Electronic device and control method thereof

Abstract

The present disclosure provides an electronic device and a control method thereof. A method, according to one embodiment, may comprise the operations of: acquiring a plurality of images; identifying the plurality of images as an image group having a specific image pattern; acquiring a first image; and acquiring a second image generated by correcting the first image according to at least a part of the specific image pattern, at least partially on the basis of a determination that the first image corresponds to the image group.

Description

Electronic device and method of controlling the same

[0001] The present disclosure relates to an electronic device and method capable of generating an image.

[0002] With the advancement of mobile communication technology, the use of portable or mobile electronic devices (e.g., smartphones, wearable devices) has become widespread, and the functions provided through these electronic devices are becoming increasingly diverse. For example, electronic devices can provide the function of capturing images and displaying the captured images.

[0003] The information described above may be provided as related art for the purpose of aiding understanding of the present disclosure. None of the foregoing is to be claimed as prior art related to the present disclosure, nor is it to be used to determine prior art.

[0004] The present disclosure relates to an electronic device and method capable of automatically correcting an image.

[0005] According to one embodiment, the electronic device comprises a memory including at least one storage medium for storing instructions; and at least one processor including a processing circuit, wherein when the instructions are executed individually or collectively by the at least one processor, the electronic device may be caused to perform at least one operation. The at least one operation may include an operation of acquiring a plurality of images. The at least one operation may include an operation of identifying the plurality of images into an image group having a specific image pattern. The at least one operation may include an operation of acquiring a first image. The at least one operation may include an operation of acquiring a second image generated by correcting the first image according to at least a part of the specific image pattern, based at least partly on a determination that the first image corresponds to the image group.

[0006] According to one embodiment, a control method for an electronic device may include at least one operation. The at least one operation may include an operation of acquiring a plurality of images. The at least one operation may include an operation of identifying the plurality of images into an image group having a specific image pattern. The at least one operation may include an operation of acquiring a first image. The at least one operation may include an operation of acquiring a second image generated by correcting the first image according to at least a part of the specific image pattern, based at least partially on a determination that the first image corresponds to the image group.

[0007] According to one embodiment, a storage medium may be provided for storing at least one instruction readable by a computer. The at least one instruction may cause the electronic device to perform at least one operation when executed by at least a part of at least one processor of the electronic device. The at least one operation may include an operation of acquiring a plurality of images. The at least one operation may include an operation of identifying the plurality of images into an image group having a specific image pattern. The at least one operation may include an operation of acquiring a first image. The at least one operation may include an operation of acquiring a second image generated by correcting the first image according to at least a part of the specific image pattern, based at least partly on a determination that the first image corresponds to the image group.

[0008] According to embodiments of the present disclosure, an electronic device and a control method thereof can automatically generate a series of images based on data regarding image patterns. The electronic device and a control method thereof can maximize the consistency of the series of images. The electronic device and a control method thereof can reduce the workload required of the user during the production process of the series of images. The electronic device and a control method thereof support original restoration and / or parallel management of the original image and the generated image for the generated image, thereby enabling the user to conveniently manage and freely adjust the series of images.

[0009] The effects obtainable from the exemplary embodiments of the present disclosure are not limited to those mentioned above, and other unmentioned effects can be clearly derived and understood by those skilled in the art to which the exemplary embodiments of the present disclosure belong from the description below. That is, unintended effects resulting from the implementation of the exemplary embodiments of the present disclosure can also be derived by those skilled in the art from the exemplary embodiments of the present disclosure.

[0010] FIG. 1 is a block diagram of an electronic device in a network environment according to various embodiments.

[0011] FIGS. 2a to 2i illustrate exemplary series of images.

[0012] FIG. 3 is a block diagram showing a configuration for image acquisition according to one embodiment.

[0013] FIGS. 4a and 4b illustrate exemplary elements of an image pattern according to one embodiment.

[0014] FIGS. 5a to 5c illustrate an image acquisition method according to one embodiment.

[0015] FIG. 6 is a flowchart for explaining the operation of an electronic device according to one embodiment.

[0016] Figures 7a and 7b illustrate an exemplary method for acquiring an image corresponding to a category of image patterns.

[0017] Figures 8a and 8b illustrate an exemplary method for acquiring an image corresponding to a category of image patterns.

[0018] Figures 9a and 9b illustrate an exemplary method for acquiring an image corresponding to a category of image patterns.

[0019] FIG. 10 is a flowchart illustrating a method for acquiring an image pattern according to one embodiment.

[0020] FIG. 11 is a flowchart illustrating an image acquisition method according to one embodiment.

[0021] FIGS. 12a and 12b illustrate an image acquisition method according to one embodiment.

[0022] FIG. 13 illustrates a generative artificial intelligence system according to one embodiment.

[0023] FIG. 14 illustrates an image generation category of an image pattern according to one embodiment.

[0024] FIGS. 15a to 15d illustrate an image acquisition method according to one embodiment.

[0025] FIGS. 16a and 16b illustrate user interface screens regarding an image pattern according to one embodiment.

[0026] FIGS. 17a and 17b illustrate execution screens of a second application according to one embodiment.

[0027] FIG. 18 illustrates a method for updating images corresponding to categories of image patterns according to one embodiment.

[0028] FIG. 19 is a flowchart for explaining an image acquisition method according to one embodiment.

[0029] Hereinafter, embodiments of the present disclosure are described in detail with reference to the drawings so that those skilled in the art can easily practice them. However, the present disclosure may be embodied in various different forms and is not limited to the embodiments described herein. In relation to the description of the drawings, the same or similar reference numerals may be used for identical or similar components. Furthermore, in the drawings and related descriptions, descriptions of well-known functions and configurations may be omitted for clarity and brevity.

[0030] An embodiment of the present disclosure will be described below with reference to the attached drawings.

[0031] FIG. 1 is a block diagram of an electronic device (101) in a network environment (100) according to various embodiments.

[0032] Referring to FIG. 1, in a network environment (100), an electronic device (101) may communicate with an electronic device (102) through a first network (198) (e.g., a short-range wireless communication network) or with at least one of an electronic device (104) or a server (108) through a second network (199) (e.g., a long-range wireless communication network). According to one embodiment, the electronic device (101) may communicate with the electronic device (104) through a server (108). According to one embodiment, the electronic device (101) may include a processor (120), memory (130), input module (150), sound output module (155), display module (160), audio module (170), sensor module (176), interface (177), connection terminal (178), haptic module (179), camera module (180), power management module (188), battery (189), communication module (190), subscriber identification module (196), or antenna module (197). In some embodiments, at least one of these components (e.g., connection terminal (178)) may be omitted from the electronic device (101), or one or more other components may be added. In some embodiments, some of these components (e.g., sensor module (176), camera module (180), or antenna module (197)) may be integrated into a single component (e.g., display module (160)).

[0033] The processor (120) can control at least one other component (e.g., a hardware or software component) of the electronic device (101) connected to the processor (120) by executing software (e.g., a program (140)), and can perform various data processing or operations. According to one embodiment, as at least part of the data processing or operations, the processor (120) can store commands or data received from other components (e.g., a sensor module (176) or a communication module (190)) in volatile memory (132), process the commands or data stored in volatile memory (132), and store the resulting data in non-volatile memory (134). According to one embodiment, the processor (120) may include a main processor (121) (e.g., a central processing unit or an application processor) or an auxiliary processor (123) that can operate independently or together with it (e.g., a graphics processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor). For example, if the electronic device (101) includes a main processor (121) and an auxiliary processor (123), the auxiliary processor (123) may be configured to use lower power than the main processor (121) or to be specialized for a designated function. The auxiliary processor (123) may be implemented separately from the main processor (121) or as part thereof.

[0034] The auxiliary processor (123) may control at least some of the functions or states associated with at least one component of the electronic device (101) (e.g., display module (160), sensor module (176), or communication module (190)) on behalf of the main processor (121) while the main processor (121) is in an inactive (e.g., sleep) state, or together with the main processor (121) while the main processor (121) is in an active (e.g., application execution) state. According to one embodiment, the auxiliary processor (123) (e.g., image signal processor or communication processor) may be implemented as part of another functionally related component (e.g., camera module (180) or communication module (190)). According to one embodiment, the auxiliary processor (123) (e.g., neural network processing unit) may include a hardware structure specialized for processing an artificial intelligence model. The artificial intelligence model may be generated through machine learning. Such learning may be performed, for example, on the electronic device (101) itself where the artificial intelligence model is executed, or through a separate server (e.g., server (108)). The learning algorithm may include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but is not limited to the examples described above. The artificial intelligence model may include a plurality of artificial neural network layers.An artificial neural network may be a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), a deep Q-network, or a combination of two or more of the above, but is not limited to the examples described above. In addition to the hardware structure, the artificial intelligence model may include a software structure, either additionally or substantially.

[0035] The memory (130) can store various data used by at least one component of the electronic device (101) (e.g., processor (120) or sensor module (176)). The data may include, for example, input data or output data for software (e.g., program (140)) and related commands. The memory (130) may include volatile memory (132) or non-volatile memory (134).

[0036] The program (140) may be stored as software in memory (130) and may include, for example, an operating system (142), middleware (144), or an application (146).

[0037] The input module (150) can receive commands or data to be used for a component of the electronic device (101) (e.g., processor (120)) from outside the electronic device (101) (e.g., user). The input module (150) may include, for example, a microphone, a mouse, a keyboard, a key (e.g., a button), or a digital pen (e.g., a stylus pen).

[0038] The sound output module (155) can output a sound signal to the outside of the electronic device (101). The sound output module (155) may include, for example, a speaker or a receiver. The speaker may be used for general purposes, such as multimedia playback or recording playback. The receiver may be used to receive incoming calls. According to one embodiment, the receiver may be implemented separately from the speaker or as part thereof.

[0039] The display module (160) can visually provide information to an external (e.g., user) of the electronic device (101). The display module (160) may include, for example, a display, a holographic device, or a projector and a control circuit for controlling said device. According to one embodiment, the display module (160) may include a touch sensor configured to detect a touch, or a pressure sensor configured to measure the intensity of the force generated by said touch.

[0040] The audio module (170) can convert sound into an electrical signal or, conversely, convert an electrical signal into sound. According to one embodiment, the audio module (170) can acquire sound through the input module (150) or output sound through the sound output module (155) or an external electronic device (e.g., electronic device (102)) (e.g., speaker or headphones) connected directly or wirelessly to the electronic device (101).

[0041] The sensor module (176) can detect the operating state of the electronic device (101) (e.g., power or temperature) or the external environmental state (e.g., user state) and generate an electrical signal or data value corresponding to the detected state. According to one embodiment, the sensor module (176) may include, for example, a gesture sensor, a gyroscope sensor, a barometric pressure sensor, a magnetic sensor, an accelerometer sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biosensor, a temperature sensor, a humidity sensor, or an illuminance sensor.

[0042] The interface (177) may support one or more specified protocols that can be used for the electronic device (101) to be connected directly or wirelessly to an external electronic device (e.g., electronic device (102)). According to one embodiment, the interface (177) may include, for example, a high definition multi-media interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

[0043] The connection terminal (178) may include a connector through which the electronic device (101) can be physically connected to an external electronic device (e.g., electronic device (102)). According to one embodiment, the connection terminal (178) may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (e.g., a headphone connector).

[0044] The haptic module (179) can convert an electrical signal into a mechanical stimulus (e.g., vibration or movement) or an electrical stimulus that can be perceived by the user through tactile or kinesthetic senses. According to one embodiment, the haptic module (179) may include, for example, a motor, a piezoelectric element, or an electric stimulation device.

[0045] The camera module (180) can capture still images and video. According to one embodiment, the camera module (180) may include one or more lenses, image sensors, image signal processors, or flashes.

[0046] The power management module (188) can manage power supplied to the electronic device (101). According to one embodiment, the power management module (188) can be implemented, for example, as at least part of a power management integrated circuit (PMIC).

[0047] The battery (189) can supply power to at least one component of the electronic device (101). According to one embodiment, the battery (189) may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0048] The communication module (190) can support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between an electronic device (101) and an external electronic device (e.g., electronic device (102), electronic device (104), or server (108)), and the performance of communication through the established communication channel. The communication module (190) may include one or more communication processors that operate independently of the processor (120) (e.g., application processor) and support direct (e.g., wired) communication or wireless communication. According to one embodiment, the communication module (190) may include a wireless communication module (192) (e.g., cellular communication module, short-range wireless communication module, or GNSS (global navigation satellite system) communication module) or a wired communication module (194) (e.g., LAN (local area network) communication module, or power line communication module). The corresponding communication module among these communication modules can communicate with an external electronic device (104) through a first network (198) (e.g., a short-range communication network such as Bluetooth, WiFi (wireless fidelity) direct, or IrDA (infrared data association)) or a second network (199) (e.g., a legacy cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (e.g., a LAN or WAN)). These various types of communication modules may be integrated into a single component (e.g., a single chip) or implemented as multiple separate components (e.g., multiple chips). The wireless communication module (192) can identify or authenticate the electronic device (101) within a communication network such as the first network (198) or the second network (199) using subscriber information (e.g., International Mobile Subscriber Identifier (IMSI)) stored in the subscriber identification module (196).

[0049] The wireless communication module (192) can support 5G networks and next-generation communication technologies following 4G networks, for example, new radio access technology. NR access technology can support high-speed transmission of high-capacity data (enhanced mobile broadband (eMBB)), minimization of terminal power and connection of multiple terminals (massive machine type communications (mMTC)), or high reliability and low latency (ultra-reliable and low-latency communications (URLLC)). The wireless communication module (192) can support a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate, for example. The wireless communication module (192) can support various technologies for securing performance in the high-frequency band, such as beamforming, massive MIMO (multiple-input and multiple-output), full-dimensional MIMO (FD-MIMO), array antenna, analog beam-forming, or largescale antenna. The wireless communication module (192) can support various requirements specified in the electronic device (101), external electronic device (e.g., electronic device (104)), or network system (e.g., second network (199)). According to one embodiment, the wireless communication module (192) can support a Peak data rate (e.g., 20 Gbps or more) for eMBB realization, loss coverage (e.g., 164 dB or less) for mMTC realization, or U-plane latency (e.g., downlink (DL) and uplink (UL) each 0.5 ms or less, or round trip 1 ms or less) for URLLC realization.

[0050] An antenna module (197) can transmit a signal or power to or from an external source (e.g., an external electronic device). According to one embodiment, the antenna module (197) may include an antenna comprising a radiator made of a conductor or a conductive pattern formed on a substrate (e.g., a PCB). According to one embodiment, the antenna module (197) may include a plurality of antennas (e.g., an array antenna). In this case, at least one antenna suitable for a communication method used in a communication network, such as a first network (198) or a second network (199), may be selected from the plurality of antennas, for example, by a communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device through the selected at least one antenna. According to some embodiments, in addition to the radiator, other components (e.g., a radio frequency integrated circuit (RFIC)) may be additionally formed as part of the antenna module (197).

[0051] According to various embodiments, the antenna module (197) may form a mmWave antenna module. According to one embodiment, the mmWave antenna module may include a printed circuit board, an RFIC disposed on or adjacent to a first surface (e.g., bottom surface) of the printed circuit board and capable of supporting a specified high frequency band (e.g., mmWave band), and a plurality of antennas (e.g., array antennas) disposed on or adjacent to a second surface (e.g., top surface or side surface) of the printed circuit board and capable of transmitting or receiving a signal of the specified high frequency band.

[0052] At least some of the above components can be connected to each other via a communication method between peripheral devices (e.g., bus, GPIO (general purpose input and output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface)) and exchange signals (e.g., commands or data) with each other.

