Electronic device for providing personalized content, operation method thereof, and recording medium on which operation method is recorded

Abstract

An electronic device according to one embodiment may comprise: at least one processor including a processing circuit; and a memory for storing instructions. The at least one processor can individually and / or collectively perform the instructions. The electronic device can: identify a first object corresponding to a primary object and a second object corresponding to an additional object from among a plurality of objects included in first content; acquire personalization information related to a user from second content; acquire at least one input prompt on the basis of the first object, the second object and the personalization information; and provide, through a user interface, third content output from a first artificial intelligence model, by providing the at least one input prompt to the first artificial intelligence model. The third content can include the first object and a third object in which at least a portion of the second object is changed.

Description

Electronic device providing personalized content, method of operation thereof and recording medium recording the method of operation

[0001] The present disclosure relates to an electronic device that provides personalized content, a method of operating the same, and a recording medium recording the same.

[0002] Electronic devices can provide various digital information (e.g., still images, video, audio, etc.). The digital information can be provided from a server or other electronic device via a communication interface, or from a storage device functionally connected to the electronic device.

[0003] For example, various digital information can be generated using artificial intelligence (AI) systems. For example, the field of digital information generation using generative AI is primarily developing based on natural language processing and machine learning technologies. As AI systems become more used, their recognition rates improve and their ability to understand user preferences more accurately is increasing. Therefore, existing rule-based smart systems are gradually being replaced by deep learning-based AI systems. AI technology encompasses machine learning (deep learning) and elements utilizing machine learning.

[0004] 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-described matters constitute prior art related to the present disclosure.

[0005] An electronic device according to one embodiment may include at least one processor including a processing circuit and a memory storing instructions. The at least one processor may individually and / or collectively execute instructions. The electronic device may identify a first object corresponding to a primary object and a second object corresponding to an additional object among a plurality of objects included in a first content. The electronic device may obtain personalized information related to a user from the second content. The electronic device may obtain at least one input prompt based on the first object, the second object, and the personalized information. The electronic device may provide at least one input prompt to a first artificial intelligence model so as to provide third content output from the first artificial intelligence model through a user interface. The third content may include a first object and a third object in which at least a portion of the second object is modified.

[0006] A method performed by an electronic device according to one embodiment may include an operation of identifying, among a plurality of objects included in a first content, a first object corresponding to a primary object and a second object corresponding to an additional object. The method performed by the electronic device may include an operation of obtaining personalized information related to a user. The method performed by the electronic device may include an operation of providing, through a user interface, second content generated based on the first object, the second object, and the personalized information. The second content may include the first object and a third object in which at least a portion of the second object is modified.

[0007] In one embodiment, the instructions of a non-transitory computer-readable recording medium having recorded thereon instructions, when executed individually and / or collectively by at least one processor including a processing circuit, may cause an electronic device to perform at least one operation. The operation performed by the processor may include an operation of identifying, among a plurality of objects included in a first content, a first object and a second object designated to be changeable through the electronic device. The operation performed by the processor may include an operation of obtaining personalized information related to a user from the second content. The operation performed by the processor may include an operation of providing, through a user interface, third content generated based on the first object, the second object, and the personalized information. The third content may include a first object and a third object in which at least a portion of the second object is changed based on the personalized information.

[0008] In connection with the description of the drawings, the same or similar reference numerals may be used for identical or similar components. Furthermore, the above and other aspects, features, and advantages of specific embodiments of the present disclosure will become more apparent in the following detailed description taken in conjunction with the drawings.

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

[0010] FIG. 2 is a block diagram of an exemplary configuration of an electronic device according to various embodiments.

[0011] FIG. 3 is a flowchart illustrating an example of a method of operating an electronic device according to various embodiments.

[0012] FIG. 4 is a block diagram of an example of a method of operating an electronic device according to various embodiments.

[0013] FIG. 5 is a diagram illustrating an example of exchanging a first electronic device and a second electronic device according to various embodiments.

[0014] FIG. 6 is a diagram illustrating an electronic device for classifying objects from content according to various embodiments.

[0015] FIG. 7 is a diagram illustrating an electronic device that obtains personalized information from content according to various embodiments.

[0016] FIG. 8 is a diagram illustrating an electronic device for obtaining an input prompt according to various embodiments.

[0017] FIG. 9 is a diagram illustrating an electronic device that acquires content using a generative artificial intelligence model according to various embodiments.

[0018] FIG. 10 is a diagram illustrating an electronic device that acquires content using a generative artificial intelligence model according to various embodiments.

[0019] FIG. 11 is a diagram illustrating an electronic device that acquires content using a generative artificial intelligence model according to various embodiments.

[0020] FIG. 12 is a diagram illustrating an electronic device that acquires content using a generative artificial intelligence model according to various embodiments.

[0021] FIG. 13 is a diagram illustrating an electronic device that acquires content using a generative artificial intelligence model according to various embodiments.

[0022] FIG. 14 is a diagram illustrating an electronic device that acquires content using a generative artificial intelligence model according to various embodiments.

[0023] FIG. 15 is a diagram showing an example of a configuration of a system including a generative artificial intelligence model according to various embodiments.

[0024] Advances in electronic devices and network technology have allowed users to differentiate between the time, frequency, exposure, and type of content they receive (feed) from web pages they visit, social network services (SNS), and applications they use. However, this content is not tailored to the user. When content is tailored to the user, it can have the effect of increasing user attention.

[0025] Below, various embodiments of the present disclosure are described in more detail with reference to the attached drawings. However, the present disclosure may be implemented in many different forms and is not limited to the various embodiments described herein. In addition, for the purpose of clearly explaining the present disclosure, parts irrelevant to the description may be omitted in the drawings, and similar parts are designated by similar reference numerals throughout the present disclosure.

[0026] The terms used in this disclosure are described as currently common terms, taking into account the functions mentioned herein. However, these terms may mean various other terms depending on the intentions of those skilled in the art, precedents, the emergence of new technologies, etc. Therefore, the terms used in this disclosure should not be interpreted solely based on their names, but rather based on the meanings of the terms and the overall content of this disclosure.

[0027] Additionally, while terms such as first, second, etc. may be used to describe various components, the components should not be limited by these terms. These terms are used to distinguish one component from another.

[0028] Throughout this disclosure, when a part is said to be "connected" to another part, this includes not only cases where the part is "directly connected," but also cases where the part is "electrically connected" with another element intervening therebetween. Furthermore, when a part is said to "include" a component, this does not exclude other components, but may include other components, unless otherwise specifically stated.

[0029] The phrases “in one embodiment” and the like appearing in various places throughout this disclosure do not necessarily all refer to the same embodiment.

[0030] An embodiment of the present disclosure may be represented by functional block configurations and various processing steps. Some or all of these functional blocks may be implemented by various hardware and / or software configurations that perform specific functions. For example, the functional blocks of the present disclosure may be implemented by one or more microprocessors or by circuit configurations for a given function. Furthermore, for example, the functional blocks of the present disclosure may be implemented in various programming or scripting languages. The functional blocks may be implemented by algorithms that execute on one or more processors. Furthermore, the present disclosure may employ conventional techniques for electronic configuration, signal processing, and / or data processing. Terms such as "mechanism," "element," "means," and "configuration" may be used broadly and are not limited to mechanical and physical configurations.

[0031] Additionally, the connecting lines or connecting members between components depicted in the drawings are merely exemplary representations of functional connections and / or physical or circuit connections. In an actual device, connections between components may be represented by various functional connections, physical connections, or circuit connections that may be replaced or added.

[0032] FIG. 1 is an example block diagram of an electronic device within a network environment according to various embodiments.

[0033] FIG. 1 is a block diagram of an electronic device (101) within a network environment (100) according to various embodiments. Referring to FIG. 1, in the network environment (100), the electronic device (101) may communicate with the electronic device (102) via a first network (198) (e.g., a short-range wireless communication network), or may communicate with at least one of the electronic device (104) or the 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 have at least one of the various components (e.g., the connection terminal (178)) omitted, or one or more other components added. In some embodiments, some of the various 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)).

[0034] The processor (120) may include various processing circuits and / or multiple processors. For example, the term "processor" as used herein, including in the claims, may include various processing circuits, including at least one processor, wherein one or more of the at least one processor may be configured to individually and / or collectively perform the various functions described herein in a distributed manner. When the terms "processor," "at least one processor," and "one or more processors" as used herein are described as being configured to perform a number of functions, these terms include, for example, without limitation, a situation where one processor performs some of the recited functions and other processor(s) perform other of the recited functions, and a situation where a single processor may perform all of the recited functions. Furthermore, the at least one processor may include a combination of processors that perform the various recited / disclosed functions (e.g., in a distributed manner). The at least one processor may execute program instructions to achieve or perform the various functions.

[0035] The processor (120) may, for example, execute software (e.g., a program (140)) to control at least one other component (e.g., a hardware or software component) of the electronic device (101) connected to the processor (120) and perform various data processing or operations. According to one embodiment, as at least a part of the data processing or operations, the processor (120) may store commands or data received from other components (e.g., a sensor module (176) or a communication module (190)) in a volatile memory (132), process the commands or data stored in the volatile memory (132), and store result data in a non-volatile memory (134). According to one embodiment, the processor (120) may include a main processor (121) (e.g., a central processing unit or an application processor) or an auxiliary processor (123) (e.g., a graphics processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor) that can operate independently or together with the main processor (121). For example, when the electronic device (101) includes the main processor (121) and the auxiliary processor (123), the auxiliary processor (123) may be configured to use less power than the main processor (121) or to be specialized for a given function. The auxiliary processor (123) may be implemented separately from the main processor (121) or as a part thereof.

[0036] The auxiliary processor (123) may control at least a portion of functions or states associated with at least one component (e.g., a display module (160), a sensor module (176), or a communication module (190)) of the electronic device (101), for example, on behalf of the main processor (121) while the main processor (121) is in an inactive (e.g., sleep) state, or together with the main processor (121) while the main processor (121) is in an active (e.g., application execution) state. In one embodiment, the auxiliary processor (123) (e.g., an image signal processor or a communication processor) may be implemented as a part of another functionally related component (e.g., a camera module (180) or a communication module (190)). In one embodiment, the auxiliary processor (123) (e.g., a neural network processing unit) may include a hardware structure specialized for processing artificial intelligence models. The artificial intelligence models may be generated through machine learning. This learning can be performed, for example, on the electronic device (101) itself where the artificial intelligence model is executed, or can be performed through a separate server (e.g., server (108)). The learning algorithm can include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but is not limited to the examples described above. The artificial intelligence model can include multiple artificial neural network layers.The artificial neural network may be one of a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), a deep Q-network, or a combination of two or more of the above, but is not limited to the examples described above. In addition to, or alternatively to, a hardware structure, an artificial intelligence model may include a software structure.

[0037] The memory (130) can store various data used by at least one component (e.g., processor (120) or sensor module (176)) of the electronic device (101). The data can include, for example, software (e.g., program (140)) and input data or output data for commands related thereto. The memory (130) can include volatile memory (132) or non-volatile memory (134).

[0038] The program (140) may be stored as software in the memory (130) and may include, for example, an operating system (142), middleware (144), or an application (146).

[0039] The input module (150) can receive commands or data to be used in a component of the electronic device (101) (e.g., a processor (120)) from an external source (e.g., a user) of the electronic device (101). The input module (150) can include, for example, a microphone, a mouse, a keyboard, a key (e.g., a button), or a digital pen (e.g., a stylus pen).

[0040] The audio output module (155) can output audio signals to the outside of the electronic device (101). The audio output module (155) can include, for example, a speaker or a receiver. The speaker can be used for general purposes, such as multimedia playback or recording playback. The receiver can be used to receive incoming calls. In one embodiment, the receiver can be implemented separately from the speaker or as part of the speaker.

[0041] The display module (160) can visually provide information to an external party (e.g., a user) of the electronic device (101). The display module (160) may include, for example, a display, a holographic device, or a projector and a control circuit for controlling the device. According to one embodiment, the display module (160) may include a touch sensor configured to detect a touch, or a pressure sensor configured to measure the intensity of a force generated by the touch.

[0042] The audio module (170) can convert sound into an electrical signal, or vice versa, convert an electrical signal into sound. According to one embodiment, the audio module (170) can acquire sound through the input module (150), output sound through the sound output module (155), or an external electronic device (e.g., electronic device (102)) (e.g., speaker or headphone) directly or wirelessly connected to the electronic device (101).

