image generation AI model. Through this training, the model understands the characteristics of Parisian landscapes and reflects these in the images it generates. After the model has completed training, the server generates landscape images specific to the Paris region based on the user's requests.

[1412] 5. Sending and displaying generated images

[1413] server

[1414] The server saves the generated image as an image file and sends it to the terminal as a response.

[1415] Terminal

[1416] The terminal receives the image file sent from the server and displays it on the user interface.

[1417] Specific examples

[1418] For example, consider the case where a user wants to generate a landscape image of Paris, Europe. The user uploads an image of a specific location in Paris to their device. The device extracts the latitude "48.8566" and longitude "2.3522" from the image and sends them to the server. The server uses a reverse geocoder API to obtain the address information "Paris, France" and retrieves landscape data related to Paris from a database. Based on this, the image generation AI model generates an image that recreates the Paris landscape. The generated image is sent to the user's device, where the user can view the realistic Paris landscape image that was generated.

[1419] ---

[1420] In this way, the present invention allows users to generate realistic landscape images of specific areas of their choice, allowing them to create high-quality content that can be used in film production, the travel industry, education, and other fields.

[1421] The processing flow will be explained below.

[1422] Step 1:

[1423] User

[1424] The user opens the image upload interface on the device, selects a photo file showing a scene from a specific area, and presses the upload button.

[1425] Step 2:

[1426] Terminal

[1427] The device analyzes the Exif information of the uploaded photo file and extracts the latitude and longitude information (e.g., latitude 48.8566, longitude 2.3522) from the Exif information.

[1428] Step 3:

[1429] Terminal

[1430] The terminal converts the extracted latitude and longitude information into JSON format and sends it to the server.

[1431] Step 4:

[1432] server

[1433] The server receives the latitude and longitude information from the device and sends it to the reverse geocoder API.

[1434] Step 5:

[1435] server

[1436] Receive the address information (e.g., Paris, France) returned by the reverse geocoder API.

[1437] Step 6:

[1438] server

[1439] The server references an internal database based on the address information and searches for and retrieves landscape data (photos and related feature data) for the relevant area.

[1440] Step 7:

[1441] server

[1442] The server inputs the landscape data of the area it has acquired into an image generation AI model, allowing the model to learn.

[1443] Preprocess the training data (e.g., normalization, data augmentation).

[1444] Formatting image and feature data as input to AI models.

[1445] Step 8:

[1446] server

[1447] The server uses a trained AI model to generate images that reflect the landscape characteristics of the specified area.

[1448] The generation task adds conditional inputs (e.g., season, day / night) to enable highly accurate generation.

[1449] Step 9:

[1450] server

[1451] The server saves the generated image as an image file and transmits it to the terminal as response data.

[1452] Step 10:

[1453] Terminal

[1454] The terminal obtains the response data received from the server, extracts the image file generated from the response data, and displays it on the user interface.

[1455] Step 11:

[1456] User

[1457] The user checks the displayed image and, if necessary, presses the download button to save the image file to their device.

[1458] ---

[1459] In this way, the system of the present invention generates realistic landscape images that reflect the unique characteristics of the area based on the location information of images uploaded by users, which can be used for a variety of purposes, such as filmmaking, travel guides, and educational materials.

[1460] Example 1

[1461] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1462] Conventional image generation systems require manual labor and complex processes to realistically recreate the scenery of a specific region. As a result, users are required to have a high level of technical knowledge and spend a lot of time, making it difficult to generate effective scenery images. Furthermore, existing systems do not fully automate the generation of realistic scenery images, and their accuracy is limited. To solve these problems, a system that allows users to easily generate realistic scenery images of specific regions is needed.

[1463] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1464] In this invention, the server includes: means for a user to upload images; means for a terminal to extract location information from metadata information of the uploaded images; means for the terminal to transmit the extracted location information to the server; means for the server to obtain address information using a reverse geocoder using the location information; means for the server to search for scenery data related to the region based on the obtained address information; means for the server to include an image generation artificial intelligence model that learns scenery data of the searched region; means for the server to generate region-specific images using the learned model; means for the server to transmit the generated images to the terminal; and means for the terminal to display the transmitted images to the user. This enables a user to easily and intuitively generate realistic scenery images of a specific region with high accuracy.

[1465] A "user" is a person or organization that uses the system to upload images and generate scenic images of a particular area.

[1466] A "terminal" is a hardware device, such as a computer or smartphone, used by a user to upload images, extract metadata information, transmit location information, and display generated images.

[1467] "Metadata information" is auxiliary information included in image files, such as Exif information. It records the location where the image was taken (latitude, longitude), the date and time of the photo, and the camera settings.

[1468] An "image generation artificial intelligence model" is a machine learning model trained to generate landscape images of a specific area, and uses deep learning technology to generate images that reflect the characteristics of the landscape.

[1469] A "reverse geocoder" is a tool or program for obtaining corresponding address information based on location information (latitude and longitude).

[1470] The "server" is a computer system that manages the entire system, processes data sent from terminals, performs reverse geocoding, searches for local landscape data, generates images using an image generation artificial intelligence model, and transmits the generated images.

[1471] "Landscape data" refers to images and other visual information related to a particular region that is used as training data for image generation.

[1472] "Address information" refers to a geographical address obtained based on specific location information (latitude and longitude), such as "Paris, France."

[1473] The present invention relates to an image generation system that enables a user to easily generate realistic landscape images of a specific area. Specific embodiments for carrying out the invention will be described below.

[1474] A user opens an image upload interface on their device (PC, smartphone, etc.). This interface is built using HTML and JavaScript. The user selects a photo file showing a scene from a specific area and presses the upload button. This action sends the image file from the device to the server as an HTTP POST request.

