Electronic device and method for generating content

Abstract

An electronic device according to one embodiment comprises: a processor; a memory for storing instructions; and a display. When executed by the processor, the instructions cause the electronic device to: display, on the display, a screen including a plurality of first keywords and first candidate content; add a second keyword into the screen on the basis of receiving of a first user input for adding the second keyword ; remove, from the screen, at least one keyword from among the plurality of first keywords on the basis of receiving of a second user input for removing the at least one keyword from among the plurality of first keywords; and change the first candidate content to second candidate content based on one or more keywords included in the screen.

Description

Electronic device and method for generating content

[0001] The present disclosure relates to an electronic device and method for generating content.

[0002] Electronic devices may include smartphones, laptops, computers, and wearable devices worn on the user's body. For example, a wearable device may be an electronic device that provides augmented reality (AR) services, which display information generated by the wearable device or an external electronic device in conjunction with external objects in the real world to provide an enhanced user experience. For example, a wearable device may include AR glasses and / or a head-mounted device (HMD).

[0003] 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 in connection with the present disclosure.

[0004] An electronic device is provided. The electronic device may include a processor including a processing circuit. The electronic device may include a memory storing instructions. The electronic device may include a display. The instructions, when individually or collectively executed by the processor, may cause the electronic device to display a screen on the display, the screen including a plurality of first keywords and first candidate content based on the plurality of first keywords. The instructions, when individually or collectively executed by the processor, may cause the electronic device to, while displaying the screen on the display, add a second keyword to the screen based on receiving a first user input for adding a second keyword, remove at least one keyword from among the plurality of first keywords from the screen based on receiving a second user input for removing at least one keyword from among the plurality of first keywords, and change the first candidate content to second candidate content based on one or more keywords included in the screen.

[0005] An electronic device is provided. The electronic device may include a processor comprising a processing circuit. The electronic device may include a memory storing instructions. The electronic device may include a display. The instructions, when individually or collectively executed by the processor, may cause the electronic device to obtain a first prompt corresponding to first content from first content while the first content is displayed through the display. The instructions, when individually or collectively executed by the processor, may cause the electronic device to display the first prompt through the display. The instructions, when individually or collectively executed by the processor, may cause the electronic device to receive a first user input for selecting at least a portion of the first content or one or more words included in the first prompt. The instructions, when individually or collectively executed by the processor, may cause the electronic device to provide a visual effect representing at least a portion of the first content or one or more words corresponding to the first user input.

[0006] A method performed by an electronic device including a display is provided. The method may include an operation of obtaining a first prompt corresponding to the first content from the first content while the first content is displayed through the display. The method may include an operation of displaying the first prompt through the display. The method may include an operation of receiving a first user input for selecting at least a portion of the first content or one or more words included in the first prompt. The method may include an operation of providing a visual effect corresponding to the at least a portion of the first content or the one or more words based on the first user input.

[0007] FIG. 1 is a block diagram of an electronic device within a network environment according to one embodiment.

[0008] Figure 2 is a block diagram illustrating components of an exemplary electronic device.

[0009] Figure 3 is a flow chart showing an operation of an exemplary electronic device to generate third content.

[0010] FIG. 4a illustrates an exemplary screen representing user input for displaying content via a display.

[0011] Figure 4b illustrates an exemplary screen representing a first user input.

[0012] Figure 4c illustrates an exemplary screen representing a second user input.

[0013] Figure 4d schematically illustrates the process of generating third content.

[0014] Figure 4e shows an exemplary screen for adjusting the degree of correction.

[0015] FIG. 5 is a flowchart illustrating operations of an exemplary electronic device for generating a description of first content.

[0016] Figure 6 illustrates exemplary operations for analyzing the original content of the first content.

[0017] FIG. 7 is a flowchart illustrating operations of an exemplary electronic device for extracting and updating a first prompt.

[0018] Figure 8 illustrates operations for updating the first prompt.

[0019] Figure 9 is a drawing for explaining the tuned-up first prompt.

[0020] FIG. 10A illustrates an exemplary screen for applying a first prompt to content displayed through another electronic device located within an external environment.

[0021] FIG. 10b illustrates an exemplary screen in which content displayed through another electronic device has been changed.

[0022] Figure 11 illustrates an exemplary screen for displaying objects related to the first prompt.

[0023] Figure 12 illustrates an exemplary screen for extracting a first prompt for a portion of the first content.

[0024] Figure 13 illustrates an exemplary screen for extracting a first prompt from one or more user preferred contents.

[0025] Figure 14a illustrates an exemplary screen for extracting a first prompt for one of the frames that make up a video.

[0026] FIG. 14b illustrates an exemplary screen in which a first prompt for one of the frames constituting the video content is applied to a second content.

[0027] Figure 14c illustrates an exemplary screen in which second content is displayed.

[0028] Figure 15a illustrates an exemplary screen that provides a first prompt based on user history.

[0029] FIG. 15b is a flowchart illustrating an operation of providing a prompt based on content modified by multiple external electronic devices.

[0030] FIG. 15c illustrates an exemplary screen that provides a prompt based on content modified by multiple external electronic devices.

[0031] Figure 16 illustrates an exemplary screen provided when use of the first content is restricted.

[0032] FIG. 17A illustrates a perspective view of a wearable device according to an exemplary embodiment.

[0033] FIG. 17b illustrates one or more hardware elements arranged within a wearable device according to an exemplary embodiment.

[0034] FIG. 18a and FIG. 18b illustrate the appearance of a wearable device according to an exemplary embodiment.

[0035] FIG. 19a and FIG. 19b illustrate a process of an electronic device changing second content according to one embodiment.

[0036] FIG. 20 is a flowchart illustrating an operation of providing candidate content of an electronic device according to an exemplary embodiment.

[0037] Figures 21, 22, 23, and 24 illustrate processes for changing first candidate content into second candidate content according to first user input.

[0038] FIG. 25 is a flowchart illustrating an operation of providing candidate content of an electronic device according to an exemplary embodiment.

[0039] Figures 26, 27, and 28 illustrate processes for changing first candidate content into second candidate content according to second user input.

[0040] FIG. 29 is a flowchart illustrating an operation of an electronic device according to an exemplary embodiment to change second content using a plurality of first keywords from first content.

[0041] Figures 30, 31, 32, and 33 illustrate processes for changing first candidate content into second candidate content according to second user input.

[0042] FIG. 34 is a flowchart illustrating operations of an electronic device providing recommended keywords according to an exemplary embodiment.

[0043] FIG. 35, FIG. 36, and FIG. 37 illustrate processes by which an electronic device according to an exemplary embodiment changes a first candidate content into a second candidate content based on a recommended keyword.

[0044] FIG. 38 is a flowchart illustrating an operation of an electronic device according to an exemplary embodiment to provide candidate content based on a conversation history of a messenger application.

[0045] FIG. 39, FIG. 40a, FIG. 40b, FIG. 40c, and FIG. 40d illustrate processes in which an electronic device according to an exemplary embodiment provides a plurality of first keywords and first candidate content according to first history information.

[0046] FIG. 41 is a flowchart illustrating an operation of an electronic device according to an exemplary embodiment to provide candidate content based on a search history of a virtual keyboard application.

[0047] FIG. 42 and FIG. 43 illustrate processes in which an electronic device according to an exemplary embodiment provides a plurality of first keywords and first candidate content according to second history information.

[0048] FIG. 1 is a block diagram of an electronic device within a network environment, according to one embodiment.

[0049] 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 an electronic device (104) or a server (108) via a second network (199) (e.g., a long-range wireless communication network). In one embodiment, the electronic device (101) may communicate with the electronic device (104) via the server (108). According to one embodiment, the electronic device (101) may include a processor (120), a memory (130), an input module (150), an audio output module (155), a display module (160), an audio module (170), a sensor module (176), an interface (177), a connection terminal (178), a haptic module (179), a camera module (180), a power management module (188), a battery (189), a communication module (190), a subscriber identification module (196), or an antenna module (197). In some embodiments, the electronic device (101) may omit at least one of these components (e.g., the connection terminal (178)), or may have one or more other components added. In some embodiments, some of these components (e.g., the sensor module (176), the camera module (180), or the antenna module (197)) may be integrated into one component (e.g., the display module (160)).

[0050] 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.

[0051] 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, in the electronic device (101) itself where artificial intelligence is performed, 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.

[0052] 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).

[0053] 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).

[0054] 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).

[0055] 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.

[0056] 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. In 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.

[0057] 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).

[0058] 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.

[0059] The interface (177) may support one or more designated protocols that may be used to directly or wirelessly connect the electronic device (101) to 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.

[0060] 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).

[0061] 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.

[0062] 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.

[0063] The power management module (188) can manage the 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).

[0064] 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.

[0065] 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).

[0066] The wireless communication module (192) can support 5G networks and next-generation communication technologies following the 4G network, such as NR access technology (new radio access technology). The NR access technology can support high-speed transmission of high-capacity data (eMBB (enhanced mobile broadband)), minimization of terminal power and connection of multiple terminals (mMTC (massive machine type communications)), or high reliability and low latency (URLLC (ultra-reliable and low-latency communications)). The wireless communication module (192) can support, for example, a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate. The wireless communication module (192) can support various technologies for securing performance in a high-frequency band, such as beamforming, massive multiple-input and multiple-output (MIMO), full dimensional MIMO (FD-MIMO), array antenna, analog beam-forming, or large scale antenna. The wireless communication module (192) can support various requirements specified in the electronic device (101), an external electronic device (e.g., the electronic device (104)), or a network system (e.g., the second network (199)). According to one embodiment, the wireless communication module (192) can support a peak data rate (e.g., 20 Gbps or more) for eMBB realization, a loss coverage (e.g., 164 dB or less) for mMTC realization, or a U-plane latency (e.g., 0.5 ms or less for downlink (DL) and uplink (UL), or 1 ms or less for round trip) for URLLC realization.

[0067] 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 by, for example, the communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device through the selected at least one antenna. 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).

[0068] In one embodiment, 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.

[0069] 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)).

[0070] 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 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.

[0071] According to an exemplary embodiment, the electronic device (101) may include a wearable device. For example, the electronic device (101) may include a head-mounted display (HMD) that is wearable on a user's head. The electronic device (101) may be referred to as a head-mounted display (HMD) device, a headgear electronic device, a glasses-type (or goggle-type) electronic device, a video see-through (VST) device, an extended reality (XR) device, a virtual reality (VR) device, and / or an augmented reality (AR) device. For example, the electronic device (101) may include an accessory (e.g., a strap) for attaching to a user's head. An example of a hardware configuration included in the electronic device (101) is described below with reference to FIG. 2. The wearable device (1700) illustrated in FIGS. 17A and 17B has an external appearance in the form of glasses, but the embodiment is not limited thereto. An example of the structure of a wearable device (1800) that can be worn on a user's head is described below with reference to FIGS. 18A and 18B.

[0072] An electronic device (101) according to an exemplary embodiment may perform functions related to augmented reality (AR) and / or mixed reality (MR). For example, the electronic device (101) may include at least one lens positioned adjacent to the user's eyes while the electronic device (101) is worn by the user. The electronic device (101) may combine ambient light passing through the lens with light emitted from a display (e.g., the display (250) of FIG. 2). A display area of ​​the display (250) may be formed within the lens through which the ambient light passes. Since the electronic device (101) combines the ambient light and the light emitted from the display (250), the user may see an image in which a real object recognized by the ambient light and a virtual object formed by the light emitted from the display (250) are mixed. The augmented reality, mixed reality, and / or virtual reality described above may be referred to as extended reality (XR). The electronic device (101) according to an exemplary embodiment may perform functions related to video see-through (VST) and / or virtual reality (VR).

[0073] Figure 2 is a block diagram illustrating components of an exemplary electronic device.

[0074] Referring to FIG. 2, an electronic device (101) according to an exemplary embodiment may include a camera (230) (e.g., a camera module (180) of FIG. 1), a sensor (240) (e.g., a sensor module (176) of FIG. 1), a memory (220) (e.g., a memory (130) of FIG. 1), a processor (210) (e.g., a processor (120) of FIG. 1), a display (250) (e.g., a display module (160) of FIG. 1), and / or a communication circuit (260) (e.g., a communication module (190) of FIG. 1). The camera (230), sensor (240), memory (220), processor (210), display (250), and / or communication circuit (260) may be electrically and / or operably coupled with each other by electronic components such as a communication bus (201). The type and / or number of hardware components included in the electronic device (101) is not limited to those illustrated in FIG. 2. For example, the electronic device (101) may include only some of the hardware components illustrated in FIG. 2, or may include hardware components not illustrated in FIG. 2 (e.g., the battery (189) of FIG. 1).

[0075] According to an exemplary embodiment, the processor (210) may control the operation of the electronic device (101). The processor (210) may include a hardware component for processing data based on instructions. The hardware component for processing data may include, for example, an arithmetic and logic unit (ALU), a field programmable gate array (FPGA), a central processing unit (CPU), and / or an application processor (AP). In an exemplary embodiment, the electronic device (101) may include one or more processors. The processor (210) may have a multi-core processor structure such as a dual core, a quad core, a hexa core, and / or an octa core. The multi-core processor structure of the processor (210) may include a structure based on a plurality of core circuits (e.g., a big-little structure) that are distinguished by power consumption, clock, and / or calculation amount per unit time. In embodiments including a processor having a multi-core processor architecture, the operations and / or functions of the present disclosure may be collectively performed by one or more cores included in the processor (210).

[0076] Any function or operation described herein may be processed by the processor (210). The processor (210) may include a processing circuit. The processor (210) may include, but is not limited to, an application processor (AP, e.g., a central processing unit (CPU)) and / or a communication processor (CP, e.g., a modem). The processor (210) may include a graphics processing unit (e.g., a GPU), a neural processing unit (NPU) (e.g., an artificial intelligence (AI) chip), a wireless-fidelity (Wi-Fi) chip, a Bluetooth chip®, a global positioning system (GPS) chip, a near field communication (NFC) chip, connectivity chips, a sensor controller, a touch controller, a finger-print sensor controller, a display drive integrated circuit (DDI), an audio CODEC chip, a universal serial bus (USB) controller, a camera controller, an image processing IC, a microprocessor unit (MPU), a system on chip (SoC), an integrated circuit (IC), or a similar circuit.

[0077] According to an exemplary embodiment, the memory (220) may include a hardware component for storing data and / or instructions input and / or output to the processor (210). The memory (220) may include, for example, volatile memory such as random-access memory (RAM) and / or non-volatile memory such as read-only memory (ROM). The volatile memory may include, for example, at least one of dynamic RAM (DRAM), static RAM (SRAM), cache RAM, and pseudo SRAM (PSRAM). The non-volatile memory may include, for example, at least one of programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), flash memory, a hard disk, a compact disc, or an embedded multi media card (eMMC). In one embodiment, the memory (220) may be referred to as storage.

[0078] According to an exemplary embodiment, the display (250) can output visual information to a user of the electronic device (101). When the user wears the electronic device (101), the display (250) can be arranged in front of the user's eyes. For example, the display (250) can be controlled by a processor (210) including a circuit such as a graphic processing unit (GPU) to output visualized information to the user. The display (250) can include a flexible display, a flat panel display (FPD), and / or electronic paper. The display (250) can include a liquid crystal display (LCD), a plasma display panel (PDP), and / or one or more light emitting diodes (LEDs). The LEDs can include organic LEDs (OLEDs). The embodiment is not limited thereto, and for example, if the electronic device (101) includes a lens for transmitting external light (or ambient light), the display (250) may include a projector (or projection assembly) for projecting light onto the lens. The display (250) may also be referred to as a display panel and / or a display module. When a user wears the electronic device (101), pixels included in the display (250) may be arranged to face one of the user's two eyes. For example, the display (250) may include display areas (or active areas) corresponding to each of the user's two eyes.

[0079] According to an exemplary embodiment, the camera (230) may include one or more optical sensors (e.g., a charged coupled device (CCD) sensor, a complementary metal oxide semiconductor (CMOS) sensor) that generate electrical signals representing the color and / or brightness of light. The camera (230) may also be referred to as an image sensor. The plurality of optical sensors included in the camera (230) may be arranged in the form of a two-dimensional array. The camera (230) may substantially simultaneously acquire electrical signals of each of the plurality of optical sensors to generate two-dimensional frame data corresponding to light reaching the optical sensors of the two-dimensional array. For example, photographic data captured using the camera (230) may mean one (a) two-dimensional frame data acquired from the camera (230). For example, video data captured using a camera (230) may refer to a sequence of a plurality of two-dimensional frame data acquired from the camera (230) according to a frame rate. The camera (230) may be positioned toward the direction in which the camera (230) receives light and may further include a flash light for outputting light toward the direction.

[0080] For example, the camera (230) may be positioned toward the external environment of a user wearing the electronic device (101). The camera (230) may be positioned toward the external environment within the electronic device (101) to capture the external environment. The processor (210) may identify one or more objects using images and / or videos acquired from the camera (230). For example, the processor (210) may be configured to identify one or more objects located within the external environment based on images and / or videos acquired from the camera (230).

[0081] According to an exemplary embodiment, the electronic device (101) may include a plurality of cameras positioned toward different directions. For example, the electronic device (101) may include a gaze tracking camera. The gaze tracking camera may be positioned toward at least one of the two eyes of a user wearing the electronic device (101). The processor (210) may identify the direction of the user's gaze using images and / or videos acquired from the gaze tracking camera. The gaze tracking camera (230) may include an infrared (IR) sensor. The gaze tracking camera (230) may also be referred to as an eye sensor, a gaze tracker, and / or an eye tracker.

[0082] According to an exemplary embodiment, the sensor (240) may generate electrical information that may be processed and / or stored by the processor (210) from non-electronic information related to the electronic device (101) and / or a user of the electronic device (101). The sensor (240) may include a global positioning system (GPS) sensor for detecting a geographic location of the electronic device (101), an audio sensor (e.g., a microphone and / or a microphone array including multiple microphones), an ambient light sensor, an inertial measurement unit (IMU) (e.g., an acceleration sensor, a gyro sensor, and / or a geomagnetic sensor), and / or a time-of-flight (ToF) sensor (or a ToF camera).

[0083] According to an exemplary embodiment, the communication circuit (260) may include circuitry for supporting transmission and / or reception of electrical signals between the electronic device (101) and an external electronic device. The communication circuit (260) may include, for example, at least one of a modem (MODEM), an antenna, and an optical / electronic (O / E) converter. The communication circuit (260) may support transmission and / or reception of electrical signals based on various types of protocols, such as Ethernet, a local area network (LAN), a wide area network (WAN), wireless fidelity (WiFi), Bluetooth, Bluetooth low energy (BLE), ZigBee, long term evolution (LTE), 5G new radio (NR), 6G and / or above-6G. In one embodiment, the communication circuit (260) may be referred to as a communication processor and / or a communication module.

[0084] According to an exemplary embodiment, instructions representing data to be processed, calculations to be performed, and / or operations to be performed by the processor (210) may be stored within the memory (220). A set of instructions may be referred to as a program, firmware, an operating system, a process, a routine, a sub-routine, and / or a software application (hereinafter, “application”). For example, the electronic device (101) and / or the processor (210) may perform at least one of the operations of FIG. 3, FIG. 5, FIG. 7, and / or FIG. 15b when a set of a plurality of instructions distributed in the form of an operating system, firmware, driver, program, and / or application is executed. That an application is installed in an electronic device (101) may mean that instructions provided in the form of an application are stored in a memory (220), and that the applications are stored in a format executable by the processor (210) (e.g., a file with an extension specified by the operating system of the electronic device (101)). For example, the application may include a program and / or a library related to a service provided to a user.

[0085] Referring to FIG. 2, programs installed in an electronic device (101) may be included in any one of different layers, including a framework layer (220a) and an application layer (220b), based on the target. The layers illustrated in FIG. 2 are logically (or for convenience of explanation) separated and may not mean that the address space of the memory (220) is separated by the layers.

[0086] According to an exemplary embodiment, the framework layer (220a) may include programs (e.g., a first application (221) and / or a second application (222)) designed to target at least one of the hardware (e.g., a camera (230), a sensor (240), a memory (220), a processor (210), a display (250), and / or a communication circuit (260)) of the electronic device (101) and / or the application layer (220b). The programs included in the framework layer (220a) may provide an API (application programming interface) that is executable (or callable) based on another program.

