Electronic device and image enhancement method

Abstract

An electronic device according to an embodiment of the present disclosure may comprise a camera, a display, a memory, and at least one processor operatively connected to the camera, the display, and the memory. The memory may store instructions which may be executed by the at least one processor and, when executed, cause the electronic device to: acquire a first image captured using the camera; determine a prompt for requesting an AI model (410) to correct the first image; transfer the first image and the determined prompt to the AI model; acquire, by the AI model, correction data generated as a result of analyzing the first image on the basis of the prompt; and display, through the display, a second image corrected on the basis of the correction data. Various other embodiments are possible.

Description

Electronic Devices and Image Enhancement Methods

[0001] This article relates to electronic devices, and for example, to methods for improving images acquired by electronic devices.

[0002] Portable electronic devices (hereinafter, "electronic devices"), such as smartphones, can provide diverse user experiences through various applications. Electronic devices can capture images of their surroundings using cameras and download and store image files over a network. Electronic devices can install and run a gallery application that displays stored images and offers various functions, such as copying / deleting / moving them, sharing them with other devices, and editing images.

[0003] Electronic devices may offer image or video editing features through their gallery applications. For example, a gallery application may offer a separate filter (or style) menu, allowing users to select editing effects, such as color adjustments.

[0004] Even when electronic devices provide a variety of correction effects for images, the user must select the correction effect to apply, and the user usability may be limited because the selection is limited to a pre-defined range.

[0005] An electronic device according to one embodiment of the present disclosure includes a camera, a display, a memory, and at least one processor operatively connected to the camera, the display, and the memory, wherein the memory may store instructions that are executable by the at least one processor and, when executed, cause the electronic device to acquire a first image captured using the camera, determine a prompt for requesting an AI model (410) to correct the first image, transmit the first image and the determined prompt to the AI ​​model, obtain correction data generated by analyzing the first image based on the prompt by the AI ​​model, and display a second image corrected based on the correction data through the display.

[0006] A method performed by an electronic device according to one embodiment of the present disclosure may include an operation of acquiring a first image captured using a camera, an operation of determining a prompt for requesting an AI model to correct the first image, an operation of transmitting the first image and the determined prompt to the AI ​​model, an operation of acquiring correction data generated as a result of analyzing the first image based on the prompt by the AI ​​model, and an operation of displaying a second image corrected based on the correction data.

[0007] A computer-readable non-transitory recording medium according to one embodiment of the present disclosure may store instructions for performing an operation of acquiring a first image captured by a camera, an operation of determining a prompt for requesting an AI model to correct the first image, an operation of transmitting the first image and the determined prompt to the AI ​​model, an operation of acquiring correction data generated as a result of analyzing the first image based on the prompt by the AI ​​model, and an operation of displaying a second image corrected based on the correction data.

[0008] According to various embodiments of the present document, an electronic device and an image enhancement method can be provided that can optimize the enhancement effect on an image captured by a camera using generative artificial intelligence.

[0009] FIG. 1 is a block diagram of an electronic device within a network environment according to various embodiments.

[0010] FIG. 2 illustrates a UI that provides a correction effect to an image according to one embodiment.

[0011] FIG. 3 is a block diagram of an electronic device according to various embodiments.

[0012] FIG. 4 is a block diagram of software configurations of an electronic device according to one embodiment.

[0013] FIG. 5 illustrates a prompt selection UI provided by an electronic device according to one embodiment.

[0014] FIGS. 6A and 6B illustrate screens displaying an original image and a corrected image according to one embodiment.

[0015] FIG. 7 illustrates a UI that allows a user to directly input a prompt according to one embodiment.

[0016] Figure 8 is a flowchart of an image enhancement method according to one embodiment.

[0017] FIGS. 9A and 9B illustrate a foldable device according to one embodiment.

[0018] FIG. 10 illustrates a flex mode operation state of a foldable device according to one embodiment.

[0019] FIGS. 11A and 11B illustrate a multi-foldable device according to one embodiment.

[0020] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings so that those skilled in the art can easily implement the present disclosure. However, the present disclosure may be implemented in various different forms and is not limited to the embodiments described herein. In connection with 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 conciseness.

[0021] FIG. 1 is a block diagram of an electronic device (101) within a network environment (100) according to various embodiments.

[0022] Referring to FIG. 1, in a network environment (100), an electronic device (101) may communicate with an electronic device (102) via a first network (198) (e.g., a short-range wireless communication network), or may communicate with at least one of an electronic device (104) or a server (108) via a second network (199) (e.g., a long-range wireless communication network). In one embodiment, the electronic device (101) may communicate with the electronic device (104) via the server (108). According to one embodiment, the electronic device (101) may include a processor (120), a memory (130), an input module (150), an audio output module (155), a display module (160), an audio module (170), a sensor module (176), an interface (177), a connection terminal (178), a haptic module (179), a camera module (180), a power management module (188), a battery (189), a communication module (190), a subscriber identification module (196), or an antenna module (197). In some embodiments, the electronic device (101) may omit at least one of these components (e.g., the connection terminal (178)), or may have one or more other components added. In some embodiments, some of these components (e.g., the sensor module (176), the camera module (180), or the antenna module (197)) may be integrated into one component (e.g., the display module (160)).

[0023] The processor (120) may, for example, execute software (e.g., a program (140)) to control at least one other component (e.g., a hardware or software component) of the electronic device (101) connected to the processor (120) and perform various data processing or operations. According to one embodiment, as at least a part of the data processing or operations, the processor (120) may store commands or data received from other components (e.g., a sensor module (176) or a communication module (190)) in a volatile memory (132), process the commands or data stored in the volatile memory (132), and store result data in a 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) (e.g., a graphics processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor) that can operate independently or together with the main processor (121). For example, when the electronic device (101) includes the main processor (121) and the auxiliary processor (123), the auxiliary processor (123) may be configured to use less power than the main processor (121) or to be specialized for a given function. The auxiliary processor (123) may be implemented separately from the main processor (121) or as a part thereof.

[0024] The auxiliary processor (123) may control at least a portion of functions or states associated with at least one component (e.g., a display module (160), a sensor module (176), or a communication module (190)) of the electronic device (101), for example, 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. In one embodiment, the auxiliary processor (123) (e.g., an image signal processor or a communication processor) may be implemented as a part of another functionally related component (e.g., a camera module (180) or a communication module (190)). In one embodiment, the auxiliary processor (123) (e.g., a neural network processing unit) may include a hardware structure specialized for processing artificial intelligence models. The artificial intelligence models may be generated through machine learning. This learning can be performed, for example, on the electronic device (101) itself where the artificial intelligence model is executed, or can be performed through a separate server (e.g., server (108)). The learning algorithm can 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 can include multiple artificial neural network layers.The artificial neural network may be one of 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, or alternatively to, a hardware structure, an artificial intelligence model may include a software structure.

[0025] The memory (130) can store various data used by at least one component (e.g., processor (120) or sensor module (176)) of the electronic device (101). The data can include, for example, software (e.g., program (140)) and input data or output data for commands related thereto. The memory (130) can include volatile memory (132) or non-volatile memory (134).

[0026] The program (140) may be stored as software in the memory (130) and may include, for example, an operating system (142), middleware (144), or an application (146).

[0027] The input module (150) can receive commands or data to be used in a component of the electronic device (101) (e.g., a processor (120)) from an external source (e.g., a user) of the electronic device (101). The input module (150) can include, for example, a microphone, a mouse, a keyboard, a key (e.g., a button), or a digital pen (e.g., a stylus pen).

[0028] The audio output module (155) can output audio signals to the outside of the electronic device (101). The audio output module (155) can include, for example, a speaker or a receiver. The speaker can be used for general purposes, such as multimedia playback or recording playback. The receiver can be used to receive incoming calls. In one embodiment, the receiver can be implemented separately from the speaker or as part of the speaker.

[0029] The display module (160) can visually provide information to an external party (e.g., a 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 the 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 a force generated by the touch.

[0030] The audio module (170) can convert sound into an electrical signal, or vice versa, convert an electrical signal into sound. According to one embodiment, the audio module (170) can acquire sound through the input module (150), output sound through the sound output module (155), or an external electronic device (e.g., electronic device (102)) (e.g., speaker or headphone) directly or wirelessly connected to the electronic device (101).

[0031] The sensor module (176) can detect the operating status (e.g., power or temperature) of the electronic device (101) or the external environmental status (e.g., user status) and generate an electrical signal or data value corresponding to the detected status. According to one embodiment, the sensor module (176) can include, for example, a gesture sensor, a gyro sensor, a barometric pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biometric sensor, a temperature sensor, a humidity sensor, or an illuminance sensor.