[0043] The sensor module (176) can detect the operating status (e.g., power or temperature) of the electronic device (101) or the external environmental status (e.g., user status) and generate an electrical signal or data value corresponding to the detected status. According to one embodiment, the sensor module (176) can include, for example, a gesture sensor, a gyro sensor, a barometric pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biometric sensor, a temperature sensor, a humidity sensor, or an illuminance sensor.

[0044] The interface (177) may support one or more designated protocols that may be used to directly or wirelessly connect the electronic device (101) with an external electronic device (e.g., the electronic device (102)). In one embodiment, the interface (177) may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

[0045] The connection terminal (178) may include a connector through which the electronic device (101) may be physically connected to an external electronic device (e.g., electronic device (102)). According to one embodiment, the connection terminal (178) may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (e.g., a headphone connector).

[0046] The haptic module (179) can convert electrical signals into mechanical stimuli (e.g., vibration or movement) or electrical stimuli that a user can perceive through tactile or kinesthetic sensations. According to one embodiment, the haptic module (179) can include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

[0047] The camera module (180) can capture still images and videos. According to one embodiment, the camera module (180) may include one or more lenses, image sensors, image signal processors, or flashes.

[0048] The power management module (188) can manage power supplied to the electronic device (101). According to one embodiment, the power management module (188) can be implemented as, for example, at least a part of a power management integrated circuit (PMIC).

[0049] A battery (189) may power at least one component of the electronic device (101). In one embodiment, the battery (189) may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0050] The communication module (190) may support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between the electronic device (101) and an external electronic device (e.g., electronic device (102), electronic device (104), or server (108)), and the performance of communication through the established communication channel. The communication module (190) may operate independently from the processor (120) (e.g., application processor) and may include one or more communication processors that support direct (e.g., wired) communication or wireless communication. According to one embodiment, the communication module (190) may include a wireless communication module (192) (e.g., a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module (194) (e.g., a local area network (LAN) communication module, or a power line communication module). Among these communication modules, the corresponding communication module can communicate with an external electronic device (104) via a first network (198) (e.g., a short-range communication network such as Bluetooth, wireless fidelity (WiFi) direct, or infrared data association (IrDA)) or a second network (199) (e.g., a long-range communication network such as a legacy cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (e.g., a LAN or WAN)). These various types of communication modules can be integrated into a single component (e.g., a single chip) or implemented as multiple separate components (e.g., multiple chips). The wireless communication module (192) can verify or authenticate the electronic device (101) within a communication network such as the first network (198) or the second network (199) by using subscriber information (e.g., an international mobile subscriber identity (IMSI)) stored in the subscriber identification module (196).

[0051] The wireless communication module (192) can support 5G networks and next-generation communication technologies following the 4G network, such as NR access technology (new radio access technology). The NR access technology can support high-speed transmission of high-capacity data (eMBB (enhanced mobile broadband)), minimization of terminal power and connection of multiple terminals (mMTC (massive machine type communications)), or high reliability and low latency (URLLC (ultra-reliable and low-latency communications)). The wireless communication module (192) can support, for example, a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate. The wireless communication module (192) can support various technologies for securing performance in a high-frequency band, such as beamforming, massive multiple-input and multiple-output (MIMO), full dimensional MIMO (FD-MIMO), array antenna, analog beam-forming, or large scale antenna. The wireless communication module (192) can support various requirements specified in the electronic device (101), an external electronic device (e.g., the electronic device (104)), or a network system (e.g., the second network (199)). According to one embodiment, the wireless communication module (192) can support a peak data rate (e.g., 20 Gbps or more) for 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.

[0052] The antenna module (197) can transmit or receive signals or power to or from an external device (e.g., an external electronic device). In one embodiment, the antenna module (197) may include an antenna including a radiator including a conductor or a conductive pattern formed on a substrate (e.g., a PCB). In one embodiment, the antenna module (197) may include a plurality of antennas (e.g., an array antenna). In this case, at least one antenna suitable for a communication method used in a communication network, such as the first network (198) or the second network (199), may be selected from the plurality of antennas, for example, by the communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device via the at least one selected antenna. In some embodiments, in addition to the radiator, another component (e.g., a radio frequency integrated circuit (RFIC)) may be additionally formed as a part of the antenna module (197).

[0053] According to various embodiments, the antenna module (197) may form a mmWave antenna module. In one embodiment, the mmWave antenna module may include a printed circuit board, an RFIC disposed on or adjacent a first side (e.g., a bottom side) of the printed circuit board and capable of supporting a designated high-frequency band (e.g., a mmWave band), and a plurality of antennas (e.g., an array antenna) disposed on or adjacent a second side (e.g., a top side or a side side) of the printed circuit board and capable of transmitting or receiving signals in the designated high-frequency band.

[0054] At least some of the above components can be interconnected and exchange signals (e.g., commands or data) with each other via a communication method between peripheral devices (e.g., a bus, GPIO (general purpose input and output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface)).

[0055] According to one embodiment, commands or data may be transmitted or received between the electronic device (101) and an external electronic device (104) via a server (108) connected to a second network (199). Each of the external electronic devices (102 or 104) may be the same or a different type of device as the electronic device (101). According to one embodiment, all or part of the operations executed in the electronic device (101) may be executed in one or more of the external electronic devices (102, 104, or 108). For example, when the electronic device (101) is to perform a certain function or service automatically or in response to a request from a user or another device, the electronic device (101) may, instead of or in addition to executing the function or service itself, request one or more external electronic devices to perform the function or at least a part of the service. One or more external electronic devices that receive the request may execute at least a portion of the requested function or service, or an additional function or service related to the request, and transmit the result of the execution to the electronic device (101). The electronic device (101) may process the result as is or additionally and provide it as at least a portion of a response to the request. For this purpose, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used, for example. The electronic device (101) may provide an ultra-low latency service by using distributed computing or mobile edge computing, for example. In another embodiment, the external electronic device (104) may include an Internet of Things (IoT) device. The server (108) may be an intelligent server utilizing machine learning and / or a neural network. According to one embodiment, the external electronic device (104) or the server (108) may be included in the second network (199).The electronic device (101) can be applied to intelligent services (e.g., smart home, smart city, smart car, or healthcare) based on 5G communication technology and IoT-related technology.

[0056] FIG. 2 is a block diagram illustrating an exemplary configuration of an electronic device according to various embodiments. The electronic device (101) according to one embodiment of FIG. 2 can provide personalized content to a user.

[0057] Referring to FIG. 2, an electronic device (101) according to one embodiment may include a processor (e.g., including a processing circuit) (220) and a memory (230). The components of the electronic device (101) illustrated in FIG. 2 are for illustrative purposes only, and the electronic device (101) may include more components than the components illustrated in FIG. 2 or may include other components that may replace at least some of the components. For example, the electronic device (101) may include at least one of a display (260) and a communication module (e.g., including a communication circuit) (290). For example, the memory (230) is not limited to a storage medium included in the electronic device (101), and may include a cloud storage external to the electronic device (101). The electronic device (101), processor (220), memory (230), display (260), and communication module (290) of FIG. 2 may each correspond to the electronic device (101), processor (120), memory (130), display module (160), and communication module (190) described above with reference to FIG. 1.

[0058] According to one embodiment, the memory (230) may store instructions that can be executed by the processor (220). The processor (220) may perform operations or control components of the electronic device (101) by executing the instructions stored in the memory (230). The memory (230) may store at least one module and / or artificial intelligence model implemented in software.

[0059] According to one embodiment, the display (260) can display at least one content. The content can include digital information provided via a wired or wireless communication network. For example, the content can include, but is not limited to, video content (e.g., TV program video, VOD (video on demand), user-created content (UCC), music videos, YouTube videos), still image content (e.g., photographs, drawings), text content (e.g., e-books (poems, novels), letters, work files), music content (e.g., music, musical pieces, radio broadcasts), web pages, and messages.

[0060] According to one embodiment, the communication module (290) may include various communication circuits and may transmit and receive data with at least one external electronic device. For example, the communication module (290) may transmit and receive content with the external electronic device. For example, the communication module (290) may transmit and receive information related to objects included in the content with the external electronic device. For example, the communication module (290) may transmit and receive input prompts provided to the generative artificial intelligence model with the external electronic device.

[0061] According to one embodiment, the processor (220) can control one or more components of the electronic device. The processor (220) can control the components of the electronic device by executing a command so that the electronic device performs a predetermined function corresponding to the command.

[0062] In the present disclosure, the operation of the electronic device (101) may be understood as being performed by at least one processor (220) executing instructions. For example, the processor (220) of the electronic device (101) may correspond to a plurality of processors that collectively perform a plurality of operations by dividing them among the processors. According to one embodiment, the processor (220) may include at least one of an application processor (AP), a central processing unit (CPU), an image signal processor (ISP), a graphical processing unit (GPU), or a neural processing unit (NPU). For example, the processor (220) may include, but is not limited to, various processing circuits and / or multiple processors. For example, as used herein, including in the claims, the term “processor” may include various processing circuits including at least one processor, wherein one or more of the at least one processor may be configured to individually and / or collectively perform various functions described herein in a distributed manner. When "processor," "at least one processor," and "one or more processors" are described herein as being configured to perform multiple functions, these terms include, but are not limited to, situations where one processor performs some of the recited functions, another processor performs other of the recited functions, and situations where a single processor can perform all of the recited functions. Furthermore, the at least one processor may comprise a combination of processors that perform various recited / disclosed functions, for example, in a distributed manner. At least one processor may execute program instructions to achieve or perform various functions.According to one embodiment, the processor (220) may identify a first object classified as a primary object and a second object classified as an additional object among a plurality of objects in the first content. The primary object may include an object that conveys a key message or purpose of the first content. The additional object may include an object that is placed in the first content to make the primary object stand out. For example, the processor (220) may identify the first object and the second object classified by the second artificial intelligence model from the first content by providing the first content to a second artificial intelligence model trained to identify objects included in the content. For example, the processor (220) may recognize a first identifier from the first content and, based on the first identifier, identify an object set as the first object from the first content. For example, the processor (220) can recognize a second identifier from the first content and, based on the second identifier, identify an object set as a second object from the first content.

[0063] According to one embodiment, the primary object may include an object or portion (e.g., an area of ​​an image, a section of audio, an element of a user interface) that is restricted from change. For example, the secondary object may include an object or portion (e.g., an area of ​​an image, a section of audio, an element of a user interface) that can be changed using user-related information in the electronic device (101). The primary object may include a product appearance, a product name, a company name, a price, a date, or an advertising copy included in the first content. The secondary object may correspond to objects other than the primary object. The secondary object may correspond to objects other than the primary object that satisfy a specific condition (e.g., a condition in which the type of object corresponds to a person, an animal, or a background, or a condition in which the size of the area occupied in the image is greater than a certain level). For example, the primary object and / or the secondary object may be designated by the producer or provider of the first content. For example, the primary object and / or the secondary object may be identified by an artificial intelligence model. For example, the embodiments of this document may be applied by classifying some of the sub-properties of an object as primary properties and others as secondary properties.

[0064] According to one embodiment, the processor (220) can obtain personalized information related to the user from second content used by the user. For example, the processor (220) can obtain personalized information from content (e.g., video, photo, music, application) being played on the electronic device (101). For example, the processor (220) can obtain personalized information from content (e.g., video, photo, music, application) to be played on the electronic device (101). For example, the processor (220) can obtain personalized information from context information (e.g., location information, information about a screen being displayed by the electronic device, information about the surrounding environment of the electronic device, status information of the electronic device, status information of the user, or schedule information of the user) obtained by the user using the electronic device (101). For example, the processor (220) can obtain personalized information output from the third artificial intelligence model by providing at least one content to a third artificial intelligence model that has been trained to obtain weights for each of the preset types from the content. For example, the electronic device (101) can obtain personalized information output from the third artificial intelligence model by providing an image currently being displayed by the electronic device (101) (e.g., fourth content) to the third artificial intelligence model. For example, the electronic device (101) can obtain personalized information output from the third artificial intelligence model by providing an image to be displayed after the third content is displayed (e.g., fifth content) to the third artificial intelligence model.

[0065] According to one embodiment, the processor (220) may obtain a first input prompt including at least a portion of a feature regarding a primary object identified from the content. For example, the processor (220) may generate a first input prompt including at least a portion of a feature regarding a first object identified from an image (e.g., first content) to obtain third content output by performing operation 340 of FIG. 3 by the electronic device (101).