[0087] An electronic device (101) according to an exemplary embodiment may be configured to provide a prompt (e.g., a first prompt) for generating another content (e.g., a fourth content) corresponding to a content (e.g., a first content). The first prompt, when input to a generative artificial intelligence model, may be referred to as a prompt for generating the first content. Since the generative artificial intelligence model has a black box structure whose internal operations are difficult to understand, it may be difficult to estimate the first prompt for obtaining the fourth content that is substantially identical to the first content. The electronic device (101) may be configured to provide the first prompt corresponding to the first content by executing instructions stored in a memory (220). The instructions may be included in a first application (221) and a second application (222).

[0088] According to an exemplary embodiment, the first application (221) may be used to estimate the original content of the content (e.g., the first content) and to generate a description of the original content. For example, the first application (221) may include a style detection unit (221a), an original estimation unit (221b), a component detection unit (221c), and / or a scene analysis unit (221d). The style detection unit (221a), the original estimation unit (221b), the component detection unit (221c), and / or the scene analysis unit (221d) may be a set of instructions or codes, instructions / codes or a storage space storing instructions / codes that are at least temporarily resided in the processor (210), or may be a part of the circuitry constituting the processor (210).

[0089] According to an exemplary embodiment, the style detection unit (221a) may be instructions or code for analyzing the style of the first content. For example, the style detection unit (221a) may be used to identify whether the first content is a real-life content (e.g., a landscape photograph) or not a real-life content (e.g., an illustration).

[0090] According to an exemplary embodiment, the original estimation unit (221b) may be used to estimate the original content of the first content from which the style detected by the style detection unit (221a) has been removed. For example, the original content may be estimated by removing the style resulting from the post-processing of the first content after capturing the image.

[0091] According to an exemplary embodiment, the component detection unit (221c) may be used to analyze original content. For example, the component detection unit (221c), when executed by the processor (210), may analyze the original content by interpreting objects and / or scenes included in the original content. For example, the component detection unit (221c), when executed by the processor (210), may analyze the original content by utilizing an analysis tool such as semantic segmentation. As a result of the analysis of the original content, attribute information may be extracted.

[0092] According to an exemplary embodiment, the scene analysis unit (221d) may be used to generate a description corresponding to a comprehensive explanation of the first content based on the first content, the original content, and the analysis results (e.g., attribute information) of the original content. The description may be used as a seed prompt to be input into a large language model (LLM) via the second application (222).

[0093] According to an exemplary embodiment, the second application (222) may be used to extract a prompt (e.g., a first prompt) from the original content and generate a fourth content corresponding to the first content. The fourth content may be referred to as content that is substantially the same as the first content or content that has a similarity greater than a threshold value. For example, the second application (222) may include a prompt extraction unit (222a), a content generation unit (222b), a prompt update unit (222c), and / or a prompt mapping unit (222d). The prompt extraction unit (222a), the content generation unit (222b), the prompt update unit (222c), and / or the prompt mapping unit (222d) may be stored in the memory (220) as a set of instructions or code.

[0094] According to an exemplary embodiment, the prompt extraction unit (222a) may be used to extract a first prompt based on a description generated by the first application (221). For example, the first prompt may be obtained by inputting a prompt based on the description into a large-scale language model.

[0095] According to an exemplary embodiment, the content generation unit (222b) may be used to obtain fourth content. For example, when executed by the processor (210), the content generation unit (222b) may generate the fourth content by inputting the first prompt and / or original content into a generative artificial intelligence model.

[0096] According to an exemplary embodiment, the prompt update unit (222c) may be used to update the first prompt based on the result of comparing the first content with the fourth content. For example, the prompt update unit (222c), when executed by the processor (210), may modify the first prompt so as to increase the similarity between the first content and the fourth content.

[0097] According to an exemplary embodiment, the prompt mapping unit (222d) may be utilized to manage and tune up the first prompt. For example, the prompt mapping unit (222d) may tune up the first prompt so that, when executed by the processor (210), substantially the same result can be output even when the first prompt is input to various generative artificial intelligence models.

[0098] For example, a program designed to target users of the electronic device (101) may be included within the application layer (220b). Programs included in the application layer (220b) (e.g., a third application (223)) may call an application programming interface (API) to cause execution of functions supported by programs classified into the framework layer (220a). For example, the third application (223) may include a screen control unit (223a), a user input unit (223b), a content generation control unit (223c), a content playback unit (223d), and / or a prompt management unit (223e). The screen control unit (223a), gesture recognition unit (223b), content generation control unit (223c), content playback unit (223d), and / or prompt management unit (223e) may be a set of instructions or codes, or a storage space storing instructions / codes that are at least temporarily resident in the processor (210), or may be part of the circuitry constituting the processor (210).

[0099] According to an exemplary embodiment, the screen control unit (223a) may be used to control a user interface (UI) for extracting a prompt and to control the operations of the first application (221) and the second application (222). The gesture recognition unit (223b) may be used to identify a user input by identifying and analyzing a senseable user gesture, such as a user's hand gesture or head gesture. The content generation control unit (223c) may be used to provide a UI for extracting a first prompt from the first content. The content playback unit (223d) may be used to display content (e.g., images and / or photos) through the display (250). The prompt management unit (223e) may be used to record the history of the list of first prompts and to manage tuned-up prompts.

[0100] The components within the first application (221), second application (222), and / or third application (223) described above are merely exemplary and are not limited thereto. Each of the components described above may cause an operation of the electronic device (101) described below. In the present disclosure, visual objects may be described as examples of UI. A visual object may refer to an object that can be deployed within a screen for transmitting and / or interacting with information, such as text, images, icons, videos, buttons, checkboxes, text boxes, sliders, and / or tables. A visual object may be referred to as a visual guide, a virtual object, a visual element, a UI element, a view object, and / or a view element. The wearable device may provide the user with functions available within a virtual space based on the execution of the XR system UI.

[0101] An electronic device according to an exemplary embodiment may provide a function capable of extracting a first prompt from first content and modifying second content based on at least a portion of the extracted first prompt. The modified second content may be referred to as third content. The first prompt may be a prompt that can generate second content corresponding to the first content by a generative artificial intelligence model, and may be extracted by the operations described in FIGS. 5 and 7. By applying the first prompt to the second content, third content reflecting the style of the first content may be provided. Hereinafter, operations of the electronic device according to an exemplary embodiment will be described.

[0102] Figure 3 is a flow chart showing an operation of an exemplary electronic device to generate third content.

[0103] The processor (210) of FIG. 2 can perform operations of an electronic device (e.g., the electronic device (101) of FIG. 2) described with reference to FIG. 3. Instructions stored in a memory (e.g., the memory (220) of FIG. 2) can, when executed by the processor (210), cause the electronic device (101) to perform operations of the electronic device (101) described in FIG. 3.

[0104] Referring to FIG. 3, in operation 301, the processor (210) may be configured to extract a first prompt (e.g., the first prompt (451) of FIG. 4b) corresponding to the first content from the first content while the first content (e.g., the first content (461) of FIG. 4b) is displayed through a display (e.g., the display (250) of FIG. 2).

[0105] According to an exemplary embodiment, the electronic device (101) may be referred to as a wearable device. The electronic device (101) may display first content through the display (250). For example, the processor (210) may display the first content based on a user input requesting the execution of software (e.g., gallery software) for displaying one or more contents. The first content may include, but is not limited to, an image and / or a video. The processor (210) may be configured to extract a first prompt corresponding to the first content while the first content is displayed. The first content may be referred to as source content for extracting the first prompt. If the electronic device (101) is a device such as a smart phone, rather than a wearable device, the first content may be referred to as content stored in the memory (220) of the electronic device (101). For example, the first content may include images and / or videos taken by the user using the electronic device (101).

[0106] According to an exemplary embodiment, the second content (e.g., the second content (462) of FIG. 4B) may be referenced as target content to which one or more properties of the first content are applied. The one or more properties of the first content may include various elements that may cause an aesthetic impression associated with the first content, such as the style, effect, and / or style of the first content. The prompt may be natural language or content to indicate content to be output from the generative artificial intelligence model, and may be used to set a goal of the generative artificial intelligence model. According to an exemplary embodiment, the first prompt may be referenced as an input sentence including natural language or a set of feature keywords, as a prompt to output content (e.g., fourth content) that is substantially the same as the first content when input to the generative artificial intelligence model. An operation of the electronic device (101) extracting the first prompt from the first content will be described below with reference to FIGS. 5 and 7. The screens corresponding to operation 301 may be referred to as the screens illustrated in FIG. 4a (e.g., the first screen (400a) of FIG. 4a). A detailed example of operation 301 is described below with reference to FIG. 4a.

[0107] In operation 302, the processor (210) may be configured to receive a first user input for selecting one or more words included within the first prompt.

[0108] According to an exemplary embodiment, the processor (210) may be configured to display the extracted first prompt through the display (250) to receive a first user input for selecting one or more words included in the first prompt. For example, the first prompt corresponding to the first content may include one or more words in natural language. Alternatively, the first prompt may be a set of feature keywords. The one or more words may be displayed through the display (250). The one or more words may correspond to properties of the first content. The user may confirm the first prompt displayed through the display (250) and provide a first user input to select one or more words included in the first prompt. The processor (210) may receive the first user input.

[0109] In operation 303, the processor (210) may be configured to identify one or more words based on receipt of a first user input.

[0110] According to an exemplary embodiment, the processor (210) may receive a first user input for a first prompt including one or more words displayed through the display (250), and identify one or more words based on the reception of the first user input. For example, the user may provide the first user input to select one or more words, from among the one or more words included in the first prompt, that correspond to attributes to be applied to second content, which is target content. The processor (210) may identify the one or more words corresponding to the first user input by identifying the first user input for the one or more words. According to an exemplary embodiment, the processor (210) may control the display (250) to provide a visual effect indicating the one or more words corresponding to the first user input to indicate that the first user input for the one or more words selected by the first user input has been identified.

[0111] For example, assuming that the first content is a beach scene with a sunrise in the background and is a real-world content characterized by the contrast between clouds and the sky around the sun, the first prompt may be a natural language such as “Generate a real-world photo including a beach with a sunrise in the background, and emphasize the contrast between the clouds around the rising sun and the sky.” The first prompt may include words such as “sunrise,” “beach,” “sky,” “cloud,” and “contrast.” Alternatively, the first prompt may be a set of characteristic keywords of the first content. The first prompt may be a set including keywords such as “realistic,” “dynamic contrast,” “sun rising,” “sea shore,” or “sun oriented.” The processor (210) may display the first prompt through the display (250) while the first content is displayed through the display (250). When a first user input is provided for at least one of the words included in the first prompt, the processor (210) may identify the words for which the first user input is provided. For example, when a user provides a first user input for the word “contrast,” the processor (210) may identify the word “contrast” based on the reception of the first user input for “contrast.” To indicate that the processor (210) has identified the first user input for the word “contrast,” the display (250) may be controlled to provide a visual effect for the word “contrast” that distinguishes it from other words. For example, the visual effect may include a color change for the word “contrast,” an underline, and / or a visual object displaying the word “contrast.” The screen corresponding to operations 302 and 303 may be referred to as the screen illustrated in FIG. 4B (e.g., the second screen (400b) of FIG. 4B).Detailed examples of actions 302 and 303 are described below with reference to FIG. 4b.

[0112] In operation 304, the processor (210) may be configured to receive a second user input to generate a third content (e.g., the third content (463) of FIG. 4e) modified from the second content using one or more words.

[0113] According to an exemplary embodiment, the processor (210) may receive a second user input for generating third content using one or more words selected by the first user input to which an effect indicated by the one or more selected words has been applied. Within the present disclosure, the third content may be referred to as content in which the second content has been corrected by applying the effect indicated by the one or more selected words to the second content. For example, the user may provide a second user input to apply the one or more words selected by the first user input to the second content.

[0114] According to an exemplary embodiment, the processor (210) may be configured to detect a hand gesture detected by a user's hand using a camera (e.g., camera (230) of FIG. 2). When the user makes a hand gesture corresponding to a second user input, the processor (210) may, in response to identifying the hand gesture, receive a second user input. For example, the second user input may be, but is not limited to, a swipe input or a scroll input for moving one or more words selected through the first user input to an area of ​​the display (250) where the second content is located. Referring to the example described above, the user may provide the second user input by moving the word "contrast" to the second content. The screen corresponding to operation 304 may be referred to as the screen illustrated in FIG. 4c (e.g., the third screen (400c) of FIG. 4c). A detailed example of operation 304 is described below with reference to FIG. 4C. Alternatively, one or more words may be selected by a controller (404) held by a user (400). For example, the controller (404) may be a device for manipulating a virtual object (440) displayed on a screen provided to the user (400). The user (400) may also provide a second user input using the controller (404).

[0115] In operation 305, the processor (210) may be configured to generate a second prompt including one or more words based on receipt of a second user input.

[0116] According to an exemplary embodiment, the processor (210) may generate a second prompt including one or more words selected through the first user input based on the receipt of the second user input. Within the present disclosure, the second prompt may be referred to as a prompt input to a generative artificial intelligence model to generate third content that is a correction of the second content. Since the third content is generated by applying an effect indicated by the one or more words selected through the first user input, the processor (210) may generate the second prompt including the one or more words selected. Referring to the example described above, the processor (210) may generate the second prompt that can generate third content in which a "contrast" effect is applied to the second content through the generative artificial intelligence model. For example, the second prompt may be referred to as a prompt such as "Create an image by applying an effect that contrasts the contrast of an object against a background environment," but the above-described prompt is merely an example for convenience of description and is not limited thereto.

[0117] In operation 306, the processor (210) may be configured to obtain third content by inputting a second prompt into the generative artificial intelligence model.

[0118] According to an exemplary embodiment, the processor (210) may input a second prompt into a generative artificial intelligence model to obtain third content. The generative artificial intelligence model may generate new content based on user input using an unstructured deep learning model. When the prompt is input into the generative artificial intelligence model, the prompt may be converted into tokens through a text encoder, and new content may be generated by denoising randomly generated noise based on the tokens. By inputting the second prompt into the generative artificial intelligence model, the third content may be output. The processor (210) may input the second content together with the second prompt into the generative artificial intelligence model. The processor (210) may display the third content through the display (250) so that the user can confirm the third content. The user may identify the third content that has been corrected from the second content. The screen corresponding to operation 306 may be referred to as the screen illustrated in FIG. 4e (e.g., the fourth screen (400e) of FIG. 4e). A detailed example of operation 306 is described below with reference to FIG. 4e.

[0119] An electronic device (101) according to an exemplary embodiment may be configured to provide third content by applying at least a portion of the properties of a first content to a second content. To apply at least a portion of the properties of the first content to the second content, the electronic device (101) may extract a first prompt that can generate content (e.g., fourth content) that is substantially identical to the first content. The electronic device (101) may display the extracted first prompt through the display (250), thereby allowing the user to intuitively recognize the properties of the first content to be applied. The electronic device (101) may generate a second prompt based on a second user input for generating the third content, and input the second prompt into a generative artificial intelligence model, thereby providing the third content. The exemplary electronic device (101) may provide an enhanced user experience by providing variously corrected contents.

[0120] Hereinafter, examples of screens of a display (250) provided to a user when an electronic device (101) performs the operations described in FIG. 3 are described. The screens described below are merely exemplary, and the embodiments of the present disclosure are not limited thereto.

[0121] Figure 4a illustrates an exemplary screen representing user input for displaying content via a display. Figure 4b illustrates an exemplary screen representing a first user input. Figure 4c illustrates an exemplary screen representing a second user input. Figure 4d schematically illustrates a process for generating third content. Figure 4e illustrates an exemplary screen for adjusting the degree of correction.

[0122] The processor of FIG. 2 (e.g., the processor (210) of FIG. 2) can perform the operations of the electronic device (101) described with reference to FIGS. 4A to 4E. Instructions stored in a memory (e.g., the memory (220) of FIG. 2) can cause the electronic device (101) to perform the operations of the electronic device (101) illustrated in FIGS. 4A to 4E when executed by the processor (210).

[0123] Referring to FIG. 4A, the electronic device (101) can display a first screen (400a) through a display (e.g., the display (250) of FIG. 2). The first screen (400a) may be a screen provided in a see-through mode or a pass-through mode. For example, the see-through mode or the pass-through mode is a mode that provides a composite image of the external environment, and the electronic device (101) can display a composite image of the external environment on the display (250). For example, in order to express an external environment existing beyond the display (250), a processor (e.g., the processor (210) of FIG. 2) can synthesize a virtual image with a real image acquired through a camera (e.g., the camera (230) of FIG. 2) and display the composite image on the display (250). According to an exemplary embodiment, the first screen (400a) may be a screen provided within a virtual reality (VR) mode, distinct from a see-through mode or a pass-through mode. For example, the first screen (400a) provided within a VR mode may include only virtual images and not real images.

[0124] According to an exemplary embodiment, the electronic device (101) may display icons (e.g., B icon, C icon, D icon, E icon, and / or F icon) corresponding to each of a plurality of software applications installed in the electronic device (101) within the first screen (400a). The first screen (400a) is a screen for providing a list of a plurality of software applications installed in the electronic device (101) and may be referred to as a home screen and / or a launcher screen. The electronic device (101) may display a panel (420) within the first screen (400a) for providing a list of frequently executed software applications. For example, the panel (420) may be referred to as a dock. Within the panel (420), the electronic device (101) may display icons (e.g., G icon and / or H icon) representing frequently executed software applications. The electronic device (101) may display the current time and / or information related to the battery of the electronic device (101) within the panel (420). However, the present invention is not limited thereto. According to an exemplary embodiment, one or more icons may be displayed within the first screen (400a). For example, the one or more icons may be superimposed on a composite image including visual objects corresponding to objects included in the external environment (e.g., a visual object (431) corresponding to a picture of a dog and a visual object (432) corresponding to a flower pot).

[0125] According to an exemplary embodiment, the electronic device (101) may display, within the first screen (400a) of FIG. 4A, an icon (410) corresponding to a software application (e.g., a gallery application) for displaying a list of contents (e.g., images and / or videos) stored in the memory (220), together with the icons. While an embodiment in which the electronic device (101) displays an icon (410) representing the software application is described, embodiments are not limited thereto, and the electronic device (101) may also display text, images, and / or videos representing the software application.

[0126] According to an exemplary embodiment, the electronic device (101) may receive a user input for executing a gallery application. The user input may be referred to as an input for selecting an icon (410) representing the gallery application within the first screen (400a). The user input may include a hand gesture detected by the user's hand (401). For example, the electronic device (101) may acquire an image and / or video of a body part including the hand (401) of the user (400) using a camera (e.g., the camera (230) of FIG. 2). Based on detecting the hand (401) included in the image and / or video, the electronic device (101) may display a virtual object (440) corresponding to the hand (401) within the first screen (400a). The virtual object (440) may include a three-dimensional graphical object representing the posture of the hand (401). For example, the posture and / or orientation of the virtual object (440) may correspond to the posture and / or orientation of the hand (401) detected by the electronic device (101).

[0127] According to an exemplary embodiment, while displaying a virtual object (440), the electronic device (101) may display a virtual object (441) having a shape of a line extending from the virtual object (440). The virtual object (441) may be referred to as a ray, a ray object, a cursor, a pointer, and / or a pointer object. The virtual object (441) may have a shape of a line extending from a portion of the hand (401) (e.g., a palm and / or a designated finger such as the index finger). In FIG. 4A, a virtual object (441) having a curved shape is illustrated, but the embodiment is not limited thereto. The user (400) may change the position and / or direction of the virtual object (440) and / or the virtual object (441) within the first screen (400a) by moving the hand (401).

[0128] According to an exemplary embodiment, while a virtual object (441) in the form of a line is displayed in an exemplary first screen (400a) extending toward an icon (410), the electronic device (101) may detect or identify a pinch gesture of a hand (401). For example, after acquiring an image (402) of a hand (401) in which the fingertips of all fingers included in the hand (401) are spaced apart from each other, the electronic device (101) may acquire an image (403) of a hand (401) including at least two fingers in the form of a ring, in which at least two fingertips (e.g., the fingertips of the thumb and the index finger) are in contact with each other. The electronic device (101) that acquires the image (403) may detect a pinch gesture expressed by at least two fingers in the form of a ring. The duration of a pinch gesture may refer to the period of time during which the fingertips of at least two fingers of a hand (401) are in contact with each other, as in image (403). The pinch gesture may correspond to, or be mapped to, a click and / or tap gesture.

[0129] According to an exemplary embodiment, in response to a pinch gesture detected while displaying the first screen (400a), the electronic device (101) may launch a gallery application corresponding to the icon (410). While an exemplary operation of launching the gallery application using a hand gesture such as a pinch gesture is described, the embodiment is not limited thereto. For example, the electronic device (101) may also launch the gallery application in response to a user's (400) utterance (e.g., "launch the gallery"), a user's (400) gaze (e.g., tracking the user's gaze), and / or a press of a physical input button.