[0032] The interface (177) may support one or more designated protocols that may be used to directly or wirelessly connect the electronic device (101) with an external electronic device (e.g., the electronic device (102)). In one embodiment, the interface (177) may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

[0033] The connection terminal (178) may include a connector through which the electronic device (101) may 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).

[0034] The haptic module (179) can convert electrical signals into mechanical stimuli (e.g., vibration or movement) or electrical stimuli that a user can perceive through tactile or kinesthetic sensations. According to one embodiment, the haptic module (179) can include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

[0035] The camera module (180) can capture still images and videos. According to one embodiment, the camera module (180) may include one or more lenses, image sensors, image signal processors, or flashes.

[0036] 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 as, for example, at least a part of a power management integrated circuit (PMIC).

[0037] A battery (189) may power at least one component of the electronic device (101). In one embodiment, the battery (189) may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0038] The communication module (190) may support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between the 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 operate independently from the processor (120) (e.g., application processor) and may include one or more communication processors that 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., a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module (194) (e.g., a local area network (LAN) communication module, or a power line communication module). Among these communication modules, the corresponding communication module can communicate with an external electronic device (104) via a first network (198) (e.g., a short-range communication network such as Bluetooth, wireless fidelity (WiFi) direct, or infrared data association (IrDA)) or a second network (199) (e.g., a long-range communication network such as 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 can 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 verify or authenticate the electronic device (101) within a communication network such as the first network (198) or the second network (199) by using subscriber information (e.g., an international mobile subscriber identity (IMSI)) stored in the subscriber identification module (196).

[0039] The wireless communication module (192) can support 5G networks and next-generation communication technologies following the 4G network, such as NR access technology (new radio access technology). The NR access technology can support high-speed transmission of high-capacity data (eMBB (enhanced mobile broadband)), minimization of terminal power and connection of multiple terminals (mMTC (massive machine type communications)), or high reliability and low latency (URLLC (ultra-reliable and low-latency communications)). The wireless communication module (192) can support, for example, a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate. The wireless communication module (192) can support various technologies for securing performance in a high-frequency band, such as beamforming, massive multiple-input and multiple-output (MIMO), full dimensional MIMO (FD-MIMO), array antenna, analog beam-forming, or large scale antenna. The wireless communication module (192) can support various requirements specified in the electronic device (101), an external electronic device (e.g., the electronic device (104)), or a network system (e.g., the 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, a loss coverage (e.g., 164 dB or less) for mMTC realization, or a U-plane latency (e.g., 0.5 ms or less for downlink (DL) and uplink (UL), or 1 ms or less for round trip) for URLLC realization.

[0040] The antenna module (197) can transmit or receive signals or power to or from an external device (e.g., an external electronic device). In one embodiment, the antenna module (197) may include an antenna including a radiator formed of a conductor or a conductive pattern formed on a substrate (e.g., a PCB). In 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 the first network (198) or the second network (199), may be selected from the plurality of antennas, for example, by the communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device via the at least one selected antenna. In some embodiments, in addition to the radiator, another component (e.g., a radio frequency integrated circuit (RFIC)) may be additionally formed as a part of the antenna module (197).

[0041] According to various embodiments, the antenna module (197) may form a mmWave antenna module. In one embodiment, the mmWave antenna module may include a printed circuit board, an RFIC disposed on or adjacent a first side (e.g., a bottom side) of the printed circuit board and capable of supporting a designated high-frequency band (e.g., a mmWave band), and a plurality of antennas (e.g., an array antenna) disposed on or adjacent a second side (e.g., a top side or a side side) of the printed circuit board and capable of transmitting or receiving signals in the designated high-frequency band.

[0042] At least some of the above components can be interconnected and exchange signals (e.g., commands or data) with each other via a communication method between peripheral devices (e.g., a bus, GPIO (general purpose input and output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface)).

[0043] According to one embodiment, commands or data may be transmitted or received between the electronic device (101) and an external electronic device (104) via a server (108) connected to a second network (199). Each of the external electronic devices (102 or 104) may be the same or a different type of device as the electronic device (101). According to one embodiment, all or part of the operations executed in the electronic device (101) may be executed in one or more of the external electronic devices (102, 104, or 108). For example, when the electronic device (101) is to perform a certain function or service automatically or in response to a request from a user or another device, the electronic device (101) may, instead of or in addition to executing the function or service itself, request one or more external electronic devices to perform the function or at least a part of the service. One or more external electronic devices that receive the request may execute at least a portion of the requested function or service, or an additional function or service related to the request, and transmit the result of the execution to the electronic device (101). The electronic device (101) may process the result as is or additionally and provide it as at least a portion of a response to the request. For this purpose, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used, for example. The electronic device (101) may provide an ultra-low latency service by using distributed computing or mobile edge computing, for example. In one 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 a neural network. According to one embodiment, the external electronic device (104) or the server (108) may be included in 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.

[0044] FIG. 2 illustrates a UI that provides a correction effect to an image according to one embodiment.

[0045] According to one embodiment, the electronic device (200) can install and execute a gallery application. Images (and / or videos) captured by the camera of the electronic device (200) or downloaded from an external source and stored in memory can be displayed on the gallery application screen displayed on the display.

[0046] In one embodiment, the gallery application may provide image correction (or editing) functionality. In this document, image correction may include, but is not limited to, applying styles, adjusting graphical characteristics (e.g., brightness, contrast, saturation, etc.), adjusting subject proportions, and adding graphical effects.

[0047] Referring to (a) of FIG. 2, according to one embodiment, the electronic device (200) may execute a gallery application and select and display a specific image. The electronic device (200) may display items for selecting options such as rotation, sharing, deletion, and editing at the bottom of the image display area (210). When an edit item (221) is selected based on a user's touch input, the electronic device (200) may activate an edit mode for the corresponding image.

[0048] Referring to (b) of FIG. 2, according to one embodiment, the electronic device (200) may provide editing functions applicable to an image in an edit mode. For example, the electronic device (200) may provide an additional menu from which editing functions such as portrait, partial coloring, and style can be selected. When a style (231) is selected based on user input, the electronic device (200) may switch to a UI that allows changing the style of the image.

[0049] Referring to (c) of FIG. 2, according to one embodiment, the electronic device (200) may display items (251, 252, 253, 254) indicating styles applicable to the image at the bottom of the image. For example, the electronic device (200) may display at least one of an item (251) for selecting a colored pencil style, an item (252) for selecting a cartoon style, an item (253) for selecting a watercolor style, an item (254) for selecting a pastel style, or a slider (259) for selecting the degree of application of a style from the original image.

[0050] According to one embodiment, the electronic device (200) can correct an image according to a selected item and the degree of application selected through a slider (259) based on user input. For example, if an item (251) that allows selection of a colored pencil style is selected, the electronic device (200) can perform digital image processing such as line emphasis, texture application, color simplification, and / or detail reduction to correct the original image into a style similar to that drawn with a colored pencil. The electronic device (200) can display a corrected image (240) with the style applied in an image display area.

[0051] As illustrated in the embodiment of FIG. 2, the electronic device (200) can provide image correction functionality through access to an options menu, such as "Style," within the gallery application. This image correction functionality can enhance the user experience by viewing the captured image and adjusting color-based filters. However, since image correction can only be performed within a predefined range, user usability may be limited.

[0052] Hereinafter, various embodiments for improving the correction effect of an image by using the function of generative artificial intelligence (GAI) by an electronic device (200) will be described with reference to FIGS. 3 to 8.

[0053] FIG. 3 is a block diagram of an electronic device according to various embodiments.

[0054] Referring to FIG. 3, an electronic device (300) according to various embodiments may include a display (330), a communication circuit (360), a camera (340), a microphone (350), a processor (310), and a memory (320). Even if at least some of the illustrated components are omitted or replaced with other components, various embodiments of the present document may be implemented. The electronic device (300) may include at least some of the components and / or functions of the electronic device (101) of FIG. 1. At least some of the components of the illustrated (or not illustrated) electronic device (300) (e.g., the communication circuit (360), the processor (310), the memory (320)) may be disposed within a housing of the electronic device (300), and at least some of the other components (e.g., the display (330), the microphone (350), the camera (340)) may be at least partially visually exposed to the outside of the housing. At least some of the components of the electronic device (300) may be operatively, functionally and / or electrically connected to one another.

[0055] According to one embodiment, the display (330) can display image information provided from the processor (310). The display (330) can be implemented as any one of a liquid crystal display (LCD), a light-emitting diode (LED) display, and an organic light-emitting diode (OLED) display, but is not limited thereto. The display (330) can be configured as a touch screen that detects a touch and / or proximity touch (or hovering) input using a part of a user's body (e.g., a finger) or an input device (e.g., a stylus pen). The display (330) can include at least some of the configurations and / or functions of the display module (160) of FIG. 1.