[0066] According to one embodiment, the processor (220) may obtain a second input prompt based on additional objects and personalized information identified from the content. For example, the processor (220) may generate a second input prompt that includes at least a portion of features regarding the additional object. For example, in order to obtain third content output by performing operation 340 of FIG. 3 by the electronic device, the second input prompt that includes at least a portion of features regarding the second object identified from the image (e.g., the first content) may be obtained. For example, the electronic device may obtain a second input prompt that includes at least a portion of personalized information output from the artificial intelligence model by providing an image currently being displayed by the electronic device (e.g., the fourth content) to an artificial intelligence model trained to obtain weights for each of the preset types from the content. For example, the electronic device may obtain a second input prompt including at least a portion of personalized information output from the artificial intelligence model by providing an image to be displayed (e.g., fifth content) after the third content is displayed to an artificial intelligence model that has been trained to obtain weights for each of the preset types from the content.

[0067] For example, the processor (220) may obtain a second input prompt that includes at least a portion of information about the second object and at least a portion of personalized information. For example, the personalized information may include information relevant to the user according to the user's interests, preferences, needs, and circumstances. For example, the personalized information may include information about at least a portion of the user's face and body. For example, the personalized information may include contextual information obtained by the user using the electronic device (e.g., location information, information about the screen being displayed by the electronic device, information about the surrounding environment of the electronic device, status information of the electronic device, status information of the user, or schedule information of the user). For example, the processor (220) may obtain a second input prompt that includes at least a portion of features obtained from an image relevant to the user.

[0068] According to one embodiment, the processor (220) may obtain third content output from the first artificial intelligence model by providing at least a portion of the first input prompt and at least a portion of the second input prompt to a first artificial intelligence model trained to generate user-customized content. For example, the third content may include a first object and a third object that is replaced with a second object or in which at least a portion of the second object is modified.

[0069] In one embodiment, the first and second input prompts may be configured as a single input prompt.

[0070] According to one embodiment, the processor (220) can identify first objects and second objects classified by the second artificial intelligence model from the first content by providing the first content to a second artificial intelligence model trained to identify objects included in the content.

[0071] According to one embodiment, at least some of the artificial intelligence models according to the present disclosure may be provided by the electronic device (101) or may be provided by another electronic device (e.g., a server). For example, in the above-described embodiment, the first artificial intelligence model may be located in the server, and the second and third artificial intelligence models may be located in the electronic device (101).

[0072] According to one embodiment, at least some of the models of the first, second and third artificial intelligence models may correspond to modules included in one artificial intelligence system that provide different functions.

[0073] According to one embodiment, at least some of the operations utilizing artificial intelligence according to the present disclosure may be performed by the processor (220) of the electronic device. For example, first content (e.g., original content) may be modified into third content (e.g., content obtained by modifying the original content) through a processor or auxiliary processor (123) specialized in processing artificial intelligence models.

[0074] Meanwhile, the function related to artificial intelligence according to the present disclosure may be operated through a processor (220) and a memory (230). The processor (220) may be composed of one or more processors. In this case, the one or more processors may be a general-purpose processor such as a central processing unit (CPU), an application processor (AP), a digital signal processor (DSP), a graphics-only processor such as a graphical processing unit (GPU), a vision processing unit (VPU), or an artificial intelligence-only processor such as a neural processing unit (NPU). The one or more processors control the processing of input data according to predefined operation rules or artificial intelligence models stored in the memory (230). Alternatively, when the one or more processors are artificial intelligence-only processors, the artificial intelligence-only processor may be designed with a hardware structure specialized for processing a specific artificial intelligence model. The processor may perform a preprocessing process for converting data to be applied to the artificial intelligence model into a form suitable for application to the artificial intelligence model.

[0075] In one embodiment, an AI model may be composed of multiple neural network layers. Each of the multiple neural network layers has multiple weight values ​​and performs neural network operations through operations between the computational results of the previous layer and the multiple weights. The multiple weights of the multiple neural network layers may be optimized based on the learning results of the AI ​​model. For example, the multiple weights may be updated during the learning process so that the loss or cost values ​​obtained from the AI ​​model are reduced or minimized.

[0076] An artificial intelligence model according to the present disclosure can be created through learning. An AI model created through learning can refer to an AI model configured to perform a desired function (or purpose) by, for example, a basic AI model learned from a plurality of learning data by predefined operating rules or a learning algorithm. The disclosed artificial intelligence model can be created by learning a plurality of text data and image data input as learning data according to predetermined criteria. The artificial intelligence model can generate result data by performing learned functions in response to the input data and output the result data. This learning can be performed on the device itself on which the artificial intelligence according to the present disclosure is performed, or can be performed through a separate server (e.g., server (108) of FIG. 1) and / or system. The server (e.g., server (108) of FIG. 1) can transmit and receive data with the electronic device (101). For example, a server (e.g., server (108) of FIG. 1) may apply data received from an electronic device (101) to an artificial intelligence model and transmit data output from the artificial intelligence model to the electronic device (101). As another example, the server (e.g., server (108) of FIG. 1) may transmit data used to update an artificial intelligence model built in the electronic device (101) to the electronic device (101). In addition, the disclosed artificial intelligence model may include a plurality of artificial intelligence models trained to perform at least one function. There may be a plurality of artificial intelligence models performing the same function, and a single artificial intelligence model may perform at least one function of the disclosed embodiments. An artificial intelligence model according to the present disclosure may be built in at least one of the electronic device (101) and a server (e.g., server (108) of FIG. 1).

[0077] According to one embodiment, the electronic device (101) can receive information about an artificial intelligence model learned from a server (e.g., server (108) of FIG. 1). For example, the server (e.g., server (108) of FIG. 1) can train an artificial intelligence model built on the server and transmit data about the artificial intelligence model updated through the training to the electronic device (101). In this case, the electronic device (101) can receive information about updated weights among the weights of the artificial intelligence model and update the artificial intelligence model built on the electronic device (101) using the received information.

[0078] The AI ​​model according to the present disclosure may include a personalized AI model. The personalized AI model may include a general AI model personalized using personalized information. Personalization may include the general AI model learning the user's personal data to improve user accuracy, thereby updating data related to at least some neural network layers of the general AI model.

[0079] Meanwhile, the artificial intelligence model used in the disclosed embodiments may be implemented in various embodiments depending on the manufacturer of the electronic device or the user of the electronic device, and is not limited by the examples above.

[0080] FIG. 3 is a flowchart illustrating an example of an operating method of an electronic device according to various embodiments. The operation of the electronic device illustrated in FIG. 3 (e.g., the electronic device (101) of FIGS. 1 and 2) may be performed by a processor (e.g., the processor (220) of FIG. 2) performing calculations or controlling components of the electronic device (e.g., the electronic device (101) of FIGS. 1 and 2). In the following embodiments, the operations may be performed sequentially, but are not necessarily performed sequentially. For example, the order of the operations may be changed, and at least two operations may be performed in parallel.

[0081] According to one embodiment, in operation 310, the electronic device may identify a first object and a second object among a plurality of objects within the first content. For example, the electronic device may identify at least one object included in at least one content. The electronic device may classify the identified object into a primary object or an additional object. The primary object may include an object that conveys a key message or purpose of the first content. The additional object may include an object that is positioned in the first content to make the primary object stand out. The first content may include digital information to be provided to the user. For example, the first content may include at least one of a still image, a moving image, text, music, a web page, or a message.

[0082] According to one embodiment, an electronic device can identify a first object classified as a primary object and a second object classified as an additional object among a plurality of objects in a first content. For example, the electronic device can identify the first object and the second object classified by the second artificial intelligence model from the first content by providing the first content to a second artificial intelligence model trained to identify objects included in the content. For example, the electronic device can identify a first identifier from the first content and, based on the first identifier, identify an object set as a first object from the first content. For example, the electronic device can identify a second identifier from the first content and, based on the second identifier, identify an object set as a second object from the first content.

[0083] According to one embodiment, in operation 320, the electronic device may obtain personalized information related to the user from the second content. For example, the second content may include content related to the user. For example, the second content may include user data. For example, the electronic device may obtain personalized information from content (e.g., a video, a photo, music, an application) currently being played on the electronic device. For example, the electronic device may obtain personalized information from content (e.g., a video, a photo, music, an application) to be played on the electronic device. For example, the second content may include personal identification information of the user. For example, the second content may include location information of the user. For example, the second content may include context information. Context information may include information indicating the situation of the electronic device. For example, the context information may include at least one of location information, information regarding the screen being displayed by the electronic device, information regarding the surrounding environment of the electronic device, status information of the electronic device, status information of the user, or schedule information of the user.

[0084] According to one embodiment, the electronic device can obtain personalized information output from the third AI model by providing second content to a third AI model trained to obtain weights for each of the preset types from the content. For example, the electronic device can obtain personalized information output from the third AI model by applying user data to the third AI model. For example, the electronic device can obtain personalized information output from the third AI model by providing the third AI model with an image currently being displayed by the electronic device (e.g., fourth content). For example, the electronic device can obtain personalized information output from the third AI model by providing the third AI model with an image to be displayed after the third content is displayed (e.g., fifth content). For example, an electronic device can obtain personalized information output from a third artificial intelligence model by providing context information (e.g., location information, information about the screen the electronic device is displaying, information about the surrounding environment of the electronic device, status information of the electronic device, status information of the user, or schedule information of the user) to the third artificial intelligence model.

[0085] According to one embodiment, in operation 330, the electronic device may obtain a first input prompt and a second input prompt. The input prompt may include information regarding content to be generated by the generative artificial intelligence model. For example, the electronic device may obtain an input prompt that includes at least a portion of the characteristics of at least one object identified from at least one piece of content.

[0086] In one embodiment, the electronic device may obtain a first input prompt that includes at least a portion of a feature regarding a primary object identified from content. For example, the electronic device may obtain a first input prompt that includes at least a portion of a feature regarding a first object identified from an image input to the electronic device (e.g., first content) to obtain third content output by performing operation 340 by the electronic device.

[0087] In one embodiment, the electronic device may obtain a second input prompt that includes at least a portion of a feature regarding an additional object identified from the content. For example, in order to obtain third content output by performing operation 340 by the electronic device, the electronic device may obtain a second input prompt that includes at least a portion of a feature regarding a second object identified from an image input to the electronic device (e.g., first content).

[0088] According to one embodiment, the electronic device may obtain a second input prompt that includes at least a portion of features regarding an additional object and at least a portion of personalized information. The personalized information may include information relevant to the user according to the user's interests, preferences, needs, and circumstances. For example, the personalized information may include information regarding at least a portion of the user's face and body. For example, the personalized information may include information obtained from contextual information (e.g., location information, information regarding a screen being displayed by the electronic device, information regarding the surrounding environment of the electronic device, status information of the electronic device, status information of the user, or schedule information of the user). For example, the electronic device may obtain a second input prompt that includes at least a portion of features obtained from an image relevant to the user. For example, the electronic device may obtain a second input prompt that includes at least a portion of features obtained from content (e.g., a video, a photo, music, an application) currently being played on the electronic device. For example, the electronic device may obtain a second input prompt that includes at least a portion of features obtained from content (e.g., a video, a photo, music, an application) to be played on the electronic device. For example, the personalized information may obtain a second input prompt that includes at least some of the features obtained from contextual information (e.g., location information, information about a screen that the electronic device is displaying, information about the surrounding environment of the electronic device, status information of the electronic device, status information of the user, or schedule information of the user).

[0089] According to one embodiment, in operation 340, the electronic device may obtain third content output from the first artificial intelligence model. The first artificial intelligence model may include a generative artificial intelligence model. The generative artificial intelligence model may include an artificial intelligence model that generates predetermined content based on a prompt input. For example, the generative artificial intelligence model may include an artificial intelligence model that receives a user's natural language prompt input and generates or modifies a predetermined type of content. For example, the generative artificial intelligence model may include, but is not limited to, a conversational artificial intelligence model, an image generation artificial intelligence model, an artificial intelligence model for composing, an artificial intelligence model for writing, and / or an artificial intelligence model for coding.

[0090] According to one embodiment, the electronic device may obtain third content output from the first artificial intelligence model by providing at least a portion of the first input prompt and at least a portion of the second input prompt to a first artificial intelligence model trained to generate user-customized content. For example, the electronic device may obtain third content including the first object and a third object replaced by the second object.