[0130] Referring to FIG. 4b, the processor (210) may display a list of contents (460) in a portion (450) of the second screen (400b) in response to a user input for executing a gallery application.

[0131] According to an exemplary embodiment, first content (461) and second content (462) may be simultaneously displayed within the partial region (450). The processor (210) may control a display (e.g., the display (250) of FIG. 2) so that a first prompt (451) corresponding to the first content (461), which is the source content, is displayed within the second screen (400b). For example, the processor (210) may extract the first prompt (451) in response to a user input for displaying the first prompt (451) and display the extracted first prompt (451). The operation of the processor (210) extracting the first prompt (451) from the first content (461) is described below with reference to FIGS. 5 and 7.

[0132] According to an exemplary embodiment, the processor (210) may receive a first user input for receiving user input for one or more words (452) included in the first prompt (451). For example, the user (400) may provide the first user input for one or more words (452) included in the first prompt (451) to select an attribute to be applied to the second content (462) via a gesture of a hand (401), such as a pinch gesture. The processor (210) may receive the first user input for the one or more words (452). For example, within a state where a virtual object (440) corresponding to a hand (401) is moved to at least partially overlap one or more words (452), the processor (210) may identify a first user input for the one or more words (452) based on identifying a gesture of the hand (401).

[0133] For example, the first prompt (451) corresponding to the first content (461) may be a natural language such as "I want to create a romantic couple or rabbits on the mood and in Van Gogh style and pastel colors Fantasy, coloring book style, pastel pencils, colorlessness." The processor (210) may control the display (250) so that the first prompt (451) is displayed in the second screen (400b). The processor (210) may control the display (250) so that a visual effect representing one or more words (452) corresponding to the first user input is provided based on receiving a first user input for one or more words (452) included in the first prompt (451). For example, if a first user input for “colorlessness” is received within the first prompt (451), the processor (210) may change the color of “colorlessness”, underline it, and / or provide a separate visual object (453) to display “colorlessness” so that the “colorlessness” can be distinguished from other words. However, the present invention is not limited thereto. The user (400) may distinguish one or more selected words (452) within the first prompt (451) through the visual effect.

[0134] Referring to FIG. 4C, the processor (210) may receive a second user input for applying one or more words (452) within the first prompt (451) to the second content (462). For example, the user (400) may provide the second user input to reflect one or more words (452) corresponding to each of one or more attributes of the first content (461) to the second content (462) for application to the second content (e.g., the second content (462) of FIG. 4B).

[0135] Referring to FIGS. 4C and 4D , the processor (210) may generate a second prompt (454) based on receipt of a second user input, and input the second prompt (454) into a generative artificial intelligence model (470), thereby obtaining third content (463). The processor (210) may display the third content (463) on a screen (e.g., the fourth screen (400d) of FIG. 4E) displayed through a display (e.g., the display (250) of FIG. 2). The user (400) may check the third content (463) displayed on the screen. For example, the processor (210) may input the second content (462) together with the second prompt (454) into the generative artificial intelligence model (470) to obtain the third content (463). The generative artificial intelligence model (470) may include an input layer (input later) (471), one or more hidden layers (472) (or intermediate layers) and output layers (473). The layers (e.g., the input layer (471), one or more hidden layers (472) and the output layer (473)) may include a plurality of nodes. The number of the one or more hidden layers (472) may vary depending on the embodiment, and the generative artificial intelligence model (470) may be referred to as a deep neural network including a plurality of hidden layers. The generative artificial intelligence model (470) may include, but is not limited to, generative adversarial networks (GAN), auto encoders (AE), variational autoencoders (VAE), diffusion models (DM), latent diffusion models (LDM), and layout diffusion models, or combinations thereof.The generative artificial intelligence model (470) may be included within the electronic device (101) or may be included within an external electronic device (e.g., a server).

[0136] For example, the user (400) may provide a drag gesture within the first prompt (451) to drag “colorlessness” to the second content (462) to apply “colorlessness” to the second content (462). For example, the second user input to apply “colorlessness” to the second content (462) may be performed in such a way that a virtual object (440) corresponding to the hand (401) moves to the second content (462) together with the word “colorlessness.” The processor (210) may generate a second prompt (454) including “colorlessness” and input the second prompt (454) into the generative artificial intelligence model (470) to obtain the third content (463). The processor (210) may input the second content (462) together with the second prompt (454) into the generative artificial intelligence model (470) to obtain the third content (463). As illustrated in FIG. 4E , the third content (463) output based on the second prompt (454) including "colorlessness" may be content in which the "colorlessness" attribute is reflected in the second content (462). For example, when comparing the second content (462) illustrated in FIG. 4B with the third content (463) illustrated in FIG. 4E , the effect of color removal can be confirmed. In addition, various embodiments may be possible. According to an exemplary embodiment, a user (400) can intuitively recognize attributes for third content (463) and, through simple user input (e.g., first user input and second user input), reflect one or more words (452) in a first prompt (451) into second content (462).

[0137] Referring to FIG. 4e, the exemplary electronic device (101) may be configured to provide a function for adjusting the degree of an attribute reflected in the third content (463). According to an exemplary embodiment, the fourth screen (400d) may be referred to as a screen in which a virtual object (480) for providing the degree of correction is provided.

[0138] According to an exemplary embodiment, the processor (210) may control a display (e.g., the display (250) of FIG. 2) to display a virtual object (480) for adjusting the degree of an attribute reflected in the second content (462) based on a user input. As the degree of an attribute to be reflected in the second content (462) is adjusted, the degree of correction may be adjusted. For example, the display (250) may display a virtual object (480) for receiving a user input within a portion (450) of the fourth screen (400d). The virtual object (480) may include, but is not limited to, a slider (481), an indicator (482), and / or a correction value (483).

[0139] For example, when a user input for moving the indicator (482) in a first direction (D1) is received, the processor (210) may decrease the degree of the attribute reflected in the second content (462). By the decrease, the degree of correction of the third content (463) may be decreased. For example, when a user input for moving the indicator (482) in a second direction (D2) opposite to the first direction (D1) is received, the processor (210) may increase the degree of the attribute reflected in the second content (462). By the increase, the degree of correction of the third content (463) may be increased. For example, the correction value (483) may be expressed as a number from 0 to 100, but is not limited thereto. The operation of increasing or decreasing the degree of the attribute may be performed by reflecting the degree of the attribute identified according to the user input in the second prompt. User input can be provided by a drag gesture in which a virtual object (440) corresponding to the hand (401) of the user (400) drags an indicator (482).

[0140] As described with reference to FIGS. 4A to 4E, the exemplary electronic device (101) can correct the second content (462) into the third content (463) based on the first prompt that can generate the first content (461) by the generative artificial intelligence model. The electronic device (101) can provide the first prompt (451) corresponding to the first content (461) in order to reflect one or more properties included in the first content (461) to the second content (462). In order for one or more properties included in the first content (461) to be accurately reflected in the second content (462), the first prompt (451) extracted from the first content (461) may be required to be a prompt that can generate content that is substantially the same as the first content (461). In the above-described embodiments, a wearable device has been described as an example of the electronic device (101), but the electronic device (101) is not limited to a wearable device. For example, the screens illustrated in FIGS. 4A, 4B, 4C, and 4E may be screens provided by a device such as a smartphone, tablet, or computer. The user input described above may be replaced with a touch input on the screen. Hereinafter, operations of the electronic device (101) for extracting a first prompt (451) from first content (461) are described.

[0141] Figure 5 is a flowchart illustrating the operations of an exemplary electronic device for generating a description of first content. Figure 6 illustrates exemplary operations for analyzing the original content of the first content.

[0142] The processor of FIG. 2 (e.g., the processor (210) of FIG. 2) can perform operations of the electronic device (101) described with reference to FIG. 5. Instructions stored in a memory (e.g., the memory (220) of FIG. 2) can cause the electronic device (101) to perform operations of the electronic device (101) described in FIG. 5 when executed by the processor (210). For example, the operations described in FIG. 5 can be referred to as operations caused by the execution of a first application (e.g., the first application (221) of FIG. 2).

[0143] In an exemplary embodiment, analysis of the original content of the first content may be required to extract the first prompt. When the first prompt extracted based on the original content of the first content is input into a generative artificial intelligence model, content substantially identical to the first content may be output. For example, if the first content is an image that has been corrected through a post-processing process, the original image before correction is restored, and the first prompt is extracted based on the original image, thereby enabling the extraction of an accurate prompt. For example, if the first content is a landscape photograph taken at a specific location that has been corrected in the style of Van Gogh, the Van Gogh effect may be removed to restore the original landscape photograph, and then the first prompt may be extracted to provide an accurate first prompt.

[0144] Referring to FIG. 5, in operation 501, the processor (210) may be configured to identify a style of the first content.

[0145] In an exemplary embodiment, style analysis of the first content may be required for extracting the first prompt. Style analysis may be referred to as analyzing whether the first content is photorealistic. For example, the processor (210) may identify whether the first content is photorealistic (e.g., a landscape photograph) or non-photorealistic content that reflects a specific style. For example, first content with an illustrative style may be identified as non-photorealistic.

[0146] In operation 502, the processor may be configured to identify whether the first content is real-world content.

[0147] According to an exemplary embodiment, if the first content is real content, the first content can be analyzed immediately. Conversely, if the first content is not real content, the analysis of the first content may be difficult. For example, if the first content is in an illustrative style, objective analysis of the first content may be difficult because the unique illustrative style is reflected in the first content. If the first content is not real content, operation 504 may be performed after operation 503. If the first content is real content, operation 504 may be performed.

[0148] In operation 503, the processor (210) may be configured to change the style of the first content to the style of the real content.

[0149] According to an exemplary embodiment, the processor (210) may change the style of the first content to the style of the real content based on identifying the first content as not being a real content. For example, if the first content is an illustration style, the processor (210) may change the style of the first content to the style of the real content by removing the illustration style. The processor (210) may use an artificial intelligence model trained to transfer the style of the illustration to change the style of the first content to the style of the real content. As the style of the first content, which is an illustration, is changed to a real content, the first content may be changed to content having realism. For example, if the illustration includes an image of an animal, the first content may be changed to content including an actual animal similar to the image of the animal.

[0150] According to an exemplary embodiment, operations 502 and 503 may be optionally performed. For example, if the original content of the first content is a creative work, the operation of converting the first content into the style of the real content may be omitted. In the case of a creative work, since the real content does not exist, operation 504 of obtaining the original content of the real content may be performed without converting the creative work into the style of the real content.

[0151] In operation 504, the processor (210) may be configured to obtain original content of the first content.

[0152] According to an exemplary embodiment, the processor (210) may be configured to obtain original content from first content that is real content or first content that has been modified to have the style of the real content. For example, if the first content is an image captured using a camera application to which a filter for displaying a specific visual effect has been applied, the processor (210) may be configured to obtain the original content by removing the visual effect. For example, the processor (210) may be configured to obtain the original content of the first content using an artificial intelligence model trained to remove the style. The operations 501, 502, and 503 described above may be referred to as operations for operation 504 for estimating the original content.

[0153] In operation 505, the processor (210) may be configured to analyze the original content.

[0154] According to an exemplary embodiment, the processor (210) may analyze the original content to generate a description corresponding to a comprehensive description of the original content. The analysis of the original content may be performed through processes such as object analysis contained within the original content, scene interpretation of the original content, and / or semantic segmentation.

[0155] Referring to FIG. 6, the operation of a processor (e.g., processor (210) of FIG. 2) that analyzes original content (601) is diagrammed. 602 of FIG. 6 represents a feature encoding process for the original content (601). The processor (210) can extract features within the original content (601). For example, the processor (210) can be configured to digitize pixel values ​​(e.g., RGB values ​​or luminance histograms) of the original content (601) or to extract features using a convolutional neural network (CNN) or a recurrent neural network (RNN) trained to extract features of the original content (601). The extracted features can be used to understand the meaning of the original content (601).

[0156] 603 of FIG. 6 represents a process for detecting an object (610) within original content (601). The processor (210) can obtain information such as color, texture, and shape based on features extracted from the original content (601). The processor (210) can preprocess the original content (601) to remove noise, classify the class of the object (610) included in the original content (601) based on the extracted features, and generate a bounding box to indicate the boundary of the classified object (610). For example, the processor (210) can detect a car (611), a cloud (612), a streetlight (613), and / or a tree (614) included in the original content (601). For example, the processor (210) may use an object detection model or a class classification model to detect an object (610), but is not limited thereto.

[0157] 604 of FIG. 6 represents a segmentation mask of the original content (601). For example, the processor (210) may obtain the segmentation mask of the original content (601) using an artificial intelligence model. The processor (210) may obtain the segmentation mask by assigning a specific label to each pixel included in the original content (601). For example, the processor (210) may assign a first label to first pixels (621) corresponding to a car included in the original content (601), and may assign a second label to second pixels (622) corresponding to a road distinct from the car. Operations for analyzing the original content (601) are not limited to the examples described above, and may also vary.

[0158] According to an exemplary embodiment, the processor (210) may analyze the original content (601) through the processes described above. The processor (210) may analyze the original content (601) through processes such as latent vectors, which are variables in the form of potential vectors of the original content (601), a latent space formed by the latent vectors, a scene description, analysis of the location and type of an object (610) within a region of interest (ROI), a semantic segmentation process for classifying pixels, and / or style or color transition.

[0159] Referring again to FIG. 5, at operation 506, the processor (210) may be configured to generate a description representing the original content based on the analysis of the original content.

[0160] According to an exemplary embodiment, the processor (210) may be configured to generate a description that comprehensively interprets the original content based on the analysis of the original content. For example, the description may include natural language representing information such as the style of the original content and objects included in the original content. The processor (210) may store the generated description in a memory (e.g., the memory (220) of FIG. 2 ). According to an exemplary embodiment, if the first content is a creative work, the description may include a description regarding the style of the creative work. For example, so that the unique style of the creator reflected in the creative work can be reflected, the description may include a description indicating the unique style.

[0161] According to an exemplary embodiment, the description of the original content generated through the operations described in FIG. 5 may be used as a seed prompt for generating a first prompt. For example, when a second application (e.g., the second application (222) of FIG. 2 ) is executed by the processor (210), the description may be input into a large-scale language model, thereby outputting the first prompt.

[0162] Below, the operations for extracting the first prompt using the above description are described.

[0163] Figure 7 is a flowchart illustrating the operations of an exemplary electronic device for extracting and updating a first prompt. Figure 8 illustrates operations for updating the first prompt. Figure 9 is a diagram illustrating a tuned-up first prompt.

[0164] The processor of FIG. 2 (e.g., the processor (210) of FIG. 2) can perform operations of the electronic device (101) described with reference to FIG. 7. Instructions stored in a memory (e.g., the memory (220) of FIG. 2) can cause the electronic device (101) to perform operations of the electronic device (101) described in FIG. 7 when executed by the processor (210). For example, the operations described in FIG. 7 can be referred to as operations caused by the execution of a second application (e.g., the second application (222) of FIG. 2).

[0165] Referring to FIG. 7, in operation 701, the processor (210) may be configured to obtain a first prompt corresponding to the first content by inputting a prompt based on a description of the original content into a large-scale language model.

[0166] According to an exemplary embodiment, the processor (210) may obtain a prompt based on a description. The description may be referred to as a description generated by the operations described in FIG. 5 . Since the description is a description obtained by analyzing the original content of the first content, when the prompt is input into a large-scale language model, a first prompt corresponding to the first content may be output. The large-scale language model is an artificial intelligence model trained with text data and may be used to obtain a prompt based on the description. For example, the processor (210) may obtain the first prompt by converting a description that comprehensively interprets the original content of the first content into a format that can be input into the large-scale language model and inputting the converted description into the large-scale language model.

[0167] In operation 702, the processor (210) may be configured to obtain fourth content by inputting the first prompt into the generative artificial intelligence model.

[0168] According to an exemplary embodiment, the fourth content may be referred to as content obtained by inputting the first prompt into the generative artificial intelligence model. The processor (210) may obtain the fourth content by inputting the first prompt corresponding to the first content into the generative artificial intelligence model. In order to obtain the fourth content, the processor (210) may input the first content or the original content of the first content into the generative artificial intelligence model together with the first prompt. Since the fourth content is generated by inputting the first prompt corresponding to the first content, it may be content similar to the first content.

[0169] In operation 703, the processor (210) may be configured to identify the similarity between the first content and the fourth content.

[0170] According to an exemplary embodiment, the processor (210) may identify similarity by comparing the first content and the fourth content. For example, the processor (210) may identify similarity by extracting first features of the first content and second features of the second content, and quantifying the similarity between the first features and the second features. For example, the similarity may be identified by quantifying pixel values ​​of pixels included in the first content and the fourth content, and comparing the pixel values. However, the present invention is not limited thereto. For example, the processor (210) may also identify similarity between the first content and the second content by using an artificial intelligence model trained to analyze the similarity of content. The similarity may be obtained as a quantified value.

[0171] In operation 704, the processor (210) may be configured to compare the similarity to a threshold value.

[0172] According to an exemplary embodiment, a threshold value for determining that the fourth content is substantially identical to the first content may be preset. For example, if the threshold value is set such that the fourth content is determined to be substantially identical to the first content when the similarity between the first content and the fourth content exceeds about 95%, the threshold value may be about 95%. The processor (210) may determine that the fourth content obtained through the generative artificial intelligence model is substantially identical to the first content based on identifying a similarity exceeding about 95%. The processor (210) may determine that the fourth content obtained through the generative artificial intelligence model is not substantially identical to the first content based on identifying a similarity of less than about 95%.

[0173] According to an exemplary embodiment, the processor (210) may identify whether the first prompt corresponds to the first content based on the similarity between the first content and the fourth content. For example, if the similarity exceeds a threshold value, the fourth content may be determined to be substantially the same content as the first content, and thus the processor (210) may determine that the first prompt used to generate the fourth content corresponds to the first content. For example, if the similarity is less than or equal to the threshold value, the fourth content may not be determined to be substantially the same content as the first content, and thus the processor (210) may determine that the first prompt used to generate the fourth content does not correspond to the first content. If a similarity less than or equal to the threshold value is identified, operation 705 may be performed. If a similarity greater than or equal to the threshold value is identified, operation 706 may be performed. Within this disclosure, expressions such as "more than" or "less than" may be used to determine whether a specific condition is satisfied or fulfilled. However, these are merely illustrative and do not exclude expressions such as "less than" or "more than." For example, a condition described as "more than" may be replaced with "more than." For example, a condition described as "less than" may be replaced with "less than."

[0174] At operation 705, the processor (210) may be configured to update the first prompt so as to increase the similarity.

[0175] According to an exemplary embodiment, the processor (210) may update the first prompt to increase the similarity between the first content and the fourth content based on identifying a similarity below a threshold value.

[0176] Referring to FIG. 8, input data (810) input to a generative artificial intelligence model (820) may include, but is not limited to, a first prompt (811), a semantic map (812) for the first content and / or the original content, text (813) for describing the first content and / or the original content, the first content and / or the original content (814), and a latent space vector (815) of the first content and / or the original content. By inputting the input data (810) to the generative artificial intelligence model (820), a fourth content may be output. Similarity may be analyzed by comparing the first content and the fourth content. For example, a processor (e.g., processor (210) of FIG. 2) may analyze the similarity by calculating an error between the first content and the fourth content using an artificial intelligence model (830), and update the first prompt (811) based on the analysis result. The first prompt (811) may be replaced with the updated first prompt, input again into the generative artificial intelligence model (820), and a new fourth content based on the updated first prompt may be regenerated.

[0177] Referring back to FIG. 7, the processor (210) can update the first prompt (811) by repeating operations 702, 703, 704, and 705 until the similarity exceeds a threshold value. By inputting the updated first prompt through operation 705 into the generative artificial intelligence model, a new fourth content is obtained (operation 702), the similarity between the first content and the new fourth content is identified (operation 703), and the identified similarity can be compared with a threshold value (operation 704).

[0178] At operation 706, the processor (210) may be configured to confirm a first prompt.

[0179] According to an exemplary embodiment, the processor (210) may determine the first prompt based on identifying a similarity exceeding a threshold value. For example, if the similarity between the first content and the fourth content exceeds approximately 95%, the processor (210) may determine the first prompt used to generate the fourth content. Since the determined first prompt may be used to generate the fourth content having a similarity exceeding the threshold value, it may be determined to be a prompt corresponding to the first content.

[0180] An exemplary electronic device (101) may provide a tuned-up first prompt. Referring to FIG. 9, the electronic device (e.g., the electronic device (101) of FIG. 2) may include a database (910) for storing tune-up information of the first prompt. The tune-up information may be referenced as information that enables the generation of content substantially identical to the first content, even when the first prompt is input into various generative artificial intelligence models.