[0056] According to one embodiment, the display (330) may be a flexible display, at least part of which is flexible and / or bendable.

[0057] According to one embodiment, the electronic device (300) may be implemented as a foldable device, in which the size of the display area can be expanded or reduced by utilizing the characteristics of the flexible display (330). For example, the electronic device (300) may include a structure that can be folded left and right based on a vertical folding axis or a structure that can be folded up and down based on a horizontal folding axis. The electronic device (300) may include a first housing (not shown) and a second housing (not shown) that are coupled to each other so as to be rotatable about the folding axis. The display (330) may be arranged across the first housing and the second housing, and may include a first display area arranged in the first housing and a second display area arranged in the second housing. The structure and usage form when the electronic device (300) is implemented as a foldable device will be described in more detail with reference to FIGS. 9 and 10.

[0058] According to one embodiment, the electronic device (300) may be implemented with a multi-folding structure that can be folded based on two or more folding axes. An embodiment in which the electronic device (300) is implemented with a multi-folding structure will be described in more detail with reference to FIG. 11.

[0059] According to one embodiment, the electronic device (300) may provide a flex mode in which the first housing and the second housing are maintained at a predetermined angle. For example, when the second housing of the electronic device (300) is placed on the floor, the angle between the first housing and the second housing may be maintained at a fixed angle.

[0060] According to another embodiment, the electronic device (300) may be implemented in another form factor, such as a rollable device.

[0061] According to one embodiment, the electronic device (300) may include at least one camera (340). For example, at least one camera (340) may be disposed on the rear of the housing where the rear cover of the electronic device (300) is disposed, and / or on the front of the housing where the display (330) is disposed. The number and / or placement of the cameras (340) included in the electronic device (300) is not limited thereto.

[0062] According to one embodiment, the cameras (340) may include components such as a lens assembly, a flash, an image sensor, an image stabilizer, camera memory, and an image signal processor. The cameras (340) may include at least some of the components and / or functions of the camera module (180) of FIG. 1.

[0063] According to one embodiment, the microphone (350) can pick up external sounds, such as a user's voice, and convert them into voice signals, which are digital data. According to one embodiment, the electronic device (300) may include a microphone in a part of a housing (not shown), or may receive voice signals picked up from an external microphone connected wired or wirelessly. According to one embodiment, the voice signal acquired from the microphone (350) is transmitted to the processor (310), and the processor (310) can convert the voice signal into text information through automatic speech recognition (ASR) and perform an operation corresponding to the text information.

[0064] According to one embodiment, the communication circuit (360) may include various configurations to support wireless communication with external devices. For example, the electronic device (300) may perform cellular wireless communication (e.g., 4G long term evolution (LTE), 5G new radio (NR)) and / or short-range wireless communication (e.g., Wi-Fi, Bluetooth) through the communication circuit (360), and there is no limitation on the type of wireless communication supported by the electronic device (300). The communication circuit (360) may include at least some of the configurations and / or functions of the communication module (190) of FIG. 1.

[0065] According to one embodiment, the memory (320) may temporarily or permanently store various data, including volatile memory and non-volatile memory. The memory (320) may include at least some of the configuration and / or functions of the memory (130) of FIG. 1, and may store the program (140) of FIG. 1. The memory (320) may store various instructions that may be executed by the processor (310). Such instructions may include control commands such as arithmetic and logical operations, data movement, and input / output that may be recognized by the processor (310).

[0066] According to one embodiment, the processor (310) is a configuration capable of performing calculations or data processing related to control and / or communication of each component of the electronic device (300), and may be configured with one or more processors. The processor (310) may include at least some of the configurations and / or functions of the processor (120) of FIG. 1. There is no limitation to the calculation and data processing functions that the processor (310) may implement on the electronic device (300), but this document will describe in detail various embodiments for optimizing the improvement effect on an image captured by the camera (340) using generative artificial intelligence (AI). The operations of the processor (310) described below may be performed by loading instructions stored in the memory (320).

[0067] In this document, the description that the processor (310) can perform a certain operation (or function, work, task) may be interpreted to mean substantially the same as that an instruction (or command, computer program) that causes the electronic device (300) (or the processor (310)) to perform the corresponding operation is stored in the memory (320) (e.g., non-volatile memory, storage). In addition, the description that the processor (310) can perform a certain operation may be interpreted to mean substantially the same as that at least one processor, without specifying the operation, can perform the corresponding operation.

[0068] According to one embodiment, the processor (310) may execute a gallery application stored in the memory (320). According to one embodiment, the gallery application may provide an image correction function. In this document, image correction may include, but is not limited to, applying a style, correcting graphic characteristics (e.g., brightness, contrast, saturation, etc.), adjusting the subject ratio, and adding graphic effects. In this document, an image to be corrected is referred to as an original image (or first image), and an image improved by applying a correction function to the original image through user input or an AI model may be referred to as a corrected image.

[0069] According to one embodiment, the processor (310) may acquire an original image (or a first image) captured using a camera (340) and display it on the display (330). When a correction function for the original image is activated based on a user input, the processor (310) may determine a prompt including a request for a correction method for the original image. Here, the prompt may include text data for requesting an AI model to analyze the original image and generate correction data.

[0070] In one embodiment, the AI ​​model may include generative artificial intelligence (AI). The AI ​​model may be trained using data related to image correction by the electronic device (300) or other electronic devices (300). For example, the AI ​​model may learn patterns in the data and, upon input of the original image and prompt, determine an optimized corrected image from the original image. The AI ​​model may also be referred to as an image improvement AI module.

[0071] In one embodiment, the AI ​​model can automatically determine and apply optimal image quality settings through analysis of captured images. This allows the system to provide optimal image quality without requiring the user to manually configure detailed settings, thereby enhancing user convenience.

[0072] In this document, the AI ​​model may include an on-device AI model and a server AI model (or AI analysis center). According to one embodiment, the processor (310) may include a neural processing unit (NPU) that processes the machine learning operations of the AI ​​model to implement the on-device AI model. The processor (310) may execute operations for analyzing image data and generating correction data by executing a deep learning algorithm through the on-device AI model.

[0073] In one embodiment, the processor (310) may transmit the generated prompt to a server (e.g., an AI analysis center) of the network via a communication circuit (360). The server may include a server AI model, and the server AI model may perform operations for generating analysis and correction data of the image and prompt.

[0074] In one embodiment, an AI model (e.g., an on-device AI model or a server AI model) may analyze an original image and generate correction data for correcting the original image based on a prompt entered or selected by a user. For example, the correction data may include parameters related to a style to be applied to the original image (e.g., colored pencil, cartoon, watercolor, etc.), graphical characteristics to be changed (e.g., brightness, contrast, saturation, etc.), subject ratio / depth effect, and graphical effects (e.g., weather, time of day).

[0075] In one embodiment, the processor (310) may provide a plurality of predetermined prompt modes. In one embodiment, the AI ​​model may be pre-trained to generate predetermined analysis and correction data for each prompt mode. For example, when any one of the plurality of prompt modes is selected, the processor (310) may transmit a predetermined prompt to the AI ​​model for the original image and the selected prompt mode. The AI ​​model may be trained to perform a predetermined task upon receiving a specific prompt, and may perform an analysis task corresponding to the prompt on the original image.

[0076] Table 1 shows examples of prompt modes.

[0077] Prompt 1Prompt 2Prompt 3Prompt 4Prompt 5UsageUserUploadFlex ModeAI AutoAdditional EffectsCorrection MethodUser PreferenceSNS Upload1 to 1 or 1 to manyTransmitGroup PhotoEffects provided according to folding angleAutomatically determined by AI modelAdditional effects such as weather and time

[0078] According to one embodiment, the AI ​​model may analyze user preferences based on the user's image correction history or user input history on the application, and generate correction data based on the analyzed user preferences. According to one embodiment, the first prompt mode may be a mode that generates a prompt for requesting the AI ​​model to correct an image based on the user's preferences in the gallery application. When the AI ​​model receives a prompt corresponding to the first prompt mode, the AI ​​model may analyze correction effects that the user has applied to multiple images through the gallery application of the electronic device (300), and identify correction effects that have been applied frequently or correction effects that have been applied to images of a similar type to the original image. For example, the AI ​​model may analyze graphic effects, such as sharpness and / or color, that the user has applied to images through the correction function of the gallery application, and generate correction data. According to one embodiment, the AI ​​model may analyze the user's preferences based on the user's activities on multiple images through the gallery application or SNS application stored in the memory (320) of the electronic device (300), and generate correction data based on the analyzed preferences. For example, an AI model could assign a higher preference to images that have been marked with a user's likes (e.g., "Likes") in an application, and / or analyze the user's preference for each image based on images deleted after capture and images saved in the user's photos. Based on the user's preference for each image, the AI ​​model could determine graphical effects, such as color, composition, and clarity, for images with a high user preference.