[1475] The device analyzes the metadata information (Exif information) from the uploaded photo file and extracts the latitude and longitude information. This analysis is performed using the Python ExifRead library. For example, in the case of an image of Paris, the extracted latitude and longitude information is latitude "48.8566" and longitude "2.3522". The acquired location information is converted to JSON format and sent to the server as an HTTP POST request.

[1476] The server uses the latitude and longitude information received from the device to send a request to a reverse geocoder API (for example, a map service API) and obtain the corresponding address information. The reverse geocoder API returns address information such as "Paris, France" based on the obtained location information. The server then uses this address information to search for and obtain scenery data for the corresponding area from a database. Database management uses MySQL or PostgreSQL.

[1477] The server then uses the acquired local landscape data to train an image-generating artificial intelligence model. Deep learning frameworks such as TensorFlow and PyTorch are used to train the model. Once training is complete, the model will understand the characteristics of Paris' landscapes and reflect them in the next image it generates. The server then generates new Paris landscape images based on user requests.

[1478] The generated image is sent from the server to the device as an HTTP response. Finally, the device displays the received image on the user interface. HTML and JavaScript technologies are used to display the generated image using the img tag.

[1479] For example, if a user executes the prompt "Prepare a landscape image of a specific location in Paris, and generate a landscape image of the corresponding area based on the latitude and longitude information extracted from the Exif information," the user uploads an image of a Paris landscape. The system then automatically executes the specified steps to generate a realistic landscape image of Paris and display it to the user.

[1480] In this way, the present invention enables users to easily generate realistic landscape images of specific areas with high accuracy, allowing users to efficiently create high-quality content that can be used in a variety of fields.

[1481] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1482] System program processing steps

[1483] Step 1: User uploads an image

[1484] The user opens an image upload interface on their device, which is built with HTML and JavaScript.

[1485] The user selects a photo file showing a scene from a specific area and presses the upload button.

[1486] Input: Photo files showing scenery from a specific area.

[1487] Output: Image data sent as an HTTP POST request.

[1488] Step 2: The device analyzes the image metadata and extracts the location information.

[1489] The device parses the metadata information (Exif information) from the uploaded photo file using the ExifRead library.

[1490] The acquired location information (latitude "48.8566", longitude "2.3522", etc.) is converted to JSON format.

[1491] Input: The uploaded image file.

[1492] Output: Geolocation data in JSON format.

[1493] Step 3: The device sends its location to the server

[1494] The device sends the extracted location information in JSON format to the server as an HTTP POST request.

[1495] Input: Geolocation data in JSON format.

[1496] Output: The HTTP POST request sent to the server.

[1497] Step 4: The server uses the location information to obtain the address information

[1498] The server analyzes the received location information and obtains the corresponding address information using a reverse geocoder API (map service API).

[1499] The requested API returns address information (e.g., "Paris, France").

[1500] Input: Geolocation data in JSON format.

[1501] Output: Address information (e.g., "Paris, France").

[1502] Step 5: The server searches for local landscape data based on the address information.

[1503] The server uses the acquired address information to search the database for scenery data for the corresponding area.

[1504] MySQL and PostgreSQL are used for database management.

[1505] Input: Address information.

[1506] Output: Landscape data related to the region.

[1507] Step 6: The server trains the image generation AI model

[1508] The server uses the acquired local landscape data as input to train an image generation artificial intelligence model using deep learning frameworks (TensorFlow and PyTorch).

[1509] Once trained, the model will understand the characteristics of the local landscape and incorporate them into the next image it generates.

[1510] Input: Regional landscape data.

[1511] Output: A trained image generation model.

[1512] Step 7: The server generates a region-specific landscape image

[1513] Using the learned image generation model, the server generates new landscape images based on user requests.

[1514] Input: A user request and a trained model.

[1515] Output: The generated landscape image.

[1516] Step 8: The server sends the generated image to the device

[1517] The generated image is sent from the server to the terminal as an HTTP response.

[1518] Input: Generated landscape images.

[1519] Output: Image data sent as an HTTP response.

[1520] Step 9: The terminal displays the generated image to the user

[1521] The device displays the received image file on the user interface using HTML and JavaScript technology, with the generated image displayed within an img tag.

[1522] Input: Received image data.

[1523] Output: The image displayed in the user interface.

[1524] Through the above steps, users can easily generate and view realistic landscape images of a specific area.

[1525] (Application example 1)

[1526] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1527] Conventional image generation systems can generate landscape images specific to a region based on images uploaded by users, but they have difficulty generating advertising content related to that region. Furthermore, manually creating region-specific advertising content requires significant time and cost. Therefore, there is a need for a system that allows users to automatically generate and efficiently provide advertising content related to a specific region.

[1528] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1529] In this invention, the server includes: means for a user to upload images; means for a terminal to extract location information from the Exif information of the uploaded images; means for the terminal to transmit the extracted location information to the server; means for the server to obtain address information using a reverse geocoder using the location information; means for the server to search for landscape data related to the region based on the obtained address information; means for the server to include an image generation AI model that learns the landscape data of the searched region; means for the server to generate region-specific images using the learned model; means for the server to transmit the generated images to the terminal; means for the terminal to display the transmitted images to the user; means for generating region-specific advertising content based on the images uploaded by the user; and means for providing the generated region-specific advertising content to the user. This enables users to automatically generate and efficiently use high-quality region-specific landscape images and advertising content based on the uploaded images.

[1530] "User" means a person or entity who utilizes the System to upload images and receive generated content.

[1531] A "terminal" is a device used by a user (e.g., a smartphone or PC) that has the function of uploading and displaying images.

[1532] "Exif information" is metadata contained in an image file, and includes information such as the date and time of shooting and location information.

[1533] "Location information" refers to a geographical location expressed in the form of latitude and longitude.

[1534] The term "server" refers to a computer system that processes data sent from a terminal via a network and executes a predetermined function.