[0053] According to one embodiment, commands or data may be transmitted or received between the electronic device (101) and an external electronic device (104) through a server (108) connected to a second network (199). Each of the external electronic devices (102 or 104) may be the same or different type of device as the electronic device (101). According to one embodiment, all or part of the operations performed on the electronic device (101) may be performed on one or more of the external electronic devices (102, 104, or 108). For example, if the electronic device (101) needs to perform a function or service automatically or in response to a request from a user or another device, the electronic device (101) may request one or more external electronic devices to perform at least part of the function or service instead of performing the function or service itself or additionally. One or more external electronic devices that receive the request may perform at least part of the requested function or service, or additional functions or services related to the request, and transmit the result of the execution to the electronic device (101). The electronic device (101) may process the above result as is or additionally and provide it as at least part of the response to the request. For this purpose, for example, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used. The electronic device (101) may provide ultra-low latency services using, for example, distributed computing or mobile edge computing. In another embodiment, the external electronic device (104) may include an Internet of Things (IoT) device. The server (108) may be an intelligent server using machine learning and / or neural networks. According to one embodiment, the external electronic device (104) or the server (108) may be included within the second network (199).The electronic device (101) can be applied to intelligent services (e.g., smart home, smart city, smart car, or healthcare) based on 5G communication technology and IoT-related technology.

[0054] The electronic device according to the various embodiments disclosed in this document may be of various forms. The electronic device may include, for example, a portable communication device (e.g., a smartphone), a computer device, a portable multimedia device, a portable medical device, a camera, a wearable device, or a consumer electronics device. The electronic device according to the embodiments of this document is not limited to the devices described above.

[0055] According to one embodiment, FIGS. 2a through 2i illustrate exemplary series of images. A series of images may refer to a plurality of images that share features such as the same subject, concept, and / or style. For example, an image may include a still image, a video, a frame included in a video, or a stereoscopic image. For example, an image may correspond to content captured through a camera or content generated through an application. For example, a series of images may include various types of content.

[0056] According to one embodiment, FIG. 2a illustrates exemplary series of images (200: 201, 202, 203, 204, 205, 206, 207, 208, 209) regarding wine. In FIG. 2a, each of the images (200) captures the wine, which is the subject of interest, being held in a hand. In each of the images (200), a dynamic message is conveyed that the wine is tilted, and the wine label is captured so that it is visible, thereby effectively conveying information about the wine.

[0057] According to one embodiment, FIG. 2b illustrates exemplary series of images (210: 211, 212, 213, 214, 215, 216, 217, 218, 219) regarding muscle growth. In FIG. 2b, each of the images (210) includes a subject so that the size and shape of the muscle are visible. The images (210) can show the muscle growth process step by step. The images (210) can effectively record the subject's efforts for muscle growth.

[0058] According to one embodiment, FIG. 2c illustrates exemplary series of images (230: 231, 232, 233, 234, 235, 236, 237, 238, 239) relating to pregnancy. In FIG. 2c, each of the images (230) depicts a woman during her pregnancy. The images (230) can capture the changes in the belly as it grows during pregnancy in stages.

[0059] According to one embodiment, FIG. 2d illustrates exemplary series of images (240: 241, 242, 243, 244, 245, 246, 247, 248, 249) relating to a specific location. In FIG. 2d, each of the images (240) is taken at a specific location (e.g., in front of a wall). The images (240) may capture the appearance of different subjects at a specific location.

[0060] According to one embodiment, FIG. 2e illustrates exemplary series of images (250: 251, 252, 253, 254, 255, 256, 257, 258, 259) regarding a specific shooting angle. In FIG. 2e, each of the images (250) may capture a view taken at a specific shooting angle. Each of the images (250) may capture a different subject taken from an aerial view.

[0061] According to one embodiment, FIG. 2f illustrates exemplary series of images (260: 261, 262, 263, 264, 265, 266, 267, 268, 269) relating to a specific concept. In FIG. 2f, each of the images (250) captures a scene taken with a specific concept. Each of the images (260) captures the same subject viewing an exhibition at an art gallery and / or museum. In each of the images (260), the subject may be placed in a specific location (e.g., the center).

[0062] According to one embodiment, FIG. 2g illustrates exemplary series of images (270: 271, 272, 273, 274, 275, 276, 277, 278, 279) relating to a particular style. In FIG. 2g, each of the images (270) captures a scene taken in the same shooting environment (e.g., lighting). The images (260) may be related objects (e.g., portable electronic devices used by a user in daily life). The images (270) may share a common style, such as similar color tones, brightness, texture, or lighting.

[0063] According to one embodiment, FIG. 2h illustrates exemplary series of images (280: 281, 282, 283, 284, 285, 286, 287, 288, 289) relating to plant growth. In FIG. 2h, each of the images (280) captures the same plant over time. The images (280) may show the growth and / or degeneration process of the plant.

[0064] According to one embodiment, FIG. 2i illustrates exemplary series of images (290: 291, 292, 293, 294, 295, 296, 297, 298, 299) regarding the growth of a child. In FIG. 2i, each of the images (290) captures the same child over time. The images (290) can show the child's growth process.

[0065] As illustrated in FIGS. 2a through 2i, a user may take various types of series of images according to life activities such as work, hobbies, and childcare. For example, multiple images having a specific composition (e.g., placing the same type of subject in the same location) may be classified into each image group corresponding to a series of images. In series of images, components such as the type of subject, the placement of the subject, the shooting composition, the shooting environment (e.g., lighting), the shooting mode (e.g., focus, shutter speed, exposure, whether to use a flash), the shooting style (e.g., panoramic shooting), the shooting location, the shooting time, or the image quality (e.g., resolution, size, aspect ratio) may form a specific pattern. For example, a type of series of images may be taken with the same shooting composition. For example, a type of series of images may be taken at predetermined time intervals. For example, a subject repeatedly photographed by the user may be identified as a subject of interest or a preferred subject.

[0066] According to one embodiment, a series of images (or a group of a series of images expressing a common theme) may be images that share aesthetic expression techniques, such as balance and harmony of the components included in each image.

[0067] According to one embodiment, each image belonging to a series of images may exist independently, but the series of images may convey a single message as a set of images. The series of images can produce effects such as enhanced storytelling, creative content development, or systematic organization. Series of images that maintain the same subject and style can enhance storytelling and convey a message to the viewer easily and clearly. Users can produce original series of images through the shooting and editing process and develop new content based on the series of images. For example, series of images with similar styles and / or colors can be systematically organized and serve as material for generating new content.

[0068] According to one embodiment, a series of images can be generated through shooting and / or editing. When shooting a series of images, the user had to maintain a consistent composition and / or angle, for example, targeting the same subject. When shooting a series of images, the user had to ensure consistency in the series of images by manually adjusting shooting conditions (e.g., lighting, background). In this case, the user had to attempt shooting repeatedly to maintain a consistent composition and / or angle. It was difficult for the user to ensure consistency in the resulting images due to changes in shooting conditions. Such shooting operations are time-consuming and labor-intensive.

[0069] According to one embodiment, to obtain a series of images, the user can edit the captured images. To obtain the series of images, the user had to adjust visual elements such as color tone, composition, and style of the captured images. The user had to maintain consistency in the series of images through editing individual images. In this case, the color tone, composition, and style had to be manually adjusted for each individual image. It was required to perform iterative work on each image to obtain a consistent series of images. It may be difficult to obtain the desired result through editing, so re-shooting (e.g., taking new images) may be necessary. For example, it may be difficult to obtain a series of images by changing the pose of the subject, out-painting the subject (e.g., expanding or moving the subject within the image), or in-painting the background (e.g., adding a background that did not originally exist) through editing. In this case, the user must attempt re-shooting to obtain the series of images. If re-shooting is difficult, images that deviate from a specific pattern of the series of images may be obtained.

[0070] Having users manually perform all processes of shooting and / or editing a series of images reduces the efficiency and productivity of the image generation process. The generated series of images may vary depending on the user's skill level and / or environmental conditions. It is difficult to maintain visual consistency among the images during the shooting and / or editing process. An automation function is required that analyzes multiple images to learn patterns and edits the images into a consistent format based on those learned patterns.

[0071] According to one embodiment of the present disclosure, an electronic device (101) can efficiently acquire a series of images having a consistent style and / or composition automatically with minimal user intervention.

[0072] In one embodiment, the electronic device (101) can analyze and classify a plurality of images having continuity and / or repetition. The electronic device (101) can learn data such as the context, layout, style, and metadata of common images from the classified images and acquire an image pattern (described in detail below) according to the user's intention for continuity and / or repetition. Even if the input image does not perfectly match the image pattern, if it falls within the category of the image pattern, the electronic device (101) can generate a new image using the input image according to the image pattern. The new image may be an image corrected from the input image. The electronic device (101) can enable the automatic generation of a series of images in a consistent format.

[0073] FIG. 3 is a block diagram showing a configuration for image acquisition according to one embodiment.

[0074] In FIG. 3, the electronic device (e.g., the electronic device (101) of FIG. 1) may include at least one of a database (310), an artificial intelligence model (AI model) (320), or a user interface (UI) (330).

[0075] According to one embodiment, the database (310) may store data regarding images and / or data regarding image patterns. At least some or all of the database (310) may be contained in an electronic device (101), a cloud server (e.g., server (108) of FIG. 1), and / or an external electronic device (e.g., external electronic device (102 or 104) of FIG. 1). In one embodiment, at least some or all of the database (310) may be contained in the electronic device (101). In one embodiment, at least some or all of the database (310) may be contained in the server (108). The database (310) may include an image database (311) and / or an image pattern database (312).

[0076] According to one embodiment, the image database (311) may store data regarding images. Data regarding images may include images (e.g., image files). For example, the images may include images taken by a user. For example, the images may include images downloaded from a server (108) and / or an external electronic device (102 and / or 104). The images may include original images obtained by taking and / or downloading. The images may include images generated by an artificial intelligence model (320). Data regarding images may include data regarding elements of the images. The elements constituting the images may include context, layout, style, and / or metadata-based data, but are not limited thereto. For example, at least some of the elements of the images may be referred to as the composition of the images.

[0077] According to one embodiment, the image pattern database (312) may store data regarding image patterns. For example, the data regarding image patterns may be information regarding identity, consistency, or similarity between the elements constituting each image included in a specific series of images (or a group of images expressing a common theme). For example, if one or more images are designated to correspond to a specific series of images group based on the consistency between the elements of each image, the image pattern database (312) may store the designated series of images group information and the image pattern elements common to the series of images by mapping them to each other. An image pattern may be defined by elements extracted by analyzing a plurality of images. An image pattern may establish criteria for producing a series of images. An image pattern may be composed of a plurality of elements. The elements constituting an image pattern may include context, layout, style, or metadata-based data, but are not limited thereto. Common elements shared in common across a plurality of images may be elements of the image pattern. The data regarding image patterns may include data regarding the elements of the image pattern. For example, data regarding elements of an image pattern may include data regarding context, data regarding layout, data regarding style, or metadata-based data.

[0078] For example, the context may include at least one of a subject (e.g., type of subject), background, scene, or subject (e.g., content and / or situation included in the image). For example, in an image, the subject may appear as a foreground object and the background as a background object. For example, multiple images may commonly include a specific subject (e.g., the same subject, the same type of subject, the subject of the same subject, a similar subject), the face of a specific person, and / or a specific background. For example, the context may further include the facial expression, wear (e.g., clothes, hat, shoes, bag, accessory), posture, or action of the subject (e.g., person). For example, as illustrated in FIG. 2a, multiple images (200) may include the same subject (or a common subject). For example, the same subject may be a liquor bottle. The electronic device (101) may acquire data regarding an image pattern containing data regarding the context based on multiple images having the same (or common) context.

[0079] For example, the layout may include at least one of the position of the subject within the image, the tilt of the subject, the composition of the subject, the ratio of the subject to the background, the orientation of the subject, the number of subjects, the arrangement of subjects, or the relationship between the subjects (e.g., the shape, perspective, or three-dimensionality that the first subject and the second subject (or background) together exhibit). For example, a plurality of images may have a common layout that includes an object tilted at a specific angle and / or a person located in the center of the image. For example, as illustrated in FIG. 2f, a plurality of images (260) may have the same layout. For example, the same layout may include a person located in the center of the image. The electronic device (101) may acquire data regarding an image pattern that includes data regarding the layout based on a plurality of images having the same layout.

[0080] For example, a style may include at least one of color tone, brightness, texture, or lighting. For example, multiple images may have a style such as a warm tone and / or a specific lighting direction. For example, as illustrated in FIG. 4a, multiple images (413, 423, 433) may have the same style. For example, the same style may include a specific lighting direction and shadows of a specific direction. The electronic device (101) may acquire data regarding an image pattern containing data regarding the style based on multiple images having the same style.

[0081] For example, metadata-based data may include at least one of a shooting time, a pattern of shooting times, location data, or a pattern of location data. Metadata may be data stored within an image file along with image information or recorded in memory in association with the image file. A pattern of shooting times may include a pattern of intervals between shooting times and / or a pattern of changes in shooting times. Location data refers to data regarding the shooting location. Location data may be obtained using GPS, Wi-Fi, and / or Bluetooth. A pattern of location data may include a movement path pattern (e.g., whether the image was taken on a specific movement path). For example, a plurality of images may include images of a child taken on a specific day and / or at a specific time (e.g., 2:00 PM) every week to record the child's growth process. For example, as illustrated in FIG. 4b, a plurality of images (414, 424, 434) may have substantially the same or similar metadata-based data. For example, a plurality of images (414, 424, 434) may be taken at substantially the same or similar time and / or at substantially the same or similar location and may contain substantially the same or similar metadata-based data. The electronic device (101) may obtain data regarding an image pattern containing said metadata-based data based on a plurality of images having substantially the same or similar metadata-based data. In one embodiment, the electronic device (101) may obtain an image pattern based on the interval between the times when the plurality of images were taken. For example, a plurality of images corresponding to a category of a specific image pattern may be taken at specific time intervals. The electronic device (101) may obtain an image pattern based on the images taken at specific time intervals.The electronic device (101) can obtain an image pattern from multiple images based on metadata of multiple images.

[0082] According to one embodiment, the image pattern database (312) may store data regarding user selection and / or feedback on image patterns. The data regarding user selection and / or feedback stored in the image pattern database (312) may be used for training an artificial intelligence model (320).

[0083] According to one embodiment, the artificial intelligence model (320) can generate and acquire data regarding image patterns. The artificial intelligence model (320) can generate and acquire images. The artificial intelligence model (320) may be a single artificial intelligence model or may be implemented as a plurality of artificial intelligence models. The artificial intelligence model (320) may be composed of a neural network (or artificial neural network) and may include a statistical learning algorithm that mimics biological neurons in machine learning and cognitive science. A neural network may refer to a model in which artificial neurons (nodes) forming a network through the connection of synapses change the strength of the synaptic connections through learning to possess problem-solving capabilities. The neurons of the neural network may include a combination of weights or biases. The neural network may include one or more layers composed of one or more neurons or nodes. For example, the electronic device (101) may include an input layer, a hidden layer, and an output layer. The neural network constituting the electronic device (101) can infer a result (output) to be predicted from an arbitrary input by changing the weights of the neurons through learning.

[0084] According to one embodiment, the artificial intelligence model (320) can generate a neural network, train or learn the neural network, perform operations based on received input data, generate an information signal based on the results of the operation, or retrain the neural network.

[0085] According to one embodiment, the artificial intelligence model (320) includes a Convolutional Neural Network (CNN), Region with Convolutional Neural Network (R-CNN), Region Proposal Network (RPN), RecuREnt Neural Network (RNN), Stacking-based Deep Neural Network (S-DNN), State-Space Dynamic Neural Network (S-SDNN), Deconvolution Network, Deep Belief Network (DBN), Restructured Boltzmann Machine (RBM), Fully Convolutional Network, Long Short-Term Memory Network (LSTM), Classification Network, Generative Modeling, Generative Adversarial Network (GAN), eXplainable AI, Continual AI, Representation Learning, AI for Material Design, BERT, SP-BERT, MRC / QA for natural language processing, Text Analysis, Dialog System, GPT-3, GPT-4, Visual Analytics, Visual Understanding, Video Synthesis for vision processing, Anomaly for ResNet data intelligence Various artificial intelligence structures and / or algorithms such as detection, prediction, time-series forecasting, optimization, recommendation, or data creation may be used, but are not limited thereto.

