Electronic device, method, and non-transitory computer-readable recording medium for managing user profile

Abstract

An electronic device is disclosed. The electronic device may comprise at least one processor including a processing circuit. The electronic device may comprise a memory including one or more storage media storing instructions. The electronic device may generate a prompt for processing an image on the basis of a user profile. The electronic device may control a generative artificial intelligence (AI) model to process the image on the basis of the prompt. The electronic device may determine whether to update the user profile on the basis of a user input related to the processed image.

Description

Electronic device, method, and non-transitory computer-readable recording medium for managing user profiles

[0001] The following descriptions relate to electronic devices, methods, and non-transitory computer-readable recording media for managing user profiles.

[0002] Artificial intelligence is a field of computer engineering and information technology that studies how to enable computers to think, learn, and develop themselves in ways that human intelligence can. It means enabling computers to imitate human intelligent behavior.

[0003] Artificial intelligence is intended to simulate human (or biological) neural activity, such as perception and / or inference, and can be implemented by hardware, software, or a combination of these designed to perform computations for simulating neural activity.

[0004] Artificial intelligence can generate new content (e.g., text, images, music, audio, video) based on instructions. AI that generates new content based on instructions can be referred to as generative AI.

[0005] The above information may be provided as background art to aid in understanding the present disclosure. No claim or determination is made as to whether any of the above is applicable as prior art related to the present disclosure.

[0006] An electronic device is disclosed. The electronic device may include at least one processor comprising a processing circuit. The electronic device may include a memory comprising one or more storage media storing instructions. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to generate a prompt for processing an image based on a user profile. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to control a generative artificial intelligence (AI) model to process the image based on the prompt. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to determine whether to update the user profile based on user input related to the processed image.

[0007] A method is disclosed. The method can be performed on an electronic device. The method may include generating a prompt for processing an image based on a user profile. The method may include controlling a generative AI model to process the image based on the prompt. The method may include determining whether to update the user profile based on user input related to the processed image.

[0008] A non-transitory computer-readable storage medium is disclosed. The non-transitory computer-readable storage medium may store a program comprising instructions. The non-transitory computer-readable storage medium may include at least one processor comprising processing circuitry. The electronic device may include a memory comprising one or more storage media storing instructions. The instructions, when individually or collectively executed by the at least one processor comprising the processing circuitry of the electronic device, may cause the electronic device to generate a prompt for processing an image based on a user profile. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to control a generative AI model to process the image based on the prompt. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to determine whether to update the user profile based on user input related to the processed image.

[0009] In connection with the description of the drawings, the same or similar reference numerals may be used for the same or similar components.

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

[0011] FIG. 2A is a block diagram of an electronic device according to one embodiment.

[0012] FIG. 2b is a block diagram of a program of an electronic device according to one embodiment.

[0013] Figure 3a illustrates an example of a prompt, according to one embodiment.

[0014] FIG. 3B illustrates an example of an operation of an electronic device processing an image according to a prompt, according to one embodiment.

[0015] FIG. 3c illustrates an example of an operation of an electronic device processing an image according to a prompt, according to one embodiment.

[0016] Figure 4a illustrates an example of a prompt, according to one embodiment.

[0017] FIG. 4B illustrates an example of an operation of an electronic device processing an image according to a prompt, according to one embodiment.

[0018] FIG. 4c illustrates an example of an operation of an electronic device processing an image according to a prompt, according to one embodiment.

[0019] FIG. 4d illustrates an example of an operation of an electronic device displaying a notification for a processed image, according to one embodiment.

[0020] Figure 5a illustrates an example of a prompt, according to one embodiment.

[0021] FIG. 5b illustrates an example of an operation of an electronic device processing an image according to a prompt, according to one embodiment.

[0022] FIG. 5c illustrates an example of an operation of an electronic device processing an image according to a prompt, according to one embodiment.

[0023] FIG. 6 illustrates an example of a prompt according to a change in a user profile, according to one embodiment.

[0024] Figure 7 is a flowchart illustrating the operation of an electronic device according to one embodiment.

[0025] Figure 8 is a flowchart illustrating the operation of an electronic device according to one embodiment.

[0026] FIG. 9 is a flowchart illustrating the operation of an electronic device according to one embodiment.

[0027] FIG. 10 is a flowchart illustrating the operation of an electronic device according to one embodiment.

[0028] FIG. 11 is a flowchart illustrating the operation of an electronic device according to one embodiment.

[0029] FIG. 12 is a flowchart illustrating the operation of an electronic device according to one embodiment.

[0030] FIG. 13 is a flowchart illustrating the operation of an electronic device according to one embodiment.

[0031] FIG. 14 is a diagram illustrating the structure of a generative AI model of an electronic device according to one embodiment.

[0032] 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.

[0033] FIG. 1 is a block diagram of an electronic device (101) within a network environment (100) according to various embodiments.

[0034] 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). According to 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)).

[0035] 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.

[0036] 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.

[0037] 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).

[0038] 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).

[0039] 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).

[0040] 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.

[0041] 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.

[0042] 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).

[0043] 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.

[0044] 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.

[0045] 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).

[0046] 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.

[0047] 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.

[0048] 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).

[0049] 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.

[0050] 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).

[0051] 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 realizing eMBB, a loss coverage (e.g., 664 dB or less) for realizing mMTC, or a U-plane latency (e.g., 0.5 ms or less for downlink (DL) and uplink (UL), or 6 ms or less for round trip) for realizing URLLC.

[0052] 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).

[0053] 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.

[0054] 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)).

[0055] 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 another embodiment, the external electronic device (104) may include an Internet of Things (IoT) device. The server (108) may be an intelligent server utilizing 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.

[0056] FIG. 2A is a block diagram of an electronic device according to one embodiment.

[0057] In one embodiment, the electronic device (101) of FIG. 2A may correspond to the electronic device (101) of FIG. 1. Referring to FIG. 2A, the electronic device (101) may include a processor (120), a memory (130), an input module (150), a display (260), and a communication circuit (290).

[0058] In one embodiment, the processor (120) may be used to execute the operations of the electronic device (101) exemplified in the descriptions of FIGS. 7 to 13. For example, the processor (120) may include at least a portion of the processor (120) of FIG. 1 or may correspond to at least a portion of the processor (120) of FIG. 1. For example, the processor (120) may include one or more processors, including an application processor (AP) and / or a communication processor (CP). For example, the processor (120) may be implemented as a single chip, such as a system on chip (SoC), or may be implemented as multiple chips. For example, the processor (120) may be implemented as a single integrated circuit or may be implemented as multiple integrated circuits. For example, the processor (120) may be distributedly arranged within the electronic device (101).

[0059] In one embodiment, the memory (130) may (at least temporarily) store instructions for executing operations of the electronic device (101) exemplified in the descriptions of FIGS. 7 to 13. The instructions may be executed by the processor (120). The instructions may be included in one or more programs (140) stored in the memory (130). For example, the memory (130) may include at least a portion of the memory (130) of FIG. 1 (or at least a portion of the non-volatile memory (134)) or may correspond to at least a portion of the memory (130) of FIG. 1 (or at least a portion of the non-volatile memory (134)). For example, the memory (130) may include a main memory (e.g., a read only memory (ROM), a random access memory (RAM), a register for the processor (120), a cache for the processor (120), a register for the communication circuit (290), a buffer (or soft buffer) for the communication circuit (290), and / or an auxiliary memory (e.g., a hard disk drive (HDD), a solid state drive (SSD)) of the electronic device (101) within the electronic device (101). For example, the memory (130) may be implemented as a single chip or may be implemented as multiple chips. For example, the memory (130) may be implemented as one integrated circuit or may be implemented as multiple integrated circuits. For example, the memory (130) may be arranged in a distributed manner within the electronic device (101).

[0060] In one embodiment, the input module (150) may include at least one physical key (e.g., buttons) for obtaining user input. For example, the input module (150) may correspond to at least a portion of the input module (150) of FIG. 1.

[0061] In one embodiment, the display (260) may display visual content (e.g., an image). For example, the display (260) may include at least a portion of the display module (160) of FIG. 1 or may correspond to at least a portion of the display module (160) of FIG. 1.

[0062] In one embodiment, the communication circuit (290) may be used for a communication connection between the electronic device (101) and another device (e.g., the electronic device (102), the electronic device (104), the server (108)). For example, the communication circuit (290) may include at least a portion of the communication module (190) (or the wireless communication module (192)) of FIG. 1, or may correspond to at least a portion of the communication module (190) (or the wireless communication module (192)) of FIG. 1. For example, the communication circuit (290) may include a communication circuit for a long-distance communication network. For example, the communication circuit (290) may be used to establish a communication link. For example, the communication circuit (290) may be implemented as a single chip or may be implemented as multiple chips. For example, the communication circuit (290) may be implemented as a single integrated circuit or may be implemented as multiple integrated circuits. For example, the communication circuit (290) may be distributed within the electronic device (101).

[0063] FIG. 2b is a block diagram of a program of an electronic device according to one embodiment.