[0091] FIG. 4 is a block diagram illustrating an example of an operating method of an electronic device according to various embodiments. FIG. 4 may include operations performed by the electronic device (101) described above with reference to FIG. 1 or FIG. 2. The operations of the electronic device illustrated in FIG. 4 may be performed by a processor (e.g., the processor (220) of FIG. 2) performing calculations or controlling components of the electronic device. The “module” used in FIG. 4 may be implemented in hardware or software or a combination thereof to perform a predetermined function. The artificial intelligence model used in FIG. 4 may include an artificial intelligence model implemented in hardware or software to perform a predetermined function.

[0092] According to one embodiment, the first content according to the embodiments of the present document may include original advertising content (e.g., video). The electronic device (101) may obtain original advertising content generated by a content provider as the first content. The electronic device (101) may confirm multimedia content (e.g., movies, dramas, broadcasts, music, audio, videos captured by the electronic device) being provided to the user as the second content. According to one embodiment, the electronic device (101) may pause playback while the multimedia content is being provided to the user and provide advertising content. For example, the electronic device (101) may modify the original advertising content by using an object (e.g., image information, multimedia data) included in a portion played before the time at which the advertising content should be provided in the multimedia content being provided to the user, and provide the modified advertising content as the third content. For example, an object included in a playback section of multimedia content previously provided to a user may be added to the original advertising content or may replace a portion of the original advertising content. For example, the electronic device (101) may use an object (e.g., image information, multimedia data) included in a portion of multimedia content to be played after the time at which the advertising content should be provided, among multimedia content being provided to a user, to modify the original advertising content and provide the modified advertising content as third content. For example, an object included in a playback section of multimedia content to be provided to a user after the advertising content has been provided may be added to the original advertising content or may replace a portion of the original advertising content.

[0093] According to one embodiment, an electronic device (e.g., 101 of FIG. 1) may provide first content (411) to an object classification module (420). The object classification module (420) may include hardware and / or software implemented to identify objects included in the content and classify the types of the identified objects. For example, the object classification module (420) may include an artificial intelligence module (421) trained to identify objects included in the content and classify their types. For example, the object classification module (420) may be a hardware and / or software module implemented to recognize an identifier included in the content and identify a first object and a second object set based on the identifier. For example, the electronic device (e.g., 101 of FIG. 1) may provide the first content as input data to the object classification module (420) implemented in the electronic device (e.g., 101 of FIG. 1). For example, an electronic device (e.g., 101 in FIG. 1) can provide the first content (411) to the object classification module (420) by transmitting the first content (411) to an external electronic device (e.g., 102 in FIG. 1) in which an object classification module (420) is implemented.

[0094] According to one embodiment, by analyzing the first content (411) input to the object classification module (420), a plurality of objects included in the first content (411) can be identified. Data output from the object classification module (420) may include information and / or characteristics regarding the objects identified from the first content (411). For example, data output from the object classification module (420) may include information regarding the appearance (e.g., size, shape, color) of each object. For example, data output from the object classification module (420) may include information regarding the location of an object within the first content. For example, data output from the object classification module (420) may include information regarding the content of text included in an object including text. The above-described examples are intended to explain examples of various embodiments and are not limited thereto.

[0095] According to one embodiment, data output from the object classification module (420) may include information regarding the type of an object identified from the first content (411). A plurality of objects included in the first content may be classified by type through the object classification module (420). For example, each of the plurality of objects may be classified as a first object (441) or a second object (443) through the object classification module (420). The first object (441) may include a primary object among the plurality of objects of the first content (411). The primary object may include an object that conveys a key message or purpose of the first content. The second object (443) may include an additional object among the plurality of objects of the first content (411). The additional object may include an object that is placed in the first content to make the primary object stand out. For example, a plurality of objects included in a first content (411) can be classified as a first object (441) or a second object (443) by an artificial intelligence module (421) trained to identify objects included in the content and classify their types. For example, a plurality of objects included in a first content (411) can be classified as a first object (441) or a second object (443) by an object classification module (420) implemented to recognize an identifier included in the content and identify a first object and a second object set based on the identifier.

[0096] According to one embodiment, an electronic device (e.g., 101 of FIG. 1) may provide second content (412) to an artificial intelligence model (430). The artificial intelligence model (430) may include an artificial intelligence model trained to obtain weights for each of preset types from the content. For example, the electronic device (e.g., 101 of FIG. 1) may provide the second content as input data to the artificial intelligence model (430) implemented in the electronic device (e.g., 101 of FIG. 1). For example, the electronic device (e.g., 101 of FIG. 1) may provide the second content (412) to the artificial intelligence model (430) by transmitting the second content (412) to an external electronic device (e.g., 102 of FIG. 1) in which the artificial intelligence model (430) is implemented.

[0097] In one embodiment, the second content (412) may include content related to the user. For example, the second content (412) may include personally identifiable information such as the user's name, gender, date of birth, address, phone number, email address, and resident registration number. For example, the second content (412) may include personal body information such as a facial image or voice information. For example, the second content (412) may include user data. The user's personal data may include the user's private data obtained by the user terminal. For example, the user data may include at least one of images taken by the user using the user terminal, location information of the user obtained using the location sensor of the user terminal, voice data of the user obtained through the microphone of the user terminal, patterns of the user using the user terminal, addresses of web pages visited by the user using the electronic device, information about applications run by the user on the electronic device, information about the user's search history, activity history (e.g., posts, comments, messages) on a social network service (SNS) used by the user, or information about the history of products purchased by the user. For example, the second content (412) may include image data stored in the electronic device used by the user. For example, the second content (412) may include content (e.g., video, photo, music, application) currently being played on the electronic device. For example, the second content (412) may include content (e.g., video, photo, music, application) to be played on the electronic device.

[0098] According to one embodiment, the second content (412) may include context information. The context information is information indicating a situation of an electronic device (e.g., 101 of FIG. 1), and may include at least one of, but is not limited to, information about the surrounding environment of the electronic device (e.g., 101 of FIG. 1), status information of the electronic device (e.g., 101 of FIG. 1), user status information, or user schedule information.

[0099] For example, the surrounding environment information of an electronic device (e.g., 101 of FIG. 1) may include environment information within a predetermined range from the electronic device (e.g., 101 of FIG. 1). For example, the surrounding environment information of an electronic device (e.g., 101 of FIG. 1) may include, but is not limited to, weather information, location information, temperature information, humidity information, illuminance information, noise information, and sound information.

[0100] For example, the status information of an electronic device (e.g., 101 of FIG. 1) may include, but is not limited to, mode information of the electronic device (e.g., 101 of FIG. 1) (e.g., sound mode, vibration mode, silent mode, power saving mode, blocking mode, multi-window mode, auto-rotate mode), location information of the electronic device (e.g., 101 of FIG. 1), time information, activation information of a communication module (e.g., WiFi ON / Bluetooth OFF / GPS (global positioning system) ON / NFC (near field communication) ON), and network connection status information of the electronic device (e.g., 101 of FIG. 1).

[0101] For example, the user's status information may include, but is not limited to, information about the user's movements and lifestyle patterns, such as information about the user's walking status, exercising status, driving status, sleeping status, and mood status.

[0102] According to one embodiment, personalized information related to the user may be output from the artificial intelligence model (430) by analyzing the second content (412) input to the artificial intelligence model (430). The personalized information may include information related to the user according to the individual's interests, preferences, needs, and situations. The personalized information output from the artificial intelligence model (430) may include at least one of information about the user's gender, information about the user's age, information about each image stored in the user's gallery application, information about the user's taste, information about the user's preferred color, information about the user's interests, information about the user's products of interest, information about the clothes the user wears, information about the purchase time of the products the user wears, information about the space the user resides in, or information about the products the user uses. For example, the personalized information may include at least a portion of the second content. The above-described examples are intended to illustrate examples of various embodiments, and the present disclosure is not limited thereto.

[0103] According to one embodiment, an electronic device may input a first object (441), a second object (443), and personalized information (445) to an input prompt generation module (450). The input prompt generation module (450) may include hardware and / or software implemented to generate a prompt to be input to a generative artificial intelligence model (470) based on the input data. The input prompt generation module (450) may include an artificial intelligence model (451) trained to identify the input data and create a prompt based on the input data. For example, an electronic device (e.g., 101 of FIG. 1) may provide the first object (441), the second object (443), and personalized information (445) as input data to an input prompt generation module (450) implemented in the electronic device (e.g., 101 of FIG. 1). For example, an electronic device (e.g., 101 of FIG. 1) may transmit a first object (441), a second object (443), and personalized information (445) to an external electronic device (e.g., 102 of FIG. 1) having an input prompt generation module (450) implemented therein, thereby providing the first object (441), the second object (443), and the personalized information (445) to the input prompt generation module (450). For example, an electronic device (e.g., 101 of FIG. 1) may provide information about features related to each of the first object (441), the second object (443), and the personalized information (445) to the external electronic device (e.g., 102 of FIG. 1) having an input prompt generation module (450) implemented therein, thereby providing the first object (441), the second object (443), and the personalized information (445) to the input prompt generation module (450).

[0104] According to one embodiment, an electronic device (e.g., 101 of FIG. 1) can obtain an input prompt output from an input prompt generation module (450). For example, the electronic device (e.g., 101 of FIG. 1) can obtain a first input prompt (461) output from the input prompt generation module (450). For example, the electronic device (e.g., 101 of FIG. 1) can obtain a second input prompt (463) output from the input prompt generation module (450).

[0105] For example, the first input prompt (461) may include an input prompt output from the input prompt generation module (450) based on the first object (441). For example, the electronic device (e.g., 101 of FIG. 1) may obtain a first input prompt (461) including at least a portion of a feature of the first object (441) and at least a portion of a feature of the third object based on the first object (441) and a third object identified as a main object from the content being displayed. For example, the electronic device (e.g., 101 of FIG. 1) may obtain a first input prompt (461) including at least a portion of a feature of the first object (441) and at least a portion of a feature of the fifth object based on the first object (441) and a fifth object identified as a main object from the content to be displayed. The above-described examples are intended to describe examples of various embodiments, and the present disclosure is not limited thereto.

[0106] For example, the second input prompt (463) may include an input prompt output from the input prompt generation module (450) based on the second object (443) and personalized information (445). For example, the electronic device (e.g., 101 of FIG. 1) may obtain the second input prompt (463) including at least a portion of a feature obtained from an image related to the user. For example, the electronic device (e.g., 101 of FIG. 1) may obtain the second input prompt (463) including at least a portion of information about the second object (443) and at least a portion of personalized information. The above-described examples are intended to describe examples of various embodiments, and the present disclosure is not limited thereto.

[0107] According to one embodiment, an electronic device (e.g., 101 of FIG. 1) may provide an input prompt output from an input prompt generation module (450) to a generative artificial intelligence model (470). The generative artificial intelligence model (470) may include an artificial intelligence model trained to generate user-customized content. For example, the generative artificial intelligence model (470) may include an artificial intelligence model that receives a natural language prompt input, an image prompt input, and / or an audio prompt input to generate or modify a specified type of content. For example, the generative artificial intelligence model may include a conversational artificial intelligence model, an image generation artificial intelligence model, an artificial intelligence model for composing, an artificial intelligence model for writing, and / or an artificial intelligence model for coding. The above-described examples are intended to illustrate examples of various embodiments, and the present disclosure is not limited thereto.

[0108] According to one embodiment, an electronic device (e.g., 101 of FIG. 1) may provide at least a portion of a first input prompt (461) and at least a portion of a second input prompt (463) output from an input prompt generation module (450) to a generative artificial intelligence model (470). For example, the first input prompt (461) may be generated based on a first object (441) provided to the input prompt generation module (450). For example, the second input prompt (463) may be generated based on a second object (443) and personalized information (445) provided to the input prompt generation module (450).

[0109] According to one embodiment, the electronic device (101) may obtain (480) the third content through the generative artificial intelligence model (470) by transmitting the first content (411) and personalized information (445) (and / or the second content (412)) to the generative artificial intelligence model (470) together with an input prompt consisting of text including a generation command and generation conditions of the third content (480).

[0110] According to one embodiment, an electronic device (e.g., 101 of FIG. 1) may obtain third content (480) output from a generative artificial intelligence model (470). For example, the electronic device (e.g., 101 of FIG. 1) may obtain third content (480) including at least one of text, image, or sound. The third content (480) may include video content (e.g., TV program video, VOD (video on demand), user-created contents (UCC), music video, YouTube video), still image content (e.g., photograph, picture), text content (e.g., e-book (poem, novel), letter, work file), music content (e.g., music, instrumental music, radio broadcast), web pages, and messages. The above-described examples are intended to describe examples of various embodiments, and the present disclosure is not limited thereto.