[0181] For example, when the first prompt is input to various artificial intelligence models (920) that are different from the generative artificial intelligence model used to extract the first prompt, content substantially identical to the first content may not be output due to different internal algorithms of each of the other generative artificial intelligence models (920). The electronic device (101) may store tune-up information mapped to each of the various artificial intelligence models (920) in the database (910) so that substantially identical results can be obtained when the first prompt is input to other generative artificial intelligence models (920).

[0182] For example, the results output when a specific word (e.g., A) is input into the first artificial intelligence model (921) and the results output when the specific word (A) is input into the second artificial intelligence model (922) or the third artificial intelligence model (923) may not be substantially the same. The electronic device (101) may acquire tune-up information about another word (e.g., A') to be replaced with the specific word (A) to suit the characteristics of the second artificial intelligence model (922) or the third artificial intelligence model (923) in order to obtain substantially the same results through the second artificial intelligence model (922) or the third artificial intelligence model (923). When the electronic device (101) uses the first artificial intelligence model (921), the specific word (A) may be input, and when the second artificial intelligence model (922) or the third artificial intelligence model (923) is used, the specific word (A) may be replaced with another word (A') and input. An exemplary electronic device (101) may provide a prompt mapped to an artificial intelligence model to be used based on tune-up information stored within a database (910).

[0183] An exemplary electronic device can extract a first prompt from first content by performing the operations described in FIGS. 5 and 7. Since the extracted first prompt is a prompt used to generate content substantially identical to the first content, a prompt that is difficult to identify due to the black box structure of a generative artificial intelligence model can be clearly identified. Referring to the second screen (400b) illustrated in FIG. 4b, the electronic device (101) displays the first prompt (451) extracted from the first content (461), thereby allowing the user (400) to select at least one word (452) within the first prompt (451). Since one or more words (452) to be applied to the second content (462) can be provided, a third content (e.g., the third content (463) of FIG. 4c) in which one or more words (452) are applied to the second content (462) can be generated. In the examples described above, the first prompt (451) is described as being extracted by obtaining original data from which the style of the first content has been removed and through a description of the original data, but is not limited thereto. For example, the first prompt (451) may be extracted from meta information (e.g., EXIF ​​(exchangeable image file format)) of the first content that can be read by a computer. For example, the meta information of the first content may include information such as a camera manufacturer (marker), a camera model, a creation date, brightness, contrast, light source saturation, white balance, exposure time, an exposure program, a lens focal length, an aperture value (F-number), and / or a shutter speed, and whether a flash is used. The processor (210) may also extract the first prompt (451) that can generate content substantially identical to the first content based on the meta information of the first content.

[0184] In the above description, it has been described that the fourth content is obtained by obtaining the first prompt to be input into the large-scale language model and inputting the first prompt into the generative artificial intelligence model, but it is not limited thereto. For example, the processor (210) may obtain the fourth content by inputting the description generated by operation 506 of FIG. 5 into the generative artificial intelligence model. According to an exemplary embodiment, the processor (210) may change the description generated based on the analysis of the original content into a description optimized for the artificial intelligence model for generating the fourth content, and input the changed description into the generative artificial intelligence model. As the changed description is input into the generative artificial intelligence model, the fourth content may be generated. In this case, operation 701 may be omitted, and operation 702 may be replaced with an operation of obtaining the fourth content by inputting the changed description into the generative artificial intelligence model.

[0185] Figure 10a illustrates an exemplary screen that applies a first prompt to content displayed via another electronic device located within an external environment. Figure 10b illustrates an exemplary screen in which content displayed via another electronic device is changed.

[0186] Although the aforementioned operations have been described as applying at least a portion of the first prompt to content stored in a memory (e.g., memory (220) of FIG. 2), they are not limited thereto. Referring to FIG. 10A, the target content to which at least a portion of the first prompt is applied may be content (1005) displayed through a display (1004) of another electronic device (1003).

[0187] Referring to FIG. 10A, the electronic device (101) may operate in a see-through mode to display an external environment through a display (e.g., a display (250) of FIG. 2). A camera (e.g., a camera (230) of FIG. 2) may provide an image captured of the external environment to a processor (e.g., a processor (210) of FIG. 2). The processor (210) may synthesize an image of the external environment onto a screen displayed through the display (250), thereby providing a composite image including the external environment. For example, referring to the screen (1001) of FIG. 10A, objects included in the external environment (e.g., a picture of a dog (431) and a flower pot (432)) may be included in the screen (1001).

[0188] For example, if another electronic device (1003) is included in an image captured by a camera (230), the other electronic device (1003) may be displayed within the screen (1001). If the other electronic device (1003) includes a display (1004) that displays content (1005), the display (1004) that displays content (1005) may be displayed within the screen (1001).

[0189] According to an exemplary embodiment, the electronic device (101) may display a first prompt (451) corresponding to first content (461) on the screen (1001). The user (400) may provide a first user input for one or more words (452) included in the first prompt (451). For example, the processor (210) may receive a first user input for “colorlessness” among the one or more words (452) included in the first prompt (451). Based on receiving the first user input for the one or more words (452), the processor (210) may control the display (250) to display a visual effect for the one or more words (452) or to display a visual object (453) including the one or more words (452).

[0190] According to an exemplary embodiment, the processor (210) may receive a second user input to apply one or more words (452) to content (1005) displayed on a display (1004) of another electronic device (1003). For example, the user (400) may provide the second user input via a drag gesture to move the one or more words (452) to the content (1005). For example, if the second user input for “colorlessness” is provided, a virtual object (440) corresponding to the hand (401) may move to the content (1005) together with the word “colorlessness.” The processor (210) may control the display (250) in response to the second user input such that the content (1005) displayed on the display (1004) of the other electronic device (1003) is corrected based on the one or more words (452).

[0191] Referring to FIG. 10b, the content (1005) displayed within the screen (1002) may be displayed in a corrected state based on one or more words (452). For example, when "colorlessness" included in the first prompt (e.g., the first prompt (451) of FIG. 10A) is applied to the content (1005), the content (1005) may be displayed in a color-free state within the screen (1002) displayed through the display (e.g., the display (250) of FIG. 2). In the see-through mode, even if the display (1004) of another electronic device (1003) located in the external environment displays the content (1005) having color, the screen (1002) provided to the user (400) may provide the content (1005) with the color removed. In FIGS. 10A and 10B, the other electronic device (1003) is illustrated as a smart phone, but is not limited thereto. As described above, the electronic device (101) may display not only the content stored in the memory (e.g., the memory (220) of FIG. 2) but also the content Instead, the content (1005) displayed on the display (1004) of another electronic device (1003) can be corrected based on at least a part of the first prompt (451) extracted from the first content (461), and the corrected content (1005) can be displayed.

[0192] In the above-described embodiments, a wearable device has been described as an example of the electronic device (101), but the electronic device (101) is not limited to a wearable device. For example, the screens illustrated in FIGS. 10A and 10B may be screens provided by capturing images using a camera of a device such as a smartphone, tablet, or computer.

[0193] Figure 11 illustrates an exemplary screen for displaying objects related to the first prompt.

[0194] Referring to FIG. 11, an exemplary electronic device (101) may display a virtual object to indicate an object related to a first prompt among objects included in the second content (1120).

[0195] According to an exemplary embodiment, the first prompt corresponding to the first content (1110) may be based on properties of objects included in the first content (1110), since it is a prompt capable of generating the first content (1110). If an object related to the first prompt exists in the second content (1120), it may be suitable to change the object related to the first prompt based on the first prompt. For example, if a property of an object included in the first content (1110) is a property suitable to be applied to the object, an object to which the property can be reflected may exist in the second content (1120). In this case, the processor (210) may control the display (e.g., the display (250) of FIG. 2) to display a virtual object within the screen (1101) to indicate another object within the second content (1120) corresponding to the object.

[0196] For example, the first content (1110) may include objects such as a sofa, a window, an air conditioner, a refrigerator, a table, and a carpet. The first prompt extracted from the first content (1110) may be a prompt that can generate content including the objects. For example, the first prompt may indicate the characteristics of each object included in the first content (1110). As illustrated in FIG. 11, if the sofa included in the first content (1110) is of the couch type, the first prompt may include a word indicating the characteristics of the couch type sofa. The second content (1120) may include objects such as a sofa, a window, a bookshelf, or a person. In the above example, among the objects included in the second content (1120), objects corresponding to the objects included in the first content (1110) may be suitable for application of the first prompt. For example, since the properties of the sofa included in the first content (1110), such as color, texture, shape, and size, are properties suitable for application to the sofa included in the second content (1120), a part of the first prompt corresponding to the sofa included in the first content (1110) can be applied to the second content (1120). When a part of the first prompt corresponding to the sofa included in the first content (1110) is applied to the second content (1120), the sofa in the second content (1120) can be corrected to a sofa having the properties of the sofa in the first content (1110).

[0197] According to an exemplary embodiment, the processor may display virtual objects (1111, 1112, 1122, 1122) to indicate objects related to the first prompt. The processor (210) may identify corresponding objects by detecting first objects included in the first content (1110) and second objects included in the second content (1120). For example, if a sofa and a window are included in the first content (1110) and a sofa and a window are included in the second content (1120), the processor (210) may identify the sofa and the window. The processor (210) may display a first virtual object (1111), a second virtual object (1112), a third virtual object (1121), and a fourth virtual object (1122) on the screen (1101) to indicate that the properties applied to the sofa and the window included in the first content (1110) can be applied to the sofa and the window included in the second content (1120). For example, the first virtual object (1111) corresponding to the sofa included in the first content (1110) and the third virtual object (1121) corresponding to the sofa included in the second content (1120) may have the same shape (e.g., a dotted box). For example, a second virtual object (1112) corresponding to a window included in the first content (1110) and a fourth virtual object (1122) corresponding to a window included in the second content (1120) may have the same shape (e.g., a dashed-dotted box). By displaying virtual objects of the same shape, a user (400) can intuitively identify an object to which the first prompt is appropriately applied within the second content (1120).

[0198] According to one embodiment, when a user selects a first virtual object (1111) and drags it to a third virtual object (1121), an attribute corresponding to the first virtual object (1111) may be applied to the third virtual object (1121) from among the first prompts. For example, when a user selects the first virtual object (1111), a word (e.g., a couch-type sofa) indicating an attribute related to an object corresponding to the first virtual object (1111) (e.g., a sofa in the first content (1110)) may be selected or displayed from among the first prompts. When the user drags a word indicating an attribute selected from among the first prompts to the third virtual object (1121), the object corresponding to the third virtual object (1121) (e.g., a sofa in the second content (1120)) may be changed to have the first attribute. For example, when a user provides user input for a first virtual object (1111), a word (e.g., couch-type sofa) representing a characteristic of an object corresponding to the first virtual object (1111) included in the first content (1110) may be selected within the first prompt. When the selected word is dragged to a third virtual object (1121) within the second content (1120), the object corresponding to the third virtual object (1121) within the second content (1120) may be corrected to a couch-type sofa.

[0199] In the above-described embodiment, a wearable device has been described as an example of an electronic device (101), but the electronic device (101) is not limited to a wearable device. For example, the screen illustrated in FIG. 11 may be a screen provided by a device such as a smartphone, tablet, or computer.

[0200] Figure 12 illustrates an exemplary screen for extracting a first prompt for a portion of the first content.

[0201] Referring to FIG. 12, an exemplary electronic device (101) may extract a first prompt (451) corresponding to a portion (1211) within a first content (1210). For example, in order to extract the first prompt (451) based on an attribute included in the portion (1211) within the first content (1210) (e.g., an object included in the portion (1211)), a user (400) may provide a user input for designating the portion (1211) via a virtual object (440) corresponding to a hand (401). For example, the user input may be, but is not limited to, a spread gesture for specifying a boundary of the portion (1211) within the first content (1210).

[0202] According to an exemplary embodiment, a processor (e.g., processor (210) of FIG. 2) may be configured to extract a first prompt (451) corresponding to the partial region (1211) based on receipt of a user input for specifying the partial region (1211). The first prompt (451), when input to a generative artificial intelligence model, may be referred to as a prompt that can generate content corresponding to the partial region (1211).

[0203] Referring to the screen (1201) illustrated in FIG. 12, a car may be located within the partial area (1211). The processor (210) may extract a first prompt (451) capable of generating content corresponding to the car within the partial area (1211) based on receiving a user input for extracting a first prompt (451) from the partial area (1211) where the car is located. The processor (210) may extract the first prompt (451) by detecting an object located within the partial area (1211). For example, the first prompt (451) may be referred to as a prompt capable of generating content for the car corresponding to the car type, color, and composition of the car located within the partial area (1211). When the first prompt (451) corresponding to the above-mentioned partial area (1211) is applied to other content including a car, the car included in the other content may be changed to an image corresponding to the car included in the above-mentioned partial area (1211).

[0204] In the above-described embodiment, a wearable device has been described as an example of an electronic device (101), but the electronic device (101) is not limited to a wearable device. For example, the screen illustrated in FIG. 12 may be a screen provided by a device such as a smartphone, tablet, or computer.

[0205] Figure 13 illustrates an exemplary screen for extracting a first prompt from one or more user preferred contents.

[0206] Referring to FIG. 13, an exemplary electronic device (101) may extract a first prompt (451) from one or more user-preferred contents. For example, the electronic device (101) may include one or more user-preferred contents stored in a memory (e.g., memory (220) of FIG. 2). For example, a user (400) may provide a user input to identify some of the contents (1310) stored in the memory as preferred contents. Based on the user input to identify some of the contents as preferred contents, the electronic device (101) may identify one or more user-preferred contents. For example, the electronic device (101) may provide an indicator (1320) indicating one or more user-preferred contents.

[0207] According to an exemplary embodiment, a processor (e.g., processor (210) of FIG. 2) may be configured to extract a first prompt (451) based on one or more user-preferred contents. For example, the processor (210) may detect common attributes of one or more user-preferred contents, which are identified as user-preferred contents by user input, and extract a first prompt (451) that may generate content based on the common attributes.

[0208] Referring to screen (1301) of FIG. 13, contents (1310) may be stored in memory (220). For example, contents (1310) may include first content (1311), second content (1312), third content (1313), and fourth content (1314). When a user selects first content (1311) and second content (1312) as preferred content, the processor (210) may be configured to display an indicator (1320) in the first content (1311) and second content (1312). The processor (210) may be configured to detect attributes commonly included in the first content (1311) and the second content (1312) and extract the first prompt (451) based on the attributes in order to extract the first prompt (451). The processor (210) may display the first prompt (451) on the screen (1301) based on the execution of a software application for providing a list of contents (1310). The user (400) may correct the third content (1313) and / or the fourth content (1314) by providing a user input to reflect at least a portion of the first prompt (451) to the third content (1313) and / or the fourth content (1314) that is not the user preferred content.

[0209] According to an exemplary embodiment, since a first prompt (451) to be applied to target content is extracted based on one or more user preferred contents, the electronic device (101) can provide attributes preferred by the user (400) for correction of the target content. The user (400) can utilize the first prompt (451) extracted based on one or more user preferred contents for correction of the target content. Since the first prompt (451) reflecting the preferences of the user (400) is provided, the target content can be corrected according to the personal preferences of the user (400).

[0210] According to an exemplary embodiment, preferred contents may be displayed based on a user's history among contents (1310) stored in the memory (220). For example, the electronic device (101) may identify preferred contents based on information related to contents uploaded to an external electronic device (e.g., a social network service server or a messenger server). Contents that the user has transmitted to an external electronic device through the electronic device (101) a specified number of times or more may be identified as preferred contents. The electronic device (101) may identify preferred contents according to the history and provide a first prompt (451) based on the preferred contents.

[0211] In the above-described embodiment, a wearable device has been described as an example of an electronic device (101), but the electronic device (101) is not limited to a wearable device. For example, the screens illustrated in FIG. 13 may be screens provided by a device such as a smartphone, tablet, or computer.

[0212] Figure 14a illustrates an exemplary screen for extracting a first prompt for one of the frames constituting a video. Figure 14b illustrates an exemplary screen for applying the first prompt for one of the frames constituting the video content to a second content. Figure 14c illustrates an exemplary screen for displaying the second content.

[0213] Referring to FIG. 14A, the first content (1400) may be a video. For example, a video may be referred to as content in which a plurality of frames (1410), which are still images, are continuously provided. The exemplary electronic device (101) may extract a first prompt (451) from one frame (1411) among the plurality of frames (1410) included in the video, and correct the second content (1420) based on the extracted first prompt (451).

[0214] According to an exemplary embodiment, a user (400) may provide a user input to extract a first prompt (451) corresponding to a frame (1411) among a plurality of frames (1400) constituting a video. Referring to the screen (1401) of FIG. 14A, for example, when a video is played, the user (400) may stop playing the video at a timing when the frame (1411) is displayed. At the timing, the frame (1411) may be displayed within the screen (1401). A first user input may be provided for the frame (1411). For example, the first user input may be performed through a virtual object (440) corresponding to the hand (401) of the user (400). A processor (e.g., processor (210) of FIG. 2) may extract a first prompt (451) corresponding to the frame (1411) based on receipt of a first user input for the frame (1411).

[0215] Referring to FIG. 14b, the user (400) may provide a drag gesture to drag at least a portion of the first prompt (451) to the second content (1420) in order to apply at least a portion of the first prompt (451) to the second content (1420) of FIG. 14a. Referring to the screen (1402) of FIG. 14b, for example, the second user input may be performed in such a way that a virtual object (440) corresponding to the hand (401) moves to the second content (1420) together with at least a portion of the first prompt (451). The processor (210) may generate a second prompt including at least a portion of the first prompt (451) and input the second prompt into a generative artificial intelligence model, thereby obtaining third content (e.g., the third content (1430) of FIG. 14c). The processor (210) may input a video, along with a second prompt, into a generative artificial intelligence model to obtain third content (1430). For example, if a portion of the first prompt (451) selected by the first user input is a word corresponding to an effect of removing color from the content, the third content (1430) may be generated by removing the color from the second content (1420). Referring to FIG. 14C, the third content (1430) may be displayed within the screen (1403). For example, if a portion of the first prompt (e.g., the first prompt (451) of FIG. 14B) selected by the first user input is a word corresponding to an effect of removing color from the content, the third content (1430) may be content with the color of the second content (1420) removed.

[0216] For example, if the second content (1420) is a video, the third content (1430) may be content that has been changed by applying the first prompt (451) to one of the plurality of frames constituting the second content (1420). The user (400) may provide a user input confirming the change to the frame and accepting the change to the second content (1420) based on the first prompt (451). The processor (210), based on receiving the user input, may generate the third content (1430) by changing all of the plurality of frames constituting the second content (1420) based on the first prompt (451).

[0217] According to an exemplary embodiment, a first prompt (451) corresponding to one frame (1411) is extracted from among a plurality of frames (1410) constituting a video, thereby providing correction of content according to the intention of the user (400). Since the user (400) can select the frame (1411) used to correct the second content (1420) from among the plurality of frames (1410), the electronic device (101) can provide an enhanced user experience.

[0218] In the above-described embodiments, a wearable device has been described as an example of an electronic device (101), but the electronic device (101) is not limited to a wearable device. For example, the screens illustrated in FIGS. 14A, 14B, and 14C may be screens provided by a device such as a smartphone, tablet, or computer.

[0219] Figure 15a illustrates an exemplary screen that provides a first prompt based on user history.

[0220] Referring to FIG. 15A, a first content (1510) may be displayed within a portion (450) of a screen (1501). As described above, a prompt (1540) corresponding to the first content (1510) may be displayed within the screen (1501). According to one embodiment, the electronic device (101) may provide a prompt based on user history along with the prompt (1540) corresponding to the first content (1510).

[0221] In one embodiment, the prompt (1550) based on the user history may be a prompt corresponding to another content (1520) previously used by the user (400). For example, if the user (400) previously used a prompt (1550) corresponding to another content (1520) to change the second content (1530), the electronic device (101) may provide the prompt (1550) together with a prompt (1540) corresponding to the first content (1510). The user (400) may change the second content (1530) by reflecting the previously used prompt (1550) to the second content (1530) together with the prompt (1540) corresponding to the first content (1510).

[0222] In one embodiment, a prompt based on user history may be provided by updating a prompt (1540) corresponding to the first content (1510). For example, the electronic device (101) may obtain the latest information on the first content (1510) from an external electronic device (1502) and update the prompt (1510) based on the latest information. For example, if the first content (1510) is a work by a specific author, the electronic device (101) may search for the author's latest work from an external electronic device (1502) (e.g., a web server) and, if the latest work is found, provide a prompt (1540) reflecting information about the latest work.