[0064] Figure 2b can be explained with reference to Figures 1 and 2a.

[0065] Referring to FIG. 2B, the program (140) may include an input collection module (210), a prompt management module (220), a content generation module (230), a feature analyzer (240), and / or a user profile database (DB) (280). In one embodiment, the content generation module (230) may include a generative artificial intelligence (AI) module (231), and a feedback module (235). In one embodiment, the feature analyzer (240) may include a feature analysis module (250), a feature management module (261), and a feature-based prompt generation module (270). In one embodiment, the feature management module (261) may include a basic feature DB (263) and a new feature DB (265).

[0066] Hereinafter, with reference to the components of FIG. 2b, the operations of the electronic device (101) generating a prompt, processing an image, and creating and / or updating a user profile are described.

[0067] Create a prompt

[0068] In one embodiment, the prompt management module (220) can generate (or identify) a prompt based on user input and / or a user profile DB (280). In one embodiment, the prompt management module (220) can generate (or identify) a prompt based on user input requesting generation of an output image being obtained. In one embodiment, the prompt management module (220) can generate (or identify) a prompt based on user profile DB (280) being updated. In one embodiment, the prompt can include data for guiding the generation of an output image through the content generation module (230) (or the generative AI module (231)). In one embodiment, the prompt can be a work instruction for the generative AI module (231). In one embodiment, the prompt can be a set of words (or a sentence including words) for generating an output image from an input image through the generative AI module (231). In one embodiment, the prompt may be a set of words (or a sentence including words) for correcting (or processing) an input image via the generative AI module (231). For example, the correction (or processing) of the image may include applying an image filter (e.g., warm, calm, lollipop, winter, pink rose, ivory, faded, soft, kiss me, black and white, cinematic, roof, shadow, monstera, palm tree, vignetting, blur, and / or bokeh) to the image. In one embodiment, the correction of the image may include adjusting the color tone (e.g., light balance, brightness, exposure, contrast, highlight, shadow, saturation, tint, color temperature, sharpness, and / or clarity) of the image. In one embodiment, the correction of the image may include applying a decoration (or decoration) (e.g., drawing, sticker, and / or text) to the image.In one embodiment, the prompt may be context input to the generative AI module (231) (e.g., information about an object (or character) (or sticker) to be included in the output image, and / or information about the location of the object).

[0069] In one embodiment, the prompt management module (220) can identify at least one user profile corresponding to the input image among one or more user profiles stored in the user profile DB (280). In one embodiment, the prompt management module (220) can identify at least one user profile corresponding to the type of the input image and / or the situation in which the input image was acquired (or photographed) (or depicted) (hereinafter, the situation of the input image) in the user profile DB (280). For example, the type of the input image can be classified according to the way in which the object included in the input image is depicted (e.g., landscape, portrait, still life). For example, the type of the input image can be classified according to the purpose of the image (e.g., background screen, lock screen (e.g., wallpaper), upload to a social network service (SNS) application, or sharing). For example, the context of an input image may be classified based on the types of objects included in the input image (e.g., people, animals, plants, objects), relationships between objects (e.g., friends, family), and / or time (e.g., morning, a.m., afternoon, evening, dawn). However, the present invention is not limited thereto. In one embodiment, the prompt management module (220) may identify at least one updated user profile among one or more user profiles stored in the user profile DB (280).

[0070] In one embodiment, the prompt management module (220) may generate (or identify) a prompt based on at least one user profile corresponding to an input image. However, the present invention is not limited thereto. In one embodiment, the prompt management module (220) may generate (or identify) a prompt based on at least one updated user profile among one or more user profiles stored in the user profile DB (280).

[0071] In one embodiment, the prompt management module (220) can generate (or identify) a prompt based on user input. For example, the prompt management module (220) can generate (or identify) a prompt based on user input to change (or modify) a presented (or displayed via the display (260)) prompt (e.g., a prompt generated based on a user profile). For example, the prompt management module (220) can generate (or identify) a prompt based on user input to enter a sentence to guide the generation of an output image without a prompt generated based on a user profile.

[0072] In one embodiment, the prompt management module (220) can output (or display) a prompt based on a user profile DB (280) through a display (260). In one embodiment, the prompt management module (220) can change the prompt based on the user profile DB (280) based on user input. In one embodiment, the user input can include a touch input for the output (or displayed) prompt, and / or an input through the input module (150), but is not limited thereto.

[0073] Image processing

[0074] In one embodiment, the content generation module (230) can generate an output image using the generative AI module (231). In one embodiment, the content generation module (230) can generate an output image by inputting a prompt to the generative AI module (231). In one embodiment, the content generation module (230) can generate an output image by inputting a prompt and an input image to the generative AI module (231). In one embodiment, the output image may be an image in which the input image is corrected (or processed). In one embodiment, the correction (or processing) of the input image may include, but is not limited to, applying an image filter to the input image, adjusting color tones, and / or applying decoration. In one embodiment, the content generation module (230) can generate an output image by inputting only a prompt without an input image to the generative AI module (231).

[0075] In one embodiment, the generative AI module (231) may include a pre-trained AI model. In one embodiment, the generative AI module (231) may include a plurality of parameters related to a neural network having a structure based on an encoder and a decoder, such as a transformer. In one embodiment, the generative AI module (231) may include a bi-directional model based on learning for an encoder (e.g., bidirectional encoder representations from transformers (BERT)) or an auto-encoding model (e.g., a diffusion model). In one embodiment, the generative AI module (231) may include an auto-regressor model based on learning for a decoder (e.g., a generative pre-trained transformer (GPT)). In one embodiment, the generative AI module (231) may include a sequence-to-sequence model (e.g., stable diffusion, DALL-E 2) based on learning for an encoder and a decoder. In one embodiment, the generative AI module (231) may include a large language model (LLM) for processing natural language based on massive parameters, but is not limited thereto. In one embodiment, the generative AI module (231) may include parameters for driving a neural network such as a convolutional neural network (CNN), a recurrent neural network (RNN), a feedforward neural network (FNN), and / or a long short-term memory (LSTM).

[0076] In one embodiment, the generative AI module (231) may correspond to the generative AI model (1450) of FIG. 14.

[0077] In one embodiment, the content generation module (230) may generate an image based on a prompt generated based on user input requesting the generation of an output image, but is not limited thereto. In one embodiment, the content generation module (230) may generate an image based on a prompt generated based on a user profile updated in the user profile DB (280).

[0078] In one embodiment, the content generation module (230) may output (or display) the generated output image through the display (260). In one embodiment, the content generation module (230) may output (or display) the output image through the display (260) in response to the output image being generated through a prompt based on user input. In one embodiment, the content generation module (230) may output (or display) the output image on the screen of an application from which user input for the prompt has been obtained. In one embodiment, the content generation module (230) may output (or display) the output image through the display (260) in response to the output image being generated through a prompt generated through an updated user profile. In one embodiment, the content generation module (230) may output (or display) a notification indicating the generation of the output image through a notification bar.

[0079] Create and / or update your user profile

[0080] In one embodiment, the feature analysis module (250) may identify (or extract) one or more features from a prompt for an output image and / or an output image. In one embodiment, the feature analysis module (250) may identify (or extract) one or more features from a prompt for an output image and / or an output image based on the type of the output image, the situation depicted by the output image (hereinafter, the situation of the output image), and / or the correction applied to the output image (e.g., the applied image filter, the applied color tone, and / or the applied decoration). For example, the type of the output image may be distinguished based on the way an object included in the output image is depicted (e.g., landscape, portrait, still life), and / or the design pattern. For example, the type of the output image may be distinguished based on the purpose of the output image (e.g., background screen, or lock screen (e.g., wallpaper), uploading to an SNS application, or sharing). For example, the context of the output image can be classified based on the types of objects included in the output image (e.g., people, animals, plants, objects), relationships between objects (e.g., friends, family), and / or time (e.g., morning, am, pm, evening, dawn). For example, if an image filter is applied to the output image, the feature analysis module (250) can identify (or extract) features related to the applied image filter (e.g., words describing the type of image filter (e.g., clear, natural, warm, cool, and / or blur, bokeh)). For example, if a specific color tone is applied to the output image, the feature analysis module (250) can identify (or extract) features related to the specific color tone applied (e.g., words describing the color tone (e.g., light balance, brightness, exposure)). For example, if a specific decoration is applied to the output image, the feature analysis module (250) can identify (or extract) features related to the specific decoration applied (e.g., words describing the decoration (e.g., names of stickers (or characters)).For example, if the output image is used as wallpaper, the feature analysis module (250) can identify (or extract) features related to the pattern design, illustration, and depiction method (e.g., person or landscape) of the output image. For example, if the output image includes a character, the feature analysis module (250) can identify (or extract) features related to the character (e.g., words describing the character shape (e.g., cute, funny), and / or the character type (e.g., rabbit)).