[0111] According to one embodiment, an electronic device (e.g., 101 of FIG. 1) can output third content (480). For example, the electronic device (e.g., 101 of FIG. 1) can output the third content (480) through at least one of a display (e.g., a display (260) of FIG. 2) or an audio module (e.g., an audio module (170) of FIG. 1) of the electronic device (e.g., 101 of FIG. 1). For example, the electronic device (e.g., 101 of FIG. 1) can output the third content (480) through the external electronic device by transmitting the third content (480) to the external electronic device. For example, the electronic device (e.g., 101 of FIG. 1) can transmit the third content (480) to the external electronic device to output the third content (480) through at least a part of the display and audio module of the external electronic device.

[0112] According to one embodiment, the electronic device (101) may update at least a portion of a primary object (e.g., the first object (441)) based on information received from a provider or producer of the primary content and provide the update through the third content (480). For example, if the primary object (e.g., the first object (441)) is an image of a product more suitable for men, and the user of the electronic device (101) is determined to be a woman based on the second content (412) or personalized information (445), the electronic device (101) may obtain a product and product image more suitable for women and provide the product and product image in the third content (480).

[0113] FIG. 5 is a diagram illustrating an example of an exchange between a first electronic device and a second electronic device according to various embodiments. Referring to FIG. 5, a first electronic device (510) and a second electronic device (520) can transmit and receive data between each other. The first electronic device (510) and the second electronic device (520) can transmit and receive data for processing or calculating various data. The first electronic device (510) and the second electronic device (520) can transmit and receive data for control. The first electronic device (510) may correspond to the electronic device (101) described above with reference to FIGS. 1 and 2. The second electronic device (520) may correspond to at least one of the electronic devices (102, 104) and the server (108) described above with reference to FIGS. 1 and 2.

[0114] The first electronic device (510) of FIG. 5 may include a computing device such as a mobile device (e.g., a smartphone, a tablet PC), a personal computer (PC), or a server, which can transmit and receive data with the second electronic device (520) via a network. The first electronic device (510) of FIG. 5 may include a computing device such as a mobile device (e.g., a smartphone, a tablet PC), a personal computer (PC), or a server, in which an artificial intelligence model (515) is built. For example, the artificial intelligence model (515) implemented in the first electronic device (510) of FIG. 5 may be implemented as a hardware chip. For example, the artificial intelligence model (515) implemented in the first electronic device (510) of FIG. 5 may be implemented as software and stored in the memory of the first electronic device (510).

[0115] The second electronic device (520) of FIG. 5 may include a computing device such as a mobile device (e.g., a smartphone, a tablet PC), a personal computer (PC), or a server, which can transmit and receive data with the first electronic device (510) via a network. The second electronic device (520) of FIG. 5 may include a computing device such as a mobile device (e.g., a smartphone, a tablet PC), a personal computer (PC), or a server, in which an artificial intelligence model (525) is built. For example, the artificial intelligence model (525) implemented in the second electronic device (520) of FIG. 5 may be implemented as a hardware chip. For example, the artificial intelligence model (525) implemented in the second electronic device (520) of FIG. 5 may be implemented as software and stored in the memory of the second electronic device (520).

[0116] According to one embodiment, a first electronic device (510) may transmit first content (e.g., 411 of FIG. 4) to a second electronic device (520). For example, the first electronic device (510) may transmit the first content to an object classification module (e.g., 420 of FIG. 4) implemented in the second electronic device (520) to input the first content. For example, the object classification module (e.g., 420 of FIG. 4) may be implemented as a hardware chip mounted in the second electronic device (520). For example, the object classification module (e.g., 420 of FIG. 4) may be implemented as software and stored in the memory of the second electronic device (520). For example, the object classification module (e.g., 420 of FIG. 4) may be implemented by an artificial intelligence model (525) trained to identify objects included in content and classify their types. For example, the first electronic device (510) can transmit simplified first content (e.g., a thumbnail) to the second electronic device (520). For example, the first electronic device (510) can transmit first content preprocessed to correspond to an artificial intelligence model (525) to the second electronic device (520). For example, the first electronic device (510) can transmit features acquired from the first content by the artificial intelligence model (515) to the second electronic device (520).

[0117] According to one embodiment, the second electronic device (520) may transmit data output from an object classification module (e.g., 420 of FIG. 4) implemented in the second electronic device (520) to the first electronic device (510). For example, the data output from the object classification module (e.g., 420 of FIG. 4) may include information and / or characteristics regarding objects identified from the first content (e.g., 411 of FIG. 4). For example, the second electronic device (520) may transmit information regarding the appearance (e.g., size, shape, color) of each of the objects output from the object classification module to the first electronic device (510). For example, the second electronic device (520) may transmit information regarding the location of each of the objects output from the object classification module within the first content to the first electronic device (510). For example, the second electronic device (520) may transmit information regarding the content of text output from the object classification module to the first electronic device (510). For example, the second electronic device (520) may transmit information regarding the types of objects (e.g., main object, additional object) identified from the first content to the first electronic device (510). The above-described examples are intended to describe examples of various embodiments, and the present disclosure is not limited thereto.

[0118] In one embodiment, the first electronic device (510) may transmit second content (e.g., 412 of FIG. 4) to the second electronic device (520). For example, the first electronic device (510) may transmit the second content to an artificial intelligence model (525) implemented in the second electronic device (520) to input the second content. For example, the artificial intelligence model (525) may include an artificial intelligence model trained to obtain weights for each of the preset types from the content. For example, the artificial intelligence model (525) may be implemented as a hardware chip mounted in the second electronic device (520). For example, the artificial intelligence model (525) may be implemented as software and stored in the memory of the second electronic device (520). For example, the first electronic device (510) may transmit simplified second content (e.g., a thumbnail) to the second electronic device (520). For example, the first electronic device (510) can transmit second content that has been preprocessed to be applied to the artificial intelligence model (525) to the second electronic device (520). For example, the first electronic device (510) can transmit features obtained from the second content by the artificial intelligence model (515) to the second electronic device (520).

[0119] According to one embodiment, the second electronic device (520) may transmit personalized information (e.g., 445 of FIG. 4) output from the artificial intelligence model (525) to the first electronic device (510). For example, the second electronic device (520) may transmit at least one of the following to the first electronic device (510): information about the user's gender output from the artificial intelligence model (525), information about the user's age, information about each of the images stored in the user's gallery application, information about the user's taste, information about the user's preferred color, information about the user's interests, information about the user's products of interest, information about the clothes the user wears, information about the time of purchase of the products the user wears, information about the space the user resides in, or information about the products the user uses. The above-described examples are intended to describe examples of various embodiments, and the present disclosure is not limited thereto.

[0120] According to one embodiment, the first electronic device (510) may transmit data output from an object classification module (e.g., 420 of FIG. 4) implemented in the first electronic device (510) to the second electronic device (520). For example, the first electronic device (510) may transmit data output from the object classification module to the second electronic device (520) in order to input information about a first object (e.g., 441 of FIG. 4) and a second object (e.g., 443 of FIG. 4) to an input prompt generation module (e.g., 450 of FIG. 4) implemented in the second electronic device (520). For example, the data output from the object classification module may include information and / or characteristics about an object identified from the first content. For example, the first electronic device (510) may transmit information about the first object and the second object to the second electronic device (520). For example, the first electronic device (510) may transmit information about the appearance (e.g., size, shape, color) of each of the first object and the second object to the second electronic device (520). For example, the first electronic device (510) may transmit information about the location of the first object and the second object within the first content to the second electronic device (520). For example, the first electronic device (510) may transmit information about the content of text included in each of the first object and the second object to the second electronic device (520). The above-described examples are intended to describe examples of various embodiments, and the present disclosure is not limited thereto.

[0121] According to one embodiment, the first electronic device (510) can transmit personalized information (e.g., 445 of FIG. 4) to the second electronic device (520). For example, the first electronic device (510) can transmit personalized information to the second electronic device (520) in order to input personalized information (e.g., 445 of FIG. 4) to an input prompt generation module (e.g., 450 of FIG. 4) implemented in the second electronic device (520). For example, the first electronic device (510) can transmit personalized information output from an artificial intelligence model (515) to the second electronic device (520). For example, the first electronic device (510) may transmit at least one of information about the user's gender, information about the user's age, information about each of the images stored in the user's gallery application, information about the user's taste, information about the user's preferred color, information about the user's interests, information about the user's products of interest, information about the clothes the user wears, information about the time of purchase of the products the user wears, information about the space the user resides in, or information about the products the user uses to the second electronic device (520). The above-described examples are provided to explain examples of various embodiments, and the present disclosure is not limited thereto.

[0122] According to one embodiment, the second electronic device (520) may transmit data output from an input prompt generation module (e.g., 450 of FIG. 4) implemented within the second electronic device (520) to the first electronic device (510). For example, the second electronic device (520) may transmit at least a portion of a first input prompt (e.g., 461 of FIG. 4) and at least a portion of a second input prompt (e.g., 463 of FIG. 4) to the first electronic device (510).

[0123] For example, the input prompt generation module (e.g., 450 of FIG. 4) may be implemented as a hardware chip mounted on the second electronic device (520). For example, the input prompt generation module (e.g., 450 of FIG. 4) may be implemented as software and stored in the memory of the second electronic device (520). For example, the input prompt generation module (e.g., 461 of FIG. 4) implemented in the second electronic device (520) may be implemented by an artificial intelligence model (525) trained to generate a prompt based on input data. For example, the artificial intelligence model (525) implementing the input prompt generation module may include a generative artificial intelligence model.

[0124] For example, data output from an input prompt generation module (e.g., 450 of FIG. 4) may include a first input prompt (e.g., 461 of FIG. 4) and a second input prompt (e.g., 463 of FIG. 4). For example, the first input prompt may include an input prompt generated based on a first object. For example, the second input prompt may include an input prompt generated based on a second object and personalized information. For example, the second input prompt may include at least a portion of information about the second object and at least a portion of the personalized information. For example, the second input prompt may include at least a portion of features acquired from an image related to the user.

[0125] According to one embodiment, the first electronic device (510) can transmit at least a portion of a first input prompt (e.g., 461 of FIG. 4) and at least a portion of a second input prompt (e.g., 463 of FIG. 4) to the second electronic device (520). For example, the first electronic device (510) can transmit the first input prompt (e.g., 461 of FIG. 4) and the second input prompt (e.g., 463 of FIG. 4) output from an input prompt generation module implemented in the first electronic device (510) to the second electronic device (520). For example, the first electronic device (510) may transmit a first input prompt (e.g., 461 of FIG. 4) and a second input prompt (e.g., 463 of FIG. 4) to the second electronic device (520) to provide the first input prompt (e.g., 461 of FIG. 4) and the second input prompt (e.g., 463 of FIG. 4) to the generative artificial intelligence model (e.g., 470 of FIG. 4) implemented in the second electronic device (520).

[0126] For example, the generative artificial intelligence model may be implemented as a hardware chip mounted on the second electronic device (520). For example, the generative artificial intelligence model may be implemented as software and stored in the memory of the second electronic device (520). For example, the generative artificial intelligence model implemented in the second electronic device (520) may include an artificial intelligence model (525) trained to generate user-customized content based on an input prompt.

[0127] For example, a first input prompt (e.g., 461 in FIG. 4) input to a generative artificial intelligence model may include an input prompt generated based on a first object (e.g., 441 in FIG. 4).

[0128] For example, a second input prompt (e.g., 463 of FIG. 4) input to a generative artificial intelligence model may include an input prompt generated based on a second object (e.g., 443 of FIG. 4) and personalized information (e.g., 445 of FIG. 4). For example, the second input prompt (e.g., 463 of FIG. 4) input to a generative artificial intelligence model may include at least a portion of features obtained from an image related to the user. For example, the second input prompt (e.g., 463 of FIG. 4) input to a generative artificial intelligence model may include at least a portion of information about the second object and at least a portion of personalized information.

[0129] According to one embodiment, the second electronic device (520) may transmit third content (e.g., 480 of FIG. 4) output from a generative artificial intelligence model (e.g., 470 of FIG. 4) implemented in the second electronic device (520) to the first electronic device (510). For example, the second electronic device (520) may transmit the third content including at least one of text, image, or sound to the first electronic device (510). For example, the second electronic device (520) may transmit the third content to the first electronic device (510) so that the first electronic device (510) outputs the third content.