[0079] In one embodiment, the second prompt mode may be an upload prompt mode. For example, the second prompt mode may be a mode that generates a prompt to request an AI model to correct an image when transmitting or sharing a captured image to another user or a group of users. When the AI ​​model receives a prompt corresponding to the second prompt mode, the AI ​​model may generate correction data based on the other party to whom the image will be transmitted and / or the application to be used. For example, the AI ​​model may determine a correction effect that emphasizes a specific person (e.g., the user, the other party to whom the image will be transmitted) among the subjects included in the image. Alternatively, the AI ​​model may determine a correction effect appropriate for a group photo containing multiple people when the photo is to be uploaded via a social networking service application or shared with multiple parties.

[0080] According to one embodiment, the AI ​​model can generate correction data that includes at least one of light adjustment, depth effect, or subject proportion adjustment for the original image.

[0081] According to one embodiment, the third prompt mode may be a mode that generates a prompt to request an AI model to correct at least one of the amount of light, depth, or aspect ratio of the image based on the folding angle when the electronic device (300) is operating in flex mode.

[0082] According to one embodiment, the electronic device (300) may be a foldable device that can be folded up and down or left and right (e.g., the electronic device (900) of FIGS. 9A and 9B)) and may include a first housing (e.g., the first housing (931) of FIGS. 9A and 9B) and a second housing (e.g., the second housing (932) of FIGS. 9A and 9B) that are rotatably coupled to each other about a folding axis (e.g., the folding axis (A) of FIG. 9A). The electronic device (300) may include a sensor that can sense a folding angle (or an angle between the first housing and the second housing).

[0083] According to one embodiment, when the third prompt mode is selected, the processor (310) may transmit a prompt corresponding to the third prompt mode, the original image, and folding angle information to the AI ​​model. According to one embodiment, the AI ​​model may generate correction data related to at least one of the light quantity, depth, or subject ratio of the image based on the folding angle. For example, when the folding angle increases, the AI ​​model may further extend the length of a person's legs, express a specific subject more deeply, and / or provide an effect of increased light quantity through a lighting effect.

[0084] In one embodiment, the fourth prompt mode may be a mode in which the AI ​​model automatically analyzes the image and generates correction data. For example, the fourth prompt mode may allow the AI ​​model to analyze the graphical characteristics of the original image, included objects, etc., and regenerate the correction image without user input.

[0085] In one embodiment, the fifth prompt mode may be a mode that generates prompts to request additional effects, such as weather / time, from the AI ​​model. For example, in the fifth prompt mode, the AI ​​model may determine the current weather, or a weather effect (e.g., clear, cloudy, rainy, snowy) that matches the original image, or the current time or a time (e.g., day or night) that matches the original image.

[0086] This document describes the first prompt mode to the fifth prompt mode as examples, but the number and / or contents of the prompt modes provided by the electronic device (300) are not limited thereto.

[0087] According to one embodiment, the processor (310) may display a prompt mode selection UI on the display (330) that allows selection of any one of a plurality of prompt modes. The processor (310) may transmit a prompt corresponding to a prompt mode selected based on user input among the plurality of prompt modes to the AI ​​model.

[0088] According to one embodiment, the processor (310) may transmit a prompt to the on-device AI model (or first AI model) of the electronic device (300) or the server AI model (or second AI model) of an external server in response to a prompt mode selected based on a user input. For example, the processor (310) may transmit a prompt to the on-device AI model in the first prompt mode or the third prompt mode, which require analysis of information stored in the electronic device (300). In addition, the processor (310) may transmit a prompt to the server AI model in the second prompt mode or the fourth prompt mode, which require information from an external server or have a large amount of data to learn.

[0089] In one embodiment, the AI ​​model may generate correction data based on the results of analyzing the original image based on the received prompt. For example, the correction data may include information such as a style to be applied to the original image, correction of graphical characteristics (e.g., brightness, contrast, saturation, etc.), adjustment of the subject ratio, and addition of graphical effects. The processor (310) may correct the original image based on the correction data received from the AI ​​model to generate a correction image.

[0090] In another embodiment, the AI ​​model may generate a corrected image by correcting the original image based on a prompt. In this case, the processor (310) may display the corrected image received by the AI ​​model on the display (330).

[0091] According to one embodiment, the processor (310) may display an original image and a corrected image together on the display (330). For example, the electronic device (300) may display an original image to be corrected, selected by a user in a gallery application, on at least a portion of a first area (e.g., the first area (331) of FIG. 6A) of the display (330), and may display a corrected image corrected by correction data of an AI model on at least a portion of a second area (e.g., the second area (333) of FIG. 6A) of the display (330). The processor (310) may display a prompt mode selection UI together with the original image and the corrected image.

[0092] According to one embodiment, when the electronic device (300) is a foldable device, the processor (310) may display an original image on a first display area (e.g., the first display area (332) of FIG. 6B, the first display area (①) of FIG. 9A) of a display (330) disposed on a first housing, and may display a corrected image on a second display area (e.g., the second display area (334) of FIG. 6B, the second display area (②) of FIG. 9A) of a display (330) disposed on a second housing. In addition, the processor (310) may display a prompt mode selection UI on the second display area.

[0093] According to one embodiment, the processor (310) may further correct the corrected image based on user input after displaying the original image and the corrected image. For example, the processor (310) may perform additional corrections, such as applying styles, correcting graphic characteristics (e.g., brightness, contrast, saturation, etc.), adjusting the subject ratio, and adding graphic effects, based on user input through the correction function provided by the gallery application.

[0094] In one embodiment, the gallery application may provide a user interface that allows the user to adjust various settings for an image.

[0095] According to one embodiment, the processor (310) may store a correction image (or additional correction image) in the memory (320) based on user input.

[0096] Instructions for performing the operations of the electronic device (300) (or processor (310)) described above may be stored on a computer-readable recording medium. The recording medium may be tangible and non-transitory. The recording medium may store one or more computer programs including the instructions.

[0097] FIG. 4 is a block diagram of software configurations of an electronic device according to one embodiment.

[0098] Referring to FIG. 4, an electronic device (400) according to various embodiments (e.g., electronic device (300) of FIG. 3) may include an AI model (410), a camera unit (420), a gallery unit (430), a prompt input unit (440), an image processing unit (450), a display unit (460), and a storage unit (470).

[0099] According to one embodiment, the camera unit (420) can display a preview image acquired in real time from a camera (e.g., camera (340) of FIG. 3) and capture an image based on user input. The image captured by the camera unit (420) can be stored in the memory of the electronic device (400) (e.g., memory (320) of FIG. 3).

[0100] According to one embodiment, the gallery section (430) can display images captured by a camera and stored in a storage (470). The gallery section (430) can provide correction functions such as applying styles, correcting graphic characteristics (e.g., brightness, contrast, saturation, etc.), adjusting subject proportions, and adding graphic effects.

[0101] According to one embodiment, the prompt input unit (440) may generate a prompt to request the AI ​​model (410) to correct the original image, and transmit the prompt to the AI ​​model (410). For example, the electronic device (400) may allow the user to select a prompt mode through a prompt mode selection UI among a plurality of predetermined prompt modes. The prompt input unit (440) may generate a prompt corresponding to the prompt mode selected through the prompt mode selection UI, and transmit the prompt to the AI ​​model (410). Alternatively, the prompt input unit (440) may transmit a prompt directly input based on the user's text input or voice input to the AI ​​model (410).

[0102] According to one embodiment, the AI ​​model (410) can generate correction data including correction effects to be applied to the original image through analysis of the captured image.

[0103] According to one embodiment, the AI ​​model (410) may refer to an AI model logically configured when the electronic device (400) includes an on-device AI model (480) or utilizes an AI analysis center (490). The AI ​​model (410) may be configured as independent hardware or software. The AI ​​model (410) may include a plurality of on-device AI models (480) and / or a plurality of AI analysis centers (490), and each AI model may be an AI model that is differentiated from each other according to the purpose and / or characteristics of the prompt. For example, at least one AI model may utilize an external diffusion server as an AI model related to image generation, and other AI models may also be utilized.

[0104] According to one embodiment, the AI ​​model (410) (e.g., the on-device AI model (480), the AI ​​analysis center (490)) may include a trained machine learning model that can analyze each input original image, interpret the content of the prompt, and infer an appropriate correction effect to apply to the original image of the prompt. The operation of the machine learning model may include a learning and inference process of finding patterns in data, storing them as models that are generalized rules, and inputting new data into the trained model to obtain results.