[0081] In one embodiment, the feature management module (261) may store one or more features (or words representing features) extracted from the feature analysis module (250) in the basic feature DB (263) and / or the new feature DB (265). In one embodiment, the feature management module (261) may store one or more features (or words representing features) in the basic feature DB (263) and / or the new feature DB (265) depending on the type and / or situation of the output image. For example, when the type and / or situation of the image from which the features are extracted are different, substantially identical features (or words representing features) may be stored in different locations (e.g., the basic feature DB (263) or the new feature DB (265)). For example, features related to characters extracted from landscape images (e.g., rabbit stickers) may be stored in a new feature DB (265), and features related to characters extracted from images containing friends (e.g., rabbit stickers) may be stored in a basic feature DB (263). However, this is not limited thereto.

[0082] In one embodiment, the feature management module (261) may store one or more features (or words) in the basic feature DB (263) and / or the new feature DB (265) based on the similarity between one or more features (or words) and the basic features (or words) stored in the basic feature DB (263). In one embodiment, the feature management module (261) may store the features extracted from the output image in the basic feature DB (263) if the features extracted from the output image have a similarity higher than or equal to a reference similarity with the basic features included in the basic feature DB (263). In one embodiment, the feature management module (261) may store the features extracted from the output image in the new feature DB (265) if the features extracted from the output image have a similarity lower than or equal to a reference similarity with the basic features included in the basic feature DB (263). Here, the similarity may be the similarity between the meanings of each of the features. For example, the similarity may be calculated based on the distance between vectors assigned to each of the meanings. However, it is not limited thereto. For example, the feature 'clear' and the feature 'clean' can be classified as features having similar meanings. For example, when the feature 'clear' is stored in the basic feature DB (263), and the feature 'clean' is newly extracted from the output image, the feature management module (261) can store the feature 'clean' in the basic feature DB (263). For example, the feature 'clear' and the feature 'calm' can be classified as features having dissimilar meanings. For example, when the feature 'clear' is stored in the basic feature DB (263), and the feature 'calm' is newly extracted from the output image, the feature management module (261) can store the feature 'calm' in the new feature DB (265). However, it is not limited thereto.

[0083] In one embodiment, the feature management module (261) may store the features stored in the new feature DB (265) in the basic feature DB (263) based on the number of times the features stored in the new feature DB (265) are extracted from an image. In one embodiment, the feature management module (261) may store the features stored in the new feature DB (265) in the basic feature DB (263) based on the number of times the features stored in the new feature DB (265) are extracted from an image exceeding a threshold number. In one embodiment, the feature management module (261) may store features of a kind that are substantially the same as (or similar to) the features newly stored in the basic feature DB (263) based on the features stored in the new feature DB (265) being stored in the basic feature DB (263). In one embodiment, the fact that the types of features are substantially the same as (or similar to) the types of image corrections associated with the features may indicate that the types of image corrections associated with the features are substantially the same as (or similar to). For example, the type of image correction may include image filters, color grading, and / or decoration. For example, if two or more features are related to image filters, the two or more features may be evaluated as being substantially the same (or similar) in type. For example, if two or more features are related to color grading, the two or more features may be evaluated as being substantially the same (or similar) in type. For example, if two or more features are related to decoration, the two or more features may be evaluated as being substantially the same (or similar) in type. However, this is not limited thereto. In one embodiment, the substantially same (or similar) in type of features means that features related to image corrections that are not simultaneously applied to an image associated with the substantially same (or similar) features may be evaluated as being substantially the same (or similar) in type.For example, since color tones can be applied to more than one image, features associated with different colors may be evaluated as belonging to different types. For example, features associated with light balance may be evaluated as belonging to a different type of feature than features associated with brightness.

[0084] In one embodiment, the feature-based prompt generation module (270) can generate a prompt based on features (or words) stored in the basic feature DB (263) and / or the new feature DB (265). For example, the prompt can be generated by combining some of the features included in the basic feature DB (263) and some of the features included in the new feature DB (265). In one embodiment, the ratio between some of the features selected from the basic feature DB (263) and some of the features selected from the new feature DB (265) can be adjusted according to a user's settings.

[0085] In one embodiment, the content generation module (230) may generate a new image based on a prompt generated by the feature-based prompt generation module (270). In one embodiment, the feature-based prompt generation module (270) may determine whether to modify the prompt and / or update the user profile based on user input regarding the output image obtained through the feedback module (235).

[0086] In one embodiment, if the user input for the output image is negative feedback (e.g., requesting deletion of the image or modification of the image), the feature-based prompt generation module (270) may newly select some features from among the features stored in the basic feature DB (263) and / or the new feature DB (265) according to a set ratio. In one embodiment, the feature-based prompt generation module (270) may generate a prompt based on the newly selected features.

[0087] In one embodiment, if the user input for the output image is positive feedback (e.g., saving the image, uploading or sharing the image, or favorite (or like) the image), the feature-based prompt generation module (270) can update the user profile DB (280) based on the prompt entered to generate the image.

[0088] In one embodiment, the user profile DB (280) can store user profiles. In one embodiment, the user profiles stored in the user profile DB (280) may vary depending on the type of image and / or the context of the image. For example, the type of image may be classified based on the way objects included in the image are depicted (e.g., landscape, portrait, still life). For example, the context of the image may be classified based on the type of objects included in the image (e.g., person, animal, plant, object), the relationship between objects (e.g., friend, family), and / or the time (e.g., morning, am, afternoon, evening, dawn). For example, the context of the image may be classified based on the context of the objects included in the image being friends or family. For example, the user profile may be a profile for generating a prompt to attach a designated character sticker when the objects included in the image are friends. However, the present invention is not limited thereto.

[0089] As described above, the basic feature DB (263) and / or the new feature DB (265) are exemplified as being updated based on the features included in the output image through the image output through the generative AI module (231), but this is merely an example. According to one embodiment, the basic feature DB (263) and / or the new feature DB (265) may be updated based on the user's activity acquired (or identified) through the input collection module (210).

[0090] In one embodiment, the input collection module (210) may collect user input through a designated application. In one embodiment, the designated application may be an application (e.g., a gallery application, a social networking service application, a camera application) related to designated content (e.g., an image). In one embodiment, the designated content may be content for analyzing a user's preferences (or creating a profile). In the following, the content may be exemplified as an image, but is not limited thereto.

[0091] In one embodiment, the input collection module (210) may identify user input for analyzing user preferences (or creating a user profile) among user inputs related to a specified application. For example, the input collection module (210) may identify user input for images among user inputs related to the specified application. For example, the input collection module (210) may identify user input for images displayed through the specified application. For example, the images displayed through the specified application may include gallery images, profile images, wallpapers, background images, emoticons, and / or characters. In one embodiment, the user input for the image may include input for correcting (or processing) the image. In one embodiment, the correction (or processing) of the image may include applying an image filter to the image. In one embodiment, the correction of the image may include adjusting the color tone of the image. In one embodiment, the correction of the image may include applying a decoration to the image.

[0092] In one embodiment, the feature analysis module (250) may identify (or extract) one or more features from content related to the user activity based on the user activity identified through the input collection module (210). In one embodiment, the feature management module (261) may store one or more features (or words representing the features) extracted from the content related to the user activity in the basic feature DB (263) and / or the new feature DB (265). In one embodiment, the feature-based prompt generation module (270) may generate a prompt based on the features (or words) stored in the basic feature DB (263) and / or the new feature DB (265). In one embodiment, the content generation module (230) may generate a new image based on the prompt generated by the feature-based prompt generation module (270). In one embodiment, the feature-based prompt generation module (270) can update the user profile based on user input for the output image obtained through the feedback module (235).

[0093] As described above, the electronic device (101) can analyze (or identify) the user's image preferences. In one embodiment, the electronic device (101) can present the user with a prompt for adjusting the image according to the user's preferences. Accordingly, the number of inputs required from the user to change the prompt can be reduced.

[0094] Additionally, the electronic device (101) can update the user profile as the user's preferences change. Accordingly, the electronic device (101) can provide the user with prompts appropriate to the user's preferences using the updated user profile.

[0095] FIG. 3A illustrates an example of a prompt according to an embodiment. FIG. 3B illustrates an example of an operation of an electronic device processing an image according to a prompt according to an embodiment. FIG. 3C illustrates an example of an operation of an electronic device processing an image according to a prompt according to an embodiment.

[0096] FIG. 3a, FIG. 3b, and FIG. 3c may be described with reference to FIG. 1, FIG. 2a, or FIG. 2b.

[0097] FIG. 3A illustrates a situation in which the prompt management module (220) outputs a prompt (e.g., applying a clear and sharp image filter). Referring to FIG. 3A, the prompt management module (220) may generate a prompt based on a request (or user input) for image correction. For example, the prompt management module (220) may generate a prompt based on a user profile corresponding to the type of input image and / or the situation of the input image. In one embodiment, the prompt management module (220) may display a screen (301) including the generated prompt through the display (260).