[0223] In one embodiment, the electronic device (101) may be configured to share a prompt used to modify the second content (1530). For example, the user (400) may transmit the prompt information used to modify the second content (1530) to an external electronic device (1502) (e.g., another user's electronic device). In one embodiment, the electronic device (101) may share a prompt related to a characteristic of a specific content. The above operation is described below with reference to FIGS. 15B and 15C .

[0224] FIG. 15b is a flowchart illustrating an operation of providing a prompt based on content modified by multiple external electronic devices. FIG. 15c illustrates an exemplary screen for providing a prompt based on content modified by multiple external electronic devices.

[0225] Referring to FIG. 15b, at operation 1505, the processor (210) may be configured to share the content (1561) with one or more external electronic devices (e.g., one or more external electronic devices (1502) of FIG. 15c) based on identifying a user input for the content (e.g., content (1561) of FIG. 15c).

[0226] Referring to FIG. 15c, the electronic device (101) can communicate with one or more external electronic devices (1502). The one or more external electronic devices (1502) can include a first external electronic device (1502a) owned by a first user (U1) different from the user of the electronic device (101) and a second external electronic device (1502b) owned by a second user (U2). For example, the first external electronic device (1502a) and / or the second external electronic device (1502b) can be a wearable device, but is not limited thereto, and can include devices such as a smart phone, a tablet, or a computer.

[0227] According to one embodiment, the electronic device (101) can share content (1561) with one or more external electronic devices (1502) and update a prompt (1562) corresponding to the content (1561) with other users (a first user (U1), a second user (U2)).

[0228] According to one embodiment, the electronic device (101) can identify a user input for sharing content (1561) received from a user (400). The user input can be referred to as a user input for selecting the content (1561) to be shared. The processor (210) can share the content (1561) with one or more external electronic devices (1502) based on identifying the user input. For example, the electronic device (101) can share the content (1561) and a prompt (1562) corresponding to the content (1561) with one or more external electronic devices (1502) via a server (1570).

[0229] In operation 1506, the processor (210) may be configured to display content (1561) and a prompt (1562) via a display (e.g., display (250) of FIG. 15c).

[0230] Referring to the screen (1560) illustrated in FIG. 15c, the processor (210) may be configured to display, through the display (250), selected content (1561) and a prompt (1562) corresponding to the content (1561). The screen (1560) may correspond to a screen provided by the first external electronic device (1502a) to the first user (U1) and a screen provided by the second external electronic device (1502b) to the second user (U2). For example, the first external electronic device (1502a) may provide a screen on which the content (1561) is displayed to the first user (U1), and the second external electronic device (1502b) may provide a screen on which the content (1561) is displayed to the second user (U2).

[0231] At operation 1507, the processor (210) may be configured to update the prompt (1562) based on modifications to the content (1561) by one or more external electronic devices (1502).

[0232] According to one embodiment, not only the user (400) of the electronic device (101), but also users (U1, U2) of one or more external electronic devices (1502) can modify the content (1561). For example, the one or more external electronic devices (1502) can provide user input for modifying the content (1561), as described above. Based on the user input, the content (1561) can be modified into other content (1563). For example, based on a user input for removing a color contained in the content (1561), the content (1561) can be modified into other content (1563) with the color removed. For example, if the content (1561) is modified into another content (1563) by the first user (U1), the modified another content (1563) can be transmitted to the server (1570). The server (1570) can provide the modified another content (1563) to the electronic device (101) and the second external electronic device (1502b). The electronic device (101) and the second external electronic device (1502b) can display the modified content (1563). The server (1570) can be omitted. For example, the electronic devices (101, 1502a, 1502b) can share the content through short-range communication (e.g., Bluetooth communication). When the content (1561) is modified into another content (1563) by a first user (U1) or a second user (U2), the modified another content (1563) can be provided to the electronic device (101) via short-range communication without going through the server (1570).

[0233] According to one embodiment, the electronic device (101) may update a prompt (1562) based on modifications to the content (1561) by one or more external electronic devices (1502). The processor (210) may update the prompt (1562) corresponding to the content (1561) before modification, based on the modified content (1563), with another prompt (1564) corresponding to the modified content (1563). As in the example described above, if the content (1561) is modified with another content (1563) with color removed, the another prompt (1564) may include a prompt such as "colorlessness."

[0234] At operation 1508, the processor (210) may be configured to display the updated prompt (1564) and the modified content (1563) via the display.

[0235] According to one embodiment, the processor (210) may provide a screen (1560) that displays the other content (1563) and the other prompt (1564). A first external electronic device (1502a) may provide a screen corresponding to the screen (1560) to a first user (U1), and a second external electronic device (1502b) may provide a screen corresponding to the screen (1560) to a second user (U2). The user (400) may identify the other content (1563) and the other prompt (1564) that have been modified through the other content (1563) and the other prompt (1564) displayed in the screen (1560).

[0236] At operation 1509, the processor (210) may be configured to store the updated prompt (1564) and the modified content (1563).

[0237] In one embodiment, the processor (210) may be configured to store the other content (1563) and the other prompt (1564) based on user input. The user (400) may provide user input to store the other content (1563) and the other prompt (1564) so ​​that the other content (1563) and the other prompt (1564) modified by other users may be available. In one embodiment, the content (1561) may be modified by multiple users, and the other prompt (1564) may be provided together with the other content (1563) generated by the modification of the content (1561).

[0238] Figure 16 illustrates an exemplary screen provided when use of the first content is restricted.

[0239] Referring to FIG. 16, there may be situations where specific permissions are required to use a prompt (1620) corresponding to content (1610). For example, if the content (1610) is a copyrighted work, there may be restrictions on the use of the prompt (1620) corresponding to the content (1610). For example, if the content (1610) is a work created by a specific person, unauthorized use of a prompt (1620) that includes characteristics such as a unique style reflected in the content (1610) may result in copyright issues. According to one embodiment, if the use of the content (1610) is restricted, the electronic device (101) may provide a screen (1601) for obtaining permissions before providing the prompt (1620). Referring to the screen (1601) of FIG. 16, the electronic device (101) may provide a visual object (1630) for using the content (1610). If the purchase of the copyrighted work is required to use the content (1610), the visual object (1630) may include text such as, "This content requires payment. Would you like to proceed to the payment screen?" The electronic device (101) may display, within the screen (1601), a visual object (1641) capable of receiving a user input for moving to the payment screen and a visual object (1642) capable of receiving a user input for rejecting payment. When a user input for the visual object (1641) is received, the electronic device (101) may provide a screen for payment (e.g., a screen of a payment site) and, after the payment is completed, display a prompt (1620).

[0240] Hereinafter, with reference to FIGS. 17A, 17B, 18A, and / or 18B, an exemplary appearance of a wearable device is illustrated as an example of the aforementioned electronic device (101). The wearable device (1700) of FIGS. 17A and 17B and / or the wearable device (1800) of FIGS. 18A and 18B may be an example of the aforementioned electronic device (101).

[0241] FIG. 17A illustrates an example of a perspective view of a wearable device according to an exemplary embodiment. FIG. 17B illustrates one or more hardware elements arranged within a wearable device according to an exemplary embodiment.

[0242] A wearable device (1700) according to an exemplary embodiment may have the form of glasses that are wearable on a body part of a user (e.g., the head). The wearable device (1700) may include a head-mounted display (HMD). For example, the housing of the wearable device (1700) may include a flexible material, such as rubber and / or silicone, that is configured to fit closely to a portion of the user's head (e.g., a portion of the face surrounding both eyes). For example, the housing of the wearable device (1700) may include one or more straps that are capable of being twined around the user's head, and / or one or more temples that are detachably attachable to the ears of the head.

[0243] Referring to FIG. 17A, a wearable device (1700) according to an exemplary embodiment may include at least one display (1750) and a frame supporting at least one display (1750).

[0244] A wearable device (1700) according to an exemplary embodiment can be worn on a part of a user's body. The wearable device (1700) can provide augmented reality (AR), virtual reality (VR), or mixed reality (MR) that combines augmented reality and virtual reality to a user wearing the wearable device (1700). For example, the wearable device (1700) can display a virtual reality image provided from at least one optical device (1782, 1784) of FIG. 17B on at least one display (1750) in response to a user's designated gesture acquired through the motion recognition cameras (1760-2, 1760-3) of FIG. 17B.

[0245] According to an exemplary embodiment, at least one display (1750) may provide visual information to a user. For example, at least one display (1750) may include a transparent or translucent lens. At least one display (1750) may include a first display (1750-1) and / or a second display (1750-2) spaced apart from the first display (1750-1). For example, the first display (1750-1) and the second display (1750-2) may be positioned at positions corresponding to the user's left and right eyes, respectively.

[0246] Referring to FIG. 17B, at least one display (1750) can provide a user with visual information transmitted from external light and other visual information distinct from the visual information through a lens included in the at least one display (1750). The lens can be formed based on at least one of a Fresnel lens, a pancake lens, or a multi-channel lens. For example, the at least one display (1750) can include a first surface (1731) and a second surface (1732) opposite the first surface (1731). A display area can be formed on the second surface (1732) of the at least one display (1750). When a user wears the wearable device (1700), external light can be transmitted to the user by being incident on the first surface (1731) and transmitted through the second surface (1732). For another example, at least one display (1750) can display an augmented reality image combined with a virtual reality image provided from at least one optical device (1782, 1784) on a real screen transmitted through external light, in a display area formed on the second surface (1732).

[0247] In an exemplary embodiment, at least one display (1750) may include at least one waveguide (1733, 1734) that diffracts light emitted from at least one optical device (1782, 1784) and transmits the diffracted light to a user. The at least one waveguide (1733, 1734) may be formed based on at least one of glass, plastic, or polymer. A nanopattern may be formed on at least a portion of the exterior or interior of the at least one waveguide (1733, 1734). The nanopattern may be formed based on a grating structure having a polygonal and / or curved shape. Light incident on one end of the at least one waveguide (1733, 1734) may be propagated to the other end of the at least one waveguide (1733, 1734) by the nanopattern. At least one waveguide (1733, 1734) may include at least one diffractive element (e.g., a diffractive optical element (DOE), a holographic optical element (HOE)), or at least one reflective element (e.g., a reflective mirror). For example, at least one waveguide (1733, 1734) may be arranged within the wearable device (1700) to guide a screen displayed by at least one display (1750) to the user's eyes. For example, the screen may be transmitted to the user's eyes based on total internal reflection (TIR) ​​occurring within the at least one waveguide (1733, 1734).

[0248] The wearable device (1700) can analyze an object included in a real image collected through a shooting camera (1760-4), combine a virtual object corresponding to an object to be provided with augmented reality among the analyzed objects, and display the virtual object on at least one display (1750). The virtual object can include at least one of text and an image regarding various information related to the object included in the real image. The wearable device (1700) can analyze the object based on a multi-camera such as a stereo camera. For the object analysis, the wearable device (1700) can perform spatial recognition (e.g., simultaneous localization and mapping (SLAM)) using the multi-camera and / or time-of-flight (ToF). A user wearing the wearable device (1700) can view an image displayed on at least one display (1750).

[0249] According to an exemplary embodiment, the frame may be formed as a physical structure that allows the wearable device (1700) to be worn on the user's body. According to an exemplary embodiment, the frame may be configured so that, when the user wears the wearable device (1700), the first display (1750-1) and the second display (1750-2) can be positioned corresponding to the user's left and right eyes. The frame may support at least one display (1750). For example, the frame may support the first display (1750-1) and the second display (1750-2) to be positioned corresponding to the user's left and right eyes.

[0250] Referring to FIG. 17A, the frame may include a region (1720) that at least partially contacts a portion of the user's body when the user wears the wearable device (1700). For example, the region (1720) of the frame that contacts a portion of the user's body may include a region that contacts a portion of the user's nose, a portion of the user's ear, and a portion of the side of the user's face that the wearable device (1700) makes contact with. According to an exemplary embodiment, the frame may include a nose pad (1710) that contacts a portion of the user's body. When the wearable device (1700) is worn by the user, the nose pad (1710) may contact a portion of the user's nose. The frame may include a first temple (1704) and a second temple (1705) that contact another portion of the user's body that is distinct from the portion of the user's body.

[0251] For example, the frame may include a first rim (1701) surrounding at least a portion of a first display (1750-1), a second rim (1702) surrounding at least a portion of a second display (1750-2), a bridge (1703) disposed between the first rim (1701) and the second rim (1702), a first pad (1711) disposed along a portion of an edge of the first rim (1701) from one end of the bridge (1703), a second pad (1712) disposed along a portion of an edge of the second rim (1702) from the other end of the bridge (1703), a first temple (1704) extending from the first rim (1701) and secured to a portion of an ear of the wearer, and a second temple (1705) extending from the second rim (1702) and secured to a portion of an ear opposite the ear. The first pad (1711) and the second pad (1712) may be in contact with a portion of the user's nose, and the first temple (1704) and the second temple (1705) may be in contact with a portion of the user's face and a portion of the user's ear. The temples (1704, 1705) may be rotatably connected to the rim through the hinge units (1706, 1707) of FIG. 17B. The first temple (1704) may be rotatably connected to the first rim (1701) through the first hinge unit (1706) disposed between the first rim (1701) and the first temple (1704). The second temple (1705) may be rotatably connected to the second rim (1702) via a second hinge unit (1707) disposed between the second rim (1702) and the second temple (1705). In an exemplary embodiment, the wearable device (1700) may use a touch sensor, a grip sensor, and / or a proximity sensor formed on at least a portion of a surface of the frame to identify an external object (e.g., a user's fingertip) touching the frame and / or a gesture performed by the external object.

[0252] According to an exemplary embodiment, a wearable device (1700) may include hardwares (e.g., hardwares described above based on the block diagram of FIG. 2) that perform various functions. For example, the hardwares may include a battery module (1770), an antenna module (1775), at least one optical device (1782, 1784), speakers (e.g., speakers 1755-1, 1755-2), microphones (e.g., microphones 1765-1, 1765-2, 1765-3), a light-emitting module, and / or a printed circuit board (PCB) (1790) (e.g., a printed circuit board). The various hardware components may be arranged within a frame.

[0253] According to an exemplary embodiment, microphones (e.g., microphones 1765-1, 1765-2, 1765-3) of the wearable device (1700) may be disposed on at least a portion of the frame to acquire sound signals. A first microphone (1765-1) disposed on the bridge (1703), a second microphone (1765-2) disposed on the second rim (1702), and a third microphone (1765-3) disposed on the first rim (1701) are illustrated in FIG. 17B , but the number and arrangement of the microphones (1765) are not limited to the exemplary embodiment of FIG. 17B . When the number of microphones (1765) included in the wearable device (1700) is two or more, the wearable device (1700) may identify the direction of the sound signal by using a plurality of microphones disposed on different portions of the frame.

[0254] According to an exemplary embodiment, at least one optical device (1782, 1784) may project a virtual object onto at least one display (1750) to provide various image information to a user. For example, at least one optical device (1782, 1784) may be a projector. At least one optical device (1782, 1784) may be disposed adjacent to at least one display (1750) or may be included within at least one display (1750) as a part of at least one display (1750). According to an exemplary embodiment, the wearable device (1700) may include a first optical device (1782) corresponding to a first display (1750-1) and a second optical device (1784) corresponding to a second display (1750-2). For example, at least one optical device (1782, 1784) may include a first optical device (1782) positioned at an edge of a first display (1750-1) and a second optical device (1784) positioned at an edge of a second display (1750-2). The first optical device (1782) may transmit light to a first waveguide (1733) positioned on the first display (1750-1), and the second optical device (1784) may transmit light to a second waveguide (1734) positioned on the second display (1750-2).

[0255] In an exemplary embodiment, the camera (1760) may include a recording camera (1760-4), an eye tracking camera (ET CAM) (1760-1), and / or a motion recognition camera (1760-2, 1760-3). The recording camera (1760-4), the eye tracking camera (1760-1), and the motion recognition cameras (1760-2, 1760-3) may be positioned at different locations on the frame and may perform different functions. The eye tracking camera (1760-1) may output data indicating the position or gaze of the eyes of a user wearing the wearable device (1700). For example, the wearable device (1700) may detect the gaze from an image including the user's pupils obtained through the eye tracking camera (1760-1).

[0256] The wearable device (1700) can identify an object (e.g., a real object and / or a virtual object) focused on by the user using the user's gaze acquired through the gaze tracking camera (1760-1). The wearable device (1700) that has identified the focused object can execute a function (e.g., gaze interaction) for interaction between the user and the focused object. The wearable device (1700) can express a part corresponding to the eye of an avatar representing the user in a virtual space using the user's gaze acquired through the gaze tracking camera (1760-1). The wearable device (1700) can render an image (or screen) displayed on at least one display (1750) based on the position of the user's eyes.

[0257] For example, the visual quality of a first region related to the gaze within an image and the visual quality (e.g., resolution, brightness, saturation, grayscale, PPI (pixels per inch)) of a second region distinct from the first region may be different from each other. The wearable device (1700) may obtain an image having the visual quality of the first region and the visual quality of the second region that match the gaze of the user using foveated rendering. For example, if the wearable device (1700) supports an iris recognition function, user authentication may be performed based on iris information obtained using a gaze tracking camera (1760-1). Although an example in which the gaze tracking camera (1760-1) is positioned toward the user's right eye is illustrated in FIG. 17B, the embodiment is not limited thereto, and the gaze tracking camera (1760-1) may be positioned solely toward the user's left eye, or toward both eyes.

[0258] In an exemplary embodiment, the capturing camera (1760-4) can capture an actual image or background to be aligned with a virtual image to implement augmented reality or mixed reality content. The capturing camera (1760-4) can be used to obtain a high-resolution image based on HR (high resolution) or PV (photo video). The capturing camera (1760-4) can capture an image of a specific object existing at a location where the user is looking and provide the image to at least one display (1750). The at least one display (1750) can display a single image in which information about the actual image or background including the image of the specific object obtained using the capturing camera (1760-4) and a virtual image provided through at least one optical device (1782, 1784) are superimposed. The wearable device (1700) can compensate for depth information (e.g., the distance between the wearable device (1700) and an external object acquired through a depth sensor) using an image acquired through the capture camera (1760-4). The wearable device (1700) can perform object recognition using an image acquired using the capture camera (1760-4). The wearable device (1700) can perform a function of focusing on an object (or subject) in an image (e.g., auto focus) and / or an optical image stabilization (OIS) function (e.g., anti-shake function) using the capture camera (1760-4). The wearable device (1700) can perform a pass-through function to display an image acquired through the capture camera (1760-4) by overlapping at least a portion of a screen representing a virtual space on at least one display (1750) while displaying a screen. In an exemplary embodiment, the capturing camera (1760-4) may be positioned on a bridge (1703) positioned between the first rim (1701) and the second rim (1702).

[0259] The gaze tracking camera (1760-1) can implement more realistic augmented reality by tracking the gaze of a user wearing a wearable device (1700) and matching the user's gaze with visual information provided to at least one display (1750). For example, when the wearable device (1700) looks straight ahead, the wearable device (1700) can naturally display environmental information related to the user's front at a location where the user is located on at least one display (1750). The gaze tracking camera (1760-1) can be configured to capture an image of the user's pupil to determine the user's gaze. For example, the gaze tracking camera (1760-1) can receive gaze detection light reflected from the user's pupil and track the user's gaze based on the position and movement of the received gaze detection light. In an exemplary embodiment, the gaze tracking camera (1760-1) can be positioned at positions corresponding to the user's left and right eyes. For example, the gaze tracking camera (1760-1) may be positioned within the first rim (1701) and / or the second rim (1702) to face the direction in which the user wearing the wearable device (1700) is positioned.

[0260] The gesture recognition cameras (1760-2, 1760-3) can recognize the movement of the user's entire body, such as the user's torso, hands, or face, or a part of the body, and thereby provide a specific event on a screen provided on at least one display (1750). The gesture recognition cameras (1760-2, 1760-3) can recognize the user's gesture (gesture recognition), obtain a signal corresponding to the gesture, and provide a display corresponding to the signal on at least one display (1750). The processor can identify the signal corresponding to the gesture, and perform a designated function based on the identification. The gesture recognition cameras (1760-2, 1760-3) can be used to perform a spatial recognition function using SLAM and / or a depth map for 6 degrees of freedom pose (6 dof pose). The processor may perform gesture recognition and / or object tracking functions using the motion recognition cameras (1760-2, 1760-3). In an exemplary embodiment, the motion recognition cameras (1760-2, 1760-3) may be positioned on the first rim (1701) and / or the second rim (1702).