[0105] In one embodiment, an AI model (e.g., an on-device AI model (480), an AI analysis center (490)) may be configured as a generative AI. A generative AI may include an AI system capable of generating text, images, or other media in response to a prompt. The generative AI may learn the patterns and structures of input training data and then generate new data with corresponding characteristics. To this end, the generative AI model may utilize machine learning, large-scale language models, and / or neural network algorithms.

[0106] According to one embodiment, the AI ​​model (410) can analyze the graphic characteristics of the original image. For example, the graphic characteristics may include, but are not limited to, resolution, color depth, brightness, contrast, saturation, luminance, sharpness, noise, focus, distortion, nonlinearity, chromatic aberration, light bleed, motion blur, white balance, tone mapping, hot pixels, lens flare, vignetting, low light noise, color cast, depth, distortion correction, auto focus, image stabilization, ISO sensitivity, aperture value, shutter speed, flash, and HDR. The electronic device (400) can calculate an optimal image quality setting value based on the analysis result of the image. The electronic device (400) can perform high-quality output processing according to the calculated image quality setting value, and in this process, the parallel processing capability of the AI ​​model (410) can be utilized.

[0107] According to one embodiment, the electronic device (400) can utilize both at least one on-device AI model (480) and at least one AI analysis center (490) (or server AI model) for image correction.

[0108] According to one embodiment, a processor (e.g., processor (310) of FIG. 3) of an electronic device (400) may include a neural processing unit (NPU) that processes machine learning operations to implement an on-device AI model (480). The processor may process image data by executing a deep learning algorithm through the on-device AI model (480).

[0109] In one embodiment, the AI ​​analysis center (490) may be an AI model built on a server in the network. The AI ​​analysis center (490) may acquire various data from various electronic devices and / or servers and perform machine learning operations based on the acquired data.

[0110] According to one embodiment, the prompt input unit (440) can transmit the original image and the prompt to the on-device AI model (480) or the AI ​​analysis center (490). According to one embodiment, the prompt input unit (440) can transmit the prompt to the on-device AI model (480) when the electronic device (400) is in the first prompt mode (or user preference mode) or the third prompt mode (or flex mode) that requires analysis of information stored in the electronic device (400). In addition, the prompt input unit (440) can transmit the prompt to the AI ​​analysis center when the electronic device requires information from an external server or is in the second prompt mode (or upload mode) or the fourth prompt mode (or AI auto mode) that has a lot of data to learn.

[0111] According to one embodiment, the prompt input unit (440) may select either the on-device AI model (480) or the AI ​​analysis center (490) depending on the security or privacy characteristics of the original image and / or prompt to be transmitted. For example, if the prompt input unit (440) determines that the image or prompt contains personal information or that it is not appropriate to transmit data outside the electronic device (400) for security reasons, the prompt input unit (440) may use only the on-device AI model (480) without using the AI ​​analysis center (490), transmit the information to the AI ​​analysis center (490) excluding the security information, or transmit the information to the AI ​​analysis center (490) by adding content requesting deletion of the security information to the prompt.

[0112] In one embodiment, the AI ​​model (410) (e.g., the on-device AI model (480), the AI ​​analysis center (490)) may analyze the original image and generate correction data based on the received original image and prompt. For example, the correction data may include information such as a style to be applied to the original image, correction of graphic characteristics (e.g., brightness, contrast, saturation, etc.), adjustment of the subject ratio, and addition of graphic effects. Alternatively, the AI ​​model (410) may correct the original image based on the original image and prompt, thereby generating a correction image.

[0113] According to one embodiment, the image processing unit (450) may generate a corrected image by correcting the original image based on the correction data received from the AI ​​model (410). If the AI ​​model (410) generates and transmits the corrected image, the operation of the image processing unit (450) may be omitted.

[0114] According to one embodiment, the electronic device (400) can display an original image and a corrected image through a display unit (460). The electronic device (400) can store the corrected image in a storage (470).

[0115] FIG. 5 illustrates a prompt selection UI provided by an electronic device according to one embodiment.

[0116] According to one embodiment, an electronic device (300) (e.g., the electronic device (300) of FIG. 3) may display a prompt mode selection UI on a display (330) (e.g., the display (330) of FIG. 3) that allows selection of any one of a plurality of prompt modes. The electronic device (300) may transmit a prompt corresponding to a prompt mode selected based on a user input from among the plurality of prompt modes to an AI model (e.g., the AI ​​model (510) of FIG. 5).

[0117] Referring to (a) of FIG. 5, the electronic device (300) may display an original image (510) on the display (330) when the gallery application is running and a correction function for a specific image is selected. According to one embodiment, the electronic device (300) may display a prompt mode selection UI (520) in a lower area of ​​the original image (510).

[0118] According to one embodiment, the prompt mode selection UI (520) may allow the user to select one of at least one predetermined prompt mode. For example, the plurality of prompt modes may include a first prompt mode that may correct graphic characteristics of an image, such as sharpness and / or color, based on user preferences in a gallery application, a second prompt mode that may correct an image to make it suitable for uploading (or transmitting, sharing), a third prompt mode that may correct an image according to a folding angle of a foldable device, a fourth prompt mode that may automatically correct an image by an AI model, and / or a fifth prompt mode that may provide additional effects, such as weather / time, to the image. The types of prompt modes are not limited thereto.

[0119] According to one embodiment, the prompt mode selection UI (520) can be scrolled left and right or up and down, and can display different prompt modes by user input (e.g., drag, flick).

[0120] Referring to (b) of FIG. 5, the electronic device (300) may select a first prompt mode based on a user input to the prompt mode selection UI (520). For example, the prompt mode selection UI (532) may be changed to indicate the first prompt mode based on a leftward flick input. The electronic device (300) may display the first prompt mode selected in the prompt mode selection UI (532) and a description of the first prompt mode (e.g., user preference).

[0121] According to one embodiment, the electronic device (300) may transmit a prompt corresponding to the selected first prompt mode to the AI ​​model. According to one embodiment, the electronic device (300) may determine the AI ​​model to transmit the first prompt mode as an on-device AI model operated by a processor of the electronic device (300) (e.g., processor (310) of FIG. 3), and transmit the prompt and the original image to the on-device AI model.

[0122] In one embodiment, the electronic device (300) may transmit additional data necessary for image correction to the AI ​​model in addition to the prompt. For example, the electronic device (300) may transmit multimedia information other than the original image (e.g., images, audio, video, text), and environmental information related to the electronic device (300) (e.g., location, weather, temperature) to the AI ​​model.

[0123] In one embodiment, the AI ​​model may analyze the original image based on the received prompt and generate correction data for correcting the original image. The AI ​​model may analyze the graphical characteristics of the original image (e.g., brightness, contrast, resolution, etc.) and the user's preferences for the gallery application. For example, the AI ​​model may analyze the corrections the user has previously applied to images based on the user's image correction history in the gallery application.

[0124] In one embodiment, the AI ​​model transmits correction data including parameters used for image correction, and the electronic device (300) can correct the original image based on the correction data to generate a corrected image. Alternatively, the AI ​​model can directly generate the corrected image based on the prompt and the original image.

[0125] According to one embodiment, the electronic device (300) may display a corrected image (540) generated based on the correction data or received from the AI ​​model on the display (330). For example, the electronic device (300) may display the corrected image (540) by removing the display of the original image (510) as shown in (b) of FIG. 5, or may display the corrected image (540) together with the original image (510).

[0126] According to one embodiment, when the prompt mode is changed according to a user input to the prompt mode selection UI (520), the electronic device (300) can transmit a prompt corresponding to the changed prompt mode to the AI ​​model.

[0127] Referring to (c) of FIG. 5, the electronic device (300) may select a fifth prompt mode based on a user input to the prompt mode selection UI (534). The fifth prompt mode may be a prompt mode that requests additional effects, such as weather or time, to be provided for the original image.

[0128] According to one embodiment, the electronic device (300) may transmit a prompt corresponding to the fifth prompt mode to the AI ​​model. Based on the received prompt, the AI ​​model may analyze the original image and generate correction data for correcting the original image. For example, the AI ​​model may analyze the original image and generate and transmit correction data or a correction image that includes additional effects, such as clouds and rainbows.

[0129] According to one embodiment, the electronic device (300) may display a correction image (550) generated based on correction data or received from an AI model on the display (330). For example, the electronic device (300) may remove the display of the correction image (540) corresponding to the first prompt mode previously displayed and display the correction image (550) corresponding to the fifth prompt mode. According to one embodiment, the electronic device (300) may display the original image (510) and the correction image (550) on separate areas of the display (330).

[0130] According to another embodiment, the electronic device (300) may allow the user to directly input the prompt as text data by touch input using a keypad and / or voice input using a microphone, without requiring the user to select one of the prompt modes.

[0131] FIGS. 6A and 6B illustrate screens displaying an original image and a corrected image according to one embodiment.