[0098] In one embodiment, the prompt management module (220) can obtain user input to change (or modify) a prompt on the screen (301). For example, the prompt management module (220) can display a menu (303) including words (e.g., clear, warm, calm) that can replace the word (310) based on a user input selecting the word (310) (e.g., clear) through the display (260). For example, the prompt management module (220) can display a menu (305) including words (e.g., vivid, retro, soft) that can replace the word (320) based on a user input selecting the word (320) (e.g., clear) through the display (260). For example, the prompt management module (220) can change at least some of the words included in the prompt through a user input for the menus (303, 305). For example, the prompt management module (220) may display a screen (307) including a prompt including words (315, 325) (e.g., warm, retro) based on a user input through the display (260). In one embodiment, the words included in the menus (303, 305) may be words (or candidate words) that the user frequently uses (or prefers) according to the user's taste. For example, the words included in the menu (303) may be words (or candidate words) that the user frequently uses (or prefers) according to the user's taste in the same (or similar) category (e.g., type of image correction) as the word (310) (e.g., clear). For example, the words included in the menu (305) may be words that the user frequently uses (or prefers) according to the user's taste in the same (or similar) category (e.g., type of image correction) as the word (320) (e.g., clear). In one embodiment, the words included in the menus (303, 305) may be included in the menus (303, 305) in a frequently used (or preferred) order.In one embodiment, a word that a user frequently uses (or prefers) may refer to a word selected by user input to modify a prompt during a certain period of time prior to an update of the user's tastes.

[0099] In one embodiment, some of the words included in the menus (303, 305) may be words included according to the user's previous tastes (or a user profile prior to the current user profile). In one embodiment, the prompt management module (220) may display the words included in the menus (303, 305) differently. For example, the prompt management module (220) may display words included according to the user's previous tastes (or words according to the previous basic characteristics) in a blurred manner. For example, the prompt management module (220) may display words included in the menus (303, 305) that are frequently used (or preferred) recently (or words according to a new characteristic) more clearly. Here, the words according to the previous basic characteristics may be words included in the previous (or pre-update) basic characteristics and not included in the current (or post-update) basic characteristics.

[0100] In one embodiment, as the prompt changes, the output image generated by the generative AI module (231) may change.

[0101] For example, referring to FIG. 3B, the generative AI module (231) may generate an output image (343) based on a prompt (330) (e.g., “Apply a clear and sharp image filter”) generated based on a user profile DB (280). In one embodiment, the generative AI module (231) may generate an output image (343) based on an input image (341) and a prompt (330) (e.g., “Apply a clear and sharp image filter”).

[0102] For example, referring to FIG. 3C, the generative AI module (231) may generate an output image (345) based on a prompt (335) generated based on a user input (350) (e.g., "Apply a warm retro image filter"). For example, the user input (350) may be an input for changing the prompt (330) (e.g., "Apply a clear and vivid image filter"). For example, the user input (350) may be a user input for changing a word (310) (e.g., clear) included in the prompt (330) to a word (315) (e.g., warm). For example, the user input (350) may be a user input for changing a word (320) (e.g., clear) included in the prompt (330) to a word (325) (e.g., retro). In one embodiment, the generative AI module (231) may generate an output image (345) based on an input image (341) and a prompt (335) (e.g., “Apply a warm retro image filter”).

[0103] Thereafter, the feature analyzer (240) may store one or more features included in the output image (345) generated based on the prompt (335) in the basic feature DB (263) and / or the new feature DB (265). For example, the feature analyzer (240) may update the user profile if the number of times a new feature is extracted by the changed prompt (335) and / or the output image (345) exceeds a threshold number. For example, if the number of times a feature related to “retro” is extracted exceeds a threshold number, the feature analyzer (240) may change the storage location of the feature related to “retro” from the new feature DB (265) to the basic feature DB (263). Thereafter, if correction of another input image having substantially the same type and / or situation as the input image (341) is requested, the prompt management module (220) may generate a prompt of “apply a warm retro image filter” instead of “apply a clear and vivid image filter.” Thereafter, the content generation module (230) can generate a new image based on the prompt generated by the feature-based prompt generation module (270). In one embodiment, the feature-based prompt generation module (270) can determine whether to modify the prompt and / or update the user profile based on user input for the output image obtained through the feedback module (235). In one embodiment, if the user input for the output image is positive feedback (e.g., saving the image, uploading the image, or sharing the image), the feature-based prompt generation module (270) can update the user profile DB (280) based on the prompt input to generate the image.

[0104] FIG. 4A illustrates an example of a prompt, according to an embodiment. FIG. 4B illustrates an example of an operation of an electronic device processing an image in response to a prompt, according to an embodiment. FIG. 4C illustrates an example of an operation of an electronic device processing an image in response to a prompt, according to an embodiment. FIG. 4D illustrates an example of an operation of an electronic device displaying a notification regarding a processed image, according to an embodiment.

[0105] FIG. 4a, FIG. 4b, FIG. 4c, and FIG. 4d may be described with reference to FIG. 1, FIG. 2a, or FIG. 2b.

[0106] In one embodiment, the electronic device (101) may display a newly generated output image on the display (260) according to the changed user preference. For example, the electronic device (101) may change an output image based on an existing user profile to an output image based on a new user profile based on a change in the user profile according to the change in the user preference. For example, the electronic device (101) may display an output image based on a new user profile on the display (260). For example, a prompt may be changed according to a change in the user profile for a specific image type and / or image context. For example, referring to FIG. 4A, a prompt (e.g., applying a blurry pink tint image filter) (401) based on the user profile DB (280) before updating may be changed to a prompt (e.g., applying a clear and natural image filter) (407) based on the user profile DB (400) after updating. The user profile DB (400) after update may be a DB in which at least one user profile among the multiple user profiles included in the user profile DB (280) before update has been changed.

[0107] Referring to FIG. 4A, as the user profile DB (280) is updated, the prompt generated by the feature management module (261) may change. For example, as the user profile DB (280) is updated, the word (410) included in the prompt (401) (e.g., hazy feeling) may change to the word (415) (e.g., clear). For example, as the user profile DB (280) is updated, the word (420) included in the prompt (401) (e.g., pink tint) may change to the word (425) (e.g., natural).

[0108] For example, referring to FIG. 4B, the output image (453) may be an image generated based on a prompt (440) (e.g., “Apply a pinkish tint image filter with a blurred feel”) generated based on the user profile DB (280) before the update. In one embodiment, the output image (453) may be an image generated based on the input image (451) and the prompt (440).

[0109] For example, referring to FIG. 4c, the output image (455) may be an image generated based on a prompt (445) (e.g., “Apply a clear and natural image filter”) generated based on the user profile DB (400) after the update. In one embodiment, the output image (455) may be an image generated based on the input image (451) and the prompt (445).

[0110] In one embodiment, the electronic device (101) may update (or reprocess) a previously corrected (or processed) output image (453) to an output image (445) based on a newly updated user profile DB (400) according to an update of the user profile DB (280). For example, referring to FIG. 4D, the electronic device (101) may display an output image (445) based on the updated user profile DB (400) on the display (260).

[0111] As described above, the electronic device (101) can reflect the user's changing preferences in the corrected images by re-correcting images corrected according to the user's past preferences according to the user's current preferences. Furthermore, the electronic device (101) can enable the user to recall past photos by re-correcting images corrected according to the user's past preferences according to the user's current preferences and then displaying the images on the display (260).

[0112] As described above, the electronic device (101) is illustrated as updating an output image (453) that has been corrected (or processed) through a past user profile DB (280) to an output image (445) based on a newly updated user profile DB (400), but this is merely an example. For example, the electronic device (101) can update (or reprocess) an output image (445) based on a newly updated user profile DB (400) to an output image (453) that has been corrected (or processed) through a past user profile DB (280). Accordingly, the electronic device (101) can enable the user to recall his or her past tastes by re-correcting an image that has been corrected according to the current user's tastes according to the user's past tastes.

[0113] FIG. 5A illustrates an example of a prompt according to an embodiment. FIG. 5B illustrates an example of an operation of an electronic device processing an image according to a prompt according to an embodiment. FIG. 5C illustrates an example of an operation of an electronic device processing an image according to a prompt according to an embodiment.

[0114] FIG. 5a, FIG. 5b, and FIG. 5c may be described with reference to FIG. 1, FIG. 2a, or FIG. 2b.

[0115] In one embodiment, the prompt management module (220) may display a prompt generated based on the user's preference on the display (260). For example, the prompt may change as the user profile regarding the type of a specific image and / or the context of the image changes. For example, referring to FIG. 5A, a prompt (e.g., applying an A character sticker) (501) based on the user profile DB (280) before the update may change to a prompt (e.g., applying a C character sticker) (507) based on the user profile DB (400) after the update.

[0116] For example, referring to FIG. 5A, as the user profile DB (280) before update is updated to the user profile DB (400), the menu for updating the word of the prompt may also be changed. For example, the prompt management module (220) may display a menu (503) including a list of character stickers that can replace the A character sticker (510) based on a user input for changing a prompt (e.g., apply A character sticker) (501) based on the user profile DB (280) before update, through the display (260). For example, the prompt management module (220) may display a menu (509) including a list of character stickers that can replace the C character sticker (515) based on a user input for changing a prompt (e.g., apply C character sticker) (507) based on the user profile DB (400) after update, through the display (260).