[0261] The camera (1760) included in the wearable device (1700) is not limited to the above-described gaze tracking camera (1760-1) and motion recognition cameras (1760-2, 1760-3). For example, the wearable device (1700) can identify an external object included in the FoV using a camera positioned toward the user's FoV. The wearable device (1700) can identify an external object based on a sensor for identifying the distance between the wearable device (1700) and the external object, such as a depth sensor and / or a time of flight (ToF) sensor. The camera (1760) positioned toward the FoV can support an autofocus function and / or an optical image stabilization (OIS) function. For example, the wearable device (1700) may include a camera (1760) (e.g., a face tracking (FT) camera) positioned toward the face to obtain an image including the face of a user wearing the wearable device (1700).

[0262] Although not shown, the wearable device (1700) according to an exemplary embodiment may further include a light source (e.g., an LED) that emits light toward a subject (e.g., a user's eyes, face, and / or an external object within the FoV) being captured using the camera (1760). The light source may include an infrared wavelength LED. The light source may be disposed on at least one of the frame and hinge units (1706, 1707).

[0263] According to an exemplary embodiment, a battery module (1770) may supply power to electronic components of a wearable device (1700). In an exemplary embodiment, the battery module (1770) may be disposed within the first temple (1704) and / or the second temple (1705). For example, the battery module (1770) may be a plurality of battery modules (1770). The plurality of battery modules (1770) may be disposed within each of the first temple (1704) and the second temple (1705). In an exemplary embodiment, the battery module (1770) may be disposed at an end of the first temple (1704) and / or the second temple (1705).

[0264] The antenna module (1775) can transmit signals or power to the outside of the wearable device (1700), or receive signals or power from the outside. In an exemplary embodiment, the antenna module (1775) can be positioned within the first temple (1704) and / or the second temple (1705). For example, the antenna module (1775) can be positioned close to one surface of the first temple (1704) and / or the second temple (1705).

[0265] The speaker (1755) can output an acoustic signal to the outside of the wearable device (1700). The acoustic output module may be referred to as a speaker. In an exemplary embodiment, the speaker (1755) may be positioned within the first temple (1704) and / or the second temple (1705) so as to be positioned adjacent to the ear of a user wearing the wearable device (1700). For example, the speaker (1755) may include a second speaker (1755-2) positioned within the first temple (1704) and thus positioned adjacent to the user's left ear, and a first speaker (1755-1) positioned within the second temple (1705) and thus positioned adjacent to the user's right ear.

[0266] The light-emitting module (not shown) may include at least one light-emitting element. The light-emitting module may emit light of a color corresponding to a specific state or emit light with an action corresponding to a specific state to visually provide information regarding a specific state of the wearable device (1700) to the user. For example, when the wearable device (1700) requires charging, it may emit red light at a regular cycle. In an exemplary embodiment, the light-emitting module may be disposed on the first rim (1701) and / or the second rim (1702).

[0267] Referring to FIG. 17B, according to an exemplary embodiment, a wearable device (1700) may include a printed circuit board (PCB) (1790). The PCB (1790) may be included in at least one of the first temple (1704) or the second temple (1705). The PCB (1790) may include an interposer disposed between at least two sub-PCBs. One or more hardwares included in the wearable device (1700) (e.g., hardwares illustrated by different blocks in FIG. 2) may be disposed on the PCB (1790). The wearable device (1700) may include a flexible PCB (FPCB) for interconnecting the hardwares.

[0268] According to an exemplary embodiment, a wearable device (1700) may include at least one of a gyro sensor, a gravity sensor, and / or an acceleration sensor for detecting a posture of the wearable device (1700) and / or a posture of a body part (e.g., a head) of a user wearing the wearable device (1700). Each of the gravity sensor and the acceleration sensor may measure gravitational acceleration and / or acceleration based on mutually perpendicular designated three-dimensional axes (e.g., an x-axis, a y-axis, and a z-axis). The gyro sensor may measure an angular velocity of each of the designated three-dimensional axes (e.g., an x-axis, a y-axis, and a z-axis). At least one of the gravity sensor, the acceleration sensor, and the gyro sensor may be referred to as an inertial measurement unit (IMU). According to an exemplary embodiment, the wearable device (1700) may identify a user's motion and / or gesture performed to execute or terminate a specific function of the wearable device (1700) based on the IMU.

[0269] FIG. 18a and FIG. 18b illustrate the appearance of a wearable device according to an exemplary embodiment.

[0270] The wearable device (1800) of FIGS. 18A and 18B may include at least a portion of the hardware of the wearable device (1700) described with reference to FIGS. 17A and / or 17B. An example of the appearance of a first side (1810) of a housing of the wearable device (1800) according to an exemplary embodiment is illustrated in FIG. 18A, and an example of the appearance of a second side (1820) opposite to the first side (1810) is illustrated in FIG. 18B.

[0271] Referring to FIG. 18A, a first surface (1810) of a wearable device (1800) according to an exemplary embodiment may have a form attachable on a body part of a user (e.g., the face of the user). Although not shown, the wearable device (1800) may further include a strap for fixing on a body part of a user, and / or one or more temples (e.g., the first temple (1704) and / or the second temple (1705) of FIGS. 17A and 17B). A first display (1750-1) for outputting an image to a left eye among the user's two eyes, and a second display (1750-2) for outputting an image to a right eye among the user's two eyes may be disposed on the first surface (1810). The wearable device (1800) may be formed on the first surface (1810) and may further include a rubber or silicone packing to prevent interference from light (e.g., ambient light) different from the light emitted from the first display (1750-1) and the second display (1750-2).

[0272] According to an exemplary embodiment, a wearable device (1800) may include cameras (1760-1) for photographing and / or tracking both eyes of a user adjacent to each of the first display (1750-1) and the second display (1750-2). The cameras (1760-1) may be referred to as the gaze tracking camera (1760-1) of FIG. 17B. According to an exemplary embodiment, a wearable device (1800) may include cameras (1760-5, 1760-6) for photographing and / or recognizing a face of a user. The cameras (1760-5, 1760-6) may be referred to as FT cameras. The wearable device (1800) can control an avatar representing the user in a virtual space based on the facial motion of the user identified using cameras (1760-5, 1760-6). For example, the wearable device (1800) can change the texture and / or shape of a portion of the avatar (e.g., a portion of the avatar representing a human face) using information obtained by cameras (1760-5, 1760-6) (e.g., an FT camera) and representing the facial expression of the user wearing the wearable device (1800).

[0273] Referring to FIG. 18B, a camera (e.g., cameras 1760-7, 1760-8, 1760-9, 1760-10, 1760-11, 1760-12)) and / or a sensor (e.g., a depth sensor 1830) may be disposed on a second surface (1820) opposite to the first surface (1810) of FIG. 18A to obtain information related to the external environment of the wearable device (1800). For example, the cameras (1760-7, 1760-8, 1760-9, 1760-10) may be disposed on the second surface (1820) to recognize external objects. The cameras (1760-7, 1760-8, 1760-9, 1760-10) of FIG. 18b can correspond to the motion recognition cameras (1760-2, 1760-3) of FIG. 17b.

[0274] For example, using cameras (1760-11, 1760-12), the wearable device (1800) can obtain images and / or videos to be transmitted to each of the user's eyes. The camera (1760-11) can be positioned on the second face (1820) of the wearable device (1800) to obtain an image to be displayed through the second display (1750-2) corresponding to the right eye among the two eyes. The camera (1760-12) can be positioned on the second face (1820) of the wearable device (1800) to obtain an image to be displayed through the first display (1750-1) corresponding to the left eye among the two eyes. The cameras (1760-11, 1760-12) can correspond to the shooting camera (1760-4) of FIG. 17B.

[0275] According to an exemplary embodiment, the wearable device (1800) may include a depth sensor (1830) disposed on a second face (1820) to identify a distance between the wearable device (1800) and an external object. Using the depth sensor (1830), the wearable device (1800) may obtain spatial information (e.g., a depth map) for at least a portion of the FoV of a user wearing the wearable device (1800). Although not shown, a microphone may be disposed on the second face (1820) of the wearable device (1800) to obtain a sound output from an external object. The number of microphones may be one or more, depending on the embodiment.

[0276] FIG. 19a and FIG. 19b illustrate a process of an electronic device changing second content according to one embodiment.

[0277] Referring to FIG. 19A, according to one embodiment, an electronic device (e.g., an HMD, a smart phone, or a computer) (101) may be configured to display a first image (1910) and a second image (1920) stored in a storage device (e.g., a memory) of the electronic device (101) or an external storage device connected to the electronic device (101). For example, the second image (1920) may be referenced as content to be modified using the first image (1910).

[0278] Referring to the screen (1901) of FIG. 19A, an electronic device (101) according to one embodiment may be configured to identify a selection of a first area (1911) within a first image (1910) based on a first interaction of a user (400), and obtain a third prompt (1931) related to the first area (1911) selected from a first prompt (1930) related to the first image (1910). The first prompt (1930) corresponds to the first image (1910), and when the first prompt (1930) is input to an artificial intelligence model, the first image (1910) may be output. The first interaction may be referenced as a user input for selecting the first area (1911) using a virtual object (1961). For example, if the first region (1911) includes a feature that has no color, the third prompt (1931) may be referenced by text such as "colorlessness."

[0279] According to one embodiment, the electronic device (101) may be configured to identify a selection of a second area (1921) within a second image (1920) based on a second interaction of the user (400). The electronic device (101) may be configured to obtain, based on the identification of the selection of the second area (1921), a fourth prompt (1941) associated with the second area (1921) within a second prompt (1940) associated with the second image (1921). The second interaction may be referenced as a user input selecting the second area (1921) using a virtual object (1962). For example, if the second area (1921) includes a feature having a color, the fourth prompt (1941) may be referenced as text such as "colorful." The fourth prompt (1941) may be obtained using an artificial intelligence algorithm.

[0280] Referring to FIG. 19B, the electronic device (101) can change the fourth prompt (1941) obtained using the artificial intelligence model based on the third prompt (1931). Referring to the screen (1902) of FIG. 19B, the electronic device (101) according to one embodiment can be configured to generate a fifth prompt (1950) including a sixth prompt (1951) for the second area (1921) of the second image (1920) by changing the fourth prompt (1941) within the second prompt (1940) based on the third prompt (1931). For example, the sixth prompt (1951) can be referenced with text such as "colorlessness." The electronic device (101) may be configured to generate a fifth prompt (1950) that includes a sixth prompt (1951) by replacing the fourth prompt (1941) within the second prompt (1940) with the sixth prompt (1951).

[0281] In one embodiment, the electronic device (101) can replace a second image (e.g., the second image (1920) of FIG. 19B) by generating a third image (1970) using the generated fifth prompt (1950). The electronic device (101) can be configured to display the third image (1970) generated by changing the second image (1920).

[0282] FIG. 20 is a flowchart illustrating an operation of providing candidate content of an electronic device according to an exemplary embodiment. FIGS. 21, 22, 23, and 24 illustrate processes for changing first candidate content to second candidate content based on a first user input.

[0283] As described above, a prompt may be referred to as an input sentence containing natural language or a set of feature keywords. The term 'keyword' as used within the present disclosure may refer to a word included in the prompt. The processor (210) of FIG. 2 may be configured to perform operations of an electronic device (e.g., electronic device (101) of FIG. 1) described with reference to FIG. 20. Instructions stored in a memory (e.g., memory (220) of FIG. 2) may, when individually or collectively executed by the processor, cause the electronic device (101) to perform operations of the electronic device (101) described in FIG. 20. The electronic device (101) described below may include a wearable device (e.g., wearable device (1700) of FIG. 17A or wearable device (1800) of FIG. 18A) including a display (e.g., display (250) of FIG. 2).

[0284] In operation 2001 of FIG. 20, the instructions, when individually or collectively executed by the processor, may cause the electronic device (101) to display a screen (2101) on a display (e.g., display (250) of FIG. 2) that includes a plurality of first keywords (2110) and first candidate content (2120) based on the plurality of first keywords (2110).

[0285] Referring to FIG. 21, a screen (2101) including a plurality of first keywords (2110) and a first candidate content (2120) may be displayed on a display (250). The plurality of first keywords (2110) and the first candidate content (2120) may be displayed through the execution of an application for generating content. However, the present invention is not limited thereto. For example, the plurality of first keywords (2110) and the first candidate content (2120) may be displayed through the execution of a messenger application or a virtual keyboard application. For example, one or more contents (2105) may be displayed on the screen (2101). The one or more contents (2105) may be one or more contents stored in the memory of the electronic device (101), but are not limited thereto. The processor may be configured to identify a first candidate content (2120) based on receiving a user input for one of one or more contents (2105) included in a screen (2101). The processor may be configured to display the screen (2101) including the identified first candidate content (2120) on the display (250). The processor may be configured to identify a plurality of first keywords (2110) based on the first candidate content (2120) and display the screen (2101) including the plurality of first keywords (2110) on the display (250).

[0286] According to an exemplary embodiment, a plurality of first keywords (2110) may be referenced as feature keywords included in a prompt input to an artificial intelligence model to generate first candidate content (2120). The first candidate content (2120) may be content generated by inputting a prompt including a plurality of first keywords (2110) to the artificial intelligence model. For example, the first candidate content (2120) may be one of contents that may be generated when a prompt including a plurality of first keywords (2110) is input to the artificial intelligence model. The plurality of first keywords (2110) may be positioned around the first candidate content (2120) within the screen (2101).

[0287] For example, as illustrated in FIG. 21, if the plurality of first keywords (2110) include lake (2111), boat (2112), cloud (2113), and / or sunny (2114), the processor may be configured to display a screen (2101) including first candidate content (2120) based on the plurality of first keywords (2110) on the display (250). The first candidate content (2120) based on the plurality of first keywords (2110) described above may be, but is not limited to, an image that an artificial intelligence model can generate using a prompt including the plurality of first keywords (2110). For example, the first candidate content (2120) may be an image representing a lake, a boat floating on a lake, clouds in the sky, or sunny weather. The user can preview content that can be generated by a plurality of first keywords (2110) through the first candidate content (2120) included in the screen (2101).

[0288] In operation 2002 of FIG. 20, the instructions, when individually or collectively executed by the processor, may cause the electronic device (101) to add a second keyword (2210) within the screen (2101) based on receiving a first user input.

[0289] According to an exemplary embodiment, the first user input may be referred to as a user input for adding a second keyword (2210) that is different from the plurality of first keywords (2110). For example, the user may additionally input a second keyword (2210) that is different from the plurality of first keywords (2110) in order to modify the first candidate content (2120) based on the plurality of first keywords (2110). Referring to FIG. 21, the processor may be configured to display a first visual object (2130) for the first user input. When a user input is provided through the first visual object (2130), the processor may be configured to display a virtual keyboard (e.g., the virtual keyboard (2220) of FIG. 22) on the display (250).

[0290] Referring to FIG. 22, the processor may be configured to display a virtual keyboard (2220) for a first user input on the display (250) based on receiving a user input for a first visual object (2130). The user may provide a first user input for adding a second keyword (2210) different from the plurality of first keywords (2110) through the virtual keyboard (2220) displayed on the display (250). The second keyword (2210) may be input through the virtual keyboard (2220).

[0291] For example, if the second keyword (2210) is 'birds', 'birds' may be entered via the virtual keyboard (2220). After 'birds' is entered, if user input (e.g., user input to a visual object (2230)) for adding the second keyword (2210) is provided, the processor may be configured to identify a request for adding the second keyword (2210) to a prompt used to generate content. In the example described above, the first user input may include an input to the first visual object (2130) of FIG. 21, an input to the virtual keyboard (2220), and an input to the visual object (2230).

[0292] Referring to FIG. 23, the instructions, when individually or collectively executed by the processor, may cause the electronic device (101) to add a second keyword (2210) within the screen (2101) based on receiving a first user input. The second keyword (2210) may be displayed together with a plurality of first keywords (2110) included within the screen (2101) (e.g., lake (2111), boat (2112), cloud (2113), and / or sunny (2114)). The user may confirm the second keyword (2210) added through the first user input through the second keyword (2210) added within the screen (2101). For example, if the second keyword (2210) added through the first user input is 'birds', the processor may be configured to add and display 'birds' within the screen (2101).

[0293] According to an exemplary embodiment, the processor may be configured to modify the first candidate content (e.g., the first candidate content (2120) of FIG. 21) to present content based on one or more keywords (2310) included within the screen (2101).

[0294] For example, since a second keyword (2210) is added to a plurality of first keywords (2110), one or more keywords (2310) included in the screen (2101) may be referred to as the plurality of first keywords (2110) and the second keyword (2210). The processor may be configured to receive a third user input via a visual object (2420) for receiving a user input requesting generation of new content based on one or more keywords (2310). Based on the third user input, the processor may be configured to change the first candidate content (2120) into new content (e.g., the second candidate content (2410) of FIG. 24) generated by inputting a prompt including the plurality of first keywords (2110) and the second keyword (2210) into the artificial intelligence model. While generating new content to be displayed in place of the first candidate content (2120), the processor may be configured to display a visual object (2320) to indicate that new content is being generated. For example, the visual object (2320) may include, but is not limited to, an icon, image, illustration, or video to indicate that new content is being generated.

[0295] In operation 2003 of FIG. 20, the instructions, when individually or collectively executed by the processor, may cause the electronic device (101) to change the first candidate content (2120) to second candidate content (2410) based on one or more keywords (2310) included within the screen (2101).

[0296] Referring to FIG. 24, the processor may be configured to change and display a second candidate content (2410) generated by inputting a prompt including one or more keywords (2310) included in a screen (2101) into an artificial intelligence model. In the example described above, since the second keyword (2210) was added through the first user input, the prompt may include a plurality of first keywords (2110) and a second keyword (2210). According to the first user input, a second keyword (2210) may be added in addition to the plurality of first keywords (2110), and the processor may be configured to display the second candidate content (2410) generated using both the plurality of first keywords (2110) and the added second keyword (2210) on the display (250).

[0297] For example, if the second keyword (2210) is 'birds', the second candidate content (2410) may be one of the contents that can be generated when a prompt including lake (2111), boat (2112), cloud (2113), sunny (2114), and bird is input to the artificial intelligence model. The second candidate content (2410) based on the plurality of first keywords (2110) and second keywords (2210) described above may be an image of the first candidate content (2120) with birds added to the sky. The user may check in advance the contents that can be newly generated by the added second keyword (2210) through the second candidate content (2410) included in the screen (2101).

[0298] In operation 2004 of FIG. 20, the instructions, when individually or collectively executed by the processor, may cause the electronic device (101) to generate content corresponding to the second candidate content (2410) based on receiving third user input.

[0299] Referring to FIG. 24, the processor may be configured to display a visual object (2420) on the display (250) for a third user input to generate content corresponding to second candidate content (2410) based on one or more keywords (2310) included in the screen (2101). For example, the visual object (2420) may include, but is not limited to, text such as 'create'. For example, the visual object (2420) may be an icon requesting generation of content. When a third user input is provided for the visual object (2420), the processor may be configured to receive the third user input. The processor may be configured to generate new content corresponding to the second candidate content (2410) by inputting a prompt including one or more keywords (2310) contained within the screen (2101) into the artificial intelligence model based on receiving a third user input. The generated content may be stored in the memory.

[0300] According to an exemplary embodiment, when a second keyword (2210) is added by a first user input, one or more keywords (2310) included in the screen (2101) may include a plurality of first keywords (2110) and a second keyword (2210). The processor may be configured to generate content corresponding to the second candidate content (2410) based on receiving a third user input for the visual object (2420) while the second candidate content (2410) based on the plurality of first keywords (2110) and the second keyword (2210) is displayed.

[0301] For example, if the plurality of first keywords (2110) include lake (2111), boat (2112), cloud (2113), and sunny (2114), and the second keyword (2210) is 'birds', the processor may be configured to generate new content corresponding to the second candidate content (2410) illustrated in FIG. 24 based on receiving the third user input.

[0302] According to an exemplary embodiment, the processor may be configured to transmit the second candidate content (2410) to a counterpart based on receiving a seventh user input while the second candidate content (2410) is displayed on the display. For example, the processor may be configured to display a visual object (2430) on the display (250) for a seventh user input for transmitting the second candidate content (2410) to the counterpart. When the seventh user input for the visual object (2430) is provided, the processor may be configured to receive the seventh user input. The processor may be configured to transmit the second candidate content (2410) to the counterpart (e.g., an external electronic device) based on receiving the seventh user input for the visual object (2430).