[1535] A "reverse geocoder" is a system that has the function of obtaining address information by inputting latitude and longitude location information.

[1536] "Address information" refers to the specific place name or address corresponding to the location information.

[1537] "Landscape data" refers to data on scenery and features associated with a particular region.

[1538] An "image generation AI model" is an artificial intelligence model that learns the characteristics of a region and generates new images based on the specified region.

[1539] "Localized advertising content" refers to advertising content that is relevant to a specific region and includes information specific to that region.

[1540] "Advertising Content" means content in the form of images or text that contains information intended to promote a product or service.

[1541] A specific embodiment of the present invention will be described. As an application example, a location-specific advertisement generation application is assumed. This system has a function that allows a user to upload an image of a specific location and generates advertisement content related to that location.

[1542] 1. Uploading images and extracting location information

[1543] User

[1544] The user uses an interface to upload images to a device, such as a smartphone or PC. The user selects an image file showing a scene from a specific area and presses the upload button.

[1545] Terminal

[1546] The device analyzes the Exif information from the uploaded image file to obtain latitude and longitude information. For example, if the latitude and longitude of the image are "35.6895" and "139.6917," the device extracts these and converts them into JSON format before sending them to the server.

[1547] 2. Obtaining address information and searching area data

[1548] server

[1549] The server receives the latitude and longitude information sent from the device and sends this location information to a reverse geocoder API (e.g., Google Maps API). The reverse geocoder API returns the address information corresponding to the latitude and longitude information. The server then searches and retrieves local landscape data from a database based on the address information obtained.

[1550] 3. Training and running image generation AI models for generating advertising content

[1551] server

[1552] The server uses the acquired local landscape data to train an image generation AI model. Through this training, the model understands the characteristics of a specific region and reflects these in the images it generates next. To generate region-specific advertisements, the server also creates prompts based on the uploaded images and generates advertising content. The generated advertisement content includes information related to the specific region and is generated as a region-specific advertising image.

[1553] 4. Providing and displaying generated advertising content

[1554] server

[1555] The server saves the generated region-specific advertising content as an image file and transmits it to the terminal as a response.

[1556] Terminal

[1557] The terminal receives the advertisement image file sent from the server and displays it on the user interface, allowing the user to check the generated advertisement content.

[1558] Specific examples

[1559] Hardware and software used

[1560] Hardware: Smartphone or PC

[1561] Software: Python, Exif reading library (exifread), image processing library (PIL), reverse geocoder API (Google Maps API)

[1562] Examples:

[1563] Let's say a user uploads an image of a Tokyo landscape. The Exif information from this image is analyzed to extract the latitude "35.6895" and longitude "139.6917." The server uses the Google Maps API to obtain the address information "Tokyo, Japan" and searches the database for landscape data related to the area. The image generation AI model uses this data to generate advertising content specific to Tokyo and sends it to the user's device. The user can then view the generated advertising image.

[1564] Example prompt sentence:

[1565] "Generate an advertising banner linked to a tourist spot in Tokyo. For example, please use an image containing a view of Shiba Park in Minato Ward, Tokyo."

[1566] In this way, the system according to the present invention can automatically generate advertising content relevant to a specific region based on an image provided by the user, and efficiently provide it to the user.

[1567] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1568] Step 1:

[1569] A user uploads an image.

[1570] How it works: A user uses the application's interface to select an image file depicting a particular area and presses the upload button.

[1571] Input: An image file selected by the user.

[1572] Output: An image file is captured on the device.

[1573] Step 2:

[1574] The device extracts location information from the Exif information of the uploaded image.

[1575] How it works: The device parses the Exif information from the image to obtain latitude and longitude information, for example, by reading the GPS Latitude and GPS Longitude from the Exif information.

[1576] Input: User uploaded image file.

[1577] Output: The extracted latitude and longitude information (e.g. "35.6895, 139.6917").

[1578] Step 3:

[1579] The terminal transmits the extracted location information to the server.

[1580] Operation: The device converts the extracted latitude and longitude information into JSON format and sends it to the server.

[1581] Input: Extracted latitude and longitude information.

[1582] Output: JSON formatted location data sent to the server.

[1583] Step 4:

[1584] The server uses the location information to obtain address information using a reverse geocoder.

[1585] How it works: The server sends the received latitude and longitude information to a reverse geocoder API (e.g., Google Maps API) to obtain the corresponding address information (e.g., "Tokyo, Japan").

[1586] Input: Location data sent to the server in JSON format.

[1587] Output: Address information returned by the Reverse Geocoder API.

[1588] Step 5:

[1589] The server searches for landscape data related to the area based on the address information acquired.

[1590] Operation: The server searches the database for and retrieves landscape data related to the address information.

[1591] Input: Address information obtained from the reverse geocoder API.

[1592] Output: Landscape data related to the region.

[1593] Step 6:

[1594] The server uses an image generation AI model that learns landscape data from the searched area.

[1595] How it works: The server inputs local landscape data and trains the image generation AI model. The model learns the characteristics of a specific area and reflects them in the next image generation.

[1596] Input: Landscape data relevant to the region.

[1597] Output: An image generation AI model that has learned the characteristics of the area.

[1598] Step 7:

[1599] The server uses the trained model to generate region-specific advertising images.

[1600] How it works: The server uses a trained image generation AI model to generate localized ad content based on the image uploaded by the user. It also provides the prompt text to the generation AI model to generate ad content.

[1601] Input: A trained image generation AI model, an uploaded image, and a prompt.

[1602] Output: Region-specific advertising images.

[1603] Step 8:

[1604] The server transmits the generated advertisement image to the terminal.

[1605] How it works: The server saves the generated ad image file and sends it to the user's device as a response.

[1606] Input: The generated ad image.