[0130] According to one embodiment, the first electronic device (510) may transmit third content (e.g., 480 of FIG. 4) output from a generative artificial intelligence model (e.g., 470 of FIG. 4) implemented in the first electronic device (510) to the second electronic device (520). For example, the first electronic device (510) may transmit the third content including at least one of text, image, or sound to the second electronic device (520). For example, the first electronic device (510) may transmit the third content to the second electronic device (520) so that the second electronic device (520) outputs the third content.

[0131] FIG. 6 is a diagram illustrating an electronic device for classifying objects from content according to various embodiments. The operation of the electronic device illustrated in FIG. 6 may be performed by a processor (e.g., the processor (220) of FIG. 2) performing calculations or controlling components of the electronic device. The object classification module (620) of FIG. 6 may correspond to the object classification module (e.g., 420 of FIG. 4) described with reference to FIG. 4. The artificial intelligence model (621) of FIG. 6 may correspond to the artificial intelligence model (e.g., 421) described with reference to FIG. 4.

[0132] According to one embodiment, the electronic device of FIG. 6 can input the first content (610) to the object classification module (620), thereby identifying objects (611, 612, 613, 614, 615) included in the first content (610) and classifying them into a first object (631) and a second object (633). The first object (631) can include a main object among the objects (611, 612, 613, 614, 615) of the first content (610). The second object (633) can include an additional object among the objects (611, 612, 613, 614, 615) of the first content (610).

[0133] According to one embodiment, the electronic device may provide the first content (610) to the object classification module (620). For example, the electronic device may provide the first content (610) as input data to the object classification module (620) implemented within the electronic device. For example, the electronic device may provide the first content as input data to the object classification module (620) implemented within the external electronic device by transmitting the first content to the external electronic device. For example, the electronic device may provide the first content including at least one of text, an image, or sound to the object classification module (620).

[0134] In one embodiment, the first content (610) may include a plurality of objects (611, 612, 613, 614, 615). For example, the first content (610) may include a first text object (611) containing information about a product to be advertised. For example, the first content (610) may include a second text object (612) containing information about an event. For example, the first content may include a third text object (613) containing information about an event date. For example, the first content (610) may include a fourth text object (614) containing information about a brand of a product. For example, the first content (610) may include a background object (615) of the background of an image.

[0135] According to one embodiment, the object classification module (620) may be implemented in hardware or software to perform the function of identifying objects from input content and classifying their types. For example, the object classification module (620) may be implemented as a hardware chip and mounted on an electronic device. For example, the object classification module (620) may be implemented as software and stored in the memory of an electronic device.

[0136] According to one embodiment, the object classification module (620) may be implemented to recognize an identifier included in the input content and perform a function of identifying a first object and a second object set based on the identifier. For example, the object classification module (620) may recognize an identifier from preset data among the data of the first content (610). For example, the object classification module (620) may recognize an identifier included in the metadata of the first content (610). For example, the identifier may be received together with the first content (610) or may be received from a server (e.g., server 108) at the request of the first electronic device (510) or the second electronic device (520). For example, the identifier may be information generated by a producer or provider of the first content.

[0137] According to one embodiment, the identifier may include information and / or characteristics related to at least one object among the objects (611, 612, 613, 614, 615) included in the first content (610). For example, the identifier may include information about the appearance (e.g., size, shape, color) of each of the objects (611, 612, 613, 614, 615). For example, the identifier may include information about the location of each of the objects (611, 612, 613, 614, 615) within the first content (610). For example, the identifier may include information about the content of each of the objects (611, 612, 613, 614) that include text. For example, the identifier may include information about the type (e.g., primary object, secondary object) of each of the objects (611, 612, 613, 614). The above examples are intended to illustrate various embodiments, and the present disclosure is not limited thereto.

[0138] According to one embodiment, the object classification module (620) can recognize information and / or characteristics related to at least one object among the objects (611, 612, 613, 614, 615) included in the first content (610) from the identifier. The object classification module (620) can recognize the type of at least one object among the objects (611, 612, 613, 614, 615) included in the first content (610) from the identifier. The object classification module (620) can output information related to the first object (631) and / or information related to the second object (633) based on the type of the recognized object. For example, the object classification module (620) can identify at least one of the appearance (e.g., size, shape, color), the location within the first content, or the content of the text of each of the plurality of objects (611, 612, 613, 614, 615) included in the first content (610) based on an identifier recognized from the metadata of the input first content (610). The object classification module (620) can identify the type of each of the plurality of objects (611, 612, 613, 614, 615) included in the first content (610) based on an identifier recognized from the metadata of the first content (610). For example, the object classification module (620) can identify the first text object (611), the second text object (612), the third text object (613), and the fourth text object (614) as main objects based on the identifiers. For example, the object classification module (620) can identify a background object (615) as an additional object based on an identifier.For example, the object classification module (620) may output information about the first text object (611), the second text object (612), the third text object (613), and the fourth text object (614) identified as main objects based on the identifiers (e.g., information about the advertised product, information about the event, information about the event date, information about the brand of the product) as information about the first object (631). For example, the object classification module (620) may output information about the background object (615) identified as an additional object (e.g., color, pattern) as information about the second object (633).

[0139] According to one embodiment, the object classification module (620) may include an artificial intelligence model (621) trained to identify objects from input content and classify the types of the objects. For example, the artificial intelligence model (621) may include a model trained to identify objects from content and classify the types of the objects through supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning. For example, the artificial intelligence model (621) may include an artificial neural network including 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), deep Q-networks, or a combination of two or more of the above. The artificial intelligence model (621) may include hardware or software implemented to perform a predetermined function. For example, the artificial intelligence model (621) may be implemented as a hardware chip and mounted on an electronic device. For example, the artificial intelligence model (621) may be implemented as software and stored in the memory of the electronic device.

[0140] According to one embodiment, the artificial intelligence model (621) can recognize information and / or features related to at least one of the objects (611, 612, 613, 614, 615) included in the first content (610) from an identifier. The artificial intelligence model (621) can recognize the type of at least one object among the objects (611, 612, 613, 614, 615) included in the first content (610). Based on the type of the recognized object, the artificial intelligence model (621) can output information related to the first object (631) and / or information related to the second object (633). For example, the artificial intelligence model (621) can output information related to the appearance (e.g., size, shape, color) of each of the objects (611, 612, 613, 614, 615) included in the first content (610). For example, the artificial intelligence model (621) can output information about the location of each of the objects (611, 612, 613, 614, 615) within the first content (610). For example, the artificial intelligence model (621) can output information about the content of objects (611, 612, 613, 614) containing text.

[0141] For example, in response to the fact that an identifier related to the input first content is not identified, the artificial intelligence model (621) can identify at least one of the appearance (e.g., size, shape, color) of each of the plurality of objects (611, 612, 613, 614, 615) included in the first content (610), the location within the first content (610), or the content of the text. For example, the artificial intelligence model (621) can identify the type of each of the plurality of objects (611, 612, 613, 614, 615) included in the first content (610). For example, the artificial intelligence model (621) can identify the first text object (611), the second text object (612), the third text object (613), and the fourth text object (614) as main objects. For example, the artificial intelligence model (621) can identify a background object (615) as an additional object. For example, the artificial intelligence model (621) can output information about the first text object (611), the second text object (612), the third text object (613), and the fourth text object (614) identified as main objects (e.g., information about the advertised product, information about the event, information about the event date, information about the brand of the product) as information about the first object (631). For example, the artificial intelligence model (621) can output information about the background object (615) identified as an additional object (e.g., color, pattern, background image) as information about the second object (633).

[0142] According to one embodiment, the object classification model (620) can identify information about the content of each of the objects (611, 612, 613, 614) containing text as a primary object, and identify the font, font size, or position of each text or word as an additional object.

[0143] FIG. 7 is a diagram illustrating an electronic device that obtains personalized information from content according to various embodiments. The electronic device illustrated in FIG. 7 may correspond to at least one of the electronic devices (101, 102, 104) and the server (108) described above with reference to FIGS. 1 and 2. The operation of the electronic device illustrated in FIG. 7 may be performed by a processor (e.g., the processor (220) of FIG. 2) performing a calculation or controlling a component of the electronic device. The artificial intelligence model (720) of FIG. 7 may correspond to the artificial intelligence model (e.g., 430 of FIG. 4) described with reference to FIG. 4. The artificial intelligence model (720) of FIG. 7 may be included in at least one of the electronic devices (101, 102, 104) and the server (108) described above with reference to FIGS. 1 and 2.

[0144] According to one embodiment, the electronic device of FIG. 7 can obtain personalized information (730) by providing second content (710) to an artificial intelligence model (720). The artificial intelligence model (720) may include an artificial intelligence model trained to obtain weights for each of preset types from the content. The electronic device can provide the second content as input data to the artificial intelligence model (720) implemented in the electronic device. The electronic device can provide the second content (710) to the artificial intelligence model (720) by transmitting the second content (710) to an external electronic device in which the artificial intelligence model (720) is implemented.

[0145] According to one embodiment, the electronic device may provide second content (710) related to the user to the artificial intelligence model (720). For example, the electronic device may provide the artificial intelligence model (720) with second content (710) that includes personally identifiable information such as the user's name, gender, date of birth, address, phone number, email address, and resident registration number. For example, the electronic device may provide the artificial intelligence model (720) with second content (710) that includes personal body information such as a facial photograph or voice information. For example, the electronic device may provide the artificial intelligence model (720) with user data acquired by the user terminal as second content (710). The user terminal may correspond to at least one of the electronic devices (101, 102, 104) described above with reference to FIGS. 1 and 2. For example, user data may include at least one of images taken by the user using the user terminal, location information of the user obtained using the location sensor of the user terminal, voice data of the user obtained through the microphone of the user terminal, patterns of the user using the user terminal, addresses of web pages visited by the user using the electronic device, information about applications run by the user on the electronic device, information about the user's search history, activity history (e.g., posts, comments, messages) on a social network service (SNS) used by the user, or information about the history of products purchased by the user. For example, the electronic device may provide the artificial intelligence model (720) with image data stored in the electronic device used by the user or image data linked to the user account. The electronic device used by the user may correspond to at least one of the electronic devices (101, 102, 104) described above with reference to FIGS. 1 and 2.

[0146] According to one embodiment, the electronic device may provide content being played on the electronic device as second content (710) to the artificial intelligence model (720). For example, the electronic device may provide at least one of a video, a photo, and music being played on the electronic device to the artificial intelligence model (720). For example, the electronic device may provide information about an application running on the electronic device (e.g., the execution time of the application, the execution frequency of the application, and information related to the user acquired by the application) to the artificial intelligence model (720).

[0147] In one embodiment, the electronic device may provide content to be played on the electronic device as second content to the artificial intelligence model (720). For example, the electronic device may provide at least one of a video, a photo, music, or a web page to be played on the electronic device to the artificial intelligence model (720).

[0148] According to one embodiment, the electronic device may provide second content (710) including context information to the artificial intelligence model (720). The context information may include at least one of, but is not limited to, information about the surrounding environment of the electronic device, status information of the electronic device, status information of the user, and schedule information of the user. For example, the electronic device may provide second content (710) including information about the surrounding environment of the electronic device, including weather information, location information, temperature information, humidity information, illuminance information, noise information, and sound information, to the artificial intelligence model (720). For example, the electronic device may provide, as second content (710), status information of the electronic device, including mode information of the electronic device (e.g., sound mode, vibration mode, silent mode, power saving mode, blocking mode, multi-window mode, auto-rotate mode), location information of the electronic device, time information, activation information of a communication module (e.g., WiFi ON / Bluetooth OFF / GPS ON / NFC ON), and network connection status information of the electronic device, to the artificial intelligence model (720). For example, an electronic device may provide second content (710) containing user status information, such as information about the user's movements and lifestyle patterns, such as the user's walking state, exercising state, driving state, sleeping state, and mood state, to an artificial intelligence model (720). The above-described examples are intended to illustrate various embodiments, and the present disclosure is not limited thereto.