[0086] According to one embodiment, the artificial intelligence model (320) may include a first artificial intelligence model (321) and / or a second artificial intelligence model (322). For example, each of the first artificial intelligence model (321) and the second artificial intelligence model (322) may correspond to a functional element included in one artificial intelligence model (320). The functions of one artificial intelligence model included in the present disclosure (e.g., the first artificial intelligence model (321)) may be performed by at least some of another artificial intelligence model (e.g., the second artificial intelligence model (322)). The functions of the artificial intelligence model included in the present disclosure may be performed by at least some of a specific processor (e.g., an application processor).

[0087] According to one embodiment, the first artificial intelligence model (321) can obtain data regarding image patterns based on image data stored in the image database (311). The first artificial intelligence model (321) may be an analytical artificial intelligence model. For example, the first artificial intelligence model (321) may be a Convolutional Neural Network (CNN). The first artificial intelligence model (321) can extract data regarding key elements from data regarding images. The first artificial intelligence model (321) can obtain data regarding image patterns based on data regarding common elements extracted from data regarding a plurality of images. A method for obtaining data regarding image patterns will be described later with reference to FIG. 10. For example, the first artificial intelligence (321) can analyze at least one image data included in the image database (311) to extract at least one pattern element (e.g., feature).

[0088] According to one embodiment, the second artificial intelligence model (322) compares data regarding an input image with data regarding an image pattern to determine whether the input image corresponds to an image generation category of the image pattern, and can generate a new image corresponding to a category of the image pattern based on the determination that the input image corresponds to an image generation category (e.g., see FIGS. 14 and 15). A method for determining whether an input image corresponds to an image generation category of an image pattern in an electronic device (101) will be described in detail below in the present disclosure. The second artificial intelligence model (322) may be a generative artificial intelligence model. A generative artificial intelligence model will be described below with reference to FIGS. 11 to 13.

[0089] According to one embodiment, the user interface (330) may support a function of receiving user input regarding an image pattern and / or a generated image. The user interface (330) may support a function of outputting information regarding the image pattern and / or the generated image (e.g., see FIGS. 7 through 9). The user interface (330) may be provided through a display (e.g., the display (160) of FIG. 1) and / or an input module (e.g., a microphone). The user interface (330) may provide functions including image pattern generation management, image generation management, data management regarding the image pattern, generated image management, and / or automatic generation function setting management.

[0090] According to one embodiment, the user interface (330) may include an interface for generating an image pattern (e.g., see FIG. 16). The interface for generating an image pattern may receive user input regarding image generation and / or output information regarding image generation. The interface for generating an image pattern may provide a notification that data regarding an image pattern may be generated. When images continuously captured by the user and / or images repeatedly recorded according to a specific subject form a certain pattern, the interface for generating an image pattern may provide a notification that data regarding an image pattern may be generated.

[0091] According to one embodiment, an interface for generating image patterns may allow a user to view training data used for generating image patterns. The interface may provide training data, such as training images used for generating image patterns and / or data regarding these images (e.g., context, layout, style, and / or metadata-based data), in a preview form. In this case, the user may review whether the image pattern matches the user's intent.

[0092] According to one embodiment, a user interface for generating an image pattern may enable updating training data. Each piece of training data may not match an image pattern. Data regarding each element of the training data may not match data regarding elements of the image pattern. The user interface for generating an image pattern may enable the user to determine whether to update the training data to match an image pattern.

[0093] According to one embodiment, the user interface (330) may include a user interface for image generation (e.g., see FIGS. 7 through 9 and 17). The user interface for image generation may receive user input regarding a function to generate a new image by applying an image pattern. For example, the user interface for image generation may provide an object for receiving user input instructing the application of an image pattern (i.e., the generation of a new image corresponding to a category of the image pattern). For example, the user interface for image generation may be provided during the execution of an application (e.g., a camera application, a gallery application, or a messenger application) (e.g., see FIGS. 7, 8 and 17). For example, the user interface for image generation may be provided together with an image pattern management user interface (e.g., see FIGS. 9a and 9b).

[0094] According to one embodiment, the user interface (330) may include an image pattern management user interface in which the user manages data regarding image patterns (e.g., see FIG. 9a and 9b). For example, the image pattern management user interface may display image patterns as a list and provide the name of each image pattern, the category to which the image pattern can be applied, training data, creation information, and / or update information. The image pattern management interface may allow the user to modify and / or delete some elements of the image pattern (e.g., context, layout, or style).

[0095] According to one embodiment, the user interface (330) may include an image pattern setting management user interface for managing settings regarding image patterns. The image pattern setting management interface may allow the user to set various options for image patterns. For example, the image pattern setting management interface may set i) whether to apply the image pattern automatically or manually, ii) whether the image pattern can be updated and the update cycle, and / or iii) whether images within the image pattern category are automatically updated when the image pattern is updated.

[0096] According to one embodiment, the user interface (330) may include a user interface that allows the user to apply a specific image processing style or effect (e.g., painting style, film photo feel) to an image pattern (e.g., see FIG. 18). Using the user interface (330), the user can update the image pattern by applying a tone, style, and / or concept to the image pattern. Using the user interface (330), the user can update a series of images in batches using the modified image pattern. Using the user interface (330), the user can save the modified series of images as originals or as converted versions (or copies) of the original series of images.

[0097] According to one embodiment, the user interface (330) may include an image management user interface for managing generated images. The image management user interface may include an image list. The image list may include thumbnails, tags, original recoverability, and / or original conversion status of images corresponding to categories of image patterns. In the image management user interface, generated images may be displayed by being distinguished by separate tags. The image management user interface may visually display the original recoverability and / or original conversion status of the generated images. The image management user interface may allow the user to modify and / or delete the generated images. The image management user interface may provide an image editing tool that can further correct the generated images if necessary. The image management user interface may provide an option to restore the generated images to their original state. The image management interface may provide an option to retain (e.g., save) both the original and generated images.

[0098] According to one embodiment, the user interface (330) may include a user interface regarding the settings of an automatic generation function. The user interface (330) may include a user interface regarding the settings of an image automatic generation function. The user interface (330) may inform the user that if the input image corresponds to an image generation category of an image pattern, the image can be converted to generate a new image. The user interface (330) may cause a new image to be generated based on receiving user input that instructs the application of an image pattern (or approves image generation). The user interface (330) may provide an image automatic generation option or an image manual generation option. If the image automatic generation option is selected, an image is automatically generated, and a tag with the meaning of 'converted file' or equivalent may be displayed on the generated image file. Using the user interface (330), the user may restore the generated image to the original. Using the user interface (330), the user may manage the generated image in parallel with the original. If the image manual generation option is selected, the user interface (330) may display the possibility of image generation so that the user may decide whether to generate the image. Using the user interface (330), the user can set image generation options to be the same or different for each image pattern. For example, using the user interface (330), the user can set the system to automatically generate an image when identifying an image that meets the image generation criteria for a first image pattern, and to receive input from the user approving image generation when identifying an image that meets the image generation criteria for a second image pattern. The user interface (330) may include a user interface regarding the setting of an automatic image pattern generation function. The user interface (330) may provide an automatic image pattern generation option or an image pattern manual generation option.If the automatic image pattern generation option is selected, an image pattern can be automatically generated. If the manual image pattern generation option is selected, the user interface (330) may display the possibility of generating an image pattern so that the user can decide whether to generate an image pattern (e.g., see FIG. 16).

[0099] According to one embodiment, the first artificial intelligence model (321) can acquire data regarding image patterns. The first artificial intelligence model (321) can acquire image data from an image database (311) (operation 331). The first artificial intelligence model (321) can acquire and store data regarding image patterns based on the acquired image data (operation 332).

[0100] According to one embodiment, in operation 331, the first artificial intelligence model (321) can obtain data regarding a plurality of images from an image database (311). The first artificial intelligence model (321) can obtain training images among the plurality of images that can be determined to be a series of images. For example, the first artificial intelligence model (321) can obtain training images in which elements such as the subject, background, or shooting angle are similar.

[0101] According to one embodiment, the first artificial intelligence model (321) can independently extract and analyze each element of each of the training images. The first artificial intelligence model (321) may be a feature extraction model. The first artificial intelligence model (321) can individually extract and analyze elements including context, layout, style, and / or metadata from image data. The first artificial intelligence model (321) can learn the regularity and / or repeatability of each of the elements. The first artificial intelligence model (321) can obtain one or more common elements that appear repeatedly in the training images. Based on one or more common elements, the first artificial intelligence model (321) can define one or more image patterns. An image pattern is defined independently by each element and, for example, may not be defined by a combination of multiple elements. The first artificial intelligence model (321) can independently extract and define multiple pattern elements of the image pattern in parallel. For example, if an image pattern is defined by a combination of multiple elements (e.g., 'hand holding a wine bottle'), it may be relatively difficult to determine whether a specific image (e.g., an image containing a wine bottle but without a hand) falls into the category of the image pattern. If an image pattern is defined independently by each element (e.g., 'wine' and 'hand'), it may be relatively simple to determine whether a specific image (e.g., an image containing a wine bottle but without a hand) falls into the category of the image pattern.

[0102] For example, consider a plurality of images including a wine bottle photographed under lighting shining from the top left. In the plurality of images, the wine bottle may be located in the center of the image. Based on the plurality of images, the electronic device (101) may obtain an image pattern including a specific context (e.g., wine bottle), a specific layout (e.g., a specific location of the wine bottle), and a specific style (e.g., specific lighting). In this image pattern, the context, layout, and style may be used independently of each other. For example, the image pattern is defined by each of the elements including 'wine bottle', 'location of the wine bottle', and 'lighting', and is not defined by a combination of multiple elements such as 'wine bottle photographed under specific lighting'.

[0103] According to one embodiment, the first artificial intelligence model (321) may define an image pattern by some or all of the elements including context, layout, style, and metadata. For example, context may be referred to as the first element of the image, layout as the second element, style as the third element, and metadata as the fourth element. For example, the elements constituting the image may have priority in relation to the identification of the image pattern. The first artificial intelligence model (321) may define an image pattern by only some of the key elements. For example, an image pattern may be defined by context (e.g., a wine bottle) and layout (e.g., a specific location on a wine bottle) without including style. The electronic device (101) may obtain data regarding an image pattern defined by a common context and a common layout from a plurality of images that have different styles (e.g., lighting) but include a common context and a common layout.

[0104] According to one embodiment, in operation 332, the first artificial intelligence model (321) can store data regarding the acquired image pattern in an image pattern database (312). The first artificial intelligence model (321) can define and store each element of the image pattern independently and in parallel. For example, referring to the plurality of images (200) illustrated in FIG. 2a, the image pattern can be defined by a plurality of individual elements including a wine bottle (context), a hand grip (context), the position of the wine bottle (layout), and a specific lighting (style). The first artificial intelligence model (321) can independently acquire and store each of the plurality of individual elements of the image pattern. In this case, when generating an image corresponding to the category of the image pattern from an input image, the electronic device (101) can acquire matching elements and non-matching elements by individually comparing each element of the image pattern with each element of the input image, and correct the non-matching elements.

[0105] According to one embodiment, the electronic device (101) can generate an image corresponding to a category of image patterns. The electronic device (101) can store data regarding an input image obtained using a user interface (330) in an image database (311) (Operation 341). The first artificial intelligence model (321) can obtain data regarding an input image from the image database (311) and determine whether the input image corresponds to an image generation category (Operation 342). The first artificial intelligence model (321) (or processor (120)) can transmit a request signal to the second artificial intelligence model (322) to generate a new image (Operation 343). The second artificial intelligence model (322) can generate a new image and store data regarding the generated image in the image database (311) (Operation 344). The electronic device (101) can transmit data regarding the image stored in the image database (311) to the user interface (330) (Operation 345).

[0106] According to one embodiment, in operation 341, the electronic device (101) may store data regarding an input image obtained using a user interface (330) in an image database (311). The input image may be obtained from the electronic device (101), a server (108), and / or an external electronic device (102 or 104).

[0107] According to one embodiment, in operation 342, the first artificial intelligence model (321) can obtain data regarding an input image from an image database (311). The first artificial intelligence model (321) can obtain data regarding an image pattern from an image pattern database (311). The first artificial intelligence model (321) can determine whether the input image corresponds to an image generation category. The first artificial intelligence model (321) can extract data regarding elements of the input image. The first artificial intelligence model (321) can obtain data regarding an image pattern from an image pattern database (312). The first artificial intelligence model (321) can compare data regarding elements of the input image with data regarding elements of the image pattern. The first artificial intelligence model (321) can compare each element of the input image with each corresponding element of the image pattern. The first artificial intelligence model (321) can determine the features shared by the data regarding the input image and the data regarding the image pattern as matching elements. Data regarding matching elements among the elements of the input image may substantially match data regarding the corresponding elements of the image pattern. For example, the first artificial intelligence model (321) may determine that an input image is included in the category of the image pattern only if at least one input image contains a matching element. In terms of the fact that images can be considered as images of the same category only if matching elements exist between them, the matching elements may be referred to as 'same category elements'. The category of the image pattern may include an image containing elements that substantially match all elements of the image pattern and an image containing elements that substantially match some elements of the image pattern. The first artificial intelligence model (321) may determine a feature that constitutes an image pattern but does not constitute an input image as a non-matching element.For example, the first artificial intelligence model (321) may determine that there is a need to generate a new image corresponding to the category of an image pattern using an input image, provided that at least one non-matching element exists. For example, since an image without a non-matching element already corresponds to the category of an image pattern, it may determine that there is no need to generate a new image.

[0108] Hereinafter, an exemplary method for determining whether an input image falls within the image generation category of an image pattern is described by the first artificial intelligence model (321). If all elements of the input image substantially match the corresponding elements of the image pattern, the first artificial intelligence model (321) may determine that the input image falls within the category of the image pattern. In this case, the first artificial intelligence model (321) may determine that new image generation is not necessary. If some elements of the input image substantially match the corresponding elements of the image pattern, the first artificial intelligence model (321) may determine that the input image may fall within the category of the image pattern. In this case, the first artificial intelligence model (321) may determine that new image generation is necessary. Even if some elements of the input image substantially match the corresponding elements of the image pattern, if the elements of the input image that do not substantially match the corresponding elements of the image pattern are not the main elements of the image pattern (e.g., if the elements that do not match between the input image and the image pattern are lighting), the first artificial intelligence model (321) may determine that the input image falls within the category of the image pattern. In this case, the first artificial intelligence model (321) may determine that new image generation is not necessary. If all elements of the input image do not substantially match the corresponding elements of the image pattern, the first artificial intelligence model (321) may determine that the input image does not fall under the category of the image pattern. In this case, the first artificial intelligence model (321) may determine that new image generation is not necessary. In other words, if all elements of the input image substantially match the corresponding elements of the image pattern, the first artificial intelligence model (321) may determine that the input image does not fall under the category of image generation.If some elements of the input image substantially match the corresponding elements of the image pattern, the first artificial intelligence model (321) may determine that the input image belongs to the image generation category. Even if some elements of the input image substantially match the corresponding elements of the image pattern, if the elements of the input image that do not substantially match the corresponding elements of the image pattern are not the main elements of the image pattern, the first artificial intelligence model (321) may determine that the input image does not belong to the image generation category. If all elements of the input image do not match the corresponding elements of the image pattern, the first artificial intelligence model (321) may determine that the input image does not belong to the image generation category.

[0109] According to one embodiment, in operation 343, the first artificial intelligence model (321) may transmit a request signal to the second artificial intelligence model (322) to generate a new image. The first artificial intelligence model (321) may transmit a request signal to the second artificial intelligence model (322) to generate a new image based on the determination that the generation of a new image is necessary. The first artificial intelligence model (321) may transmit a request signal to the second artificial intelligence model (322) to generate a new image based on the determination that the input image falls within the image generation category. The new image may be an image corrected from the input image (e.g., a newly captured image).