[1607] Output: The ad image file sent to the device.

[1608] Step 9:

[1609] The terminal displays the transmitted advertisement image to the user.

[1610] Operation: The device displays the received advertisement image file on the user interface so that the user can check it.

[1611] Input: Ad image file sent from server.

[1612] Output: The ad image displayed in the user interface.

[1613] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1614] The present invention provides an image generation system that allows a user to generate a landscape image of a specific area. Furthermore, by combining an emotion engine that recognizes the user's emotions and adjusts the characteristics of the generated image, it is possible to generate a landscape image customized according to the user's emotions. Specific embodiments for implementing the invention are described below.

[1615] ---

[1616] 1. User interaction and image upload

[1617] User

[1618] The user opens the image upload interface using a device (PC, smartphone, etc.), selects a photo file showing a scene from a specific area, and presses the upload button.

[1619] 2. Extracting and sending location information

[1620] Terminal

[1621] The device analyzes the Exif information of the uploaded photo file to obtain latitude and longitude information. For example, for an image of Paris, the device extracts latitude "48.8566" and longitude "2.3522". The device converts this location information into JSON format and sends it to the server.

[1622] 3. Obtaining address information and searching area data

[1623] server

[1624] The server sends the latitude and longitude information received from the device to a reverse geocoder API (e.g., Google Maps API). The reverse geocoder API returns address information (e.g., "Paris, France") corresponding to the latitude and longitude information. The server then searches and retrieves local landscape data from a database based on the returned address information.

[1625] 4. Image generation AI model training and image generation

[1626] server

[1627] The server uses the local landscape data it acquires as input to train an image generation AI model. Through this training, the model understands the characteristics of Parisian landscapes and reflects this in the images it subsequently generates. After the model has completed training, the server generates landscape images specific to the Paris region based on the user's requests.

[1628] 5. Manipulating the Emotion Engine

[1629] server

[1630] The server is equipped with an emotion engine that recognizes the user's emotions. When the user operates the system, the emotion engine acquires the user's emotion data (e.g., happiness, sadness, excitement, etc.) in real time via, for example, a camera or microphone. The acquired emotion data is then analyzed.

[1631] 6. Image Adjustment Based on Emotion Data

[1632] server

[1633] The server adjusts the characteristics of the generated image (such as color tone, brightness, and contrast) based on the emotion data obtained from the emotion engine. For example, if the user's emotion is "happiness," it generates a landscape image of Paris with bright and vivid colors.

[1634] 7. Sending and displaying generated images

[1635] server

[1636] The server saves the generated image as an image file and sends it to the terminal as a response.

[1637] Terminal

[1638] The terminal receives the image file sent from the server and displays it on the user interface.

[1639] Specific examples

[1640] For example, consider the case where a user wants to generate a landscape image of Paris, Europe. The user uploads an image of a specific location in Paris to their device. The device extracts the latitude "48.8566" and longitude "2.3522" from the image and sends them to the server. The server uses a reverse geocoder API to obtain the address information "Paris, France" and retrieves landscape data related to Paris from a database. Based on this, the image generation AI model generates an image that recreates the Paris landscape. The emotion engine recognizes the user's emotions in real time, and if the user is recognized as "happy," an image with bright and vivid colors is generated. The generated image is sent to the user's device, where the user can view the realistic Paris landscape image that was generated.

[1641] ---

[1642] In this way, the system of the present invention not only generates images that reflect the unique characteristics of a region based on the location information of images uploaded by users, but also generates customized images based on the user's emotional data, allowing users to use more personalized, high-quality content for a variety of purposes.

[1643] The processing flow will be explained below.

[1644] Step 1:

[1645] User

[1646] The user opens the image upload interface on the device, selects a photo file showing a scene from a specific area, and presses the upload button.

[1647] Step 2:

[1648] Terminal

[1649] The device analyzes the Exif information of the uploaded photo file to obtain latitude and longitude information. For example, for an image of Paris, the latitude "48.8566" and longitude "2.3522" are extracted.

[1650] Step 3:

[1651] Terminal

[1652] The terminal converts the extracted latitude and longitude information into JSON format and sends it to the server.

[1653] Step 4:

[1654] server

[1655] The server receives the latitude and longitude information from the device and sends it to the reverse geocoder API to obtain the address information.

[1656] Step 5:

[1657] server

[1658] Receive the address information (e.g., Paris, France) returned from the reverse geocoder API and search the database to obtain landscape data for the corresponding area.

[1659] Step 6:

[1660] server

[1661] The server inputs the acquired local landscape data into an image generation AI model, allowing the AI ​​model to learn. The learning data is preprocessed and normalized, and then formatted as input for the AI ​​model.

[1662] Step 7:

[1663] server

[1664] The server uses a trained AI model to generate images that reflect the characteristics of the specified area. Depending on the generation task, conditional inputs (e.g., season, time of day, etc.) can be added to achieve high-precision generation.

[1665] Step 8:

[1666] server

[1667] The server's emotion engine acquires the user's emotion data, for example, by analyzing the user's facial expressions and voice in real time using a camera and microphone.

[1668] Step 9:

[1669] server

[1670] Based on the acquired emotional data, the system adjusts the characteristics of the generated image (color tone, brightness, contrast, etc.). For example, if the user is recognized as "happy," it generates an image with bright and vivid colors.

[1671] Step 10:

[1672] server

[1673] The server saves the generated image as an image file and transmits it to the terminal as response data.

[1674] Step 11:

[1675] Terminal

[1676] The terminal acquires the response data received from the server, extracts the image file generated from the response data, and displays it on the user interface.

[1677] Step 12:

[1678] User

[1679] The user checks the displayed image and, if necessary, presses the download button to save the image file to his / her terminal.