[0117] For example, referring to FIG. 5B, the output image (543) may be an image generated based on a prompt (530) (e.g., “Apply A character sticker”) generated based on the user profile DB (280) before updating. In one embodiment, the output image (543) may be an image generated based on the input image (541) and the prompt (530). In one embodiment, an A character sticker (553) may be attached to the output image (543).

[0118] For example, referring to FIG. 5c, the output images (545, 547) may be images generated based on a prompt (535) (e.g., “Apply C character sticker”) generated based on the user profile DB (400) after the update. In one embodiment, the output images (545, 547) may be images generated based on the input image (541) and the prompt (535). In one embodiment, the output images (545, 547) may have C character stickers (555, 557) attached to them.

[0119] As described above, the electronic device (101) can generate prompts for decorations to be attached based on the user's current preferences as the user's preferences change. Accordingly, the electronic device (101) can generate prompts that reflect the user's changing preferences.

[0120] FIG. 6 illustrates an example of a prompt according to a change in a user profile, according to one embodiment.

[0121] FIG. 6 may be described with reference to FIG. 1, FIG. 2a, or FIG. 2b.

[0122] In one embodiment, the prompt management module (220) may generate a prompt based on user input requesting the creation of a wallpaper. In one embodiment, the prompt management module (220) may generate a prompt for the creation of a wallpaper based on a user profile for the creation of a wallpaper.

[0123] In one embodiment, referring to FIG. 6, the prompt management module (220) may generate a prompt combining "pink / purple hue", "toned-down", "surreal", and "castle" based on a user input requesting the generation of a wallpaper between time points t1 and t2. In one embodiment, the generative AI module (231) may generate an image (610) based on the prompt generated between time points t1 and t2.

[0124] After time t2, the user profile may be updated. After time t2, as the user profile is updated, at least one of the plurality of elements associated with the generation of the wallpaper (e.g., the third element and the fourth element) may be changed. For example, a feature (or word) associated with the third element (e.g., preferred composition) may be changed from "surreal" to "natural," "close-up," and "soft-focus." For example, a feature (or word) associated with the fourth element (e.g., preferred object) may be changed from "castle" to "flowers." In one embodiment, the prompt management module (220) may generate a prompt combining "pink / purple hue," "toned-down," "natural, close-up, soft-focus," and "flowers" based on a user input requesting the generation of a wallpaper between time t2 and t3. In one embodiment, the generative AI module (231) can generate an image (620) based on a prompt generated between time points t2 and t3.

[0125] After time t3, the user profile may be updated. After time t3, as the user profile is updated, at least one element (e.g., the first element) among the multiple elements related to the generation of the wallpaper may be changed. For example, a feature (or word) related to the first element (e.g., preferred color) may be changed from pink / purple hue to pink / orange hue. In one embodiment, the prompt management module (220) may generate a prompt combining "pink / orange hue," "toned-down," "natural, close-up, soft-focus," and "flowers" based on a user input requesting the generation of the wallpaper between time t3 and time t4. In one embodiment, the generative AI module (231) may generate an image (630) based on the prompt generated between time t3 and time t4.

[0126] After time t4, the user profile may be updated. As the user profile is updated after time t4, at least one element (e.g., the second element) among the multiple elements related to the generation of the wallpaper may be changed. For example, a feature (or word) related to the second element (e.g., preferred color) may be changed from toned-down to vibrant. In one embodiment, the prompt management module (220) may generate a prompt combining "pink / orange hue," "vibrant," "natural, close-up, soft-focus," and "flowers" based on a user input requesting the generation of the wallpaper after time t4. In one embodiment, the generative AI module (231) may generate images (640, 650) based on the prompt generated after time t4. For example, the generative AI module (231) can generate a single image (640) or a dynamic image (650) in which multiple images (651, 653, 655) are sequentially changed. For example, the generative AI module (231) can generate a dynamic image (650) in which multiple images (651, 653, 655) are sequentially changed when the user's feedback on one image (640) is positive (e.g., favorite (or like)).

[0127] Figure 7 is a flowchart illustrating the operation of an electronic device according to one embodiment.

[0128] FIG. 7 may be described with reference to FIG. 1, FIG. 2a, or FIG. 2b.

[0129] In the following examples, the operations may be performed sequentially, but are not necessarily sequential. For example, the order of the operations may be changed, and at least two operations may be performed in parallel.

[0130] Referring to FIG. 7, in operation 710, according to one embodiment, the electronic device (101) may identify a user profile. A user profile for an input image may be identified. The user profile for the input image may be a user profile associated with the type of the image and / or the situation in which the input image was captured. For example, a user profile DB (280) may store a plurality of user profiles that are distinguished from each other according to the type of the input image and / or the situation in which the input image was captured. For example, the plurality of user profiles may be distinguished as user profiles for landscapes, portraits, or still lifes. For example, the plurality of user profiles may be distinguished as user profiles for the purpose of the image (e.g., background screen, lock screen (e.g., wallpaper), uploading to an SNS application, or sharing). For example, multiple user profiles may be distinguished for the context in which the input image was captured (or acquired) (or depicted) (e.g., the types of objects included in the image (e.g., people, animals, plants, objects), the relationships between objects (e.g., friends, family), and / or the time of day (e.g., morning, am, afternoon, evening, dawn)).

[0131] In operation 720, in one embodiment, the electronic device (101) may process an image based on a user profile. In one embodiment, the electronic device (101) may identify at least one user profile corresponding to an input image among one or more user profiles stored in a user profile DB (280). In one embodiment, the electronic device (101) may identify at least one user profile corresponding to a type of an input image and / or a situation in which the input image was acquired (or photographed) (or depicted) (hereinafter, a situation of the input image) in the user profile DB (280). In one embodiment, the electronic device (101) may generate an output image processed from the input image based on the identified user profile. However, the present invention is not limited thereto. In one embodiment, the electronic device (101) may generate an output image based on a user profile without an input image.

[0132] In one embodiment, the electronic device (101) may process an image using a prompt based on a user profile. In one embodiment, the prompt may be a set of words (or a sentence including words) for correcting (or processing) an input image through a generative AI module (231). Hereinafter, with reference to FIG. 8, an operation of the electronic device (101) processing an image using a prompt based on a user profile will be described.

[0133] Figure 8 is a flowchart illustrating the operation of an electronic device according to one embodiment.

[0134] FIG. 8 may be described with reference to FIG. 1, FIG. 2A, or FIG. 2B. The operations of FIG. 8 may be included in operation 720 of FIG. 7.

[0135] In the following examples, the operations may be performed sequentially, but are not necessarily sequential. For example, the order of the operations may be changed, and at least two operations may be performed in parallel.

[0136] Referring to FIG. 8, in operation 810, in one embodiment, the electronic device (101) may generate a prompt based on a user profile. The electronic device (101) may generate a prompt to guide the generation of an output image through a generative AI module (231) based on the user profile. For example, the electronic device (101) may generate a prompt that includes at least one of the words included in the user profile.

[0137] In operation 820, in one embodiment, the electronic device (101) may update a prompt based on a user input. In one embodiment, the electronic device (101) may output (or display) a prompt based on a user profile DB (280) through a display (260). In one embodiment, the electronic device (101) may obtain a user input for the prompt while the prompt is output through the display (260). In one embodiment, the electronic device (101) may present (or output) (or display) candidate words based on the user input for the prompt. For example, the candidate words may be words of substantially the same type (or category) as a word selected by the user input. The fact that the types (or categories) of the words are substantially the same may indicate that the types (or categories) of image corrections associated with the words are substantially the same (or similar). For example, the types (or categories) of image corrections can be categorized into image filters, color tones, and / or decoration. For example, if two or more words are related to image filters, the two or more words may be evaluated as having substantially the same (or similar) type (or category). For example, if two or more words are related to color tones, the two or more words may be evaluated as having substantially the same (or similar) type (or category). For example, if two or more words are related to decoration, the two or more words may be evaluated as having substantially the same (or similar) type (or category). However, this is not limited thereto. For example, since color tones can be applied more than once to a single image, words related to different color tones may be evaluated as having different types (or categories). For example, words related to light balance may be evaluated as having a different type of word than words related to brightness.In one embodiment, the candidate words may be words related to new features included in the new feature DB (265). In one embodiment, the candidate words may be selected in descending order of the number of times they have been extracted among words related to the new features. However, this is not limited thereto. In one embodiment, the candidate words may be words related to a user profile prior to the update (or a user profile prior to the current user profile).

[0138] In one embodiment, the electronic device (101) can change a prompt based on a user profile DB (280) based on a user input. In one embodiment, the electronic device (101) can change the prompt based on a user input of selecting a word from among candidate words. In one embodiment, the user input may include a touch input for at least one word from among the output (or displayed) candidate words, and / or an input through the input module (150). However, the present invention is not limited thereto.