[0303] According to an exemplary embodiment, an electronic device (101) provides first candidate content (2120) based on a plurality of first keywords (2110), so that a user can check content (e.g., first candidate content (2120) of FIG. 21) that can be generated through the plurality of first keywords (2110). The user can directly add a new keyword (e.g., second keyword (2210)) to modify the first candidate content (2120). The electronic device (101) can provide an improved user experience by identifying the second keyword (2210) added through the first user input and providing second candidate content (2410) using the plurality of first keywords (2110) and the second keyword (2210).

[0304] FIG. 25 is a flowchart illustrating an operation of providing candidate content of an electronic device according to an exemplary embodiment. FIGS. 26, 27, and 28 illustrate processes for changing first candidate content to second candidate content according to a second user input.

[0305] The processor (210) of FIG. 2 may be configured to perform operations of the electronic device (101) described with reference to FIG. 25. Instructions stored in a memory (e.g., memory (220) of FIG. 2) may, when individually or collectively executed by the processor (210), cause the electronic device (101) to perform operations of the electronic device (101) described in FIG. 25.

[0306] In operation 2501 of FIG. 25, the instructions, when individually or collectively executed by the processor, may cause the electronic device (101) to display a screen (2601) on the display (250) that includes a plurality of first keywords (2110) and first candidate content (2120) based on the plurality of first keywords (2110).

[0307] Action 2501 can substantially correspond to action 2001 of FIG. 20. The descriptions of action 2001 of FIG. 20 can be substantially equally applied to action 2501.

[0308] In operation 2502 of FIG. 25, the instructions, when individually or collectively executed by the processor, may cause the electronic device (101) to remove at least one keyword from among a plurality of first keywords (2110) from the screen (2601) based on receiving a second user input.

[0309] According to an exemplary embodiment, the second user input may be referenced as a user input for removing at least one keyword from among the plurality of first keywords (2110). For example, the user may exclude at least one keyword from among the plurality of first keywords (2110) to modify the first candidate content (2120) based on the plurality of first keywords (2110).

[0310] Referring to FIG. 26, the processor may be configured to display a second visual object (2610) for a second user input. The second visual object (2610) may be displayed for each of a plurality of first keywords (2110). When a second user input is provided through the second visual object (2610), the processor may be configured to remove at least one keyword corresponding to the user input from among the plurality of keywords. The processor may be configured to remove at least one keyword corresponding to the second user input and display the remaining keyword(s) excluding the at least one keyword from among the plurality of first keywords (2110) on the display (250). The second user input is not limited to an input for the second visual object (2610). For example, the second user input may be provided through a user gesture for the plurality of first keywords (2110). For example, for any one of the plurality of first keywords (2110) included in the screen (2601), a second user input may be provided through a drag input outside the screen (2601).

[0311] For example, as illustrated in FIG. 26, a second user input may be provided for a second visual object (2610) displayed on a cloud (2113) among a plurality of first keywords (2110). Referring to FIG. 27, the processor may be configured to remove cloud from the plurality of first keywords (2110) on the screen (2601) and display the remaining keywords (e.g., lake (2111), boat (2112), sunny (2114)) based on receiving a second user input for removing cloud (2113).

[0312] For example, since at least one keyword has been removed from among the plurality of first keywords (2110), one or more keywords (2710) included in the screen (2601) may be referred to as the remaining keyword(s) excluding at least one keyword from among the plurality of first keywords (2110). The processor may be configured to change the first candidate content (e.g., the first candidate content (2120) of FIG. 26) into new content (e.g., the second candidate content (2410) of FIG. 28) generated by inputting a prompt including only the remaining keyword(s) excluding at least one keyword from among the plurality of first keywords (2110) into the artificial intelligence model. For example, the second candidate content (2410) illustrated in FIG. 28 may be displayed based on a user input for a visual object (2420) for generating the second candidate content. While generating new content to be displayed in place of the first candidate content (2120), the processor may be configured to display a visual object (2720) to indicate that new content is being generated. For example, the visual object (2720) may include, but is not limited to, an icon, image, illustration, or video to indicate that new content is being generated.

[0313] In operation 2503 of FIG. 25, the instructions, when individually or collectively executed by the processor, may cause the electronic device (101) to change the first candidate content (2120) to second candidate content (2410) based on one or more keywords (2710) included within the screen (2601).

[0314] Referring to FIG. 28, the processor may be configured to change and display a second candidate content (2410) generated by inputting a prompt including one or more keywords (2710) included in a screen (2601) into an artificial intelligence model. In the example described above, since at least one keyword among the plurality of first keywords (2110) is removed through the second user input, the prompt may include the remaining keyword(s) excluding at least one keyword among the plurality of first keywords (2110). According to the second user input, at least one keyword among the plurality of first keywords (2110) may be excluded, and the processor may be configured to display, on the display (250), the second candidate content (2410) generated using only the remaining keyword(s) that are different from the at least one keyword.

[0315] For example, if at least one keyword removed through the second user input is cloud, the second candidate content (2410) may be one of the contents that may be generated when a prompt including lake (2111), boat (2112), and sunny (2114) is input to the artificial intelligence model. The second candidate content (2410) based on the remaining keyword(s) excluding at least one keyword among the plurality of first keywords (2110) described above may be an image of the first candidate content (2120) with clouds removed from the sky. The user may check in advance the contents that may be newly generated by the remaining keyword(s) excluding at least one keyword removed among the plurality of first keywords (2110) through the second candidate content (2410) included in the screen (2601).

[0316] In operation 2504 of FIG. 25, the instructions, when individually or collectively executed by the processor, may cause the electronic device (101) to generate content corresponding to the second candidate content (2410) based on receiving third user input.

[0317] Referring to FIG. 28, the processor may be configured to display a visual object (2420) on the display (250) for a third user input to generate second candidate content (2410) based on one or more keywords (2710) included in a screen (2601). When a third user input for the visual object (2420) is provided, the processor may be configured to receive the third user input. Based on receiving the third user input, the processor may be configured to generate new content corresponding to the second candidate content (2410) by inputting a prompt including one or more keywords (2710) included in the screen (2601) into an artificial intelligence model. The generated content may be stored in a memory.

[0318] According to an exemplary embodiment, when at least one keyword is removed by a second user input, one or more keywords (2710) included in the screen (2601) may include the remaining keyword(s) excluding at least one keyword among the plurality of first keywords (2110). The processor may be configured to generate content corresponding to the second candidate content (2410) based on receiving a third user input for the visual object (2420) while the second candidate content (2410) based on the remaining keyword(s) is displayed.

[0319] For example, if the plurality of first keywords (2110) include lake (2111), boat (2112), cloud (2113), and sunny (2114), and at least one keyword removed through a second user input is cloud (2113), the processor may be configured to generate new content corresponding to the second candidate content (2410) illustrated in FIG. 28 based on receiving a third user input.

[0320] According to an exemplary embodiment, an electronic device (101) provides first candidate content (2120) based on a plurality of first keywords (2110), thereby allowing a user to check content (e.g., second candidate content (2410)) that can be generated through the plurality of first keywords (2110). The user can remove at least one keyword from among the plurality of first keywords (2110) to modify the first candidate content (2120). The electronic device (101) can provide an improved user experience by identifying at least one keyword that is removed through a second user input and providing second candidate content (2410) using the remaining keyword(s) from among the plurality of first keywords (2110).

[0321] According to an exemplary embodiment, the first user input and the second user input may overlap. For example, the user may add a second keyword (2210) different from the plurality of first keywords (2110) through the first user input, and remove at least one keyword from the plurality of first keywords (2110) through the second user input. The processor may provide new second candidate content (2410) using the second keyword (2210) identified through the first user input and the remaining keyword(s) from the plurality of first keywords (2110) identified through the second user input. The electronic device (101) according to the exemplary embodiment may provide an improved user experience by providing free modification of content.

[0322] FIG. 29 is a flowchart illustrating an operation of an electronic device according to an exemplary embodiment to change second content using a plurality of first keywords from first content. FIGS. 30, 31, 32, and 33 illustrate processes for changing first candidate content into second candidate content based on a second user input.

[0323] The processor (210) of FIG. 2 may be configured to perform operations of the electronic device (101) described with reference to FIG. 29. Instructions stored in a memory (e.g., memory (220) of FIG. 2) may, when individually or collectively executed by the processor (210), cause the electronic device (101) to perform operations of the electronic device (101) described in FIG. 29.

[0324] In operation 2901 of FIG. 29, the instructions, when individually or collectively executed by the processor, may cause the electronic device (101) to receive a fourth user input for selecting first content (3010).

[0325] According to an exemplary embodiment, operation 2901 may be an operation preceding operation 2001 of FIG. 20 or operation 2501 of FIG. 25. For example, a plurality of first keywords (2110) for providing first candidate content (2120) may be obtained from first content (3010).

[0326] According to an exemplary embodiment, the first content (3010) may be at least one of the contents stored in the memory. Referring to FIG. 30, the processor may be configured to display the contents stored in the memory through a gallery application. The first content (3010) may be at least one of the contents stored in the memory. The user may provide a fourth user input for selecting the first content (3010) from among the contents displayed through the gallery application. The processor may be configured to receive the fourth user input for selecting the first content (3010). For example, multiple contents may be selected through the fourth user input.

[0327] In operation 2902 of FIG. 29, the instructions, when individually or collectively executed by the processor, may cause the electronic device (101) to obtain a plurality of first keywords (2110) from the first content (3010).

[0328] Operation 2902 of FIG. 29 may be referred to as the operation described above with reference to FIGS. 5 and 7. For example, in operation 2902, the processor may be configured to identify the style of the first content (3010) to obtain the original content of the first content (3010) and generate a description based on the analysis of the original content. The processor may be configured to obtain the prompt by inputting a large-scale language model with a prompt based on the description of the original content. The processor may be configured to obtain a plurality of first keywords (2110) from keywords included in the prompt. When a plurality of contents are selected through a fourth user input, the plurality of first keywords (2110) may be obtained from the plurality of contents.

[0329] In operation 2903 of FIG. 29, the instructions, when individually or collectively executed by the processor, may cause the electronic device (101) to display a screen (3101) including a plurality of first keywords (2110) and first candidate content (2120) on the display (250).

[0330] Operation 2903 of FIG. 29 may substantially correspond to operation 2001 of FIG. 20. The descriptions of operation 2001 of FIG. 20 may substantially be applied to operation 2903.

[0331] Referring to FIG. 31, the processor may be configured to display a screen (3101) including a plurality of first keywords (2110) and first candidate content (2120) on the display (250). Since the plurality of first keywords (2110) are obtained from the first content (e.g., the first content (3010) of FIG. 30), the first candidate content (2120) may be substantially the same as or similar to the first content (3010). For example, if the first content (3010) is an image including a house located on a roadside and a cloud, the plurality of first keywords (2110) obtained from the first content (3010) may include roadside (3111), house (3112), and cloud (3113). When a prompt including a plurality of first keywords (2110) including roadside (3111), house (3112), and cloud (3113) is input into an artificial intelligence model, the first candidate content (2120), which is one of the contents to be generated, may be substantially identical to or similar to the first content (3010). As illustrated in FIG. 31, the first candidate content (2120) based on the plurality of first keywords (2110) may be substantially identical to the first content (3010) illustrated in FIG. 30.

[0332] In operation 2904 of FIG. 29, the instructions, when individually or collectively executed by the processor, may cause the electronic device (101) to add a second keyword (2210) to the screen based on receiving the first user input.

[0333] Operation 2904 of FIG. 29 may substantially correspond to operation 2002 of FIG. 20. The descriptions of operation 2002 of FIG. 20 may be substantially identically applied to operation 2904. Operation 2904 of FIG. 29 may be omitted.

[0334] In operation 2905 of FIG. 29, the instructions, when individually or collectively executed by the processor, may cause the electronic device (101) to remove at least one keyword from among the plurality of first keywords (2110) based on receiving a second user input.

[0335] Operation 2905 of FIG. 29 may substantially correspond to operation 2502 of FIG. 25. The descriptions of operation 2502 of FIG. 25 may be substantially identically applied to operation 2905. Operation 2905 of FIG. 29 may be omitted.

[0336] In operation 2906 of FIG. 29, the instructions, when individually or collectively executed by the processor, may be configured to cause the electronic device (101) to receive a fifth user input for selecting second content (3210).

[0337] Referring to FIG. 31, the processor may be configured to display a visual object (3120) for selecting second content (3210) to be corrected using a plurality of first keywords (2110). For example, the visual object (3120) may include, but is not limited to, text such as “Apply” or “Apply to other content.” The processor may be configured to display contents (e.g., contents (3200) of FIG. 32) that may be selected as second content (3210) based on identifying a user input for the visual object (3120).

[0338] Referring to FIG. 32, the processor may be configured to display contents (3200) that can be selected as second content (3210) through the display (250). For example, the contents (3200) may be contents stored in memory, but are not limited thereto. A user may select the second content (3210) by providing a fifth user input to one of the contents (3200) displayed through the display (250). For example, the processor may be configured to identify, among the contents (3200), the content selected by the fifth user input as the second content (3210). For example, the second content (3210) may be content including an image of a car.

[0339] In operation 2907 of FIG. 29, the instructions, when individually or collectively executed by the processor, may cause the electronic device (101) to change the first candidate content (2120) to third candidate content (3310) based on one or more keywords included within the screen and the second content (3210).

[0340] According to one embodiment, the processor may be configured to generate third candidate content (3310), which is one of the contents that can be generated by inputting one or more keywords included in the screen and second content (3210) into an artificial intelligence model. The processor may be configured to change the first candidate content (2120) to the generated third candidate content (3310). If the processor receives a first user input through operation 2904, the one or more keywords included in the screen may include a plurality of first keywords (2110) and a second keyword (e.g., the second keyword (2210) of FIG. 22). If the processor receives a second user input through operation 2905, the one or more keywords included in the screen may include the remaining keyword(s) excluding at least one keyword among the plurality of first keywords (2110).

[0341] As illustrated in FIG. 32, if the second content (3210) is a content including an image of a car, as illustrated in FIG. 33, the third candidate content (3310) may be an image including a house, clouds, and a car located on the side of a road. The image may be one of the contents that can be generated by inputting a prompt including road (3111), house (3112), and cloud (3113) and the second content (e.g., the second content (3210) of FIG. 32) into an artificial intelligence model.

[0342] Figure 34 is a flowchart illustrating operations of an electronic device according to an exemplary embodiment to provide recommended keywords. Figures 35, 36, and 37 illustrate processes of an electronic device according to an exemplary embodiment to change first candidate content to second candidate content based on recommended keywords.

[0343] The processor (210) of FIG. 2 may be configured to perform operations of the electronic device (101) described with reference to FIG. 34. Instructions stored in a memory (e.g., memory (220) of FIG. 2) may, when individually or collectively executed by the processor (210), cause the electronic device (101) to perform operations of the electronic device (101) described in FIG. 34.

[0344] In operation 3401 of FIG. 34, the instructions, when individually or collectively executed by the processor, may cause the electronic device (101) to display a plurality of recommended keywords within the screen (3501).

[0345] According to an exemplary embodiment, the plurality of recommended keywords may be categorized. Referring to FIG. 35, the processor may be configured to display visual objects (3510) representing categories for the plurality of recommended keywords on the display (250) to suggest the plurality of recommended keywords. The visual objects (3510) may be displayed together with a plurality of first keywords (2110) and first candidate content (2120).

[0346] For example, the visual objects (3510) may include, but are not limited to, a visual object (3511) representing recommended keywords for modifying the style of the content, a visual object (3512) representing recommended keywords for adding people to the content, and a visual object (3513) representing recommended keywords for modifying the location of the content. The user may provide a sixth user input for selecting at least one recommended keyword via the visual objects (3510).

[0347] In operation 3402 of FIG. 34, the instructions, when individually or collectively executed by the processor, may cause the electronic device (101) to add at least one recommended keyword to the screen (3501) based on receiving a sixth user input.

[0348] According to an exemplary embodiment, the sixth user input may be referred to as a user input for selecting at least one recommended keyword from among the recommended keywords suggested by the electronic device (101). Referring to FIG. 36, the sixth user input may be provided through at least one of the visual objects (3510).

[0349] For example, in response to a user input for a visual object (3513) representing recommended keywords for adding people to content, the electronic device (101) may be configured to display visual objects (3610) representing people that can be added to the content. Information related to the people may be obtained from, but is not limited to, the frequency with which the people appear in content stored in the memory. For example, the processor may be configured to add, to the screen (3501), recommended keywords (3620) related to a visual object (3611) representing a specific person (e.g., visual object (3611) of FIG. 36 ) among the visual objects (3610). The recommended keywords (3620) displayed on the screen (3501) may be a name (e.g., James) or a nickname given to the specific person, or may appear as an image representing the specific person.

[0350] In operation 3403 of FIG. 34, the instructions, when individually or collectively executed by the processor, may cause the electronic device (101) to add a second keyword (2210) within the screen (3501) based on receiving a first user input.

[0351] Operation 3403 of FIG. 34 may substantially correspond to operation 2002 of FIG. 20. The descriptions of operation 2002 of FIG. 20 may be substantially identically applied to operation 3403. Operation 3403 of FIG. 34 may be omitted.

[0352] In operation 3404 of FIG. 34, the instructions, when individually or collectively executed by the processor, may cause the electronic device (101) to remove at least one keyword from among the plurality of first keywords (2110) based on receiving a second user input.

[0353] Operation 3404 of FIG. 34 may substantially correspond to operation 2502 of FIG. 25. The descriptions of operation 2502 of FIG. 25 may be substantially identically applied to operation 3404. Operation 3404 of FIG. 34 may be omitted.

[0354] In operation 3405 of FIG. 34, the instructions, when individually or collectively executed by the processor, may cause the electronic device (101) to change the first candidate content (2120) to second candidate content (2410) based on one or more keywords included within the screen (3501).

[0355] According to an exemplary embodiment, one or more keywords included in the screen (3501) may include at least one recommended keyword added to the screen (3501) in operation 3402. In the example described with reference to FIG. 36, when a recommended keyword (3620) is added to the screen (3501) through a sixth user input for the visual object (3511), the one or more keywords included in the screen (3501) may include a plurality of first keywords (2110) and the recommended keyword (3620). The processor may be configured to change the first candidate content (2120) to second candidate content (2410) based on the one or more keywords included in the screen (3501).

[0356] Referring to FIG. 37, the processor may be configured to change the first candidate content (e.g., the first candidate content (2120) of FIG. 35) into the second candidate content (2410). The second candidate content (2410) may be one of the contents that may be generated by inputting a prompt including one or more keywords included in the screen (3501) into the artificial intelligence model. For example, if a recommended keyword (3620) is added to the screen (3501) through a sixth user input for a visual object (3611), the second candidate content (2410) may include a specific person (3711) corresponding to the recommended keyword (3620).

[0357]

[0358] FIG. 38 is a flowchart illustrating an operation of an electronic device according to an exemplary embodiment to provide candidate content based on a conversation history of a messenger application. FIGS. 39, 40a, 40b, 40c, and 40d illustrate processes of an electronic device according to an exemplary embodiment to provide a plurality of first keywords and first candidate content based on first history information.

[0359] An electronic device (101) according to an exemplary embodiment may provide recommended keywords based on the usage history of the electronic device (101). The recommended keywords may be referenced as keywords used to modify content. For example, the electronic device (101) may provide recommended keywords based on the application execution history of the electronic device (101). As an example of the electronic device (101) providing recommended keywords based on the execution history, the execution history of a messenger application or the execution history of a virtual keyboard application is described, but the embodiments of the present disclosure are not limited thereto. The electronic device (101) may provide various recommended keywords based on the usage history of the electronic device (101).

[0360] The processor (210) of FIG. 2 may be configured to perform operations of the electronic device (101) described with reference to FIG. 38. Instructions stored in a memory (e.g., memory (220) of FIG. 2) may, when individually or collectively executed by the processor (210), cause the electronic device (101) to perform operations of the electronic device (101) described in FIG. 38.

[0361] According to an exemplary embodiment, the plurality of first keywords (2110) can be obtained from a conversation history with a user of an external electronic device through a messenger application.

[0362] In operation 3801 of FIG. 38, the instructions, when individually or collectively executed by the processor, may cause the electronic device (101) to identify first history information based on a conversation via a messenger application.

[0363] Referring to FIG. 39, a user of an electronic device (101) can converse with a user of an external electronic device via a messenger application. The conversation history (3910) with the user of the external electronic device via the messenger application can be stored in memory. The processor can be configured to identify first history information based on the conversation via the messenger application. The first history information can include, for example, the conversation history (3910) of FIG. 39 .

[0364] According to an exemplary embodiment, a visual object (3920) for receiving user input requesting content generation from the conversation history (3910) may be displayed on the display (250). Based on receiving user input for the visual object (3920), the processor may display the screen illustrated in FIG. 40A.