[1680] ---

[1681] In this way, the system of the present invention not only generates images that reflect the unique characteristics of a region based on the location information of images uploaded by users, but also generates customized images based on the user's emotional data, allowing users to use more personalized, high-quality content for a variety of purposes.

[1682] Example 2

[1683] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1684] Conventional image generation systems can generate landscape images that reflect the characteristics of a specific region from images uploaded by users, but they lack customization based on the user's emotions. Also, they have few interactive elements, so there is a need for technology to provide more personalized content.

[1685] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes emotion recognition means for acquiring and analyzing emotion data of the user, means for adjusting the characteristics of the generated image based on the acquired emotion data, and means including an image generation model that learns using landscape data of the searched area as input. This makes it possible to generate high-quality landscape images customized based on the user's emotions while reflecting the regional characteristics of the image uploaded by the user.

[1686] "Image file" means a file containing visual information stored in digital format.

[1687] A "terminal" is an electronic device operated by a user, and includes a personal computer, a smartphone, etc.

[1688] "Exif information" is metadata embedded in an image file, and includes information such as the date and time of the image being taken and its location.

[1689] "Location information" refers to latitude and longitude data that indicates a specific location.

[1690] A "server" refers to a computer system that provides services over a network.

[1691] "Reverse geocoding" refers to the process of obtaining corresponding address information from latitude and longitude information.

[1692] "Address information" refers to geographical description data that indicates a specific location.

[1693] "Landscape data" refers to digital images and information that show the scenery and features of a particular area.

[1694] An "image generation model" refers to a machine learning model that is trained to generate new images based on input data.

[1695] "Emotion recognition means" refers to technology for acquiring and analyzing a user's emotions in real time.

[1696] "Emotion data" refers to information that indicates the user's emotional state.

[1697] "Characteristics" refers to visual elements such as color, brightness, and contrast in images and data.

[1698] The present invention provides an image generation system that allows a user to generate a landscape image of a specific area. Furthermore, by combining an emotion engine that recognizes the user's emotions and adjusts the characteristics of the generated image, it is possible to generate a landscape image customized according to the user's emotions. Specific embodiments for implementing the invention are described below.

[1699] First, a user uploads an image using a device such as a PC or smartphone. The device analyzes the latitude and longitude from the Exif information in the uploaded image file, converts this location information into JSON format, and sends it to the server. The device then selects an image of a specific area, for example, and presses the "upload" button.

[1700] The server sends the received latitude and longitude information to a reverse geocoder API (e.g., Google Maps API) to obtain the corresponding address information. Based on this address information, the server searches and obtains the landscape data of the relevant area from the database.

[1701] The acquired landscape data of the area becomes input data for training an image generation AI model (e.g., Generative Adversarial Network: GAN) on the server. Through this training process, the AI ​​model will be able to recognize the characteristics of the area and reflect them in the next image generation.

[1702] Once the model has completed its training, the server generates a new landscape image with the unique characteristics of the region according to the user's request. This generated image is not left as is; rather, the emotion engine further adjusts the image's color tone, brightness, contrast, and other characteristics based on the results of acquiring and analyzing the user's emotional data.

[1703] Specifically, the system captures the user's emotions (e.g., happiness, sadness, excitement, etc.) in real time through a camera and microphone, and if the user is recognized as happy, for example, the image is adjusted to have brighter, more vivid colors.

[1704] Finally, the server sends the generated image to the terminal, which displays the received image file on the user interface, allowing the user to check the generated realistic landscape image.

[1705] Specific examples

[1706] For example, consider a case where a user wants to generate a landscape image of Paris, Europe. The user uploads an image of a specific location in Paris to their device. The device extracts the latitude "48.8566" and longitude "2.3522" from the image and sends them to the server. The server uses a reverse geocoder API to obtain the address information "Paris, France" and retrieves landscape data related to Paris from a database. An image generation AI model uses this information to generate an image that recreates the Paris landscape. The emotion engine recognizes the user's emotions in real time, and if it recognizes "happiness," it generates an image with bright, vivid colors. The generated image is sent to the user's device, where the user can view the realistic Paris landscape image.

[1707] Prompt Sentence Examples

[1708] "Upload a picture of Paris and sit back and relax while we analyze the sentiment of your image."

[1709] Through the above process, the system of the present invention can generate images that reflect the characteristics of a particular region based on the location information of images uploaded by users, as well as generate customized images based on the user's emotional data, allowing users to enjoy more personalized, high-quality content.

[1710] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1711] Step 1:

[1712] User image upload

[1713] The user opens the image upload interface using a device (such as a PC or smartphone), selects a photo file showing a scene from a specific area, and presses the upload button.

[1714] Input: An image file selected by the user.

[1715] Output: Image file uploaded to the device

[1716] Specific operation: When the user selects an image file and clicks the "Upload" button, the image file is uploaded to the device.

[1717] Step 2:

[1718] Extracting location information

[1719] The device analyzes the Exif information of the uploaded image file and extracts the latitude and longitude information. For example, in the case of an image of Paris, the device extracts the latitude "48.8566" and longitude "2.3522".

[1720] Input: Image file containing Exif information

[1721] Output: Extracted latitude and longitude information (e.g., latitude "48.8566", longitude "2.3522")

[1722] What happens: The device parses the Exif metadata of the image file to read the latitude and longitude, which are then prepared for transmission to the server in the next step.

[1723] Step 3:

[1724] Sending location information

[1725] The device converts the acquired latitude and longitude information into JSON format and sends it to the server. This JSON data contains the necessary location information.

[1726] Input: Extracted latitude and longitude information

[1727] Output: Location information sent to the server in JSON format

[1728] Specific operation: The device converts the latitude and longitude information into JSON format and sends it to the server as an HTTP request.