[0110] According to one embodiment, in operation 344, the second artificial intelligence model (322) can generate a new image and store data regarding the generated image in an image database (311). The second artificial intelligence model (322) can generate a new image corresponding to a category of image patterns using an input image. The second artificial intelligence model (322) can generate a new image by maintaining matching elements in the input image and correcting non-matching elements. The operation of generating a new image will be described later with reference to FIGS. 11 and 12.

[0111] According to one embodiment, in operation 345, the electronic device (101) can transmit data regarding an image stored in an image database (311) to a user interface (330). The user interface (330) can provide the image to the user, for example, through a display (display (160) of FIG. 1).

[0112] FIGS. 4a and 4b illustrate exemplary elements of an image pattern according to one embodiment. In FIGS. 4a and 4b, the image pattern may be composed of a plurality of elements. Redundant descriptions of the elements constituting the image pattern are omitted (see FIG. 3).

[0113] FIGS. 5a to 5c illustrate an image acquisition method according to one embodiment.

[0114] In FIG. 5a to 5c, the electronic device (101) can acquire an image pattern (550) and acquire a second image (580) corresponding to the category of the acquired image pattern (550) using the first image (560).

[0115] FIG. 5a illustrates a process of acquiring an image pattern (550) according to one embodiment. In FIG. 5a, an electronic device (101) may acquire an image pattern (550) from a plurality of images (500: 501, 502, 503, 504, 505, 506, 507, 508, 509). In FIG. 5a, the image pattern (550) is described schematically, but for convenience of explanation, the image pattern (550) is not limited to being defined by a single image, but may be defined by each element corresponding to context, layout, style, and / or metadata, and data regarding each element may be stored as text, image, video, and / or code. As components of data regarding an image pattern (550), data regarding the context of the image pattern (550), data regarding the layout, data regarding the style, and / or metadata-based data may each be stored as text, an image, a video, and / or code. The electronic device (101) may acquire data regarding each element of a plurality of images (500). In the middle drawing of FIG. 5a, the electronic device (101) may acquire at least one of data regarding the context (510), data regarding the layout (520), data regarding the style (530), or metadata-based data (540) of one image (501) among the plurality of images (500). For example, the data regarding the context (510) may include data regarding a hand (522), a bottle (524), and / or a label (523). For example, data (520) regarding the layout may include the position of each of the hand (522), bottle (524), and label (523), the tilt of each of the hand (522), bottle (524), and label (523), and the ratio of the hand (522), bottle (524), and label (523) to the background.For example, data regarding style (530) may include data regarding subject style (541), background style (Background Style, BG Style) (542), and / or lighting style (543). For example, subject style (541) may include at least one of the color tone, brightness, or texture of the subject. For example, background style (542) may include at least one of the color tone, brightness, or texture of the background. For example, metadata-based data (540) may include at least one of data regarding the time of shooting and / or location. The electronic device (101) may acquire at least one of context data (510), layout data (520), style data (530), or metadata-based data (540) for each of the plurality of images (500). The electronic device (101) can obtain data regarding an image pattern (550) based on data regarding elements of a plurality of images (500) (e.g., 510, 520, 530, and / or 540). The electronic device (101) can obtain common elements shared by the plurality of images (500). The electronic device (101) can define the image pattern (550) as a common element. For example, data regarding the image pattern (550) may include at least one of data regarding a common context (e.g., hand, wine bottle, and label), data regarding a common layout (e.g., position of hand, wine bottle, and label), data regarding a common style (e.g., lighting), or data based on common metadata (e.g., location data). The electronic device (101) can label the image pattern (550). For example, the electronic device (101) can label the image pattern (550) as 'wine paper'. The electronic device (101) can store the image pattern (550).The electronic device (101) may store an image pattern (550) in the electronic device (101), a server (e.g., the server (108) of FIG. 1), and / or an external electronic device (e.g., the external electronic device (102 or 104) of FIG. 1). The electronic device (101) may identify an image pattern based on images when it acquires common elements shared in a specific number (e.g., three) or more of images over a certain period (e.g., one week). The electronic device (101) may acquire and store data regarding the image pattern and define a series of images corresponding to the category of the image pattern. For example, if the electronic device (101) acquires a specific number or more of images containing a specific (e.g., predefined) type of subject such as a bottle, a person, a pet, and / or a car, it may consider those images as candidate images for identifying the image pattern and may identify the image pattern based on those images.

[0116] FIG. 5b illustrates a process of comparing an input image and an image pattern according to one embodiment. In FIG. 5b, an electronic device (101) may acquire a first image (560). The first image (560) may be an input image acquired from an electronic device (101), a server (108), and / or an external electronic device (102 or 104). The electronic device (101) may acquire data (570: 571, 572, 573, 574) regarding elements of the first image (560). The data regarding elements (570) may include data regarding context (571), data regarding layout (572), data regarding style (573), and / or metadata-based data (574). For example, the data regarding context (571) may include data regarding a hand (561), a bottle (562), and / or a label (563). For example, data (572) regarding layout may include data regarding the position of each of the hand (561), bottle (562), and / or label (563), the tilt of each of the hand (561), bottle (562), and label (563), and the ratio of the hand (561), bottle (562), and / or label (563) to the background. For example, data (573) regarding style may include data regarding subject style (565), background style (BG Style) (566), and / or lighting style (567). For example, metadata-based data (574) may include at least one of data regarding the time of shooting and / or location. The electronic device (101) may compare data regarding the first image (560) with data regarding the image pattern (550) to determine whether the first image (560) corresponds to an image generation category of the image pattern (550). The electronic device (101) can determine whether the data regarding the elements of the first image (560) substantially matches the data regarding the elements of the image pattern (550).If all elements of the first image (560) substantially match the corresponding elements of the image pattern, the electronic device (101) may determine that the first image (560) falls within the category of the image pattern (550). The electronic device (101) may designate the first image (560) as one of a specific series of images (e.g., "wine scraps"). In this case, the electronic device (101) may determine that no new image creation is required. If some elements of the first image (560) substantially match the corresponding elements of the image pattern (550), the electronic device (101) may determine that the first image (560) falls within the category of the image pattern (550). In this case, the electronic device (101) may determine that no new image creation is required. If all elements of the first image (560) do not substantially match the corresponding elements of the image pattern (550), the electronic device (101) may determine that the first image (560) cannot fall into the category of the image pattern (550). The electronic device (101) may designate the first image (560) as not belonging to a specific series of images (e.g., "wine scraps"). In this case, the electronic device (101) may determine that new image generation is not necessary.

[0117] FIG. 5b is an example of a case in which, according to one embodiment, some elements substantially match and some elements do not substantially match. The table shown below FIG. 5b represents data (570) regarding elements of a first image (560) according to one embodiment. In the table shown below FIG. 5b, data (571) regarding the context of the first image (560) substantially matches data (510) regarding the context of the image pattern (550), data (572) regarding the layout of the first image (560) does not match data (520) regarding the layout of the image pattern (550), data (573) regarding the style of the first image (560) does not match data (530) regarding the style of the image pattern (550), and metadata-based data (574) of the first image (560) may substantially match metadata-based data (540) of the image pattern (550). The electronic device (101) may determine that the first image (560) may correspond to the image pattern (550). The electronic device (101) may determine that a new image generation is required.

[0118] FIG. 5c illustrates a process of obtaining a second image (580) corresponding to the category of an image pattern (550) using a first image (560) according to one embodiment. An electronic device (101) may obtain the second image (580) using an artificial intelligence model (555). The artificial intelligence model (555) may be a generative artificial intelligence model (e.g., the second artificial intelligence model (322) of FIG. 3). The artificial intelligence model (555) may take the first image (560) and the image pattern (550) as inputs and output a second image (580) corresponding to the category of the image pattern (550). In one embodiment, the artificial intelligence model (555) may convert non-matching elements in the first image (560) that do not match the image pattern (550) according to the corresponding elements of the image pattern (550). As a result, data regarding the elements of the second image (580) may substantially match the data regarding the elements of the image pattern (550). The fact that data regarding components between an image and an image pattern substantially matches does not mean that data regarding corresponding elements must match completely, but rather means a degree of similarity greater than a specified value or level (e.g., a degree perceived by the user as significantly similar). For example, data regarding elements of the second image (580) may include data regarding context (591), data regarding layout (592), data regarding style (593), and / or metadata-based data (594). For example, as shown in the table at the bottom right of FIG. 5c, the data regarding context (591), data regarding layout (592), data regarding style (593), and / or metadata-based data (594) of the second image (580) may each match the data regarding context (510), data regarding layout (520), data regarding style (530), and / or metadata-based data (540) of the image pattern (550).In FIGS. 5a through 5c, elements constituting an image and / or image pattern are described as including context, layout, style, and / or metadata-based data, but are not limited thereto.

[0119] FIG. 6 is a flowchart for explaining the operation of an electronic device (101) according to one embodiment.

[0120] In the following operational embodiments, each operation may be performed sequentially, but is not necessarily performed sequentially. For example, the order of each operation may be changed, or at least two operations may be performed in parallel.

[0121] In one embodiment, the electronic device (101) can acquire data regarding an image pattern in operation 610. The operation of acquiring data regarding an image pattern is omitted as it overlaps with the one described in FIG. 3.

[0122] In one embodiment, the electronic device (101) may receive an input instructing the application of an image pattern to a first image in operation 620. The first image may be an input image. In one embodiment, the electronic device (101) may acquire the input image by capturing it with a camera (e.g., the camera (180) of FIG. 1). In one embodiment, the electronic device (101) may acquire the input image from a server (e.g., the server (108) of FIG. 1) and / or an external electronic device (e.g., the external electronic device (102 and / or 104) of FIG. 1). The electronic device (101) may download the input image. The first image may be an image corresponding to the image generation category of the image pattern. Refer to FIG. 14 and 15 for a method of determining whether the first image corresponds to the image generation category of the image pattern in the electronic device (101). The electronic device (101) may receive an input instructing the application of an image pattern to the first image through a user interface. The electronic device (101) may provide a user interface for confirming whether an image pattern is applied to a first image (e.g., see FIGS. 7 through 9). An input instructing the application of an image pattern to a first image may include an input instructing the automatic application of an image pattern. The electronic device (101) may be configured to automatically apply an image pattern to an image corresponding to an image generation category of the image pattern.

[0123] In one embodiment, the electronic device (101) may, in operation 630, obtain a second image corresponding to the category of the image pattern using a first image based on receiving an input instructing the application of the image pattern. The electronic device (101) may compare data regarding the elements of the first input image with data regarding the elements of the image pattern to determine the matching elements among the elements of the input image that substantially match the elements of the image pattern and the non-matching elements that substantially do not match the elements of the input image pattern. The electronic device (101) may independently compare each element of the input image with each corresponding element of the image pattern. The electronic device (101) may convert the non-matching elements in the first image to match the corresponding elements of the image pattern. By converting the non-matching elements in the first image to match the corresponding elements of the image pattern, a second image corresponding to the category of the image pattern may be generated.

[0124] In one embodiment, the electronic device (101) may store a second image in operation 640. In one embodiment, the electronic device (101) may store a second image together with a first image. In one embodiment, the electronic device (101) may store a second image in place of the first image. The electronic device (101) may store the second image in the electronic device (101), a server (108), and / or an external electronic device (102 and / or 104).

[0125] Figures 7a and 7b illustrate an exemplary method for acquiring an image corresponding to a category of image patterns.

[0126] In FIGS. 7a and 7b, the electronic device (101) can execute a camera application capable of capturing an image by controlling a camera (e.g., camera (180) in FIG. 1). When executing the camera application, the electronic device (101) can display a preview image (e.g., a first image (701)) acquired by the camera in real time through a display (e.g., display (160) in FIG. 1). The execution screen (710) of the camera application may include the preview image. The electronic device (101) can acquire (e.g., capture) the first image (701) using the camera. For example, the first image (701) may be an example of a preview image acquired in real time by the camera. For example, the first image (701) may be an example of an image captured by the camera. For example, the first image (701) may be an image of a wine bottle being held so that the wine label is visible. The electronic device (101) can determine whether the first image (701) corresponds to an image generation category of a predetermined image pattern (702). For example, the image pattern (702) may include context (e.g., a wine bottle, a hand holding the wine bottle, and a label of the wine), layout (e.g., the wine bottle is tilted relative to a vertical line), style (e.g., lighting located in the upper left of the image), and / or metadata (e.g., specific location data). The electronic device (101) may obtain the image pattern (702) from the electronic device (101), a server (e.g., the server (108) of FIG. 1) and / or an external electronic device (e.g., the external electronic device (102 and / or 104) of FIG. 1). The electronic device (101) may provide a user interface to check whether the image pattern (702) is applied to the first image (701) based on the determination that the first image (701) corresponds to an image generation category of the image pattern (702). For example, the user interface may be provided through a display (e.g., the display (160) of FIG. 1).For example, the user interface may include an object (703). The electronic device (101) may store an image modified to match the image pattern (702) when the first image (701) is captured, based on receiving user input (e.g., a touch on the YES button (706)) that applies an image pattern (702) to the first image (701).

[0127] According to one embodiment, the execution screen (720) of the camera application includes an object (703). The electronic device (101) can use the object (703) to check whether an image pattern (702) is applied to a first image (701). The object (703) may include UI elements that receive user input and cause the electronic device (101) to apply the image pattern (702) to the first image (701). The object (703) may include a message (704) for checking whether the image pattern (702) is applied to the first image (701) (e.g., "Similar pattern detected" and / or "Would you like to generate the acquired image as a 'wine bottle' pattern?"), an object (705) regarding the non-application of the image pattern (702), and / or an object (706) regarding the application of the image pattern (702). The electronic device (101) may receive input through an object (705) indicating non-application of an image pattern (702). The electronic device (101) may identify a touch on the object (705) as a command indicating non-application of the image pattern (702). The electronic device (101) may display a preview image (e.g., a first image (701)) based on receiving a command indicating non-application of the image pattern (702). The electronic device (101) may provide feedback regarding non-application of the image pattern (702). For example, the feedback may include a message such as "Image pattern not applied." The electronic device (101) may receive input through an object (706) indicating application of the image pattern (702) to the first image (701). The electronic device (101) can identify a touch on an object (706) as a command instructing the application of an image pattern (702) to a first image (701). Based on receiving an input instructing the application of the image pattern (702), the electronic device (101) can use the first image (701) to obtain a second image (715) corresponding to the category of the image pattern (702).In one embodiment, if there are multiple image patterns similar to the first image (701), the electronic device (101) can check with the user which of the multiple image patterns to apply.

[0128] According to one embodiment, the execution screen (730) of the camera application may include an object (707) indicating that the electronic device (101) is generating a second image (715). The object (707) may include a message (708) (e.g., "Generating image" and / or "Applying "wine bottle" pattern").