[0149] According to one embodiment, the electronic device may obtain personalized information (730) output from the artificial intelligence model (720). For example, the electronic device may obtain personalized information (730) including at least one of information about the user's gender, information about the user's age, information about each image stored in the user's gallery application, information about the user's taste, information about the user's preferred color, information about the user's interests, information about the user's products of interest, information about the clothes the user wears, information about the purchase time of the products the user wears, information about the trends of the user's products of interest, information about the user's movement path, information about the weather in the area where the user is located, information about the space the user resides in or the products the user uses, information about the user's behavior in using the electronic device, information about the user's sleep pattern, and information about the user's health. The above-described examples are intended to illustrate examples of various embodiments, and the present disclosure is not limited thereto. For example, the electronic device may obtain personalized information (730) as a profile. The profile may include a database in which information about the user is stored. The electronic device can store the acquired personalized information in its memory.

[0150] FIG. 8 is a diagram illustrating an electronic device that obtains an input prompt according to various embodiments. The operation of the electronic device illustrated in FIG. 8 may be performed by a processor (e.g., the processor 220 of FIG. 2) performing a calculation or controlling a component of the electronic device. The input prompt generation module (820) of FIG. 8 may include hardware and / or software implemented to generate a prompt to be input to a generative artificial intelligence model (e.g., 470 of FIG. 4) based on input data. The input prompt generation module (820) may include an artificial intelligence model trained to identify input data and create a prompt based on the input data. The artificial intelligence model may include a generative artificial intelligence model trained to generate a prompt. The input prompt generation module (820) of FIG. 8 may correspond to the input prompt generation module (450 of FIG. 4) described with reference to FIG. 4. The artificial intelligence model included in the input prompt generation module (820) of FIG. 8 may correspond to the artificial intelligence model (451 of FIG. 4) described with reference to FIG. 4.

[0151] According to one embodiment, the electronic device may provide a first object (811), a second object (813), and personalized information (815) to an input prompt generation module (820). For example, the electronic device may provide the first object (811), the second object (813), and personalized information (815) as input data to the input prompt generation module (820). For example, the electronic device may provide information regarding features related to each of the first object (811), the second object (813), and the personalized information (815) to the input prompt generation module (820) as input data.

[0152] According to one embodiment, the electronic device may obtain an input prompt output from the input prompt generation module (820). For example, the electronic device may obtain an input prompt generated in the user's natural language. For example, the electronic device may obtain an input prompt generated in machine language recognizable by a generative artificial intelligence model. For example, the electronic device may obtain an input prompt including at least a portion of an image. For example, the electronic device may obtain an input prompt including at least a portion of a feature obtained from an image. For example, the electronic device may include information about the appearance of an object (e.g., information expressed in text, images, and lines regarding size, shape, and color).

[0153] According to one embodiment, the input prompt generation module (820) can generate a first input prompt (831) based on the first object (811). For example, the input prompt generation module (820) can generate a first input prompt (831) that includes information about the appearance (e.g., size, shape, color) of the first object (811). For example, the input prompt generation module (820) can generate a first input prompt (831) that includes information about the location of the first object (811). For example, the input prompt generation module (820) can generate a first input prompt (831) that includes information about the content of text of the first object (811). The input prompt generation module (820) can output the first input prompt (831).

[0154] According to one embodiment, the input prompt generation module (820) can generate a second input prompt (833) based on the second object (813). For example, the input prompt generation module (820) can generate a second input prompt (833) that includes information about the appearance (e.g., size, shape, color) of the second object (813). For example, the input prompt generation module (820) can generate a second input prompt (833) that includes information about the location of the second object (813). For example, the input prompt generation module (820) can generate a second input prompt (833) that includes information about the content of text of the second object (813). The input prompt generation module (820) can output the second input prompt (833).

[0155] According to one embodiment, the input prompt generation module (820) may generate a second input prompt (833) based on the second object (813) and the personalized information (815). For example, the input prompt generation module (820) may generate the second input prompt (833) such that content combining at least a portion of the second object (813) and at least a portion of the personalized information (815) is generated by a generative artificial intelligence model (e.g., 470 of FIG. 4). For example, the personalized information (815) may include at least one of information about the user's gender, information about the user's age, information about each image stored in the user's gallery application, information about the user's taste, information about the user's preferred color, information about the user's interests, information about the user's products of interest, information about the clothes the user wears, information about the time of purchase of the products the user wears, information about the user's trend of products of interest, information about the user's movement path, information about the weather in the area where the user is located, information about the space the user resides in or information about the products the user uses, information about the user's behavior in using electronic devices, information about the user's sleep pattern, and information about the user's health. For example, the input prompt generation module (820) may generate a second input prompt (833) that causes content including the user's name obtained from the personalized information (815) and the text of the second object (813) to be generated by a generative artificial intelligence model. For example, the input prompt generation module (820) can generate a second input prompt (833) that causes the generative artificial intelligence model to generate content that includes at least a portion of an image related to the user (e.g., the user's face, the user's body, clothes worn by the user, products purchased by the user, products searched for by the user, or the user's living space) in at least a portion of the second object.According to one embodiment, the input prompt generation module (820) may additionally or alternatively generate a second input prompt (833) based on the second content (710) in relation to the personalized information (815). The above-described examples are intended to illustrate various embodiments, and the present disclosure is not limited thereto. The input prompt generation module (820) may output the generated second input prompt (833).

[0156] FIG. 9 is a diagram illustrating an electronic device, according to one embodiment, acquiring content using a generative artificial intelligence model. The operation of the electronic device illustrated in FIG. 9 may be performed by a processor (e.g., the processor 220 of FIG. 2) performing calculations or controlling components of the electronic device. In addition, the operation of the electronic device illustrated in FIG. 9 may be performed solely by the electronic device, or some operations may be performed through an external electronic device. The module of FIG. 9 may be implemented as hardware or software to perform a predetermined function. The artificial intelligence model of FIG. 9 may include hardware or software implemented to perform a predetermined function.

[0157] According to one embodiment, the electronic device may input first content (910). For example, the electronic device may input first content (910) including a game advertisement image. The electronic device may provide the first content (910) to an object classification module (920). The object classification module (920) may correspond to the object classification module (420 of FIG. 4) described with reference to FIG. 4 and the object classification module (620 of FIG. 6) described with reference to FIG. 6. The first content (910) may include a character (911), a background (913), and text (915). For example, the first content (910) may include identifiers related to objects (911, 913, 915) included in the first content.

[0158] According to one embodiment, the electronic device can obtain information about each of the objects (911, 913, 915) included in the first content (910) output from the object classification module (920). For example, the electronic device can obtain information about the appearance (e.g., size, shape, color) of each of the character (911), the background (913), and the text (915) from the object classification module (920). For example, the electronic device can obtain information about the content of the text (915) from the object classification module (920).

[0159] According to one embodiment, the electronic device can identify a first object (931) and a second object (933) among objects included in the first content (910). The first object (931) can include an object classified as a main object of the first content (910). The second object (933) can include an object classified as an additional object of the first content (910). The electronic device can identify the first object (931) and the second object (933) based on information regarding the type to which each of the plurality of objects of the first content (910) output from the object classification module (920) is classified. For example, the electronic device can identify a character (911) and text (915) as the first object (931). For example, as a result of identifying the character (911), the electronic device may obtain the features that the character (911) is located in the center of the screen and is wearing a red and blue suit and mask. In addition, the electronic device may identify "the face and costume cannot be changed, and the pose can be changed" as an attribute related to the character (911). For example, as a result of identifying the text (915), the electronic device may obtain the features that the words "The Amazing MAN" are left-aligned in a Sanskrit font and a size of 15, and the attribute that "cannot be changed." For example, the electronic device may identify the background (913) as the second object (933). For example, as a result of identifying the background (913), the electronic device may obtain the features of a cityscape including a skyline made up of multiple buildings.

[0160] According to one embodiment, the electronic device may provide a first object (931), a second object (933), and personalized information (935) to an input prompt generation module (940). The personalized information (935) may include information obtained based on the second content from an artificial intelligence model trained to obtain weights for each of the preset types from the content. The artificial intelligence model may correspond to the artificial intelligence model described with reference to FIG. 4 (e.g., 430 of FIG. 4) and the artificial intelligence model described with reference to FIG. 7 (e.g., 720 of FIG. 7). The personalized information (935) may include information relevant to the user according to the user's interests, preferences, needs, and circumstances. For example, the personalized information (935) may include information regarding at least a portion of the user's face and body.

[0161] According to one embodiment, the electronic device may obtain an input prompt output from an input prompt generation module (940). The input prompt generation module (940) may correspond to the input prompt generation module described with reference to FIG. 4 (e.g., 450 of FIG. 4) and the input prompt generation module described with reference to FIG. 8 (e.g., 820 of FIG. 8).

[0162] According to one embodiment, the electronic device may obtain a first input prompt (951) output from the input prompt generation module (940) based on the first object (931). For example, the electronic device may obtain a first input prompt (951) including information about the appearance (e.g., size, shape, color) of the character (911) and attributes (e.g., information about changeable / non-changeable objects). For example, the electronic device may obtain a first input prompt (951) including the content of text (915). For example, the electronic device may obtain a first input prompt (951) such as "[Object 1] A character located in the center of the screen, wearing a red and blue suit and mask, [Object 1 properties] The costume and face of the first object cannot be changed, the pose can be changed, [Object 2] The words "The Amazing MAN" are displayed at the top in a left-aligned state with a font: Sanskrit size: 15, [Object 2 properties] cannot be changed."

[0163] According to one embodiment, the electronic device may obtain a second input prompt (953) output from the input prompt generation module (940) based on the second object (933) and personalized information (935). For example, the electronic device may obtain a second input prompt (953) including information about the user's face. For example, the electronic device may obtain a second input prompt (953) including information about the user's body. For example, the electronic device may obtain a second input prompt (953) including information about clothes worn by the user. For example, the electronic device may obtain a second input prompt (953) for changing a feature (e.g., color) of the background (913). For example, the electronic device may obtain a second input prompt (953) such as "[Background] Autumn park in the middle of high-rise buildings in a large city, [Background property] Changeable, [Object] Centered on the screen, created as a human appearance image using data in which the user's face is revealed among personalized information, [Object property] Changeable within data in which the user's face is included in personalized information."

[0164] According to one embodiment, the electronic device may provide at least a portion of the first input prompt (951) and at least a portion of the second input prompt (953) to the generative artificial intelligence model (960). The generative artificial intelligence model (960) may include an artificial intelligence model trained for generating user-customized content. The generative artificial intelligence model (960) may correspond to the generative artificial intelligence model described with reference to FIG. 4 (e.g., 470 of FIG. 4). For example, the electronic device may provide at least a portion of the first input prompt (951), which includes information about the appearance (e.g., size, shape, color) of the character (911) and the content of the text (915), to the generative artificial intelligence model (960). For example, the electronic device may provide at least a portion of the second input prompt (953), which includes information about the user's face and skeleton and information about the color of the background, to the generative artificial intelligence model (960). For example, the electronic device may provide an input prompt such as "[Object 1] located in the center of the screen, character wearing a red and blue suit and mask, [Object 1 attribute] the costume and face of the first object cannot be changed, the pose can be changed, [Object 2] the words "The Amazing MAN" are displayed at the top in a left-aligned state with a font size of 15 in Sanskrit, [Object 2 attribute] cannot be changed, [Background] an image of an autumn park in the middle of high-rise buildings in a large city, [Background attribute] changeable to an image of an autumn park included in personalized information, [Object 3] located in the center of the screen, a human appearance image created using data in which the user's face is revealed among personalized information, [Object 3 attribute] changeable within data in which the user's face is included in personalized information" to the generative artificial intelligence model (960). According to one embodiment, the electronic device may obtain third content (970) output from the generative artificial intelligence model (960).For example, the electronic device can obtain third content (970) output from the generative artificial intelligence model (960) based on at least a portion of the first input prompt (951) and at least a portion of the second input prompt (953). For example, the electronic device can obtain third content (970) including a character, a portion of the user's face and body, and text. For example, the electronic device can obtain third content (970) including a user carried by a character and a title of a game corresponding to the first input prompt (951) and the second input prompt (953) input to the generative artificial intelligence model (960).

[0165] According to one embodiment, the electronic device can output third content (970). For example, the electronic device can output the third content (970) using at least one of a display and an audio module of the electronic device. For example, the electronic device can transmit the third content (970) to an external electronic device in order to output the third content (970) using at least one of a display and an audio module of the external electronic device.