[1729] Step 4:

[1730] Obtaining address information

[1731] The server sends the received latitude and longitude information to a reverse geocoder API (e.g., a geographic information API) to obtain the corresponding address information. This API returns the address information corresponding to the latitude and longitude information.

[1732] Input: JSON data containing latitude and longitude information

[1733] Output: The address information obtained (e.g., "Paris, France")

[1734] Specific operation: The server sends latitude and longitude information to the API and receives address information returned from the API.

[1735] Step 5:

[1736] Searching for geographical data

[1737] Based on the acquired address information, the server searches the database for landscape data for the area and retrieves the relevant data.

[1738] Input: Address information

[1739] Output: Landscape data of the relevant area

[1740] Specific operation: The server uses the address information as a search key in the database to retrieve landscape data for the corresponding area.

[1741] Step 6:

[1742] Learning an image generation AI model

[1743] The server uses the acquired local landscape data as input to train the image generation AI model. Through this training process, the model will be able to recognize the local characteristics.

[1744] Input: Regional landscape data

[1745] Output: Trained image generation AI model

[1746] How it works: The server feeds local landscape data to the AI ​​model and applies a learning algorithm to train the model.

[1747] Step 7:

[1748] Image generation

[1749] Using the image generation AI model that has completed training, the server generates new landscape images based on the user's requests.

[1750] Input: Trained image generation AI model, user request (prompt sentence)

[1751] Output: Generated landscape image

[1752] Specific operation: The server uses the trained AI model to perform the calculations necessary to generate a new landscape image and generate an image file.

[1753] Step 8:

[1754] Emotion recognition by emotion engine

[1755] The server has an emotion recognition unit that captures and analyzes the user's emotion data in real time. The server captures the user's emotions (e.g., happiness, sadness, excitement, etc.) through a camera and microphone.

[1756] Input: User emotion data acquired through camera and microphone

[1757] Output: Parsed user's emotional state

[1758] Specific operation: The server collects emotional data through the camera and microphone, and applies an emotion analysis algorithm to recognize the user's emotional state.

[1759] Step 9:

[1760] Image adjustment

[1761] The server adjusts the characteristics of the generated image based on information from the emotion recognition means, for example, if the user is recognized as "happy," it adjusts the color tone of the image to be brighter and more vivid.

[1762] Input: Generated landscape image, analyzed user's emotional state

[1763] Output: Adjusted landscape image

[1764] Specific behavior: The server adjusts the color tone, brightness, contrast, and other characteristics of the generated image based on the emotional state.

[1765] Step 10:

[1766] Sending generated images

[1767] The server saves the adjusted image as a file and transmits it to the terminal as response data.

[1768] Input: Adjusted landscape image

[1769] Output: The final generated image sent to the device.

[1770] Specific operation: The server sends the adjusted image to the device as an HTTP response.

[1771] Step 11:

[1772] Displaying the generated image

[1773] The terminal receives the image file sent from the server and displays it on the user interface.

[1774] Input: Image file received from the server

[1775] Output: The final generated image displayed in the user interface.

[1776] Specific behavior: The device receives the image file and displays it to the user in a browser or application.

[1777] Through the above specific processing, the system of the present invention can generate images that reflect the unique characteristics of a region based on the location information of images uploaded by users, and can also provide high-quality landscape images customized to match the user's emotional data.

[1778] (Application example 2)

[1779] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1780] Existing image generation systems can generate region-specific landscape images based on images uploaded by users, but they do not customize the images based on the user's emotions, making it difficult to provide an optimized experience for each individual user. Furthermore, applications such as virtual tourism require real-time landscape images that reflect the user's emotions, but no system exists that can meet this need. This limits the user experience and poses the challenge of being unable to provide a personalized tourism experience based on emotions.

[1781] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1782] In this invention, the server includes a means for training an image generation AI model, an emotion recognition means for recognizing a user's emotion, and a means for adjusting the characteristics of the generated image based on the emotion, thereby enabling the server to customize region-specific landscape images according to the user's emotion and provide a more personalized sightseeing experience.

[1783] An "image generation AI model" is an artificial intelligence algorithm that learns specific features and patterns based on input data and generates realistic images.

[1784] "Emotion recognition means" refers to technology including sensors and software for identifying a user's emotions in real time.

[1785] "Exif information" is metadata embedded in image files taken with a digital camera, and includes information such as the date and time the image was taken and its location.

[1786] A "reverse geocoder" is a technology or API for obtaining corresponding address information based on latitude and longitude information.

[1787] "Landscape data" is image data of scenery and buildings related to a specific area, and is data that reflects the characteristics of that area.

[1788] A "terminal" is a device used to upload or receive images, including smartphones and personal computers.

[1789] "Address information" is physical address data corresponding to a specific latitude and longitude obtained by a reverse geocoder.

[1790] "Location-specific imagery" is imagery that reflects the characteristics and visual elements of a particular geographic location and recreates the landscape of a particular region.

[1791] "Means for adjusting the characteristics of the generated image based on emotion" refers to a technology that analyzes the user's emotional data and dynamically changes the color tone, brightness, contrast, etc. of the generated image based on the results.

[1792] The present invention provides an image generation system that allows a user to generate landscape images of a specific area, and also provides a function that recognizes the user's emotions and adjusts the characteristics of the generated image. Specific embodiments of the invention are described below.

[1793] 1. User interaction and image upload

[1794] The user opens the image upload interface using a device (PC, smartphone, etc.), selects an image file showing a scene from a specific area, and presses the upload button. This uploaded image contains Exif information, which allows location information to be obtained.

[1795] 2. Extracting and sending location information

[1796] The device analyzes the Exif information of the uploaded image and obtains the latitude and longitude information. For example, for an image of Paris, the latitude "48.8566" and longitude "2.3522" are extracted. The device converts this location information into JSON format and sends it to the server.