[0129] According to one embodiment, the electronic device (101) may display an object (709) regarding the storage of the generated second image (715) on an execution screen (740) when the second image (715) is generated normally. The electronic device (101) may store the second image (715). In one embodiment, the electronic device (101) may store the second image (715) as the original and not store the first image (701). In one embodiment, the electronic device (101) may store the first image (701) as the original and store the second image (715) as a converted version (or copy) of the first image (701). The electronic device (101) may store the second image (715) as the original or a copy depending on user input. The electronic device (101) may provide a user interface for receiving user input. The user interface may include an object (709). The object (709) may include a message (711) confirming the completion of the creation of the second image and whether the second image is saved (e.g., "Image creation complete" and / or "Would you like to save the created image?"), the first image (701), a preview image (716) of the second image, an object (712) regarding the cancellation of the application of the image pattern (702), an object (713) regarding the saving of the original, and / or an object (714) regarding the saving of a copy. The preview image (716) of the second image may be an exemplary image that previews the second image (715) in a thumbnail form. The electronic device (101) may receive an input instructing the cancellation of the application of the image pattern (702) through the object (712). The electronic device (101) may identify a touch on the object (712) as a command instructing the cancellation of the application of the image pattern (702). The electronic device (101) may not store the second image (715) based on receiving a command instructing the cancellation of the application of the image pattern (702). The electronic device (101) may provide feedback regarding the cancellation of the application of the image pattern (702).For example, the feedback may include a message such as "Image pattern application canceled." The electronic device (101) may receive an input instructing the storage of the second image (715) through an object (713 or 714). The electronic device (101) may receive an input instructing the storage of the second image (715) as an original through an object (713). The electronic device (101) may identify a touch on the object (713) as a command instructing the storage of the second image (715) as an original. The second image (715) may be stored as an original based on receiving an input instructing the storage of the second image (715) as an original. When the second image (715) is stored as an original, the first image (701) may not be stored. The electronic device (101) may receive an input instructing the storage of the second image (715) as a copy through an object (714). The electronic device (101) can identify a touch on the object (714) as a command instructing to save a second image (715) as a copy. Based on receiving an input instructing to save a second image (715) as a copy, the first image (701) can be saved as the original and the second image (715) can be saved as a copy.

[0130] According to one embodiment, the electronic device may store the second image (715) in accordance with user input instructing to store the second image (715) and may display an execution screen (750) including the second image (715). The electronic device (101) may display the second image (715) on a display (160). The electronic device (101) may provide the second image (715) through the execution screen (750) of a camera application.

[0131] Figures 8a and 8b illustrate an exemplary method for acquiring an image corresponding to a category of image patterns.

[0132] According to one embodiment, in FIGS. 8a and 8b, an electronic device (101) can run a first application (e.g., a gallery application) capable of browsing images. The execution screen (810) of the first application may include a plurality of images (800: 801, 802, 803, 804). The electronic device (101) may acquire a plurality of images (800) by a camera (e.g., the camera (180) of FIG. 1). The electronic device (101) may acquire a plurality of images (800) from an external electronic device (e.g., the external electronic device (102, 104, or 108) of FIG. 1). The electronic device (101) may acquire a first image (801) from the plurality of images (800). For example, the first image (801) may be substantially the same as the first image (701) of FIG. 7a. The electronic device (101) can determine whether the first image (801) corresponds to an image generation category of a predetermined image pattern. For example, the predetermined image pattern may be substantially the same as the image pattern (702) of FIG. 7a. Based on the determination that the first image (801) corresponds to an image generation category of an image pattern, the electronic device (101) may provide a user interface to check whether the image pattern is applied to the first image (801). For example, the electronic device (101) may display an object (805) on at least a portion of the first image (801). The electronic device (101) may use the object (805) to indicate that the first image (801) can be converted to correspond to a category of an image pattern, and / or check whether the image pattern is applied to the first image (801). The object (805) may be converted into an object (806) in response to user input (e.g., a short touch).

[0133] According to one embodiment, the execution screen (820) of the first application may include an object (806). The object (806) may include UI elements that receive user input and cause the electronic device (101) to apply an image pattern to the first image (801). The object (806) may include an object (807) regarding the non-application of the image pattern and / or an object (808) regarding the application of the image pattern. In one embodiment, the electronic device (101) may display the image pattern to be applied based on receiving user input (e.g., a long touch) through the object (806). The electronic device (101) may receive input indicating the non-application of the image pattern through the object (807). The electronic device (101) may receive input indicating the application of the image pattern to the first image (801) through the object (808). The functions supported by each of the objects (807) and (808) are substantially identical or duplicate the functions supported by each of the objects (705) and (706), so the description is omitted.

[0134] According to one embodiment, the execution screen (830) of the first application may include an object (809) indicating that the electronic device (101) is generating a second image (815). The object (809) may be substantially the same as the object (707) of FIG. 7a.

[0135] According to one embodiment, the execution screen (840) of the first application may include an object (812) regarding the storage of the second image. The object (812) may be substantially the same as the object (709) of FIG. 7b.

[0136] According to one embodiment, the execution screen (850) of the first application may include a second image (815). The electronic device may store the second image (815) according to user input (e.g., touch of object (817) or object (818)) that stores the second image (815), and may display the execution screen (850) including the second image (815). The electronic device (101) may provide the second image (815) through the execution screen (850) of the first application.

[0137] Figures 9a and 9b illustrate an exemplary method for acquiring an image corresponding to a category of image patterns.

[0138] In FIGS. 9a and 9b, the electronic device (101) may provide a user interface regarding an image pattern. The user interface may support a function to modify and / or delete the image pattern. The user interface may support a function to generate an image corresponding to the category of the image pattern by selecting candidate images corresponding to the category of the image pattern.

[0139] According to one embodiment, FIG. 9a and 9b illustrate user interface screens (910, 920, 930, 940, and / or 950). A user interface screen (910) may include an object (902, 903, 904) regarding the type of image pattern and / or an object (905) regarding the management of an image pattern. An object (902, 903, 904) regarding the type of image pattern may include the name of the image pattern and / or a representative image of the image pattern. An electronic device (101) may display an object (905) regarding the management of an image pattern in response to user input regarding an object (902, 903, or 904) regarding the type of image pattern. An object (905) regarding the management of image patterns may include an object (915) regarding generated images, an object (925) regarding candidate images, an object (935) regarding image pattern modification, an object (945) regarding image pattern deletion, and / or an object (955) regarding automatic pattern application. An object (915) regarding generated images may receive input for managing generated images. A generated image may be an image converted by an electronic device (101) to correspond to a category of image patterns. An object (925) regarding candidate images (described in detail below) may receive input for managing candidate images corresponding to an image generation category of image patterns. An object (935) regarding image pattern modification may receive input regarding image pattern modification. An object (945) regarding image pattern deletion may receive input regarding image pattern deletion. An object (955) regarding automatic pattern application may receive input regarding automatic application of image patterns. For example, if the user selects automatic application of an image pattern, the electronic device (101) can automatically obtain an image corresponding to the category of the image pattern using the image when an image corresponding to the image generation category of the image pattern is identified.

[0140] According to one embodiment, a user interface screen (920) may include one or more candidate images (900: 901, 911, 921, 931, 941) corresponding to an image generation category of an image pattern (902). An electronic device (101) may display the candidate images (900) based on receiving user input regarding an object (925) concerning the candidate images.

[0141] According to one embodiment, a user interface screen (930) may include an object (906) regarding image generation. An electronic device (101) may display the object (906) based on receiving user input regarding a candidate image (e.g., 901). Based on receiving user input regarding the object (906), the electronic device (101) may generate a second image (919) corresponding to a category of the image pattern (901).

[0142] According to one embodiment, the user interface screen (940) may include an object (907) indicating that the electronic device (101) is generating a second image (919). The object (907) may be substantially the same as the object (707) of FIG. 7a.

[0143] According to one embodiment, the electronic device (101) may display an object (912) regarding the storage of the generated second image (919) on a user interface screen (950) when the second image (919) is generated normally. The object (912) may be substantially the same as the object (709) of FIG. 7b.

[0144] FIG. 10 is a flowchart illustrating a method for acquiring an image pattern according to one embodiment.

[0145] In FIG. 10, an electronic device (101) (e.g., the first artificial intelligence model (321) of FIG. 3) can acquire an image pattern. In the following operation embodiments, each operation may be performed sequentially, but is not necessarily performed sequentially. For example, the order of each operation may be changed, or at least two operations may be performed in parallel.

[0146] According to one embodiment, an electronic device (101) can analyze images stored in an image database in operation 1010. The electronic device (101) can acquire image data from an image database (e.g., image database (311) of FIG. 3) and analyze the acquired image data. Based on the acquired image data, the electronic device (101) can extract and / or analyze elements (e.g., features) that constitute the image. For example, the electronic device (101) can convert elements of the image into feature vectors.

[0147] According to one embodiment, the electronic device (101) can determine, in operation 1020, whether there exist training images that can be classified as image patterns (or determined to be a series of images). The electronic device (101) can determine that images with similar elements are training images. For example, the electronic device (101) can determine that images with similar elements, such as a subject, background, and / or shooting angle, are training images. For example, the electronic device (101) can determine whether images are similar to each other by comparing feature vectors of the images.

[0148] According to one embodiment, if learning images exist, the electronic device (101) can acquire the learning images in operation 1030.

[0149] According to one embodiment, an electronic device (101) can analyze elements of training images in operation 1040. The electronic device (101) can acquire data regarding each element of the training images and extract common elements that are commonly shared in some or all of the training images among each element of the training images. The elements may include at least one of context, layout, style, or metadata-based data, but are not limited thereto.

[0150] According to one embodiment, the electronic device (101) can determine whether it can generate an image pattern in operation 1050. For example, if the number of training images is greater than or equal to a threshold, the electronic device (101) can generate an image pattern. If the number of training images is less than the threshold, the electronic device (101) cannot generate an image pattern.

[0151] According to one embodiment, if an image pattern can be generated, the electronic device (101) can acquire and store data regarding the image pattern in operation 1060. The electronic device (101) can acquire data regarding the image pattern based on data regarding each element of the training images. The data regarding the image pattern may include common elements that are commonly shared in some or all of the training images among the elements of each of the training images.

[0152] According to one embodiment, if a training image does not exist or if an image pattern cannot be generated, the electronic device (101) may wait for the input of a new image in operation 1070. When a new image is input, the electronic device (101) may store the new image in an image database.

[0153] In one embodiment, some or all of operations 1010 to 1070 may be performed by the first artificial intelligence model (321) of FIG. 3. The image pattern acquisition method illustrated in FIG. 10 is merely an example, and the image pattern acquisition method may include any known method.

[0154] FIG. 11 is a flowchart illustrating an image acquisition method according to one embodiment.

[0155] In FIG. 11, the electronic device (101) (e.g., the second artificial intelligence model (322) of FIG. 3) can acquire an image corresponding to a category of image patterns. In the following operation embodiments, each operation may be performed sequentially, but is not necessarily performed sequentially. For example, the order of each operation may be changed, or at least two operations may be performed in parallel.

[0156] According to one embodiment, the electronic device (101) may acquire a new input image in operation 1110. For example, the input image may be acquired from the electronic device (101), a server (e.g., the server (108) of FIG. 1), and / or an external electronic device (e.g., the external electronic device (102 or 104) of FIG. 1).

[0157] According to one embodiment, the electronic device (101) can analyze an input image in operation 1120. The electronic device (101) can analyze the input image and obtain data regarding the elements of the input image.

[0158] According to one embodiment, the electronic device (101) can compare an input image with an image pattern in operation 1130. The electronic device (101) can compare data regarding elements of the input image with data regarding elements of the image pattern. The electronic device (101) can determine whether data regarding each element of the input image is similar (or substantially identical) to data regarding the corresponding element of the image pattern. The electronic device (101) can compare data regarding the context of the input image with data regarding the context of the image pattern. The electronic device (101) can determine whether data regarding the context of the input image is similar to data regarding the context of the image pattern. The electronic device (101) can compare data regarding the layout of the input image with data regarding the layout of the image pattern. The electronic device (101) can determine whether data regarding the layout of the input image is similar to data regarding the layout of the image pattern. The electronic device (101) can compare data regarding the style of the input image with data regarding the style of the image pattern. The electronic device (101) can determine whether data regarding the style of an input image is similar to data regarding the style of an image pattern. The electronic device (101) can compare the metadata-based data of the input image with the metadata-based data of the image pattern. The electronic device (101) can determine whether the metadata-based data of the input image is similar to the metadata-based data of the image pattern.

[0159] According to one embodiment, the electronic device (101) may determine, in operation 1140, whether an input image corresponds to an image generation category of an image pattern (e.g., see FIG. 14 and 15a through 15d). If the data regarding all elements of the input image substantially matches the data regarding the corresponding elements of the image pattern, the electronic device (101) may determine that the input image corresponds to the classification of the image pattern and does not correspond to an image generation category. If the data regarding some elements of the input image substantially matches the data regarding the corresponding elements of the image pattern, the electronic device (101) may determine that the input image corresponds to an image generation category of the image pattern. If the data regarding all elements of the input image does not substantially match the data regarding the corresponding elements of the image pattern, the electronic device (101) may determine that the input image does not correspond to an image generation category of the image pattern.

[0160] According to one embodiment, if it is determined that an input image corresponds to an image generation category of an image pattern, the electronic device (101) can generate an image corresponding to the category of an image pattern in operation 1150.

[0161] According to one embodiment, if it is determined that the input image does not correspond to the image generation category of the image pattern, the electronic device (101) may not support the image generation function in operation 1160.

[0162] In one embodiment, some or all of operations 1110 to 1160 may be performed by the second artificial intelligence model (322) of FIG. 3. The image acquisition method is not limited to the method illustrated in FIG. 11.

[0163] FIGS. 12a and 12b illustrate an image acquisition method according to one embodiment.

[0164] In FIGS. 12a and 12b, the electronic device (101) can obtain (or generate) a new image (1203) corresponding to an image pattern (1202) from an input image (1201). Based on data regarding the input image (1201) and the image pattern (1202), the electronic device (101) can generate a new image (1203) by retaining matching elements in the input image (1201) and correcting non-matching elements. In one embodiment, the electronic device (101) can use one or more elements of the input image (1201) in an image generation prompt. Based on data regarding the image pattern (1202), the electronic device (101) can generate an image generation prompt by combining additional elements into the image generation prompt. The electronic device (101) can adjust the weights of the elements used in the prompt. The electronic device (101) can adjust the weights of the elements used in the prompt according to context and / or similarity. For example, the electronic device (101) can configure an image generation prompt to generate an image in which the elements of the input image (1201) that are similar to the elements of the image pattern (1202) are maintained as much as possible by increasing the weight of the elements of the input image (1201) that are similar to the elements of the image pattern (1202) and decreasing the weight of the elements of the input image (1201) that are similar to the elements of the image pattern (1202).

[0165] In one embodiment, the electronic device (101) may provide an image generation prompt as an input value to an image generation model (e.g., the second artificial intelligence model (322) of FIG. 3). The image generation model (322) may generate an image (1203) corresponding to an image pattern (1202) based on the prompt.

[0166] In FIG. 12a, the electronic device (101) may obtain an image generation prompt for generating a second image (1203) by extracting some elements of the input image (1201) and some elements of the image pattern (1202). The electronic device (101) may extract matching elements from the input image (1201). The electronic device (101) may use the matching elements extracted from the input image (1201) in an image and / or text format in the image generation prompt. For example, the electronic device (101) may use an image corresponding to the matching elements extracted from the input image (1201) in the image generation prompt. For example, if the input image (1201) contains a subject identical to the image pattern (e.g., a wine bottle, a label, and a hand), the prompt may be configured to retain an image containing such subject in the generated image (1203). The electronic device (101) can extract some or all of the matching elements among the elements of the input image (1201) that substantially match the elements of the image pattern (1202) into the image itself and use them as the main prompt of the image generation model (322). The prompt element based on the matching elements extracted from the input image (1201) can be referred to as the 'input image-based prompt element'.

[0167] According to one embodiment, the electronic device (101) may extract non-matching elements from an image pattern (1202) and utilize them in a prompt of an image generation model (322). The electronic device (101) may utilize the non-matching elements extracted from the image pattern (1202) in an image and / or text format in an image generation prompt. For example, if the lighting of the input image (1201) and the image pattern (1202) is substantially non-matching, data regarding the lighting of the image pattern (1202) (e.g., uniform white lighting) may be utilized in an image and / or text format in an image generation prompt. For example, if the layout of the input image (1201) and the image pattern (1202) is substantially non-matching, data regarding the layout of the image pattern (1202) (e.g., center and / or diagonal layout) may be utilized in an image and / or text format in an image generation prompt. The electronic device (101) may additionally provide text and / or images based on the image pattern (1202) to the prompt configuration to compensate for substantially mismatched elements between the input image (1201) and the image pattern (1202). The prompt element based on the mismatched elements extracted from the image pattern (1202) may be referred to as an 'image pattern-based prompt element'.