[0139] In operation 830, in one embodiment, the electronic device (101) may process an image based on a prompt. In one embodiment, the electronic device (101) may generate an output image by inputting the prompt to the generative AI module (231). In one embodiment, the electronic device (101) may generate an output image by inputting the prompt and the input image to the generative AI module (231). For example, the processing of the image may include applying an image filter to the image (e.g., warm, calm, lollipop, winter, pink rose, ivory, faded, soft, kiss me, black and white, cinematic, roof, shadow, monstera, palm tree, vignetting, blur, and / or bokeh). In one embodiment, the processing of the image may include adjusting a color tone (e.g., light balance, brightness, exposure, contrast, highlight, shadow, saturation, tint, color temperature, sharpness, and / or clarity) of the image. In one embodiment, processing of an image may include applying decorations to the image (e.g., drawings, stickers, and / or text).

[0140] FIG. 9 is a flowchart illustrating the operation of an electronic device according to one embodiment.

[0141] FIG. 9 may be described with reference to FIG. 1, FIG. 2A, or FIG. 2B. The operations of FIG. 9 may be performed after operation 720 of FIG. 7, or after operation 830 of FIG. 8.

[0142] In the following examples, the operations may be performed sequentially, but are not necessarily sequential. For example, the order of the operations may be changed, and at least two operations may be performed in parallel.

[0143] Referring to FIG. 9, in operation 910, in one embodiment, the electronic device (101) may identify an input related to a processed image. For example, the input related to the processed image may include a user input for changing a prompt input to the generative AI module (231). For example, the input related to the processed image may include a user input related to feedback on an output image output by the generative AI module (231).

[0144] In operation 920, in one embodiment, the electronic device (101) may update a user profile based on an input. For example, if a prompt has changed based on the input, the electronic device (101) may update the user profile based on the changed prompt. For example, if feedback (or positive feedback) regarding an output image has been obtained based on the input, the electronic device (101) may update the user profile based on the output image.

[0145] For example, the electronic device (101) may extract one or more features from the changed prompt. For example, the electronic device (101) may update a user profile based on one or more features extracted from the changed prompt. Hereinafter, with reference to FIG. 10, an operation of the electronic device (101) updating a user profile based on one or more features extracted from the changed prompt will be described.

[0146] For example, the electronic device (101) may extract one or more features from the output image. For example, the electronic device (101) may update a user profile based on one or more features extracted from the output image. Hereinafter, with reference to FIG. 11, an operation of the electronic device (101) updating a user profile based on one or more features extracted from the output image will be described.

[0147] FIG. 10 is a flowchart illustrating the operation of an electronic device according to one embodiment.

[0148] FIG. 10 may be described with reference to FIG. 1, FIG. 2a, or FIG. 2b. The operations of FIG. 10 may be included in operation 920 of FIG. 9.

[0149] In the following examples, the operations may be performed sequentially, but are not necessarily sequential. For example, the order of the operations may be changed, and at least two operations may be performed in parallel.

[0150] Referring to FIG. 10, in operation 1010, in one embodiment, the electronic device (101) may identify a changed prompt based on a user input. For example, the change in the prompt may include a prompt generated by the prompt management module (220) being changed by a user input. For example, the user input may be an input for changing the prompt "Apply a clear and vivid image filter" to the prompt "Apply a warm retro image filter." For example, the user input may be an input for changing the prompt "Apply a blurry pinkish tint image filter" to the prompt "Apply a clear and natural image filter." For example, the user input may be an input for changing the prompt "Apply an A character sticker" to the prompt "Apply a C character sticker."

[0151] In operation 1020, in one embodiment, the electronic device (101) can identify the changed feature based on the changed prompt. For example, if the prompt "Apply clear and vivid image filter" is changed to the prompt "Apply warm retro image filter", the electronic device (101) can identify the changed feature (e.g., changed words (change from clear to warm, or change from vivid to retro)). For example, if the prompt "Apply a blurry pinkish tint image filter" is changed to the prompt "Apply a clear and natural image filter", the electronic device (101) can identify the changed feature (e.g., changed words (change from blurry to clear, or change from pinkish tint to natural)). For example, if the prompt “Apply A character sticker” is changed to the prompt “Apply C character sticker,” the electronic device (101) can identify the changed feature (e.g., changed words (change from A character sticker to C character sticker)).

[0152] In operation 1030, in one embodiment, the electronic device (101) may update the user profile based on the changed characteristics. Hereinafter, with reference to FIG. 12, an operation of the electronic device (101) updating the user profile based on the changed characteristics will be described.

[0153] FIG. 11 is a flowchart illustrating the operation of an electronic device according to one embodiment.

[0154] FIG. 11 may be described with reference to FIG. 1, FIG. 2a, or FIG. 2b. The operations of FIG. 11 may be included in operation 920 of FIG. 9.

[0155] In the following examples, the operations may be performed sequentially, but are not necessarily sequential. For example, the order of the operations may be changed, and at least two operations may be performed in parallel.

[0156] Referring to FIG. 11, in operation 1110, in one embodiment, the electronic device (101) may identify a selected image based on a user input. For example, the electronic device (101) may identify at least one output image selected by the user input among output images through the generative AI module (231).

[0157] In operation 1120, in one embodiment, the electronic device (101) may identify features based on the selected image. For example, the electronic device (101) may identify features indicating image processing applied to the selected image. For example, if an image filter is applied to the output image, the electronic device (101) may identify (or extract) features related to the applied image filter (e.g., words describing the type of image filter). For example, if a specific color tone is applied to the output image, the electronic device (101) may identify (or extract) features related to the specific color tone applied (e.g., words describing the color tone). For example, if a specific decoration is applied to the output image, the electronic device (101) may identify (or extract) features related to the specific decoration applied (e.g., words describing the decoration). For example, when the output image is used as wallpaper, the electronic device (101) can identify (or extract) features related to the pattern design, illustration, and depiction method (e.g., person or landscape) of the output image. For example, when the output image includes a character, the electronic device (101) can identify (or extract) features related to the character (e.g., words describing the character shape (e.g., cute, funny), and / or the character type (e.g., rabbit)).

[0158] In operation 1130, in one embodiment, the electronic device (101) may update a user profile based on the identified feature. Hereinafter, with reference to FIG. 12, an operation of the electronic device (101) updating a user profile based on the identified feature will be described.

[0159] FIG. 12 is a flowchart illustrating the operation of an electronic device according to one embodiment.

[0160] FIG. 12 may be described with reference to FIG. 1, FIG. 2a, or FIG. 2b. The operations of FIG. 12 may be included in operation 920 of FIG. 9.

[0161] In the following examples, the operations may be performed sequentially, but are not necessarily sequential. For example, the order of the operations may be changed, and at least two operations may be performed in parallel.

[0162] Referring to FIG. 12, in operation 1210, in one embodiment, the electronic device (101) may identify a feature. In one embodiment, the feature may be a feature indicating words changed by a user input. For example, the feature may be a feature indicating image processing applied to an output image. However, the present invention is not limited thereto. For example, the feature may indicate the type and / or situation of the output image.

[0163] In operation 1220, in one embodiment, the electronic device (101) can determine whether the identified feature is included in the basic feature DB (263). For example, the electronic device (101) can determine whether the identified feature is a feature included in the basic feature DB (263).

[0164] In operation 1220, in one embodiment, based on determining that the identified feature is included in the basic feature, the electronic device (101) may perform operation 1250. In operation 1220, based on determining that the identified feature is not included in the basic feature, the electronic device (101) may perform operation 1230.

[0165] In operation 1230, in one embodiment, the electronic device (101) may update a new feature. In one embodiment, the electronic device (101) may store the identified feature in a new feature DB (265). In one embodiment, the electronic device (101) may increase the number of identifications (or extractions) of the identified feature stored in the new feature DB (265).

[0166] In operation 1240, in one embodiment, the electronic device (101) can determine whether there is a change greater than a threshold value. In one embodiment, the electronic device (101) can determine whether the number of times an identified feature stored in the new feature DB (265) has changed greater than a threshold value.

[0167] In one embodiment, based on determining that the number of times the identified feature is identified is greater than or equal to a threshold value in operation 1240, the electronic device (101) may perform operation 1250. In one embodiment, based on determining that the number of times the identified feature is identified is less than the threshold value in operation 1240, the electronic device (101) may perform operation 1210 again. For example, based on determining that the number of times the identified feature is identified is less than the threshold value, the electronic device (101) may perform the operations according to FIG. 12 again for another feature. However, the present invention is not limited thereto. For example, based on determining that the number of times the identified feature is identified is less than the threshold value, the electronic device (101) may terminate the operations according to FIG. 12.