[1797] 3. Obtaining address information and searching area data

[1798] The server uses the reverse geocoder API to obtain address information (e.g., "Paris, France") from the latitude and longitude information received from the device. Based on the returned address information, the server searches for and obtains landscape data for the corresponding area from a database.

[1799] 4. Image generation AI model training and image generation

[1800] The server uses the local landscape data it acquires as input to train an image generation AI model. Through this training, the model understands the characteristics of Paris' landscapes and reflects this in the images it subsequently generates. After the model has completed training, the server generates region-specific landscape images based on the user's requests.

[1801] 5. Manipulation of emotion recognition measures

[1802] The server is equipped with an emotion recognition means for recognizing the user's emotions. When the user operates the system, the emotion recognition means acquires the user's emotion data (e.g., happiness, sadness, excitement, etc.) in real time via, for example, a camera or microphone. The acquired emotion data is then analyzed.

[1803] 6. Image Adjustment Based on Emotion Data

[1804] The server adjusts the characteristics of the generated image (color tone, brightness, contrast, etc.) based on the emotion data acquired from the emotion recognition means. For example, if the user's emotion is "happiness," it generates a region-specific landscape image with bright, vivid colors.

[1805] 7. Sending and displaying generated images

[1806] The server saves the generated image as an image file and sends it to the terminal as a response. The terminal receives the image file sent from the server and displays it on the user interface.

[1807] Specific examples

[1808] For example, if a user uploads an image of the Eiffel Tower in Paris, the location information (latitude 48.8584, longitude 2.2945) is extracted. If emotion recognition detects "excitement," a colorful, dynamic image of the Eiffel Tower is generated.

[1809] Prompt Sentence Examples

[1810] "A user uploads an image of the Eiffel Tower. If emotion recognition detects excitement, generate a colorful, animated image of the Eiffel Tower."

[1811] In this way, the system of the present invention can generate images that reflect the characteristics of a particular region based on the location information of images uploaded by users, as well as generate customized images based on the user's emotional data, allowing users to use more personalized, high-quality content for a variety of purposes.

[1812] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1813] Step 1:

[1814] A user opens the image upload interface on a terminal, selects an image file showing a scene from a specific area, and presses the upload button. The input is the image file selected by the user. The output is the image file uploaded to the terminal.

[1815] Step 2:

[1816] The device analyzes the Exif information of the uploaded image and obtains the latitude and longitude information. The input is the image file. The data is processed by extracting the latitude and longitude from the Exif information. The output is location information such as latitude "48.8566" and longitude "2.3522".

[1817] Step 3:

[1818] The location information extracted by the device is converted to JSON format and sent to the server. The input is latitude and longitude information. The location information is converted to JSON format as data processing. The location information data in JSON format is sent to the server as output.

[1819] Step 4:

[1820] The server uses the reverse geocoder API to obtain address information from the latitude and longitude information received from the device. The input is location data in JSON format. For data calculation, the location information is sent to the reverse geocoder API and the corresponding address information is received. The output is address information such as "Paris, France."

[1821] Step 5:

[1822] Based on the address information acquired by the server, the landscape data for the relevant area is searched and acquired from the database. The input is the address information. A database search is performed as a data calculation. The landscape data for the relevant area is obtained as the output.

[1823] Step 6:

[1824] The server uses the landscape data of the area acquired as input to train an image generation AI model. The input is the landscape data of the area. The AI ​​model is trained as a data calculation. The trained image generation AI model is obtained as an output.

[1825] Step 7:

[1826] The server uses the trained image generation AI model to generate region-specific images. The input is the trained AI model and the user's request. The data is processed to generate a landscape image. The output is a region-specific image.

[1827] Step 8:

[1828] The server operates the emotion recognition means to recognize the user's emotions and acquires the user's emotion data. The input is the emotion data obtained when the user operates the device. The data is analyzed by the emotion recognition means as a data calculation. The output is the user's emotion data.

[1829] Step 9:

[1830] The server adjusts the characteristics (color tone, brightness, contrast, etc.) of the generated image based on the emotion data acquired from the emotion recognition means. The input is the emotion data and the generated image. The image characteristics are adjusted as part of the data processing. The adjusted image is obtained as the output.

[1831] Step 10:

[1832] The server saves the generated image as an image file and sends it to the terminal as a response. The input is the generated image. The image file is sent as a data calculation. The image file is sent to the terminal as an output.

[1833] Step 11:

[1834] The terminal receives the image file sent from the server and displays it on the user interface. The input is the image file sent from the server. The data is processed by converting the image into a display format. The output is the adjusted image displayed to the user.

[1835] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1836] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1837] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1838] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1839] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1840] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1841] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1842] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1843] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1844] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1845] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1846] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1847] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1848] 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.

[1849] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1850] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1851] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1852] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1853] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1854] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1855] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1856] The following is further disclosed regarding the above embodiment.

[1857] (Claim 1)

[1858] a means for a user to upload an image;

[1859] A means for extracting location information from Exif information of an uploaded image by the terminal;

[1860] means for transmitting the extracted location information by the terminal to a server;

[1861] A means for the server to obtain address information by a reverse geocoder using the location information;

[1862] A means for searching landscape data related to the region based on the address information acquired by the server;

[1863] A means including an image generation AI model that learns landscape data of the searched area in the server;

[1864] a means for the server to generate region-specific images using the trained model;

[1865] means for transmitting the image generated by the server to the terminal;

[1866] The system includes means for the terminal to display the transmitted image to the user.

[1867] (Claim 2)

[1868] The system according to claim 1, further comprising a reverse geocoding means including a means for acquiring address information using location information extracted from the Exif information of the image, and a means for searching for landscape data of the area based on the acquired address information.

[1869] (Claim 3)

[1870] The system of claim 1, further comprising means for training the image generation AI model to generate images that reflect the characteristics of a particular region.