[0168] In FIG. 12b, the electronic device (101) can obtain an image generation prompt by merging an input image-based prompt element and an image pattern-based prompt element. For example, the electronic device (101) can obtain an image generation prompt by merging a text and / or image prompt element based on an input image and a text and / or image prompt element based on an image pattern. The electronic device (101) can pass the image generation prompt to an image generation model (322). The image generation model (322) can generate a new image (1205) based on the image generation prompt.

[0169] According to one embodiment, an input image (1204) may include an input image-based prompt area (1211) and an image pattern-based prompt area (1212). An electronic device (101) may extract some or all of the matching elements in the input image (1204) that substantially match elements of the image pattern (1202) into the image itself and utilize them for an image generation prompt. When generating an image (1205), the image of the input image-based prompt area (1211) may be retained. When generating an image (1205), the image of the image pattern-based prompt area (1212) may not be retained. The image of the image pattern-based prompt area (1212) may be newly generated based on the image pattern (1202). For example, an image generation model (322) may retain the image of a subject (e.g., hand, wine bottle and / or label) that substantially matches elements of the image pattern in the input image (1204).

[0170] For example, an image generation model (322) can generate a new image (1205) based on an image generation prompt, reflecting the context of the input image (1204) and the style of the image pattern (1202). The image generation model (322) can maintain the image region (1211) corresponding to the matching element extracted from the input image (1204) as is, while supplementing the non-matching element in the image pattern-based prompt region (1212) based on data regarding the image pattern (1202). For example, an electronic device (101) can adjust elements such as the tilt and / or size, background, and color of the subject in the image pattern-based prompt region (1212) based on the image pattern (1202). In this process, part of the object (e.g., background) of the input image (1204) may be inpainted / or part of the object (e.g., subject) may be outpainted / or part of the object, or the position of the shadow may be moved / or the size may be changed.

[0171] According to one embodiment, the electronic device (101) can determine whether elements of the generated image (1205) substantially match the key elements of the image pattern (1202) (e.g., context, layout, style, and / or metadata-based data). The electronic device (101) can perform additional corrections, if necessary, to ensure that the elements of the image (1205) match the elements of the image pattern (1202).

[0172] FIG. 13 illustrates a generative artificial intelligence system according to one embodiment.

[0173] According to one embodiment, a user query / response interface (1310) may receive input (e.g., user input or data acquired or generated by an electronic device (e.g., the electronic device (101) of FIG. 1). Data acquired or generated by the electronic device may include, for example, image or video data generated using a processor (e.g., the processor (120) of FIG. 1), values ​​received through a sensor (e.g., the sensor module (176) of FIG. 1) or a sensor hub (e.g., external illumination, angle of the electronic device, display (e.g., the display module (160) of FIG. 1) or temperature of the electronic device, display size or expansion / reduction information, or images captured by an image sensor). User input may be in the form of natural language, touch coordinates or stylus coordinates acquired through a touch panel or digitizer included in the display, images and / or videos, but is not limited thereto. Additionally, context information may be transmitted along with the transmission of user input. Context information may include various additional information at the time of user input. It is possible. For example, additional information may include information about the application currently being used by the user or the user's location information. Additionally, user input may be in a mixed form of the aforementioned natural language, images, sounds, and context information. Furthermore, user input may be in a non-natural language form, such as selecting a menu. The user query / response interface (1310) may output to the user the results of the generative artificial intelligence system (1300) and / or the results of analyzing the input. The output may be in the form of natural language or specific content, and may also be provided in the form of an action requested by the user. The user query / response interface (1310) may output to the user the results of the generative artificial intelligence system (1300). The output may be in the form of natural language or specific content, and may also be provided in the form of an action requested by the user.

[0174] According to one embodiment, the AI ​​framework (1340) receives user input and can coordinate and control each component necessary to perform the user's intent based on the user's query.

[0175] According to one embodiment, user input received from a user query / response interface (1310) may be transmitted to a prompt design component (1341). The prompt design component (1341) may be used to generate prompts suitable for inputting user input into a large language model (LLM) or a large multimodal model (LMM). The prompt design component (1341) may be an AI component that uses machine learning algorithms or neural networks to develop better prompts over time. The prompt design component (1341) may generate prompts by accessing a knowledge component containing user preference data, a prompt library, and prompt examples based on user input, and transmit the generated prompts to the LLM or LMM.

[0176] According to one embodiment, the API / Plug-in management component (1342) can perform the role of communicating with external information when there is a request for additional information when transmitting user input as input to a generative model. The API / Plug-in management component (1342) establishes a channel to communicate with the outside of the AI ​​Interface via an API, and can enable access to various data sources (e.g., knowledge repository (1320)) through the established channel. Additionally, if the API / Plug-in management component (1342) needs to perform an action that executes the user input as a final step rather than an intermediate result in an application or service, it can request such action from the application / service component (1330) via an API. Information obtained from the outside may be used to generate a prompt in the prompt design component (1341) along with the user input, or it may be transmitted as input to the generative model.

[0177] According to one embodiment, an output modification component (or refiner component) (1343) can fine-tune the output of a generative model. For example, the output modification component (1343) can verify whether the content generated through the LLM and / or LMM is irrelevant, contains biased content, or contains harmful content. Additionally, the output modification component (1343) can determine the extent to which the output matches what the user wants and, if additional processing is required, proceed with that process. Furthermore, the output modification component (1343) can configure and provide the user with hints to avoid unwanted output.

[0178] According to one embodiment, a generative AI model (1360) may generally refer to an artificial intelligence neural network that generates new forms of data based on user input information. The generative AI model (1360) may include a model that generates images and / or a model that generates language. Models that generate images include, but are not limited to, generative adversarial networks (GANs) and variational autoencoders (VAEs), and examples include diffusion-based generative models that use VAEs and Transformer structures. Models that generate language are models trained to output the most statistically appropriate output value based on input values, and examples include models such as CHAT-GPT 3 and CHAT-GPT 4. There are also large multimodal models (LMMs) that can recognize various forms of data input, such as text, images, and voice, and generate new data corresponding to them.

[0179] FIG. 14 illustrates an image generation category of an image pattern according to one embodiment.

[0180] In FIG. 14, the electronic device (101) can analyze each element of the input image and the image pattern to distinguish the category to which the input image belongs and determine whether the input image corresponds to the image generation category of the image pattern. The electronic device (101) can compare data regarding the elements of the input image with data regarding the elements of the image pattern. The electronic device (101) can identify among the data regarding the elements of the input image that substantially match the data regarding the elements of the image pattern and can identify the elements in the input image that substantially match the elements of the image pattern as matching elements. Substantially matching does not need to match 100%, but may include matching above a threshold (e.g., similarity). The 'matching elements' may be referred to as 'similar elements'. The electronic device (101) can identify among the data regarding the elements of the input image that substantially do not match the data regarding the elements of the image pattern and can identify the elements in the input image that substantially do not match the elements of the image pattern as non-matching elements. Substantially, non-match does not need to be 100% non-match, and may include non-match (e.g., dissimilarity) above a threshold. 'Non-match elements' may be referred to as 'dissimilar elements'. The category (1430) regarding image patterns may include an image generation category (1432) and an image non-generation category (1431 and 1433). The image non-generation category (1431 and 1433) may include a first image non-generation category (1431) and a second image non-generation category (1433). The input image may correspond to the left category of the image pattern category (1430) when there are fewer similar elements, and to the right category of the image pattern category (1430) when there are more similar elements.

[0181] According to one embodiment, the first criterion (1410) may be used to determine that an input image is of a different classification from an image pattern. If the input image does not have a matching element that substantially matches the minimum major element of the image pattern, the input image may be determined not to satisfy the first criterion (1410). In this case, the input image may fall into the first image non-generation category (1431). The minimum major element may include the major characteristic elements of the image pattern (e.g., subject and / or background). There may be one or more major characteristic elements. For example, an input image containing the same subject as the subject of the image pattern may be determined to satisfy the first criterion (1410). An input image that does not satisfy the first criterion (1410) does not fall into the category of an image pattern. An input image that satisfies the first criterion (1410) may fall into the category of an image pattern. The electronic device (101) may not support an image generation function for an input image that falls into the first image non-generation category (1431).

[0182] According to one embodiment, the second criterion (1420) may be used to determine that the input image is of substantially the same classification (or category) as the image pattern. If the input image has a matching element that substantially matches the greatest major element of the image pattern, the input image may be determined to satisfy the second criterion (1420). In this case, the input image may fall under the second image non-generated category (1433). For example, the greatest major element may include the context and layout of the image pattern. The greatest major element may include the least major element. The electronic device (101) may not support an image generation function for the input image that falls under the second image non-generated category (1433). The user may identify the input image that satisfies the second criterion (1420) as a series of images of the image pattern. It may not be substantially necessary to generate an image using the input image that satisfies the second criterion (1420).

[0183] According to one embodiment, if an input image satisfies a first criterion (1410) but does not satisfy a second criterion (1420), the input image may fall into an image generation category (1432). An input image falling into an image generation category (1432) may include one or more non-matching elements that substantially do not match elements of an image pattern. An electronic device (101) may support an image generation function for an input image falling into an image generation category (1432). An electronic device (101) may generate an image falling into an image pattern category using an input image falling into an image generation category (1432). An electronic device (101) may obtain a new image by correcting an input image falling into an image generation category (1432) according to at least a portion of an image pattern.

[0184] According to the examples described above, categories related to image generation can be determined, for example, by an operation that determines commonalities or similarities between an input image (e.g., a newly captured image) and previously identified series of images (or image patterns).

[0185] FIGS. 15a to 15d illustrate an image acquisition method according to one embodiment.

[0186] In FIG. 15a, the electronic device (101) can acquire data regarding an image pattern. In figure (1510) of FIG. 15a, the electronic device (101) can acquire a plurality of images (1511, 1512, 1513, 1514, 1515, 1516) that can be used to acquire an image pattern. In figure (1520) of FIG. 15a, the electronic device (101) can acquire data regarding an image pattern (1530) from the images (1511, 1512, 1513, 1514, 1515, 1516). The data regarding an image pattern (1530) may include at least one of data regarding context (1531), data regarding layout (1532), data regarding style (1533), or metadata-based data (1534). For example, an electronic device (101) can obtain data (1530) regarding an image pattern described in Table 1 from images (1511, 1512, 1513, 1514, 1515, 1516). As described in Table 1, the data (1530) regarding an image pattern may include data regarding characteristic elements in terms of context, objects, layout, style, and / or metadata.

[0187] Data regarding image patterns (1530) Data regarding context (1531) Subject: Holding a bottle with a hand to record information about the corresponding bottle Object: Bottle: Alcoholic beverage bottle such as wine or champagne Label: Label exposed in the front Hand: Holding the upper part of the bottom of the bottle, so only the thumb is exposed without covering the bottle Data regarding layout (1532): Bottles arranged diagonally in the image and hand style holding the bottom of the bottle without covering the bottle Data regarding style (1533): Background: Bright and monotone background lighting Low brightness lighting in the upper left corner and faint shadow Metadata-based data (1534): The shooting location is the user's home

[0188] In FIGS. 15b through 15d, the electronic device (101) can determine whether an input image satisfies a first criterion (e.g., the first criterion (1410) of FIG. 14) and / or a second criterion (e.g., the second criterion (1420) of FIG. 14), and can determine whether it corresponds to an image generation category of an image pattern based on whether the first criterion (1410) and / or the second criterion (1420) are satisfied. The electronic device (101) can compare data regarding elements of an input image (1540, 1560, or 1580) with data regarding elements of an image pattern (1530). The electronic device (101) can determine whether data regarding elements of an input image (1540, 1560, or 1580) substantially matches data regarding elements of an image pattern (1530). If data regarding the least major element among the elements of an image pattern does not substantially match data regarding the elements of an input image (1540, 1560, or 1580), the electronic device (101) may determine that the input image (1540, 1560, or 1580) does not satisfy the first criterion. For example, data regarding the least major element of an image pattern may be at least some of the data regarding context (1531) (data regarding subject, bottle, and label) and data regarding layout (1532). If data regarding the most major element among the elements of an image pattern substantially matches data regarding the elements of an input image (1540, 1560, or 1580), the electronic device (101) may determine that the input image (1540, 1560, or 1580) satisfies the second criterion. For example, data regarding the greatest major element of an image pattern may be data regarding context (1531) and data regarding layout (1532).In the right column of Tables 2 through 4, O indicates that the data regarding the elements of the input image (1540, 1560, or 1580) substantially matches the data regarding the elements of the image pattern, and X indicates that they do not substantially match. FIG. 15b illustrates an exemplary case where the input image (1540) does not satisfy the first criterion (1410). In this case, the electronic device (101) may not generate an image because the data regarding the minimum major elements among the elements of the image pattern does not substantially match the data regarding the elements of the input image (1540). In the left diagram of FIG. 15b, the electronic device (101) can analyze the input image (1540). The electronic device (101) can obtain data regarding the elements of the input image (1540). The electronic device (101) can determine whether the input image (1540) corresponds to an image generation category of the image pattern based on data (1530) regarding elements of the image pattern and data regarding elements of the input image (1540). The electronic device (101) can compare the data regarding elements of the input image (1540) with the data (1530) regarding elements of the image pattern. The electronic device (101) can determine whether the data regarding elements of the input image (1540) substantially matches the data (1530) regarding elements of the image pattern. As indicated in the right column of Table 2, the data regarding all elements of the image pattern does not substantially match the data regarding the corresponding elements of the input image (1540). The data regarding the least major elements among the elements of the image pattern (e.g., data regarding subject, bottle, and label, and data regarding layout (1532)) does not substantially match the data regarding the corresponding elements of the input image (1540). The input image (1540) does not meet the first criterion. The input image (1540) falls into the first image non-generated category (e.g., the first image non-generated category (1431) of FIG. 14).In this case, the electronic device (101) may not generate an image (1550).

[0189] Data regarding image patterns (1530) Matching Data regarding context (1531) Subject: Holding a bottle with a hand to record information about the bottle X Object: Bottle: Alcoholic beverage bottle such as wine or champagne X Label: Label exposed in the front X Hand: Holding the upper part of the bottom of the bottle, so only the thumb is exposed without obscuring the bottle X Data regarding layout (1532): Bottles arranged diagonally in the image and a hand holding the bottom of the bottle without obscuring the bottle X Data regarding style (1533): Background: Bright and monotone background X Lighting: Low brightness lighting in the upper left corner and faint shadows X Metadata-based data (1534): Shooting location is the user's home X

[0190] FIG. 15c illustrates an exemplary case in which an input image satisfies the first criterion (1410) but does not satisfy the second criterion (1420). In the left drawing of FIG. 15c, an electronic device (101) can analyze an input image (1560). The electronic device (101) can obtain data regarding elements of the input image (1560). Based on data regarding elements of an image pattern (1530) and data regarding elements of the input image (1560), the electronic device (101) can determine whether the input image (1560) corresponds to an image generation category of an image pattern. The electronic device (101) can compare data regarding elements of the input image (1560) with data regarding elements of an image pattern (1530). The electronic device (101) can determine whether the data regarding elements of the input image (1560) substantially matches the data regarding elements of an image pattern (1530). As indicated in the right column of Table 3, data regarding the least major elements of the image pattern (e.g., data regarding the subject, bottle, and label, and data regarding the layout (1532)) substantially match the data regarding the corresponding elements of the input image (1560), but data regarding some elements of the image pattern does not match the data regarding the corresponding elements of the input image (1560). The input image (1560) satisfies the first criterion but does not satisfy the second criterion. The input image (1560) falls within the image generation category of the image pattern. In this case, the electronic device (101) can generate an image (1570) using the image (1560).