[0168] In operation 1250, in one embodiment, the electronic device (101) may update the basic feature. In one embodiment, the electronic device (101) may store the identified feature in the basic feature DB (263). In one embodiment, the electronic device (101) may change the storage location of a feature of a type that is substantially the same as (or similar to) the type of the identified feature whose storage location is changed from the new feature DB (265) to the basic feature DB (263) from the basic feature DB (263) to the new feature DB (265) based on the identified feature stored in the new feature DB (265) being stored in the basic feature DB (263).

[0169] In operation 1260, in one embodiment, the electronic device (101) may update the user profile based on the updated characteristics. Hereinafter, with reference to FIG. 13, an operation of the electronic device (101) updating the user profile based on the updated characteristics will be described.

[0170] FIG. 13 is a flowchart illustrating the operation of an electronic device according to one embodiment.

[0171] FIG. 13 may be described with reference to FIG. 1, FIG. 2a, or FIG. 2b. The operations of FIG. 13 may be included in operation 1260 of FIG. 12.

[0172] In the following examples, the operations may be performed sequentially, but are not necessarily sequential. For example, the order of the operations may be changed, and at least two operations may be performed in parallel.

[0173] Referring to FIG. 13, in operation 1310, in one embodiment, the electronic device (101) may generate a prompt based on updated features. The electronic device (101) may generate a prompt based on updated features in response to additional user input requesting image processing. For example, the electronic device (101) may generate a prompt that includes updated features among features stored in the base feature DB (263). For example, the electronic device (101) may generate a prompt that includes updated features among features stored in the new feature DB (265). For example, the electronic device (101) may generate a prompt by combining features stored in the base feature DB (263) and / or features stored in the new feature DB (265). For example, some of the features included in the prompt may be updated features.

[0174] In operation 1320, in one embodiment, the electronic device (101) may process an image based on a prompt. In one embodiment, the electronic device (101) may generate an output image by inputting the prompt to the generative AI module (231). For example, the processing of the image may include applying an image filter to the image. In one embodiment, the processing of the image may include adjusting the color tone of the image. In one embodiment, the processing of the image may include applying a decoration to the image.

[0175] In operation 1330, in one embodiment, the electronic device (101) may determine whether positive feedback exists. For example, if a save, upload, share, or favorite (or like) request is made for an image generated through a prompt based on updated features, the electronic device (101) may determine that positive feedback exists. For example, if a delete or edit request is made for an image generated through a prompt based on updated features, the electronic device (101) may determine that negative feedback exists.

[0176] In one embodiment, based on determining that positive feedback exists in operation 1330, the electronic device (101) may perform operation 1340. In one embodiment, based on determining that positive feedback does not exist in operation 1330 (or that negative feedback exists), the electronic device (101) may terminate the operations according to FIG. 13.

[0177] In operation 1340, in one embodiment, the electronic device (101) may update a user profile based on the updated characteristics. For example, the electronic device (101) may update a user profile for correction of an image having substantially the same type and / or context as the output image. Subsequently, a prompt with positive feedback may be generated based on the updated user profile.

[0178] FIG. 14 is a diagram illustrating the structure of a generative AI model of an electronic device according to one embodiment.

[0179] FIG. 14 may be described with reference to FIG. 1, FIG. 2a, or FIG. 2b.

[0180] In one embodiment, a user interface (UI) (1410) may be an element for interaction between an electronic device (101) and a user. For example, the UI (1410) may be an element for receiving (or acquiring) a user's input. For example, the UI (1410) may be an element for providing (or outputting) a result of the user's input.

[0181] In one embodiment, the UI (1410) may be a graphical UI (GUI) for user interaction (e.g., acquisition of touch input and / or display of results) via the display (260). In one embodiment, the UI (1410) may be a voice UI (VUI) (or an auditory UI (AUI)) for user interaction (e.g., acquisition of voice signals and / or output of audio signals) via the audio output module (155) (or the audio module (170)). In one embodiment, the UI (1410) may be a natural UI (NUI) for user interaction (e.g., acquisition of user gestures or gaze) via the camera module (180). In one embodiment, the UI (1410) may be a physical UI (PUI) (or a tangible UI (TUI)) for user interaction (e.g., input to a physical button) via the input module (150).

[0182] In one embodiment, the UI (1410) may be configured for interaction between the electronic device (101) and the user for the purpose of querying the user and / or responding to the query. In one embodiment, the UI (1410) may receive user input. For example, the user input may include natural language input (e.g., voice signal input, and / or text input), and / or input for selecting (or indicating) content (e.g., images and / or videos). The user input may also be in a mixed form of the above-described natural language, images, sounds, and context information. The user input may also be in a non-natural language form, such as selecting a menu.

[0183] In one embodiment, the UI (1410) may identify (or obtain) information about the context related to the time (or situation) at which the user's input is obtained, for the purpose of the user's inquiry and / or response to the inquiry. In one embodiment, the information about the context may include additional information at the time of the user input. For example, the additional information may include information about the application currently being used by the user or location information of the user (or the electronic device (101)).

[0184] In one embodiment, the electronic device (101) may output the results of a generative AI model (1450) to the user via a UI (1410). In one embodiment, the output may be in the form of natural language or specific content. In one embodiment, the output may be provided in a form requested by the user (e.g., an action).

[0185] In one embodiment, the UI (1410) may transmit information about the user's input and / or context to an artificial intelligence (AI) framework (1420). In one embodiment, the AI ​​framework (1420) may obtain information about the user's input and / or context from the UI (1410).

[0186] In one embodiment, the AI ​​framework (1420) may coordinate and / or control each of the components (e.g., interface management element (1421), prompt design element (1423), or output modification element (1425)) necessary to perform a task according to the user's intent identified based on the user's query (or query included in the user input).

[0187] In one embodiment, the AI ​​framework (1420) may transmit user input obtained from the UI (1410) to a prompt design element (1423).

[0188] In one embodiment, the prompt design element (1423) may generate a prompt suitable for inputting user input into a generative AI model (1450) (e.g., a large language model (LLM) and / or a larger multimodal model (LMM)).

[0189] In one embodiment, the prompt design element (1423) may be an AI component that utilizes a machine learning algorithm or neural network. Accordingly, the prompt design element (1423) may change the prompt generated through learning.

[0190] In one embodiment, the prompt design element (1423) may access a knowledge element (or knowledge repository (1430)) containing user preference data, a prompt library, and prompt examples based on user input to generate a prompt, and pass the generated prompt to a generative AI model (1450) (e.g., an LLM and / or LMM).

[0191] In one embodiment, the interface management element (1421) can communicate with external elements. In one embodiment, the interface management element (1421) can obtain additional information from external elements when there is a request for additional information when passing user input (or a prompt based on user input) as input to the generative AI model (1450). In one embodiment, the interface management element (1421) can establish a channel for communicating with the outside of the AI ​​framework (1420) through an application programming interface (API), and can enable the AI ​​framework (1420) to access various data sources (e.g., a knowledge repository (1430)) through the established channel. In addition, the interface management element (1421) can request the service element (1440) through the API to perform an action that performs the user input as a final result rather than an intermediate result when the application and / or service needs to perform the action. Information obtained from external elements may be used to generate prompts in the prompt design element (1423) along with user input or may be passed as input to the generative AI model (1450).

[0192] In one embodiment, the output modification component (1425) can fine-tune the output from the generative AI model (1450). For example, the output modification component (1425) can verify (e.g., verify for relevance, bias, and / or harmfulness) the content generated by the generative AI model (1450) (e.g., LLM and / or LMM). In addition, the output modification component (1425) can determine to what extent the output result matches the result desired by the user and, if additional adjustment is needed, can perform additional tasks for additional adjustment. Additionally, the output modification component (1425) can provide the user with hints to prevent (or reduce) undesired output.

[0193] In one embodiment, a generative AI model (1450) may generally refer to an artificial intelligence neural network that generates new types of data based on user input information. The generative AI model (1450) may include a model that generates images and / or a model that generates language. The model that generates images may include a generative adversarial network (GAN), a variational autoencoder (VAE), and / or a diffusion-based generative model that uses a VAE and a transformer architecture. The model that generates language may be a model trained to output statistically most appropriate output values ​​based on input values. For example, the model that generates language may include a model such as CHAT-GPT 3 or CHAT-GPT 4. In addition, the generative AI model (1450) may be an LMM that can recognize various types of data input, such as text, images, and voice, and generate new data corresponding thereto.

[0194] As described above, the electronic device (101) may include at least one processor (120) including a processing circuit. The electronic device (101) may include a memory (130) including one or more storage media for storing instructions. The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to generate a prompt (330, 335) for processing an image (341) based on a user profile. The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to control a generative artificial intelligence (AI) model (231) to process the image (341) based on the prompt (330, 335). The above instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to determine whether to update the user profile based on user input related to the processed image (343, 345).

[0195] The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to obtain the user input (350) for changing the prompt (330). The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to control the generative AI model (231) to process the image (341) based on the prompt (335) that has been changed based on the user input (350).

[0196] The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to identify at least one word among the one or more words included in the prompt (335) that is distinct from words for common characteristics. The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to determine whether to update the user profile based on the number of times the at least one word has been input as a prompt to the generative AI model (231).