[0132] According to one embodiment, the electronic device (300) (e.g., the electronic device (300) of FIG. 3) may display an original image (or first image) and a corrected image (or second image) together on the display. For example, the electronic device (300) may display an original image to be corrected, selected by a user in a gallery application, on at least a portion of a first area (331) of the display (330) (the display (330) of FIG. 3), and may display a corrected image corrected by correction data of an AI model on at least a portion of a second area (333) of the display.

[0133] Referring to FIG. 6A, the electronic device (300) can display an original image (610) in a first area (331) at the top of the display (330) and display a corrected image (620) in a second area (333) at the bottom of the first area (331). In addition, the electronic device (300) can display a currently selected prompt mode (e.g., a fifth prompt mode) (630) in a third area (335) at the bottom of the second area (333).

[0134] According to one embodiment, the electronic device (300) may be a foldable device that can be folded up and down or left and right. The electronic device may include a first housing (302) and a second housing (304) that is rotatably coupled to the first housing (302). Referring to FIG. 6B, the display (330) includes a first display area (332) disposed in the first housing (302) and a second display area (334) disposed in the second housing (304), and the first display area (332) and the second display area (334) can be folded up and down based on a horizontal folding axis.

[0135] According to one embodiment, the electronic device (300) can display an original image (640) in at least a portion of a first display area (332) and a corrected image (650) in at least a portion of a second display area (334). Additionally, the electronic device can display a currently selected prompt mode (660) at the bottom of the corrected image (650) in the second display area (334).

[0136] According to one embodiment, when the electronic device (300) is implemented as a foldable device as shown in FIG. 6B, the electronic device (300) may recognize the folding state of the electronic device (300) and provide recommended keywords and effects accordingly. For example, in flex mode, special effects for unique photography may be emphasized, and recommended keywords that are different from those in general situations may be provided. For example, the electronic device (300) may generate a prompt corresponding to the flex mode and transmit it to an AI model (e.g., the AI ​​model (410) of FIG. 4) to adjust the body proportions of a subject or emphasize lighting effects in flex mode. The AI ​​model may generate correction data of the original image to emphasize changes in the image according to the folding angle in flex mode. For example, the AI ​​model may provide effects such as correcting the length of a person's legs to be longer as the folding angle increases, expressing a specific subject more deeply, and / or increasing the amount of light, such as a lighting effect.

[0137] According to one embodiment, the electronic device (300) may be implemented as a multi-foldable device that can be folded based on two or more folding axes. For example, the display of the electronic device (300) may include a first display area and a second display area that can be folded to face each other based on a first folding axis, and a third display area that can be folded to face each other based on the second display area and the second folding axis. In this case, the electronic device (300) may display an original image in the first display area, a corrected image in the second display area, and a prompt in the third display area.

[0138] According to one embodiment, the electronic device (300) can generate multiple correction images for an original image through multiple prompt modes. According to one embodiment, the electronic device (300) can simultaneously display multiple correction images in distinct areas.

[0139] According to one embodiment, when the electronic device (300) is implemented as a foldable device (e.g., the electronic device (900) of FIGS. 9A and 9B), a correction image A generated based on a prompt A among a plurality of prompt modes may be displayed in a first display area (e.g., the first display area (①) of FIG. 9A), and a correction image B generated based on a prompt B may be displayed in a second display area (e.g., the second display area (②) of FIG. 9A).

[0140] According to one embodiment, when the electronic device (300) is implemented as a multi-foldable device (e.g., the electronic device (1100) of FIGS. 11A and 11B), a correction image A generated based on a prompt A among a plurality of prompt modes may be displayed in a first display area (e.g., the first display area (1110) of FIG. 11A), a correction image B generated based on a prompt B may be displayed in a second display area (e.g., the second display area (1120) of FIG. 11A), and a correction image C generated based on a prompt C may be displayed in a third display area (e.g., the third display area (1130) of FIG. 11A).

[0141] As illustrated in FIGS. 6A and 6B, the electronic device (300) can simultaneously display the original image and the corrected image, thereby allowing the user to check the correction effect applied by the AI ​​model.

[0142] FIG. 7 illustrates a UI that allows a user to directly input a prompt according to one embodiment.

[0143] According to one embodiment, the electronic device (300) may determine a prompt including a request for correction of the original image (710) based on a user's voice or text input.

[0144] According to one embodiment, when a correction function for a specific image is selected in a gallery application, the electronic device (300) may input text based on a touch input via a keypad, or convert user voice input via a microphone (e.g., microphone (350) of FIG. 3) into text. Referring to FIG. 7 (a), the electronic device (300) may display the input text (e.g., “Change the weather in the image”) on a prompt input UI (750).

[0145] According to one embodiment, the electronic device (300) may transmit the input prompt and the original image (710) to an AI model (e.g., the AI ​​model (410) of FIG. 4). The AI ​​model may analyze the text of the received prompt to determine a correction method for the original image (710). Alternatively, the AI ​​model may analyze the text of the prompt to determine whether it corresponds to one of a plurality of prompt modes (e.g., the fifth prompt mode). According to one embodiment, the electronic device (300) may analyze the content of the prompt input by the user and transmit the prompt to an on-device AI model or a server AI model.

[0146] In one embodiment, the AI ​​model may analyze an original image (710) based on a received prompt and generate correction data for correcting the original image (710). For example, the AI ​​model may analyze the prompt, identify a request to change the weather in the original image (710), and generate and transmit correction data or a correction image (720) that includes additional effects such as clouds and rainbows.

[0147] According to one embodiment, the electronic device (300) may display a correction image (720) generated based on correction data or received from an AI model on the display (330). Referring to (b) of FIG. 7, the electronic device (300) may display the original image (710) in a first area at the top of the display (330) and the correction image (720) in a second area at the bottom of the first area. In addition, the electronic device (300) may display an input prompt (750) in a third area at the bottom of the second area.

[0148] Figure 8 is a flowchart of an image enhancement method according to one embodiment.

[0149] According to one embodiment, the illustrated method can be performed by an electronic device (e.g., electronic device (300) of FIG. 3), and the technical features described above may be omitted from the description below.

[0150] According to one embodiment, at operation 810, the electronic device may launch a gallery application and select an original image.

[0151] According to one embodiment, in operation 815, the electronic device may activate a prompt mode selection UI (e.g., the prompt mode selection UI (520) of FIG. 5). According to one embodiment, the electronic device may provide a plurality of predetermined prompt modes. For example, the plurality of prompt modes may include a first prompt mode that may correct graphic characteristics of an image, such as sharpness and / or color, based on user preferences in a gallery application, a second prompt mode that may correct an image to be suitable for uploading (or transfer, sharing), a third prompt mode that may correct an image according to a folding angle of a foldable device, a fourth prompt mode that may automatically correct an image by an AI model, and / or a fifth prompt mode that may provide additional effects, such as weather / time, to the image.

[0152] According to one embodiment, at operation 820, the electronic device may select a prompt to transmit to an AI model (e.g., AI model (410) of FIG. 4) based on user input. For example, the prompt mode selection UI may be scrollable left and right or up and down, and may select one of a plurality of prompt modes based on user input (e.g., drag, flick).

[0153] According to one embodiment, in operation 825, the electronic device may determine an AI model to transmit the original image and the prompt based on pre-learned information. The electronic device may select at least one of an on-device AI model operable by a processor of the electronic device (e.g., an on-device AI model (480) of FIG. 4) and a server AI model (or AI analysis center) operable on a server of the network (e.g., an AI analysis center (490) of FIG. 4). For example, the electronic device may transmit the prompt to the on-device AI model when in the first prompt mode (or user preference mode) or the third prompt mode (or flex mode) that requires analysis of information stored in the electronic device. In addition, the processor may transmit the prompt to the server AI model when in the second prompt mode (or upload mode) or the fourth prompt mode (AI auto mode) that requires information from an external server or has a large amount of data to learn.

[0154] In one embodiment, the electronic device may select either the on-device AI model or the AI ​​analysis center based on the security or privacy characteristics of the original image and / or prompt to be transmitted. For example, if the electronic device determines that the image or prompt contains personal information or that transmitting the data outside the electronic device is inappropriate for security reasons, the electronic device may transmit the prompt to the on-device AI model.

[0155] According to one embodiment, at operation 830, the electronic device may transmit the original image and prompt to the on-device AI model.

[0156] According to one embodiment, at operation 835, the on-device AI model may analyze the original image and generate correction data. The processor of the electronic device may execute a deep learning algorithm through the on-device AI model to analyze the original image and perform the requested action in the prompt.

[0157] In one embodiment, at operation 840, the electronic device may transmit the original image and the prompt to the server AI model. The electronic device may transmit the original image and the prompt to the server AI model using wireless communication via a communication circuit (e.g., the communication circuit (360) of FIG. 3).