[1871] "Example 1"

[1872] (Claim 1)

[1873] a means for a user to upload an image;

[1874] A means for extracting location information from metadata information of an uploaded image by the terminal;

[1875] means for transmitting the extracted location information by the terminal to a server;

[1876] A means for the server to obtain address information by a reverse geocoder using the location information;

[1877] A means for searching for landscape data related to the area based on the address information acquired by the server;

[1878] A server includes an image generation artificial intelligence model that learns landscape data of the searched area;

[1879] a means for the server to generate region-specific images using the trained model;

[1880] means for transmitting the image generated by the server to the terminal;

[1881] The system includes means for the terminal to display the transmitted image to the user.

[1882] (Claim 2)

[1883] The system of claim 1 further comprising a reverse geocoding means including means for obtaining address information using location information extracted from metadata information of the image, and means for searching for local scenery data based on the obtained address information.

[1884] (Claim 3)

[1885] 2. The system of claim 1, further comprising means for training the image generation artificial intelligence model to generate images that reflect the characteristics of a particular region.

[1886] "Application Example 1"

[1887] (Claim 1)

[1888] a means for a user to upload an image;

[1889] A means for extracting location information from Exif information of an uploaded image by the terminal;

[1890] means for transmitting the extracted location information by the terminal to a server;

[1891] A means for the server to obtain address information by a reverse geocoder using the location information;

[1892] A means for searching landscape data related to the region based on the address information acquired by the server;

[1893] A means including an image generation AI model that learns landscape data of the searched area in the server;

[1894] a means for the server to generate region-specific images using the trained model;

[1895] means for transmitting the image generated by the server to the terminal;

[1896] means for the terminal to display the transmitted image to the user;

[1897] means for generating geo-specific advertising content based on images uploaded by users;

[1898] Means for providing generated localized advertising content to users

[1899] A system including:

[1900] (Claim 2)

[1901] The system according to claim 1, further comprising a reverse geocoding means including a means for acquiring address information using location information extracted from the Exif information of the image and a means for searching for local landscape data based on the acquired address information, and a means for generating localized advertising content.

[1902] (Claim 3)

[1903] The system of claim 1, wherein the image generation AI model and the local-specific advertisement generation means comprise means for learning to generate images and advertisement content that reflect the characteristics of a specific region.

[1904] "Example 2: Combining Emotion Engines"

[1905] (Claim 1)

[1906] a means for a user to upload an image file;

[1907] A means for analyzing and extracting location information from the Exif information of the uploaded image file by the terminal;

[1908] means for transmitting the extracted location information by the terminal to a server;

[1909] A means for the server to obtain address information by reverse geocoding using the transmitted location information;

[1910] A means for searching landscape data related to the region based on the address information acquired by the server;

[1911] A means for the server to include an image generation model that learns using landscape data of the searched area as input;

[1912] A means for the server to generate region-specific images using the trained image generation model;

[1913] means for transmitting the image generated by the server to the terminal;

[1914] means for the terminal to display the transmitted image to the user;

[1915] An emotion recognition means for the server to acquire and analyze emotion data of a user;

[1916] The system includes a server that adjusts characteristics of the generated image based on information from the emotion recognition means.

[1917] (Claim 2)

[1918] The system according to claim 1, further comprising: means for acquiring address information using location information extracted from the Exif information of the image; and reverse geocoding means for searching for landscape data of the area based on the acquired address information.

[1919] (Claim 3)

[1920] 2. The system of claim 1, further comprising means for training the image generation model to generate images that reflect the characteristics of a particular region.

[1921] (Claim 4)

[1922] 2. The system of claim 1, wherein the server comprises means for adjusting characteristics of the generated image based on the user's emotional data.

[1923] "Application example 2 when combining emotion engines"

[1924] (Claim 1)

[1925] a means for a user to upload an image;

[1926] A means for extracting location information from Exif information of an uploaded image by the terminal;

[1927] means for transmitting the extracted location information by the terminal to a server;

[1928] A means for the server to obtain address information by a reverse geocoder using the location information;

[1929] A means for searching landscape data related to the region based on the address information acquired by the server;

[1930] A means including an image generation AI model that learns landscape data of the searched area in the server;

[1931] a means for the server to generate region-specific images using the trained model;

[1932] A server includes an emotion recognition means for recognizing an emotion of a user;

[1933] a means for adjusting the characteristics of the generated image based on the emotion acquired by the emotion recognition means;

[1934] means for transmitting the image generated by the server to the terminal;

[1935] The system includes means for the terminal to display the transmitted image to the user.

[1936] (Claim 2)

[1937] The system according to claim 1, further comprising a reverse geocoding means including a means for acquiring address information using location information extracted from the Exif information of the image, and a means for searching for landscape data of the area based on the acquired address information.

[1938] (Claim 3)

[1939] 2. The system of claim 1, wherein the image generation AI model comprises means for learning to generate images that reflect the characteristics of a particular region and the emotions of a user. [Explanation of symbols]

[1940] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for a user to upload an image; A means for extracting location information from Exif information of an uploaded image by the terminal; means for transmitting the extracted location information by the terminal to a server; A means for the server to obtain address information by a reverse geocoder using the location information; A means for searching landscape data related to the region based on the address information acquired by the server; A means including an image generation AI model that learns landscape data of the searched area in the server; a means for the server to generate region-specific images using the trained model; means for transmitting the image generated by the server to the terminal; The system includes means for the terminal to display the transmitted image to the user.

2. The system according to claim 1, further comprising a reverse geocoding means including a means for acquiring address information using location information extracted from the Exif information of the image, and a means for searching for local landscape data based on the acquired address information.

3. The system of claim 1, further comprising means for training the image generation AI model to generate images that reflect the characteristics of a particular region.

Images