[0365] In operation 3802 of FIG. 38, the instructions, when individually or collectively executed by the processor, may cause the electronic device (101) to identify a plurality of first keywords (2110) based on the first history information.

[0366] According to an exemplary embodiment, the processor may be configured to identify a plurality of first keywords (e.g., the plurality of first keywords (2110) of FIG. 40A) based on the first history information. For example, referring to the conversation history (3910) of FIG. 39, the processor may be configured to analyze keywords such as shopping (4011), Sunday (4012), and / or 2pm (4013) from the first history information, and identify the analyzed keywords from the first history information as the plurality of first keywords (2110). Referring to FIG. 40A, the processor may be configured to display, on the display (250), a screen including a visual object (4001) for receiving a user input for generating a plurality of first keywords (2110) identified based on the first history information and a first candidate content (2120) based on the plurality of first keywords (2110). The processor may be configured to generate first candidate content (2120) based on a plurality of first keywords (2110) based on identifying a user input through the visual object (4001).

[0367] In operation 3803 of FIG. 38, the instructions, when individually or collectively executed by the processor, may cause the electronic device (101) to display a screen including a plurality of first keywords (2110) and first candidate content (2120) on the display (250).

[0368] According to an exemplary embodiment, the processor may be configured to display first candidate content (e.g., first candidate content (2120) of FIG. 40b), which may be generated by inputting a prompt including a plurality of first keywords (2110) identified based on first history information into an artificial intelligence model, together with the plurality of first keywords (2110). For example, when a user input is provided to a visual object (4001) of FIG. 40a, the processor may be configured to display a screen including the plurality of first keywords (2110) and the first candidate content (2120) on the display (250).

[0369] Referring to FIG. 40B, the processor may be configured to display a screen (4001) including a plurality of first keywords (2110), such as shopping (4011), Sunday (4012), and / or 2pm (4013), and first candidate content (2120) based on the plurality of first keywords (2110). The first candidate content (2120) may include images related to the plurality of first keywords (2110). For example, the first candidate content (2120) may include an image (4021) related to the keyword shopping (4011), an image (4022) related to the keyword Sunday (4012), and / or an image (4023) related to the keyword 2pm (4013). After operation 3803, the operations described in FIG. 20 or the operations described in FIG. 25 may be performed. For example, the processor may be configured to, based on receiving a first user input from a user, add a second keyword that is different from the plurality of first keywords (2110), and change the first candidate content (2120) based on the plurality of first keywords (2110) and the second keyword to the second candidate content. For example, the processor may be configured to, based on receiving a second user input from a user, remove at least one keyword from the plurality of first keywords (2110), and change the first candidate content (2120) to the second candidate content based on the remaining keyword(s).

[0370] According to an exemplary embodiment, the processor may be configured to provide recommended keywords and / or recommended contents based on the usage history of the electronic device (101). For example, the processor may be configured to identify recommended keywords and / or recommended contents from the usage history of an application, the search history entered through the electronic device (101), and / or contents stored in the memory of the electronic device (101), and display the identified recommended keywords and / or recommended contents on the display (250).

[0371] Referring to FIG. 40B, the processor may be configured to display recommended contents (4002) and recommended keywords (4003) based on the usage history of the electronic device (101) on the display (250). The recommended contents (4002) and recommended keywords (4003) may be displayed together with the first rear content (2120). To change the candidate contents (2120), the user may provide a user input for at least one of the recommended contents (4002) and recommended keywords (4003) displayed on the display (250). For example, among the recommended keywords (4003), a user input for CAP may be provided.

[0372] Referring to FIG. 40c, among the recommended keywords (4003), at least one keyword for which a user input has been provided may be included in the plurality of first keywords (2110). For example, if a user input for CAP has been provided, CAP (4014) may be added to one or more keywords included in the screen. The processor may receive a user input for a visual object (4004) for changing the first candidate content (2120) based on one or more keywords (4011, 4012, 4013, 4014) included in the screen. Since CPA (4014), which is one of the recommended keywords (4003), has been added to one or more keywords (4011, 4012, 4013, 4014) included in the screen, the first candidate content (2120) may be changed.

[0373] Referring to FIG. 40d, the processor may change the first candidate content (2120) to the second candidate content (2410). Referring to the second candidate content (2410) illustrated in FIG. 40d, an image (4024) related to the added CAP (4014) may be added. According to one embodiment, the electronic device (101) may enhance the user experience by providing recommended keywords related to the usage history of the electronic device (101).

[0374] FIG. 41 is a flowchart illustrating an operation of an electronic device according to an exemplary embodiment to provide candidate content based on a search history of a virtual keyboard application. FIG. 42 and FIG. 43 illustrate processes of an electronic device according to an exemplary embodiment to provide a plurality of first keywords and first candidate content based on second history information.

[0375] The processor (210) of FIG. 2 may be configured to perform operations of the electronic device (101) described with reference to FIG. 41. Instructions stored in a memory (e.g., memory (220) of FIG. 2) may, when individually or collectively executed by the processor (210), cause the electronic device (101) to perform operations of the electronic device (101) described in FIG. 41.

[0376] According to an exemplary embodiment, the plurality of first keywords (2110) may be obtained from a search history via a virtual keyboard application.

[0377] In operation 4101 of FIG. 41, the instructions, when individually or collectively executed by the processor, may cause the electronic device (101) to identify second history information related to a search history via the virtual keyboard application based on executing the virtual keyboard application.

[0378] Referring to FIG. 42, the processor may be configured to display a virtual keyboard (4110) on the display (250) based on identifying the execution of a virtual keyboard application. A user of the electronic device (101) may search for a specific word using the virtual keyboard (4110) displayed based on the execution of the virtual keyboard application. The processor may be configured to identify search terms entered through the virtual keyboard application and store second history information based on search history related to the search terms. For example, among search terms entered through the virtual keyboard application, search terms that have been entered frequently recently may be identified through the second history information.

[0379] In operation 3702 of FIG. 41, the instructions, when individually or collectively executed by the processor, may cause the electronic device (101) to identify a plurality of first keywords (2110) based on the second history information.

[0380] According to an exemplary embodiment, the processor may be configured to identify a plurality of first keywords (2110) based on the second history information. As described above, the processor may identify recently frequently entered search terms through the second history information, and may be configured to identify the recently frequently entered search terms as the plurality of first keywords (2110). For example, referring to FIG. 42, if the frequently entered search terms through the virtual keyboard application are orchestra and conductor, the processor may be configured to identify orchestra and conductor as the plurality of first keywords (2110).

[0381] In operation 4103 of FIG. 41, the instructions, when individually or collectively executed by the processor, may cause the electronic device (101) to display a screen (4301) including a plurality of first keywords (2110) and first candidate content (2120) on the display (250).

[0382] According to an exemplary embodiment, the processor may be configured to display first candidate content (2120) that may be generated by inputting a prompt including a plurality of first keywords (2110) identified based on second history information into an artificial intelligence model, together with the plurality of first keywords (2110). Referring to FIG. 43, the first candidate content (2120) may include images related to the plurality of first keywords (2110). Referring to FIG. 43, the processor may be configured to display a screen (4301) that includes a plurality of first keywords (2110), such as orchestra (4311) and / or conductor (4312), and first candidate content (2120) based on the plurality of first keywords (2110). The first candidate content (2120) may include images related to the plurality of first keywords (2110). For example, the first candidate content (2120) may include an image (4321) related to the keyword orchestra (4311) and / or an image (4322) related to the keyword conductor (4312). After operation 3703, the operations described in FIG. 20 or the operations described in FIG. 25 may be performed.

[0383] An electronic device (101) is provided. The electronic device (101) may include a processor (210) including processing circuitry. The electronic device (101) may include a memory (220) that stores instructions. The electronic device (101) may include a display (250). The instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to obtain a first prompt (451) corresponding to the first content (461) from the first content (461) while the first content (461) is displayed through the display (250). The instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to display the first prompt (451) through the display (250). The instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to receive a first user input for selecting at least a portion of the first content (461) or one or more words included in the first prompt (451). The instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to provide a visual effect representing the at least a portion of the first content (461) or the one or more words corresponding to the first user input.

[0384] According to one embodiment, the instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to obtain the first prompt for generating the first content using an artificial intelligence model.

[0385] According to one embodiment, the instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to obtain the original content (601) of the first content (461) to obtain the first prompt (451). The instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to generate a description representing the original content (601).

[0386] In one embodiment, the instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to obtain the first prompt (451) by inputting a prompt based on the description into a large language model (LLM). The instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to obtain the fourth content by inputting the first prompt (451) into the artificial intelligence model (470). The instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to confirm or update the first prompt (451) based on a comparison of the first content (461) and the fourth content.

[0387] According to one embodiment, the instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to identify a similarity between the first content (461) and the fourth content. The instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to confirm the first prompt (451) based on identifying the similarity exceeding a threshold value. The instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to update the first prompt (451) so that the similarity increases based on identifying the similarity below the threshold value.

[0388] According to one embodiment, the above description may correspond to the first prompt (451).

[0389] According to one embodiment, the instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to store tune-up information of the first prompt (451) in the memory (220) to obtain the third content (463) using another artificial intelligence model (920) different from the artificial intelligence model (470).

[0390] According to one embodiment, the instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to obtain the first prompt (451) from metadata of the first content (461).

[0391] In one embodiment, the instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to receive a first user input for selecting one or more words included in the first prompt (451). The instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to receive a second user input for generating third content (463) to be modified from second content (462) using the one or more words (452) identified based on receipt of the first user input. The instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to generate a second prompt (454) based on the one or more words (452). The above instructions, when executed individually or collectively by the processor (210), may cause the electronic device (101) to obtain the third content (463) by inputting the second prompt (454) into the artificial intelligence model (470).

[0392] According to one embodiment, the instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to control the display (250) to simultaneously display the first content (461) and the second content (462).

[0393] According to one embodiment, the electronic device (101) may further include a camera (230). The second content (462) may include content (1005) displayed through another electronic device (1003) contained within an external environment captured by the camera (230).

[0394] According to one embodiment, the instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to identify, from among one or more objects included in the second content (1120), an object associated with the first prompt (451). The instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to display, within the first content (1110) and the second content (1120), a virtual object (1111; 1112; 1121; 1122) for representing the object associated with the first prompt (451).

[0395] According to one embodiment, the instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to obtain the first prompt (451) corresponding to the partial region (1211) of the first content (1210) based on receipt of a third user input for the partial region (1211).

[0396] According to one embodiment, the instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to obtain the first prompt (451) based on one or more user preferred contents.

[0397] According to one embodiment, the first prompt (451) may be a prompt that, when input to the artificial intelligence model (470), generates content corresponding to the first content (461).

[0398] A method performed by an electronic device (101) including a display (250) is provided. The method may include an operation of obtaining a first prompt (451) corresponding to the first content (461) from the first content (461) while the first content (461) is displayed through the display (250). The method may include an operation of displaying the first prompt (451) through the display (250). The method may include an operation of receiving a first user input for selecting at least a portion of the first content (461) or one or more words included in the first prompt (451). The method may include an operation of providing a visual effect corresponding to the at least a portion of the first content (461) or the one or more words based on the first user input.

[0399] According to one embodiment, the method may further include obtaining the first prompt for generating the first content using an artificial intelligence model.

[0400] According to one embodiment, the method may further include an operation of obtaining the first prompt (451) from metadata of the first content (461).

[0401] In one embodiment, the method may further include receiving a first user input for selecting one or more words included in the first prompt (451). The method may further include receiving a second user input for generating third content (463) to be changed from the second content (462) using the one or more words (452) identified based on the reception of the first user input. The method may further include generating a second prompt (454) including the one or more words (452) based on the reception of the second user input. The method may further include obtaining the third content (463) by inputting the second prompt (454) into an artificial intelligence model (470).

[0402] According to one embodiment, the method may further include obtaining the first prompt (451) based on one or more user preferred contents.

[0403] An electronic device (101) is provided. The electronic device (101) may include a processor (210) including a processing circuit. The electronic device (101) may include a memory (220) that stores instructions. The electronic device (101) may include a display (250). The instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to display a screen including a plurality of first keywords (2110) and first candidate content (2120) based on the plurality of first keywords (2110) on the display (250). The instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to add a second keyword (2210) to the screen while displaying the screen on the display (250), based on receiving a first user input for adding the second keyword (2210), remove at least one keyword from among the plurality of first keywords (2110) from the screen based on receiving a second user input for removing the at least one keyword from among the plurality of first keywords (2110), and change the first candidate content (2120) to second candidate content (2410) based on one or more keywords included in the screen.

[0404] According to one embodiment, the instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to generate content corresponding to the second candidate content (2410) based on receiving a third user input for generating content corresponding to the second candidate content (2410).

[0405] According to one embodiment, the instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to obtain the plurality of first keywords (2110) from the first content (3010) based on receiving a fourth user input for selecting the first content (3010). The instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to display, on the display (250), the screen including the plurality of first keywords (2110) and first candidate content (2120) based on the plurality of first keywords (2110).

[0406] According to one embodiment, the instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to change the first candidate content (2120) to a third candidate content (3310) based on one or more keywords included in the screen and the second content (3210) based on receiving a fifth user input for selecting the second content (3210) while displaying the screen on the display (250).

[0407] According to one embodiment, the instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to display a plurality of recommended keywords within the screen, the recommended keywords being different from the plurality of first keywords (2110). The instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to add the at least one recommended keyword within the screen based on receiving a sixth user input for selecting at least one recommended keyword from among the plurality of recommended keywords.

[0408] According to one embodiment, the instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to identify first history information based on a conversation via a messenger application. The instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to identify the plurality of first keywords (2110) based on the first history information. The instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to display, on the display (250), the screen including the plurality of first keywords (2110) and the first candidate content (2120) based on the plurality of first keywords (2110), based on identifying the plurality of first keywords (2110) from the first history information.

[0409] According to one embodiment, the instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to identify second history information based on a search history via the virtual keyboard application. The instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to identify the plurality of first keywords (2110) based on the second history information. The instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to display, on the display (250), the screen including the plurality of first keywords (2110) and the first candidate content (2120) based on the plurality of first keywords (2110), based on identifying the plurality of first keywords (2110) from the second history information.

[0410] According to one embodiment, the instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to transmit the second candidate content (2410) to a counterpart based on receiving a seventh user input.

[0411] According to one embodiment, the plurality of first keywords (2110) may be positioned around the first candidate content (2120) within the screen.

[0412] According to one embodiment, the instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to display a visual object (2610) for the second user input on the display. The instructions, when individually or collectively executed by the processor (210), may cause the electronic device (101) to remove at least one keyword from among the plurality of first keywords (2110) within the screen based on receiving the second user input for the visual object (2610).

[0413] In one embodiment, the first candidate content may correspond to content generated when a prompt including the plurality of first keywords is input into an artificial intelligence model.

[0414] In one embodiment, the plurality of first keywords may correspond to feature keywords included in a prompt input to the artificial intelligence model to generate the first candidate content.

[0415] According to one embodiment, the electronic device may include a wearable device.

[0416] A method of an electronic device is provided. The method may include an operation of displaying a screen on a display of the electronic device, the screen including a plurality of first keywords and first candidate content based on the plurality of first keywords. The method may include an operation of adding a second keyword to the screen based on receiving a first user input for adding the second keyword while the screen is displayed on the display. The method may include an operation of removing at least one keyword from among the plurality of first keywords from the screen based on receiving a second user input for removing the keyword from among the plurality of first keywords. The method may include an operation of changing the first candidate content to second candidate content based on one or more keywords included in the screen.

[0417] According to one embodiment, the method may further include generating the content corresponding to the second candidate content based on receiving a third user input for generating the content corresponding to the second candidate content.

[0418] 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, electronic devices, or home appliances. Electronic devices according to the embodiments of this document are not limited to the aforementioned devices.

[0419] 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.

[0420] 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).

[0421] 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 (120) (e.g., the processor (120)) of a 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.

[0422] According to one embodiment, the method according to various embodiments disclosed in the present 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., compact disc read only memory (CD-ROM)), or may be distributed online (e.g., downloaded or uploaded) via 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 a memory (130) of a manufacturer's server, an application store's server, or a relay server.

[0423] 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 placed 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 electronic devices, A processor comprising a processing circuit; Memory for storing instructions; and Including a display, The above instructions, when individually or collectively executed by the processor, cause the electronic device to: Displaying a screen including a plurality of first keywords and first candidate content based on the plurality of first keywords on the display, While the above screen is displayed on the above display: Based on receiving a first user input for adding a second keyword, adding said second keyword within said screen, Based on receiving a second user input for removing at least one keyword from among the plurality of first keywords, removing at least one keyword from among the plurality of first keywords from the screen, and causing the first candidate content to be changed to a second candidate content based on one or more keywords included in the screen; Electronic devices.

2. In paragraph 1, The instructions, when individually or collectively executed by the processor, cause the electronic device to generate content corresponding to the second candidate content based on receiving a third user input for generating content corresponding to the second candidate content. Electronic devices.

3. In paragraph 1 or 2, The above instructions, when individually or collectively executed by the processor, cause the electronic device to: Based on receiving a fourth user input for selecting the first content, obtaining the plurality of first keywords from the first content, and Based on obtaining the plurality of first keywords from the first content, causing the screen to be displayed on the display, which includes the plurality of first keywords and the first candidate content based on the plurality of first keywords. Electronic devices.

4. In paragraph 3, The instructions, when individually or collectively executed by the processor, cause the electronic device to change the first candidate content to a third candidate content based on one or more keywords included in the screen and the second content, based on receiving a fifth user input for selecting the second content while displaying the screen on the display. Electronic devices.

5. In any one of paragraphs 1 to 4, The above instructions, when individually or collectively executed by the processor, cause the electronic device to: In the above screen, a plurality of recommended keywords are displayed, which are different from the plurality of first keywords, and Based on receiving a sixth user input for selecting at least one recommended keyword from among the plurality of recommended keywords, causing the at least one recommended keyword to be added to the screen. Electronic devices.

6. In any one of paragraphs 1 to 5, The above instructions, when individually or collectively executed by the processor, cause the electronic device to: Identify first-hand history information based on conversations through messenger applications, Based on the above first history information, identifying the plurality of first keywords, and Based on identifying the plurality of first keywords from the first history information, causing the screen including the plurality of first keywords and the first candidate content based on the plurality of first keywords to be displayed on the display. Electronic devices.

7. In any one of paragraphs 1 to 6, The above instructions, when individually or collectively executed by the processor, cause the electronic device to: Identifying second history information based on search history through the above virtual keyboard application, Based on the second history information, the plurality of first keywords are identified, and Based on identifying the plurality of first keywords from the second history information, causing the screen including the plurality of first keywords and the first candidate content based on the plurality of first keywords to be displayed on the display. Electronic devices.

8. In any one of paragraphs 1 to 7, The above instructions, when individually or collectively executed by the processor, cause the electronic device to transmit the second candidate content to the counterpart based on receiving a seventh user input. Electronic devices.

9. In any one of paragraphs 1 to 8, The above plurality of first keywords are: Within the above screen, positioned around the first candidate content, Electronic devices.

10. In any one of paragraphs 1 to 9, The above instructions, when individually or collectively executed by the processor, cause the electronic device to: Displaying a visual object for the second user input on the display, and causing at least one of said plurality of first keywords to be removed from said screen based on receiving said second user input for said visual object; Electronic devices.

11. In any one of paragraphs 1 to 10, The above first candidate content is, Corresponding to the content generated when a prompt including the above plurality of first keywords is input to an artificial intelligence model, Electronic devices.

12. In any one of paragraphs 1 to 11, The above plurality of first keywords are: In order to generate the first candidate content, corresponding to the feature keywords included in the prompt input to the artificial intelligence model, Electronic devices.

13. In any one of paragraphs 1 to 12, The above electronic device, Including a wearable device, Electronic devices.

14. In the method of an electronic device, An action of displaying a screen including a plurality of first keywords and first candidate content based on the plurality of first keywords on a display of the electronic device; An action of adding a second keyword within the screen based on receiving a first user input for adding a second keyword while displaying the screen on the display; An operation of removing at least one keyword from among the plurality of first keywords from the screen based on receiving a second user input for removing at least one keyword from among the plurality of first keywords; and An action comprising changing the first candidate content to a second candidate content based on one or more keywords included in the screen. method.

15. In paragraph 14, Further comprising a method of generating the content corresponding to the second candidate content based on receiving a third user input for generating the content corresponding to the second candidate content. method.

Images