[0197] The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to obtain the user input selecting the processed image (345). The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to identify one or more words describing the processed image (345) selected based on the user input. The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to identify at least one word among the one or more words that is distinct from words for a common characteristic. The above instructions, when executed individually or collectively by the at least one processor (120), may cause the electronic device (101) to determine whether to update the user profile based on the number of times the at least one word is identified as a word describing the processed image (345) processed by the generative AI model (231).

[0198] One or more words included in the above prompts (330, 335) may include one or more first words for common features and one or more second words for new features. The first words and the second words may be words belonging to different categories.

[0199] As described above, the electronic device (101) may include a display (260). The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to display the prompt (330) through the display (260). The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to obtain the user input (350) for changing a word among one or more words included in the prompt (330). The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to change the prompt (330) based on the user input (350).

[0200] The above instructions, when executed individually or collectively by the at least one processor (120), may cause the electronic device (101) to display, through the display (260), a menu (303, 305) comprising a plurality of candidate words that are replaceable with the word (310, 320) indicated by the user input.

[0201] The plurality of candidate words may include words associated with new features selected when the prompt is changed by another user input and / or words associated with previous basic features. The words (310, 320) and the plurality of candidate words may be included in the same category. The words associated with the new features and the words associated with the previous basic features may be expressed differently when displayed through the display (260).

[0202] The above instructions, when executed individually or collectively by the at least one processor (120), may cause the electronic device (101) to reprocess an image (453) processed based on the user profile before the change based on the user profile after the change, based on the user profile after the change.

[0203] The above instructions, when executed individually or collectively by the at least one processor (120), may cause the electronic device (101) to reprocess an image processed based on the changed user profile based on the changed user profile based on the user profile before the change.

[0204] As described above, the method may be performed in an electronic device (101). The method may include an operation of generating a prompt (330, 335) for processing an image (341) based on a user profile. The method may include an operation of controlling a generative artificial intelligence (AI) model (231) to process the image (341) based on the prompt (330, 335). The method may include an operation of determining whether to update the user profile based on a user input related to the processed image (343, 345).

[0205] The method may include an action of obtaining the user input (350) for changing the prompt (330). The method may include an action of controlling the generative AI model (231) to process the image (341) based on the prompt (335) changed based on the user input (350).

[0206] The method may include an operation of identifying at least one word among one or more words included in the prompt (330) that is distinct from words for common characteristics. The method may include an operation of determining whether to update the user profile based on the number of times the at least one word has been input as a prompt (330) to the generative AI model (231).

[0207] The method may include an action of obtaining the user input for selecting the processed image (345). The method may include an action of identifying one or more words describing the processed image (345) selected based on the user input. The method may include an action of identifying at least one word among the one or more words that is distinct from words having a common characteristic. The method may include an action of determining whether to update the user profile based on the number of times the at least one word is identified as a word describing the processed image (345) processed by the generative AI model (231).

[0208] One or more words included in the above prompts (330, 335) may include one or more first words for common features and one or more second words for new features. The first words and the second words may be words belonging to different categories.

[0209] The method may include an action of displaying the prompt (330) through the display (260). The method may include an action of obtaining user input for changing a word among one or more words included in the prompt (330). The method may include an action of changing the prompt (330) based on the user input.

[0210] The above may include an action of displaying a menu (303, 305) including a plurality of candidate words that can be replaced with the word (310, 320) indicated by the above user input through the display (260).

[0211] The plurality of candidate words may include words associated with new features selected when the prompt is changed by another user input and / or words associated with previous basic features. The words (310, 320) and the plurality of candidate words may be included in the same category. The words associated with the new features and the words associated with the previous basic features may be expressed differently when displayed through the display (260).

[0212] Based on the change in the above user profile, an operation may be included to reprocess the image (453) processed based on the user profile before the change based on the user profile after the change.

[0213] Based on the change in the above user profile, an operation may be included to reprocess the image (341) processed based on the changed user profile based on the user profile before the change.

[0214] As described above, a non-transitory computer readable storage medium can store a program including instructions. It can include at least one processor (120) including processing circuitry. The electronic device (101) can include a memory (130) including one or more storage media storing instructions. The instructions, when individually or collectively executed by the at least one processor (120) including processing circuitry of the electronic device (101), can cause the electronic device (101) to generate a prompt (330, 335) for processing an image (341) based on a user profile. The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to control a generative artificial intelligence (AI) model (231) to process the image (341) based on the prompt (330, 335). The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to determine whether to update the user profile based on user input related to the processed image (343, 345).

[0215] 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.

[0216] 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 component (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.

[0217] 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).

[0218] 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.

[0219] According to one embodiment, the method according to various embodiments disclosed in this document may be provided as included in a computer program product. The computer program product may be traded as a product between a seller and a buyer. The computer program product may be distributed in the form of a machine-readable storage medium (e.g., a compact disc read-only memory (CD-ROM)), or may be distributed online (e.g., by download or upload) through an application store (e.g., Play Store™) or directly between two user devices (e.g., smart phones). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily generated in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0220] 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 (101), At least one processor (120) comprising a processing circuit; and A memory (130) including one or more storage media storing instructions, wherein the instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101) to: Based on the user profile, generate a prompt (330, 335) to process the image (341), Controlling the generative AI (artificial intelligence) model (231) to process the image (341) based on the above prompt (330, 335), Based on the user input related to the processed image (343, 345), causing a decision to be made as to whether to update the user profile. Electronic devices.

2. In claim 1, The above instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101) to: Obtaining the user input (350) to change the above prompt (330), Causing the generative AI model (231) to process the image (341) based on the changed prompt (335) based on the user input (350). Electronic devices.

3. In claim 2, The above instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101) to: Identify at least one word among the one or more words included in the above prompt (335) that is distinct from the words for common features, Causing a decision on whether to update the user profile based on the number of times at least one word is input as a prompt to the generative AI model (231). Electronic devices.

4. In any one of claims 1 to 3, The above instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101) to: Obtaining the user input for selecting the processed image (345), Identifying one or more words describing the processed image (345) selected based on the user input; Identify at least one word among the above one or more words that is distinct from the words for common features, Causing a decision on whether to update the user profile based on the number of times at least one word is identified as a word describing the processed image (345) processed through the generative AI model (231). Electronic devices.

5. In any one of claims 1 to 4, One or more words included in the above prompt (330, 335) include one or more first words for common features and one or more second words for new features, The above first words and the above second words are words belonging to different categories. Electronic devices.

6. In any one of claims 1 to 5, Including a display (260), The above instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101) to: The above prompt (330) is displayed through the above display (260), Obtaining the user input (350) for changing a word among one or more words included in the above prompt (330), causing the prompt (330) to be changed based on the user input (350); Electronic devices.

7. In claim 6, The above instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101) to: Causing the display (260) to display a menu (303, 305) containing a plurality of candidate words that can be replaced with the word (310, 320) indicated by the user input. Electronic devices.

8. In claim 7, The above multiple candidate words include words related to new features selected when the prompt is changed by another user input and / or words related to previous basic features, The above words (310, 320) and the above multiple candidate words are included in the same category, Words related to the above new features and words related to the above previous basic features are expressed differently when displayed through the display (260). Electronic devices.

9. In any one of claims 1 to 8, The above instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101) to: Based on the change of the above user profile, causing the image (453) processed based on the above user profile before the change to be reprocessed based on the above user profile after the change. Electronic devices.

10. In any one of claims 1 to 9, The above instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101) to: Based on the change of the above user profile, causing the image processed based on the above user profile after the change to be reprocessed based on the above user profile before the change. Electronic devices.

11. In a method performed in an electronic device (101), An action to generate a prompt (330, 335) for processing an image (341) based on the user profile. An operation of controlling a generative AI (artificial intelligence) model (231) to process the image (341) based on the above prompt (330, 335), and An operation for determining whether to update the user profile based on user input related to the processed image (343, 345) method.

12. In claim 11, An operation of obtaining the user input (350) for changing the above prompt (330), and An operation for controlling the generative AI model (231) to process the image (341) based on the changed prompt (335) based on the user input (350). method.

13. In claim 12, An operation of identifying at least one word among one or more words included in the above prompt (330) that is distinct from words for common characteristics, and An operation for determining whether to update the user profile based on the number of times at least one word is input as a prompt (330) to the generative AI model (231). method.

14. In any one of claims 11 to 13, An action of obtaining the user input for selecting the processed image (345), An action of identifying one or more words describing the processed image (345) selected based on the user input; An operation of identifying at least one word among the above one or more words that is distinct from words for common characteristics, and An operation for determining whether to update the user profile based on the number of times at least one word is identified as a word describing the processed image (345) processed through the generative AI model (231). method.

15. In any one of claims 11 to 14, One or more words included in the above prompt (330, 335) include one or more first words for common features and one or more second words for new features, The above first words and the above second words are words belonging to different categories. method.

Images