[0158] According to one embodiment, in operation 845, the server AI model may analyze the original image and generate correction data.

[0159] According to one embodiment, in operation 850, the electronic device may correct an original image based on correction data generated from an on-device AI model or a server AI model. For example, the correction data may include information such as a style to be applied to the original image, correction of graphic characteristics (e.g., brightness, contrast, saturation, etc.), adjustment of the subject ratio, and addition of graphic effects, and the electronic device may generate a corrected image by reflecting the information in the correction data to the original image.

[0160] In another embodiment, the AI ​​model may correct the original image based on the original image and the prompt, generate a corrected image, and transmit the generated corrected image to the electronic device. In this case, operation 850 may be omitted.

[0161] According to one embodiment, the electronic device can display an original image and a corrected image together on a display. If the electronic device is implemented as a foldable device, the electronic device can display the original image in a first display area located in a first housing, and the corrected image in a second display area located in a second housing.

[0162] According to one embodiment, at operation 855, the electronic device may further correct the corrected image based on user input. For example, a gallery application may provide a correction function for an image, and may further correct the corrected image based on user input at operation 850.

[0163] According to one embodiment, at operation 860, the electronic device may store the corrected image.

[0164] According to one embodiment, instructions for performing each operation constituting the method may be stored in a tangible, non-transitory computer-readable recording medium.

[0165] FIG. 9A and FIG. 9B illustrate an electronic device that can be folded up / down based on a horizontal folding axis (A) based on a state in which the electronic device (900) is placed in a vertical direction (or portrait direction).

[0166] FIG. 9A is a diagram illustrating an electronic device (900) in an unfolded state (or unfolding state, or flat state) according to one embodiment. FIG. 9B is a diagram illustrating an electronic device (900) in a folded state (or folding state) according to one embodiment.

[0167] Referring to FIGS. 9A and 9B , the electronic device (900) may include a foldable housing (930), a first display module (934), and / or a second display module (935). The first display module (934) may be a foldable display that is formed of at least a portion of a flexible material and can be folded up / down about a horizontal folding axis (A).

[0168] According to one embodiment, the foldable housing (930) may include a first housing (931), a second housing (932), and a hinge structure (933). The first housing (931) and the second housing (932) may be connected through the hinge structure (933) and may be rotatable relative to each other with respect to the hinge structure (933).

[0169] According to one embodiment, the display area (934A) of the first display module (934) is an active area of ​​the first display module (934) capable of displaying an image, and may include a first display area (①) and a second display area (②). The first display area (①) and the second display area (②) may be distinguished based on the folding axis (A).

[0170] According to one embodiment, the electronic device (900) may be provided in an infolding manner in which the display area (934A) of the first display module (934) is folded inward. For example, the electronic device (900) may be folded in a direction in which the first display area (①) positioned above and the second display area (②) positioned below meet each other based on the horizontal folding axis (A).

[0171] According to one embodiment, the first display area (①) is disposed on the first housing (931), and the shape of the first display area (①) can be maintained by the support of the first housing (931). The second display area (②) is disposed on the second housing (932), and the shape of the second display area (②) can be maintained by the support of the second housing (932). The first display area (①) and the second display area (②) can be provided substantially flat in an unfolded state.

[0172] According to one embodiment, when a predetermined condition is satisfied in an intermediate state where the angle between the first housing (931) and the second housing (932) is greater than a certain angle, the electronic device (900) can operate in a predetermined operation mode (e.g., flex mode).

[0173] According to one embodiment, when viewing the unfolded state of the electronic device (900) (see FIG. 9a), the display areas (①, ②) of the first display module (934) may be provided in a symmetrical form with respect to the folding axis (A) of the electronic device (900).

[0174] According to one embodiment, the electronic device (900) may include a folding angle sensor (not shown) capable of sensing an angle between a first display area (①) and a second display area (②). The folding angle sensor may transmit the sensed angle to a processor (e.g., processor (310) of FIG. 3).

[0175] FIG. 10 illustrates a flex mode of a foldable device according to one embodiment.

[0176] According to one embodiment, the electronic device (900) may execute a flex mode when a predetermined condition is satisfied in an intermediate state between a fully folded state and an unfolded state. The flex mode may be an operation mode that provides a predetermined screen to each of the first display area (①) and the second display area (②) when the angle between the first display area (①) and the second display area (②) (or the angle between the first housing where the first display area (①) is arranged and the second housing where the second display area (②) is arranged) is within a predetermined angle range in a partially folded state of the display.

[0177] According to one embodiment, the flex mode is designed to take into account a scenario in which a user uses the electronic device (900) while partially folding it and placing it in a specific location. The electronic device (900) can execute the flex mode when the electronic device (900) is positioned in a horizontal direction with the folding axis (A) parallel to the ground. Here, the set angle range, which is the execution condition of the flex mode, may be from 80 degrees to 130 degrees, but is not limited thereto.

[0178] According to one embodiment, the angle between the first display area (①) and the second display area (②) can be adjusted by a user's operation in the flex mode state. An angle sensor of the electronic device can transmit the angle adjusted according to the user's operation to the processor.

[0179] According to one embodiment, when the electronic device (900) operates in the flex mode, it can operate in the third prompt mode during the image correction process, and transmit the prompt corresponding to the third prompt mode, the original image, and folding angle information sensed by the angle sensor to the AI ​​model together with the original image.

[0180] FIGS. 11A and 11B illustrate a multi-foldable device according to one embodiment.

[0181] According to one embodiment, the electronic device (1100) (e.g., the electronic device (300) of FIG. 3) may be implemented as a multi-foldable device in which multiple sides can be folded based on multiple folding axes.

[0182] Referring to FIGS. 11A and 11B, the electronic device (1100) may include a first folding axis (B) and a second folding axis (C). The display of the electronic device (1100) may include a first display area (1110), a second display area (1120), and a third display area (1130) which are distinguished from each other based on the first folding axis (B) or the second folding axis (C). The first display area (1110), the second display area (1120), and the third display area (1130) may be supported by respective housings (not shown), and the respective housings may be coupled to each other so as to be rotatable based on the first folding axis (B) or the second folding axis (C).

[0183] According to one embodiment, the first display area (1110) and the second display area (1120) are distinguished based on the first folding axis (B) and can be folded in directions facing each other. The second display area (1120) and the third display area (1130) are distinguished based on the second folding axis (C) and can be folded in directions facing each other.

[0184] According to one embodiment, an electronic device (1100) implemented as a multi-foldable device may support flex mode.

[0185] Referring to FIG. 11A, the electronic device (1100) can be maintained in a state in which the first display area (1110) is rotated at a predetermined angle (θ1) with respect to the second display area (1120) from the unfolded state. The second display area (1120) and the third display area (1130) can be unfolded in a flat shape. In this case, the electronic device (1100) can maintain its shape while the housing of the second display area (1120) and the housing of the third display area (1130) are placed on a surface. The angle between the first display area (1110) and the second display area (1120) can be adjusted according to a user's operation, and the angle between the first display area (1110) and the second display area (1120) can be sensed by an angle sensor and transmitted to the processor.

[0186] Referring to FIG. 11B, the electronic device (1100) can be maintained in a state in which the second display area (1120) is rotated at a predetermined angle (θ2) with respect to the third display area (1130) from the unfolded state. The first display area (1110) and the second display area (1120) can be unfolded in a flat shape. In this case, the electronic device (1100) can maintain its shape while the housing of the third display area (1130) is placed on the surface. The angle between the second display area (1120) and the third display area (1130) can be adjusted according to the user's operation, and the angle between the second display area (1120) and the third display area (1130) can be sensed by an angle sensor and transmitted to the processor.

[0187] An electronic device (300) according to various embodiments of the present document may include a camera (340), a display (330), a memory (320), and at least one processor (310) operatively connected to the camera, the display, and the memory.

[0188] According to one embodiment, the memory may store instructions that can be executed by at least one processor, and when executed, cause the electronic device to obtain a first image captured using the camera, determine a prompt for requesting correction of the first image to an AI model (410), transmit the first image and the determined prompt to the AI ​​model, obtain correction data generated by analyzing the first image based on the prompt by the AI ​​model, and display a second image corrected based on the correction data through the display.

[0189] According to one embodiment, the memory may store instructions that cause the electronic device to correct the first image to generate the second image based on the correction data.

[0190] According to one embodiment, the memory may store instructions that cause the electronic device to obtain the second image corrected by the AI ​​model.

[0191] According to one embodiment, the memory may store instructions that cause the electronic device to transmit a prompt corresponding to a prompt mode selected based on a user input among a plurality of prompt modes to the AI ​​model.