[0191] Data regarding image patterns (1530) Matching Data regarding context (1531) Subject: Holding a bottle with a hand to record information about the bottle O Object: Bottle: Alcoholic beverage bottle such as wine or champagne O Label: Label exposed in the front O Hand: Holding the upper part of the bottom of the bottle, so only the thumb is exposed without obscuring the bottle X Data regarding layout (1532): Bottles arranged diagonally in the image and a hand holding the bottom of the bottle without obscuring the bottle X Data regarding style (1533): Background: Bright and monotone background X Lighting: Low brightness lighting in the upper left corner and faint shadows X Metadata-based data (1534): Shooting location is the user's home O

[0192] FIG. 15d illustrates an exemplary case in which an input image satisfies the second criterion (1420). In the top drawing of FIG. 15d, an electronic device (101) can analyze an input image (1580). The electronic device (101) can obtain data regarding elements of the input image (1580). Based on data regarding elements of an image pattern (1530) and data regarding elements of the input image (1580), the electronic device (101) can determine whether the input image (1580) corresponds to an image generation category of an image pattern. The electronic device (101) can compare data regarding elements of the input image (1580) with data regarding elements of an image pattern (1530). The electronic device (101) can determine whether the data regarding elements of the input image (1580) substantially matches the data regarding elements of an image pattern (1530). As indicated in the right column of Table 4, the data regarding the most major element among the elements of the image pattern (data regarding context (1531) and data regarding layout (1532)) substantially matches the data regarding the corresponding element of the input image (1580). The input image (1580) satisfies the second criterion. The input image (1580) falls into the second image non-generation category. In this case, the electronic device (101) may not generate an image (1590).

[0193] Data regarding image patterns (1530) Matching Data regarding context (1531) Subject: Holding a bottle with a hand to record information about the bottle O Object: Bottle: Alcoholic beverage bottle such as wine or champagne O Label: Label exposed on the front O Hand: Holding the upper part of the bottom of the bottle, so only the thumb is exposed without obscuring the bottle O Data regarding layout (1532): Bottles arranged diagonally in the image and a hand holding the bottom of the bottle without obscuring the bottle O Data regarding style (1533): Background: Bright and monotone background O Lighting: Low brightness lighting in the upper left corner and faint shadows O Metadata-based data (1534): Shooting location is the user's home O

[0194] FIGS. 16a and 16b illustrate user interface screens (1610, 1620, 1630, 1640) regarding an image pattern according to one embodiment. In FIGS. 16a and 16b, the electronic device (101) may provide a user interface regarding an image pattern (e.g., the user interface (330) of FIG. 3). The user interface (330) may provide a notification that data regarding an image pattern may be generated, and may allow viewing and updating of the training data used to generate the data regarding the image pattern. The electronic device (101) may provide a notification that data regarding an image pattern may be generated when certain conditions are met. For example, the electronic device (101) may provide a notification that data regarding an image pattern may be generated when a subject of the same type is photographed more than a specified number of times within a certain period.

[0195] According to one embodiment, a user interface screen (1610) includes an object (1600) regarding image pattern generation. The object (1600) regarding image pattern generation may include an image (1601) corresponding to the category of image patterns, a message (1602) regarding image pattern generation, an object (1603) regarding disapproval of image pattern generation, and / or an object (1604) regarding approval of image pattern generation. The image (1601) corresponding to the category of image patterns may include an exemplary image corresponding to the category of image patterns. The message (1602) regarding image pattern generation may include messages such as "Generate pattern data" and / or "An identical repeating pattern has been detected. Would you like to save the pattern?". The electronic device (101) may receive an input disapproving image pattern generation through the object (1603). The electronic device (101) may identify a touch on the object (1603) as a command disapproving image pattern generation. The electronic device (101) may not generate an image pattern based on receiving a command that disapproves the generation of an image pattern. The electronic device (101) may provide feedback regarding the non-generation of an image pattern. For example, the feedback may include a message such as "No image pattern generated." The electronic device (101) may receive an input approving the generation of an image pattern through an object (1604). The electronic device (101) may identify a touch on the object (1604) as a command approving the generation of an image pattern. The electronic device (101) may generate an image pattern based on receiving an input approving the generation of an image pattern.

[0196] According to one embodiment, a user interface screen (1620) may include an object (1650) regarding training image updates. Each of the training images used to learn the image pattern may not correspond to a category of image patterns that is representative of the training images. After acquiring the image pattern, the electronic device (101) may update the training images so that each of the training images corresponds to a category of image patterns. The object (1650) may include a message (1651) regarding training image updates, a list of training images (1652), an object (1653) regarding the non-application of the image pattern, and / or an object (1654) regarding the application of the image pattern. For example, the message (1651) regarding training image updates may include messages such as "Update possible images" and / or "Would you like to update the images used for pattern learning to match the generated pattern data?". The list of training images (1652) may include thumbnails of each of the training images. The user may select one or more thumbnails. The electronic device (101) may receive input through the object (1653) instructing the non-application of an image pattern. The electronic device (101) may identify a touch on the object (1653) as a command instructing the non-application of an image pattern. Based on receiving the command instructing the non-application of an image pattern, the electronic device (101) may not update the training image (i.e., may maintain the training image). The electronic device (101) may receive input through the object (1654) instructing the application of an image pattern. The electronic device (101) may identify a touch on the object (1654) as a command instructing the application of an image pattern. Based on receiving the input instructing the application of an image pattern, the electronic device (101) may generate an image corresponding to the category of the image pattern using the training image.For example, the electronic device (101) can correct the training image (e.g., correct lighting, angle of the bottle) so that the training image has the tone and / or layout of the image pattern.

[0197] In one embodiment, the electronic device (101) can create a collage using the learning images. The electronic device (101) can adjust the tone and / or layout of each learning image based on the collage. For example, the electronic device (101) can match the tone of the learning images or adjust the position and / or size of the subject so that the overall atmosphere of the learning images in the collage is unified.

[0198] According to one embodiment, the user interface screen (1630) may include an object (1660) indicating that the electronic device (101) is generating an image. The object (1660) may be substantially the same as the object (707) of FIG. 7a.

[0199] According to one embodiment, a user interface screen (1640) may include an object (1670) regarding the completion of a training image update. The object (1670) may include a message (1671) regarding the completion of an image update and / or a list (1672) of training images. For example, the message (1671) regarding the completion of an image update may include a message such as "Image update completed". The list of training images (1672) may include thumbnails of training images that have not been updated and / or updated training images.

[0200] FIGS. 17a and 17b illustrate execution screens (1710, 1720, 1730, 1740, 1750) of a second application according to one embodiment.

[0201] In FIGS. 17a and 17b, the electronic device (101) can run a second application. For example, the second application may be a messenger application capable of sharing one or more images with a server (e.g., server (108) in FIG. 1) and / or an external electronic device (e.g., external electronic device (102 and / or 104) in FIG. 1).

[0202] According to one embodiment, the electronic device (101) can obtain data regarding images used when executing the second application (e.g., images uploaded by the user through the second application). The electronic device (101) can obtain data regarding image patterns from the uploaded images. When uploading images through the second application, the electronic device (101) can determine whether the first image (1701) falls within the category of the image pattern. The electronic device (101) can convert the first image (1701) into a second image (1715) that falls within the category of the image pattern and upload it according to the user's input or settings.

[0203] According to one embodiment, the execution screen (1710) of the second application includes a first image (1701) and an object (1702) regarding image upload. The electronic device (101) can receive an input instructing an image upload through the object (1702) regarding image upload.

[0204] According to one embodiment, a user interface screen (1720) includes an object (1703). The object (1703) may be substantially the same as the object (703) illustrated in FIG. 7a. The electronic device (101) may receive an input instructing the creation of a second image (1715) through the object (1703).

[0205] According to one embodiment, the execution screen (1730) of the second application may include an object (1704) indicating that the electronic device (101) is generating a second image (1715). The object (1707) may be substantially the same as the object (707) shown in FIG. 7b.

[0206] According to one embodiment, the execution screen (1740) of the second application includes an object (1705) regarding the upload of the second image (1715). The object (1705) may include a message (1706) confirming the completion of the creation of the second image and whether the second image is uploaded (e.g., "Image creation complete" and / or "Would you like to upload the created image?"), the first image (1701), the second image (1715), an object regarding non-uploading (1707), and / or an object regarding uploading (1708). The electronic device (101) may receive an input indicating not to upload via the object (1707). The electronic device (101) may identify a touch on the object (1707) as a command indicating not to upload. The electronic device (101) may not upload the second image (1715) based on receiving a command indicating not to upload. The electronic device (101) can receive an input instructing the upload of a second image (1715) through an object (1708). The electronic device (101) can identify a touch on the object (1708) as a command instructing the upload of the second image (1715). The second image (1715) can be uploaded based on receiving the input instructing the upload of the second image (1715).

[0207] According to one embodiment, the execution screen (1750) of the second application includes a second image (1715). The electronic device (101) may provide the second image (1715) when the second application is executed. The electronic device (101) may generate an image corresponding to a category of image patterns at the time of execution of the second application, thereby providing convenience in using the second application.

[0208] FIG. 18 illustrates a method for updating images corresponding to categories of image patterns according to one embodiment.

[0209] In FIG. 18, the electronic device (101) can update an image pattern and, based on the updated image pattern, update some or all of the training images used to acquire data regarding the image pattern. The electronic device (101) can update the image pattern by applying a specific image processing style (e.g., painting style, film photography feel) to the image pattern. For example, the electronic device (101) can update the image pattern by applying a specific style, tone, and / or concept to the image pattern. The electronic device (101) can acquire and store images (1820) corresponding to the category of the updated image pattern using images corresponding to the category of the image pattern (e.g., training images (1810) used to acquire the image pattern). In one embodiment, the electronic device (101) can store the acquired images (1820) along with the original training images (1810) as copies. In one embodiment, the electronic device (101) can update the training images (1810) in batches to correspond to a category of the updated image pattern. For example, the electronic device (101) can update the image pattern by applying a color field painting style to the image pattern. The electronic device (101) can update the training images (1810) to obtain images (1820) that correspond to a category of the updated image pattern. The obtained images (1820) may have a color field painting style similar to the updated image pattern.

[0210] FIG. 19 is a flowchart for explaining an image acquisition method according to one embodiment.

[0211] In the following operational embodiments, each operation may be performed sequentially, but is not necessarily performed sequentially. For example, the order of each operation may be changed, or at least two operations may be performed in parallel.

[0212] In one embodiment, operations 1910 to 1940 may be understood as being performed in a processor (e.g., processor (120) of FIG. 1) of an electronic device (e.g., electronic device (101) of FIG. 1).

[0213] In one embodiment, the electronic device (101) can acquire a plurality of images in operation 1910. The electronic device (101) can acquire a plurality of images from a database (e.g., the image database (311) of FIG. 3).

[0214] In one embodiment, the electronic device (101) can identify a plurality of images as an image group having a specific image pattern in operation 1920. The plurality of images may fall within the category of the specific image pattern. The electronic device (101) can obtain data regarding the specific image pattern by analyzing the plurality of images. The image group may include a plurality of images. The image group may include a plurality of images that fall within the category of the specific image pattern. The description of the image pattern is omitted as it overlaps with that in FIG. 3. The electronic device (101) can identify a plurality of images that fall within the category of the specific image pattern as a series of images belonging to a single group. The image group may include a series of images belonging to a single group (e.g., a series of images regarding a child's growth record).

[0215] In one embodiment, the electronic device (101) may acquire a first image in operation 1930. The first image may be an input image. The description of the input image is omitted as it overlaps with FIG. 6.

[0216] In one embodiment, the electronic device (101) may, in operation 1940, obtain a second image generated by correcting the first image according to at least a portion of a specific image pattern. The electronic device (101) may obtain a second image generated by correcting the first image according to at least a portion of a specific image pattern based at least partially on a determination that the first image corresponds to an image group. The first image corresponding to an image group having a specific image pattern may include the meaning that the first image corresponds to a category of a specific image pattern. The image group may include the first image. The electronic device (101) may determine whether the first image corresponds to an image group having a specific image pattern. The electronic device (101) may determine whether the first image corresponds to a category of a specific image pattern. The electronic device (101) may obtain a second image generated by correcting the first image according to at least a portion of a specific image pattern based at least partially on a determination that the first image corresponds to a category of a specific image pattern. The electronic device (101) may refrain from correcting the first image based on the determination that the first image does not fall into a specific image pattern category. The electronic device (101) may determine whether the first image falls into a specific image pattern category and corresponds to a first category designated in relation to the specific image pattern. The electronic device (101) may determine whether the first image falls into a first category. The electronic device (101) may determine whether the first image falls into a specific image pattern category and corresponds to a second category designated in relation to the specific image pattern. The electronic device (101) may determine whether the first image falls into a second category. The electronic device (101) may determine whether the first image falls into a first category or a second category. The first category may refer to the 'image generation category' of the image pattern described in FIG. 14.The second category may refer to the 'image non-generated category', 'first image non-generated category', and / or 'second image non-generated category' of the image pattern described in FIG. 14. The electronic device (101) may correct the first image based on the determination that the first image corresponds to the first category. The electronic device (101) may refrain from correcting the first image based on the determination that the first image corresponds to the second category. The electronic device (101) may obtain data regarding the elements of the first image. The electronic device (101) may compare the data regarding the elements of the first image with the data regarding the elements of the image pattern to obtain data regarding the matching elements that match the data regarding the elements of the image pattern among the data regarding the elements of the first image, and data regarding the non-matching elements that do not match the elements of the image pattern. The electronic device (101) may determine that the first image belongs to a first category based on the determination that the first image includes one or more matching elements and one or more non-matching elements. The electronic device (101) may determine that the first image belongs to a first category based on the determination that the first image has matching elements that substantially match the minimum major element of the image pattern, and non-matching elements that substantially do not match the maximum major element of the image pattern. The electronic device (101) may correct data regarding non-matching elements in the first image according to at least a part of the image pattern. The electronic device (101) may correct the first image such that the non-matching elements match the corresponding elements of the image pattern by converting data regarding non-matching elements in the first image according to data regarding corresponding elements of the image pattern.The electronic device (101) may determine that the first image belongs to the second category based on the determination that the first image does not include a matching element or does not include a non-matching element. The electronic device (101) may determine that the first image belongs to the second category based on the determination that the first image does not include a matching element. The electronic device (101) may determine that the first image belongs to the second category based on the determination that the first image does not include a non-matching element. The electronic device (101) may determine that the first image belongs to the second category based on the determination that the first image has a matching element that substantially matches the minimum major element and the maximum major element of the image pattern.

[0217] In one embodiment, the electronic device (101) (e.g., smartphone and / or tablet) may be designed so that a user can easily create a series of images when running an image capturing application (e.g., camera application) and / or an image management application (e.g., gallery application).

[0218] In one embodiment, an electronic device (101) (e.g., smart glasses and / or a smart watch) can provide a shooting assistance function in real time by utilizing data regarding image patterns. For example, the electronic device (101) can automatically adjust or recommend a subject and composition to create a series of images.

[0219] In one embodiment, an electronic device (101) (e.g., an AI camera and an IoT device) can utilize data regarding image patterns to automatically generate a series of images regarding a specific event (e.g., a child growth record, a pet activity record).

[0220] In one embodiment, the electronic device (101) may provide a series of images management and / or automatic classification of series of images based on image patterns when a photo management app (e.g., Google Photos, Apple Photos) is launched. For example, the electronic device (101) may automatically classify or album series of images based on the same subject.

[0221] In one embodiment, the electronic device (101) can automatically upload a series of images in a format optimized for social media platforms (e.g., Instagram, Facebook) or convert them into a story format and upload them.

[0222] In one embodiment, the electronic device (101) can provide an automatic editing template that matches user settings by using data regarding image patterns when running a professional image editing program such as Adobe Lightroom and / or Photoshop.

[0223] In one embodiment, the electronic device (101) can analyze data regarding image patterns and provide meaningful information to the user. The electronic device (101) can utilize the data regarding image patterns in conjunction with various services and applications, such as personalized analysis tools.