[0192] According to one embodiment, the memory may store instructions that cause the electronic device to display a prompt mode selection UI on the display that allows selection of any one of the plurality of prompt modes.

[0193] According to one embodiment, the memory may store instructions that cause the electronic device to transmit the first image and the prompt to a first AI model of the electronic device or to a second AI model of an external server, in response to a prompt mode selected from among the plurality of prompt modes.

[0194] According to one embodiment, the memory may store instructions that cause the electronic device to display the second image together with the first image on the display.

[0195] According to one embodiment, the electronic device includes a first housing and a second housing rotatably coupled to the first housing, the display includes a first display area disposed on the first housing and a second display area disposed on the second housing, and the memory can store instructions that cause the electronic device to display the first image on at least a portion of the first display area and to display the second image and the prompt mode selection UI on at least a portion of the second display area.

[0196] According to one embodiment, the memory may store instructions that cause the electronic device to determine the prompt based on a user's voice or text input.

[0197] According to one embodiment, the AI ​​model may analyze user preferences based on the user's image correction history or user input history on the application, and generate the correction data based on the analyzed user preferences.

[0198] According to one embodiment, the AI ​​model can generate the correction data including at least one of light amount adjustment, depth effect, or subject ratio adjustment for the first image.

[0199] In one embodiment, the AI ​​model may generate the correction data including an effect of changing at least one of weather or time for the first image.

[0200] A method performed by an electronic device according to various embodiments of the present document may include an operation of acquiring a first image captured using a camera, an operation of determining a prompt for requesting an AI model to correct the first image, an operation of transmitting the first image and the determined prompt to the AI ​​model, an operation of acquiring correction data generated as a result of analyzing the first image based on the prompt by the AI ​​model, and an operation of displaying a second image corrected based on the correction data.

[0201] According to one embodiment, the method may further include an operation of generating the second image by correcting the first image based on the correction data.

[0202] According to one embodiment, the operation of obtaining the correction data may include an operation of obtaining the second image corrected by the AI ​​model.

[0203] In one embodiment, the act of transmitting the prompt to the AI ​​model may include an act of transmitting a prompt corresponding to a prompt mode selected based on user input from among a plurality of prompt modes to the AI ​​model.

[0204] According to one embodiment, the method may further include an action of displaying a prompt mode selection UI for selecting any one of the plurality of prompt modes.

[0205] According to one embodiment, the operation of transmitting the prompt to the AI ​​model may include an operation of transmitting the first image and the prompt to a first AI model of the electronic device or to a second AI model of an external server, corresponding to a prompt mode selected from among the plurality of prompt modes.

[0206] According to one embodiment, the act of displaying the second image may include an act of displaying the second image together with the first image.

[0207] A computer-readable non-transitory recording medium according to various embodiments of the present document may store instructions for performing an operation of acquiring a first image captured by a camera, an operation of determining a prompt for requesting an AI model to correct the first image, an operation of transmitting the first image and the determined prompt to the AI ​​model, an operation of acquiring correction data generated as a result of analyzing the first image based on the prompt by the AI ​​model, and an operation of displaying a second image corrected based on the correction data.

[0208] Electronic devices according to the various embodiments disclosed in this document may take various forms. Electronic devices may include, for example, portable communication devices (e.g., smartphones), computer devices, portable multimedia devices, portable medical devices, cameras, wearable devices, or home appliances. Electronic devices according to the embodiments of this document are not limited to the aforementioned devices.

[0209] The various embodiments of this document and the terminology used therein are not intended to limit the technical features described in this document to specific embodiments, but should be understood to include various modifications, equivalents, or substitutes of the 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 the items, unless the context clearly indicates otherwise. In this document, each of the phrases "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" can include any one of the items listed together in the corresponding phrase among those phrases, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used merely to distinguish one component from another, and do not limit the components in any other respect (e.g., importance or order). When a component (e.g., a first component) is referred to as "coupled" or "connected" to another (e.g., a second component), with or without the terms "functionally" or "communicatively," it means that the component can be connected to the other component directly (e.g., wired), wirelessly, or through a third component.

[0210] The term "module" used in 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. A module may be an integral component, or a minimum unit or part of such a component 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).

[0211] Various embodiments of the present document may be implemented as software (e.g., a program (140)) including one or more instructions stored in a storage medium (e.g., an internal memory (136) or an external memory (138)) readable by a machine (e.g., an electronic device (101)). For example, a processor (e.g., a processor (120)) of the machine (e.g., an electronic device (101)) may call at least one instruction among the one or more instructions stored from the storage medium and execute it. This enables the machine to operate to perform at least one function according to the at least one called instruction. The one or more instructions may include code generated by a compiler or code executable by an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' simply means that the storage medium is a tangible device and does not contain signals (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently or temporarily on the storage medium.

[0212] According to one embodiment, the method according to various embodiments disclosed in this document may be provided as a computer program product. The computer program product may be traded between sellers and buyers as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)) or may be provided through an application store (e.g., Play Store). TM ) or directly between two user devices (e.g., smart phones), online distribution (e.g., downloading or uploading). In the case of online distribution, at least a portion of the computer program product may be at least temporarily stored or temporarily created in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0213] According to various embodiments, each component (e.g., a module or a program) of the above-described components may include one or more entities, and some of the entities may be separated and arranged in other components. According to various embodiments, one or more components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In such a case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to the integration. According to various embodiments, the operations performed by a module, program, or other component 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 (300), Camera (340); display (330); memory (320); and At least one processor (310) operatively connected to the camera, the display, and the memory, The above memory is executable by at least one processor, and when executed, the electronic device: Acquire a first image captured using the above camera, Determine a prompt to request correction of the first image above to the AI ​​model (410), The first image and the determined prompt are transmitted to the AI ​​model, By the AI ​​model, the correction data generated by analyzing the first image based on the prompt is obtained, and An electronic device storing instructions for displaying a second image corrected based on the above correction data through the display.

2. In paragraph 1, The above memory, the electronic device, An electronic device storing instructions for generating the second image by correcting the first image based on the correction data.

3. In paragraph 1, The above memory, the electronic device, An electronic device storing instructions for obtaining the second image corrected by the AI ​​model.

4. In any one of paragraphs 1 to 3, The above memory, the electronic device, An electronic device storing instructions for transmitting a prompt corresponding to a prompt mode selected based on user input from among multiple prompt modes to the AI ​​model.

5. In paragraph 4, The above memory, the electronic device, An electronic device storing instructions for causing a prompt mode selection UI to be displayed on the display, wherein any one of the plurality of prompt modes can be selected.

6. In paragraph 4 or 5, An electronic device storing instructions for transmitting the first image and the prompt to a first AI model of the electronic device or to a second AI model of an external server, in response to a prompt mode selected from among the plurality of prompt modes.

7. In any one of paragraphs 1 to 6, The above memory, the electronic device, An electronic device storing instructions for displaying the second image together with the first image on the display.

8. In any one of paragraphs 1 to 7, First housing; and It includes a second housing that is rotatably coupled to the first housing, The display includes a first display area disposed on the first housing and a second display area disposed on the second housing, The above memory, the electronic device, Displaying the first image in at least a part of the first display area, and An electronic device storing instructions for displaying the second image and the prompt mode selection UI in at least a portion of the second display area.

9. In paragraph 1, The above memory, the electronic device, An electronic device storing instructions for determining the prompt based on a user's voice or text input.

10. In any one of paragraphs 1 to 9, An electronic device in which the AI ​​model analyzes user preferences based on the user's image correction history or user input history on the application, and generates the correction data based on the analyzed user preferences.

11. In any one of paragraphs 1 to 10, An electronic device in which the AI ​​model generates correction data including at least one of light amount adjustment, depth effect, or subject ratio adjustment for the first image.

12. In any one of paragraphs 1 to 11, An electronic device wherein the AI ​​model generates the correction data including an effect of changing at least one of weather or time for the first image.

13. In a method performed by an electronic device, An action of acquiring a first image captured using a camera; An action for determining a prompt to request the AI ​​model to correct the first image; An action of transmitting the first image and the determined prompt to the AI ​​model; An operation of obtaining correction data generated as a result of analyzing the first image based on the prompt by the AI ​​model; A method comprising an action of displaying a second image corrected based on the above correction data.

14. In paragraph 13, The action of displaying the above second image is: A method comprising an action of displaying the second image together with the first image.

15. In a non-transitory computer-readable recording medium, An action of acquiring a first image captured using a camera; An action for determining a prompt to request the AI ​​model to correct the first image; An action of transmitting the first image and the determined prompt to the AI ​​model; An operation of obtaining correction data generated as a result of analyzing the first image based on the prompt by the AI ​​model; A recording medium storing instructions for performing an operation of displaying a second image corrected based on the above correction data.

Images