[0224] The electronic device (101) can obtain statistical data from a plurality of images (or groups of images). For example, the electronic device (101) can obtain statistical data by analyzing data regarding image patterns. The electronic device (101) can obtain statistical data, such as changes in the quantity of objects by time and category, based on a series of images recorded by the user, and provide it to the user. For example, based on a series of wine records, the electronic device (101) can analyze the amount of wine consumed by period, the variety of wine, and / or wine consumption patterns. For example, based on a series of exercise records, the electronic device (101) can analyze exercise intensity by specific body part and / or areas that are under-exercised. For example, based on a series of diet records, the electronic device (101) can analyze the nutritional components of the diet and / or the intake ratio of specific food groups. The electronic device (101) can provide statistical data obtained under various execution conditions. The electronic device (101) may provide statistical data based at least in part on a request for displaying an image belonging to an image group. For example, the electronic device (101) may provide statistical data when providing an image through a gallery application, when providing a user interface regarding image patterns, and / or when taking additional series of images.

[0225] The electronic device (101) can obtain statistical data from multiple images (or groups of images). For example, the electronic device (101) can provide numerical data regarding changes in the body of an object (e.g., a user) and / or changes in the environment by comparing training images used to obtain image patterns. The electronic device (101) can analyze the training images using Vision AI. The electronic device (101) can provide suggestions to the user based on the analyzed information. The electronic device (101) can suggest specific actions to the user. For example, based on a series of growth records images, the electronic device (101) can analyze the amount of change in a child's height and / or predict growth trends. For example, based on a series of pregnancy records images, the electronic device (101) can provide a graph of changes in abdominal size and monthly fluctuations. For example, based on a series of fitness records images, the electronic device (101) can provide a graph regarding the degree of muscle development by exercise area and / or recommend muscle areas that are under-exercised. For example, the electronic device (101) may suggest specific actions to the user based on information identified from multiple interconnected images. For example, the electronic device (101) may provide content (e.g., images, videos) that suggests step-by-step and / or time-based actions to the user to achieve a specific goal. For example, it may suggest exercising a muscle area that lacks exercise in a specific way. For example, if a specific change is identified from an image included in a series of images, the electronic device (101) may highlight the corresponding change in the image (e.g., distinguishing it from other areas of the image using an icon or text).For example, in a series of images (or image patterns) themed around a growth record, if a diaper no longer appears at a specific point in time, this can be identified as a change (or inflection point) consistent with the theme of the growth record, and the identified change can be displayed to the user.

[0226] The electronic device (101) can utilize data obtained from multiple images in conjunction with healthcare and life log services. The electronic device (101) can analyze data regarding image patterns and provide more sophisticated data by linking the analysis results with healthcare, diet management, and life log services. For example, when an exercise and healthcare app is launched, the electronic device (101) can recommend customized exercises based on the analysis results of a series of fitness records images. For example, when a diet / nutrition management app is launched, the electronic device (101) can recommend nutritional components to supplement based on the analysis results of a series of diet records images. For example, when a pregnancy and / or parenting app is launched, the electronic device (101) can provide customized advice and / or health check items based on the analysis results of a series of pregnancy records images.

[0227] In one embodiment, the electronic device (101) can generate a customized image based on data regarding an image pattern using an advanced image generation model. For example, the electronic device (101) can apply a specific style (e.g., painting style, film photography feel) to the image pattern (e.g., see FIG. 18).

[0228] In one embodiment, the electronic device (101) may detect information about the surrounding environment of the electronic device. For example, the surrounding environment of the electronic device (101) may include a specific subject and / or a place where the electronic device (101) is located. Based on the information about the surrounding environment, the electronic device (101) may provide a user interface that suggests taking a series of images.

[0229] In one embodiment, the electronic device (101) is a wearable device (e.g., a glasses-type device) or can communicate with a wearable device. The electronic device (101) may suggest taking a picture or automatically take a picture when an object of a series of images is detected in the user's surrounding environment through the wearable device.

[0230] In one embodiment, the electronic device (101) can generate a series of images in real time in an eXtended Reality (XR) environment (e.g., virtual reality and / or augmented reality). The electronic device (101) can acquire data regarding 3D image patterns. For example, the electronic device (101) can visually represent the series of images in a virtual reality space.

[0231] In one embodiment, the electronic device (101) can automatically acquire data regarding image patterns using metadata-based data of an image. The electronic device (101) can specifically define image patterns by analyzing metadata regarding the shooting environment, such as the shooting time and / or shooting location data of the image. The electronic device (101) can increase the accuracy of the automatic image pattern generation function by using metadata-based data. The electronic device (101) can suggest capturing an image based on metadata-based data of previously acquired images (e.g., shooting cycle / location / time). For example, the electronic device (101) can notify the timing when image capture is required based on metadata-based data of previously acquired images. For example, the electronic device (101) can monitor the user's surrounding environment through the electronic device (101) or another electronic device connected to the electronic device (101) (e.g., a wearable electronic device), and when a subject of a series of images (e.g., a subject) is detected in the surrounding environment, it can automatically capture an image or suggest capturing an image to the user.

[0232] In one embodiment, when a new image is acquired (e.g., captured), the electronic device (101) may display images similar to the acquired new image (e.g., previously stored images) and indicate that there is a subject that can be identified as a series of images.

[0233] In one embodiment, the electronic device (101) may receive a user's query regarding the acquisition of a series of images for a specific subject. The electronic device (101) may generate and provide information regarding the subject, layout, and / or shooting cycle required for the acquisition of the series of images. For example, if the user asks how to take a series of images for a growth record, the electronic device (101) may suggest to the user information regarding at what time, at what cycle, and / or with what composition the subject should be photographed.

[0234] In one embodiment, the electronic device (101) comprises a memory (130) including at least one storage medium for storing instructions; and at least one processor (120) including a processing circuit, wherein when the instructions are executed individually or collectively by the at least one processor, the electronic device causes at least one operation to be performed, and the at least one operation may include: an operation of acquiring a plurality of images; an operation of identifying the plurality of images as an image group having a specific image pattern; an operation of acquiring a first image; and an operation of acquiring a second image generated by correcting the first image according to at least a part of the specific image pattern based at least part of a determination that the first image corresponds to the image group.

[0235] In one embodiment, the operation of acquiring the second image may include: an operation of determining whether the first image corresponds to a designated first category in relation to the image pattern; and an operation of correcting the first image based on the determination that the first image corresponds to the designated first category.

[0236] In one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may be caused to perform an operation of refraining from the adjusting of the first image based on the determination that the first image corresponds to a second category specified in relation to the image pattern.

[0237] In one embodiment, the operation of determining whether the first image corresponds to the first category may include: the operation of obtaining data regarding elements of the first image; the operation of comparing the data regarding elements of the first image with data regarding elements of the image pattern to obtain a matching element that matches the elements of the image pattern and a non-matching element that does not match the elements of the image pattern among the elements of the first image; and the operation of determining that the first image corresponds to the first category if the first image includes one or more matching elements and one or more non-matching elements.

[0238] In one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may be caused to perform an operation of determining that the first image corresponds to the second category if the first image does not contain the non-matching element.

[0239] In one embodiment, the operation of acquiring the second image may include an operation of correcting the first image such that the non-matching element matches the corresponding element of the image pattern by converting data regarding the non-matching element in the first image according to data regarding the corresponding element of the image pattern.

[0240] In one embodiment, the operation of acquiring the second image may include: acquiring data regarding a corresponding element of the image pattern corresponding to the non-matching element; acquiring an image generation prompt based on the data regarding the matching element and the data regarding the corresponding element; and inputting the image generation prompt into an artificial intelligence model.

[0241] In one embodiment, the element may include at least one of context, layout, style, or metadata-based data.

[0242] In one embodiment, the context includes at least one of a subject, a background, or a theme, the layout includes at least one of the position of the subject, the tilt of the subject, or the ratio of the subject to the background, the style includes at least one of color tone, brightness, texture, or lighting, and the metadata-based data may include at least one of a shooting time, a pattern of the shooting time, location data, or a pattern of the location data.

[0243] In one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may be caused to perform an operation of correcting at least some of the plurality of images according to the specific image pattern.

[0244] In one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may be caused to perform: an operation of acquiring statistical data for a specific subject based on the image group including the plurality of images and the first image; and an operation of providing the statistical data based at least partially on a request for displaying an image belonging to the image group.

[0245] In one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may be caused to perform an operation of providing a user interface that suggests a specific action to a user of the electronic device based on the statistical data.

[0246] In one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may be caused to perform: an operation of detecting information about the surrounding environment of the electronic device; and an operation of providing a user interface that suggests capturing the first image corresponding to the image group based on the information about the surrounding environment.

[0247] In one embodiment, when the instructions are executed individually or collectively by the at least one processor, the electronic device may be caused to perform an operation that provides a user interface capable of selecting the automatic application of the image pattern.

[0248] In one embodiment, a control method for an electronic device (101) may include: an operation of acquiring a plurality of images; an operation of identifying the plurality of images as an image group having a specific image pattern; an operation of acquiring a first image; and an operation of acquiring a second image generated by correcting the first image according to at least a part of the specific image pattern based on at least a part of a determination that the first image corresponds to the image group.

[0249] In one embodiment, the operation of acquiring the second image may include: an operation of determining whether the first image corresponds to a designated first category in relation to the image pattern; and an operation of correcting the first image based on the determination that the first image corresponds to the designated first category.

[0250] In one embodiment, based on the determination that the first image corresponds to a second category specified in relation to the image pattern, the operation of refraining from adjusting the first image may be included.

[0251] In one embodiment, the operation of determining whether the first image corresponds to the first category may include: the operation of obtaining data regarding elements of the first image; the operation of comparing the data regarding elements of the first image with data regarding elements of the image pattern to obtain a matching element that matches the elements of the image pattern and a non-matching element that does not match the elements of the image pattern among the elements of the first image; and the operation of determining that the first image corresponds to the first category if the first image includes one or more matching elements and one or more non-matching elements.

[0252] In one embodiment, the operation of acquiring the second image may include an operation of correcting the first image such that the non-matching element matches the corresponding element of the image pattern by converting data regarding the non-matching element in the first image according to data regarding the corresponding element of the image pattern.

[0253] In one embodiment, the operation of acquiring the second image may include: acquiring data regarding a corresponding element of the image pattern corresponding to the non-matching element; acquiring an image generation prompt based on the data regarding the matching element and the data regarding the corresponding element; and inputting the image generation prompt into an artificial intelligence model.

[0254] The various embodiments of this document and the terms used therein are not intended to limit the technical features described in this document to specific embodiments, and should be understood to include various modifications, equivalents, or substitutions of said embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of said items unless the relevant context clearly indicates otherwise. In this document, phrases such as "A or B," "at least one of A and B," "at least one of A or B," "A, B or C," "at least one of A, B and C," and "at least one of A, B, or C" may each include any one of the items listed together in the corresponding phrase, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used simply to distinguish said components from other said components and do not limit said components in any other aspect (e.g., importance or order). Where any (e.g., 1st) component is referred to as "coupled" or "connected" to another (e.g., 2nd) component, with or without the terms "functionally" or "communicationly," it means that said any component may be connected to said other component directly (e.g., via a wire), wirelessly, or through a third component.

[0255] The term “module” as used in the various embodiments of this document may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit, for example. A module may be a component formed integrally, or a minimum unit of said component or a part thereof that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0256] According to various embodiments, each component (e.g., module or program) of the components described above may include a singular or multiple entities, and some of the multiple entities may be separated and placed in other components. According to various embodiments, one or more of the components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Generally or additionally, multiple components (e.g., module or program) may be integrated into a single component. In this case, the integrated component may perform one or more functions of each of the multiple components in the same or similar manner as those performed by the corresponding component among the multiple components prior to integration. According to various embodiments, operations performed by the module, program, or other components may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

Claims

1. In an electronic device (101), Memory (130) including at least one storage medium for storing instructions; and It includes at least one processor (120) including a processing circuit, and When the above instructions are executed individually or collectively by the at least one processor, the electronic device causes at least one operation to perform, and the at least one operation is, The operation of acquiring multiple images; The operation of identifying the above plurality of images into an image group having a specific image pattern; The operation of acquiring a first image; and The operation of obtaining a second image generated by correcting the first image according to at least a part of the specific image pattern, based at least in part on the determination that the first image corresponds to the image group. An electronic device including 2. In Paragraph 1, The operation of acquiring the second image above is, An operation to determine whether the first image corresponds to a designated first category in relation to the image pattern; and An operation to correct the first image based on the determination that the first image corresponds to the designated first category. An electronic device including 3. In Paragraph 2, When the above instructions are executed individually or collectively by the at least one processor, the electronic device: An operation to refrain from correcting the first image based on the determination that the first image corresponds to a second category designated in relation to the image pattern. An electronic device that causes to perform.

4. In Paragraph 3, The operation of determining whether the above first image corresponds to the above first category is, An operation to acquire data regarding the elements of the first image; The operation of comparing data regarding elements of the first image with data regarding elements of the image pattern to obtain matching elements and non-matching elements among the elements of the first image that match the elements of the image pattern; and If the first image includes one or more matching elements and one or more non-matching elements, the operation of determining that the first image corresponds to the first category An electronic device including 5. In Paragraph 4, When the above instructions are executed individually or collectively by the at least one processor, the electronic device: If the first image does not include the non-matching element, the operation of determining that the first image corresponds to the second category An electronic device that causes to perform.

6. In Paragraph 4, The operation of acquiring the second image above is, An operation to correct the first image such that the non-matching element matches the corresponding element of the image pattern by converting the data regarding the non-matching element in the first image according to the data regarding the corresponding element of the image pattern. An electronic device including 7. In Paragraph 4, The operation of acquiring the second image above is, An operation to acquire data regarding the corresponding element of the image pattern corresponding to the above-mentioned non-matching element; An operation to obtain an image generation prompt based on data regarding the matching element and data regarding the corresponding element; and The action of inputting the above image generation prompt into the artificial intelligence model An electronic device including 8. In any one of paragraphs 4 through 7, The above element is an electronic device comprising at least one of context, layout, style, or metadata-based data.

9. In Paragraph 8, The above context includes at least one of a subject, a background, or a theme, and The above layout includes at least one of the position of the subject, the tilt of the subject, or the ratio of the subject to the background, and The above style includes at least one of color tone, brightness, texture, or lighting, and An electronic device comprising at least one of the above metadata-based data, a shooting time, a pattern of the above shooting time, location data, or a pattern of the above location data.

10. In any one of paragraphs 1 through 9, When the above instructions are executed individually or collectively by the at least one processor, the electronic device: Operation of correcting at least some of the plurality of images according to the specific image pattern An electronic device that causes to perform.

11. In any one of paragraphs 1 through 10, When the above instructions are executed individually or collectively by the at least one processor, the electronic device: An operation of acquiring statistical data for a specific subject based on the image group including the plurality of images and the first image; and An operation of providing the statistical data based at least partially on a request for displaying an image belonging to the above image group. An electronic device that causes to perform.

12. In Paragraph 11, When the above instructions are executed individually or collectively by the at least one processor, the electronic device: Operation of providing a user interface that suggests a specific action to the user of the electronic device based on the above statistical data. An electronic device that causes to perform.

13. In any one of paragraphs 1 through 12, When the above instructions are executed individually or collectively by the at least one processor, the electronic device: Operation of detecting information about the surrounding environment of the above electronic device; and Operation of providing a user interface that suggests capturing the first image corresponding to the image group based on information about the surrounding environment. An electronic device that causes to perform.

14. In any one of paragraphs 1 through 13, When the above instructions are executed individually or collectively by the at least one processor, the electronic device: Operation of providing a user interface that can select the automatic application of the above image pattern An electronic device that causes to perform.

15. A method for controlling an electronic device (101), The operation of acquiring multiple images; The operation of identifying the above plurality of images into an image group having a specific image pattern; The operation of acquiring a first image; and The operation of obtaining a second image generated by correcting the first image according to at least a part of the specific image pattern, based at least in part on the determination that the first image corresponds to the image group. A control method including

Images