[0166] FIG. 10 is a diagram illustrating an electronic device that acquires content using a generative artificial intelligence model according to various embodiments. The operation of the electronic device illustrated in FIG. 10 may be performed by a processor (e.g., the processor (220) of FIG. 2) performing calculations or controlling components of the electronic device. In addition, the operation of the electronic device illustrated in FIG. 10 may be performed by the electronic device alone, or some operations may be performed through an external electronic device. The module of FIG. 10 may be implemented as hardware or software to perform a predetermined function. The artificial intelligence model of FIG. 10 may include hardware or software implemented to perform a predetermined function.

[0167] According to one embodiment, the electronic device may input first content (1010). For example, the electronic device may input first content (1010) including a product advertisement image. The electronic device may provide the first content (1010) to an object classification module (1020). The object classification module (1020) may correspond to the object classification module (420 of FIG. 4) described with reference to FIG. 4 and the object classification module (620 of FIG. 6) described with reference to FIG. 6. The first content (1010) may include a person (1011), a first product (1013), a second product (1015), and text (1017). For example, the first content (1010) may include identifiers related to objects (1011, 1013, 1015, 1017) included in the first content (1010).

[0168] According to one embodiment, the electronic device can obtain information about each of the objects (1011, 1013, 1015, 1017) included in the first content (1010) output from the object classification module (1020). For example, the electronic device can obtain information about the appearance (e.g., size, shape, color) of each of the person (1011), the first product (1013), the second product (1015), and the text (1017) from the object classification module (1020). For example, the electronic device can obtain information about the content of the text (1017) from the object classification module (1020). For example, as an identification result of the first product (1013), the electronic device can obtain the characteristics of a detergent container located at the upper right corner of the screen, having a blue body, an orange lid, and a red logo. The electronic device can identify an attribute of the first product (1013) that is unchangeable. For example, the electronic device can obtain the features of the text (1017) being located in the upper left corner, the word XX detergent being in a Sanskrit font and a size of 15, and being left-aligned. The electronic device can identify the property of the text (1017) being unchangeable. For example, the electronic device can obtain the features of the person (1011) being located in the center left corner of the screen, sitting with the right side of the face exposed, and putting in laundry. The electronic device can identify the property of the person (1011) being changeable in the data in which the user's face is included in the personalized information. For example, the electronic device can obtain the features of the white colored washing machine being located in the center right corner of the screen, as the identification result of the second product (1015). The electronic device can identify the properties of the second product (1015) being model name AA, fixed black color, and product orientation being changeable.

[0169] According to one embodiment, the electronic device can identify a first object (1031) and a second object (1033) among the objects included in the first content (1010). For example, the electronic device can identify a first product (1013) and text (1017) as the first object (1031). For example, the electronic device can identify a person (1011) and a second product (1015) as the second object (1033).

[0170] According to one embodiment, the electronic device may provide a first object (1031), a second object (1033), and personalized information (1035) to an input prompt generation module (1040). The personalized information (1035) may include information acquired based on the second content from an artificial intelligence model trained to acquire weights for each of the preset types from the content. The artificial intelligence model may correspond to the artificial intelligence model described with reference to FIG. 4 (e.g., 430 of FIG. 4) and the artificial intelligence model described with reference to FIG. 7 (e.g., 720 of FIG. 7). For example, the personalized information (1035) may include information relevant to the user according to the user's interests, preferences, needs, and circumstances. For example, the personalized information (1035) may include information (1036) regarding at least a portion of the user's face and body. For example, the personalized information (1035) may include information (1037) regarding a washing machine used by the user.

[0171] According to one embodiment, the electronic device may obtain an input prompt output from an input prompt generation module (1040). The input prompt generation module (1040) may correspond to the input prompt generation module described with reference to FIG. 4 (e.g., 450 of FIG. 4) and the input prompt generation module described with reference to FIG. 8 (e.g., 820 of FIG. 8).

[0172] According to one embodiment, the electronic device may obtain a first input prompt (1051) output from the input prompt generation module (1040) based on the first object (1031). For example, the electronic device may obtain a first input prompt (1051) including information about the appearance (e.g., size, shape, color) and location of the first product (1013). For example, the electronic device may obtain a first input prompt (1051) including the content of text (1017). For example, the electronic device may obtain a first input prompt (1051) such as "[Object 1] detergent container located at the upper right of the screen, having a blue body, an orange lid, and a red logo, [Object 1 property] cannot be changed, [Object 2] the word XX detergent is displayed at the upper left in a left-aligned state with a font: Sanskrit, size: 15, [Object 2 property] cannot be changed."

[0173] According to one embodiment, the electronic device may obtain a second input prompt (1053) output from the input prompt generation module (1040) based on the second object (1033) and personalized information (1035). For example, the electronic device may obtain a second input prompt (1053) that includes information about the user's face. For example, the electronic device may obtain a second input prompt (1053) that includes information about the user's body. For example, the electronic device may obtain a second input prompt (1053) that includes information about clothes worn by the user. For example, the electronic device may obtain a second input prompt (1053) that includes information about the appearance (e.g., size, shape, color) and model name of a product used by the user. For example, the electronic device may obtain a second input prompt (1053) that includes information about the appearance (e.g., size, shape, color), model name, and location of the second product. For example, the electronic device can obtain a second input prompt (1053) such as "[Background] Image of an apartment laundry room with a pantry, [Background attribute] Changeable to the laundry room image included in the personalized information, [Object 3] Located in the left center of the screen, using data showing the user's right face among the personalized information, create an image of a person sitting and putting in laundry, [Object 3 attribute] Changeable within data containing the user's face included in the personalized information, [Object 4] Located in the right center of the screen, create an image of a washing machine with model name AA and color black, [Object 4 attribute] Color and model name cannot be changed, product direction can be changed."

[0174] According to one embodiment, the electronic device may provide a first input prompt (1051) and a second input prompt (1053) to a generative artificial intelligence model (1060). The generative artificial intelligence model (1060) may include an artificial intelligence model trained for generating user-customized content. The generative artificial intelligence model (1060) may correspond to the generative artificial intelligence model described with reference to FIG. 4 (e.g., 470 of FIG. 4). For example, the electronic device may provide at least a portion of the first input prompt (1051), which includes information about the appearance (e.g., size, shape, color) and location of the first product (1013), and information about the content of the text (1017), to the generative artificial intelligence model (1060). For example, the electronic device may provide at least a portion of a second input prompt (1053) to the generative artificial intelligence model (1060) that includes information about the user's face and skeleton, information about the appearance and model name of a product used by the user, and information about the appearance (e.g., size, shape, color) and location of a second product.For example, the electronic device may provide an input prompt such as "[Object 1] located in the upper right corner of the screen, detergent container with blue body, orange lid, and red logo, [Object 1 attribute] cannot be changed, [Object 2] located in the upper left corner, the word XX detergent is displayed in font: Sanskrit, size: 15, left-aligned, [Object 2 attribute] cannot be changed, [Background] apartment laundry room with pantry, [Background attribute] changeable to laundry room image included in personalized information, [Object 3] located in the left center of the screen, created as an image of sitting and putting in laundry using data showing the user's right face among personalized information, [Object 3 attribute] changeable within data containing the user's face included in personalized information, [Object 4] located in the right center of the screen, created as an image of a washing machine with model name AA, black color, [Object 4 attribute] color and model name cannot be changed, product direction can be changed."

[0175] In one embodiment, the electronic device may obtain third content (1070) output from the generative artificial intelligence model (1060). For example, the electronic device may obtain third content (1070) output from the generative artificial intelligence model (1060) based on at least a portion of the first input prompt (1051) and at least a portion of the second input prompt (1053). For example, the electronic device may obtain third content (1070) including a product name, an advertising product, parts of the user's face and body, and a washing machine used by the user.

[0176] In one embodiment, the electronic device may output third content (1070). For example, the electronic device may output the third content (1070) using at least one of a display and an audio module of the electronic device. For example, the electronic device may transmit the third content (1070) to an external electronic device in order to output the third content (1070) using at least one of a display and an audio module of the external electronic device.

[0177] FIG. 11 is a diagram illustrating an electronic device that acquires content using a generative artificial intelligence model according to various embodiments. The operation of the electronic device illustrated in FIG. 11 may be performed by a processor (e.g., the processor 220 of FIG. 2) performing calculations or controlling components of the electronic device. In addition, the operation of the electronic device illustrated in FIG. 11 may be performed by the electronic device alone, or some operations may be performed through an external electronic device. The module of FIG. 11 may be implemented as hardware or software to perform a predetermined function. The artificial intelligence model of FIG. 11 may include hardware or software implemented to perform a predetermined function.

[0178] According to one embodiment, the electronic device may input first content (1110). For example, the electronic device may input first content (1110) including a product advertisement image.

[0179] According to one embodiment, the electronic device may provide the first content (1110) to the object classification module (1120). The object classification module (1120) may correspond to the object classification module described with reference to FIG. 4 (e.g., 420 of FIG. 4) and the object classification module described with reference to FIG. 6 (e.g., 620 of FIG. 6). The first content (1110) may include identifiers related to objects (1011, 1013, 1015, 1017) included in the first content (1110). According to one embodiment, the electronic device may obtain information about each of the objects included in the first content (1110) output from the object classification module (1120). For example, the electronic device can obtain information about the appearance (e.g., size, shape, color) of the first object, the second object, and the background included in the first content (1110) from the object classification module (1120). For example, the electronic device can obtain the characteristic of a translucent shower head having a filter in the handle as a result of identifying the first object. The electronic device can identify the attribute of the first object that it is unchangeable. For example, the electronic device can obtain the characteristic of a shower head filter as a result of identifying the second object. The electronic device can identify the attribute of the second object that it is changeable and deletable. For example, the electronic device can obtain the characteristic of a yellow background. The electronic device can identify the attribute of the background that it is changeable.

[0180] According to one embodiment, the electronic device can identify a first object (1131) and a second object (1133) among the objects included in each of the first contents (1110). For example, the electronic device can identify the first object (1131) and the second object (1133) classified by the object classification module (1120) based on the identifier. For example, the electronic device can identify the first object (1131) and the second object (1133) classified by an artificial intelligence model trained to identify objects included in the contents and classify their types. For example, the electronic device can identify a showerhead in the first contents (1110) as the first object (1131). For example, the electronic device can identify a filter and a background in the first contents (1110) as the second object (1133).

[0181] According to one embodiment, an electronic device may obtain personalized information from a plurality of contents (1111, 1113). The personalized information (1135) may include information obtained based on second content from an artificial intelligence model trained to obtain weights for each of the preset types from the contents. The artificial intelligence model may correspond to the artificial intelligence model described with reference to FIG. 4 (e.g., 430 of FIG. 4) and the artificial intelligence model described with reference to FIG. 7 (e.g., 720 of FIG. 7). For example, the personalized information (1135) may include information relevant to the user according to the user's interests, preferences, needs, and circumstances. For example, the personalized information (1135) may include information regarding at least a portion of the user's face and body. For example, the electronic device may obtain personalized information from content being played on the electronic device (e.g., video, photo, music, web page, application). For example, an electronic device can obtain personalized information from content (e.g., videos, photos, music, web pages, applications) to be played on the electronic device. For example, an electronic device can obtain personalized information from contextual information (e.g., location information, information about the screen being displayed by the electronic device, information about the surrounding environment of the electronic device, status information of the electronic device, status information of the user, or schedule information of the user) obtained when the user uses the electronic device. For example, an electronic device can obtain personalized information about a product of interest of the user from a homepage (1111) selling a filter being displayed by the electronic device. For example, an electronic device can obtain personalized information about the appearance of a part of the user's body from an image (1113) of the user washing his or her hands stored in the user's gallery.

[0182] According to one embodiment, the electronic device may provide the first object (1131), the second object (1133), and personalized information (1135) to the input prompt generation module (1140). For example, the electronic device may provide the input prompt generation module (1140) with features regarding a shower identified from the first content (1110) as a primary object. For example, the electronic device may provide the input prompt generation module (1140) with features regarding a filter and a background identified from the first content (1110) as additional objects. For example, the electronic device may provide the input prompt generation module (1140) with features of an image including a user's hand as personalized information (1135).

[0183] According to one embodiment, the electronic device may obtain an input prompt output from an input prompt generation module (1140). The input prompt generation module (1140) may correspond to the input prompt generation module described with reference to FIG. 4 (e.g., 450 of FIG. 4) and the input prompt generation module described with reference to FIG. 8 (e.g., 820 of FIG. 8).

[0184] According to one embodiment, the electronic device may obtain a first input prompt (1151) output from the input prompt generation module (1140) based on a first object (1131) included in the first content (1110). For example, the electronic device may obtain a first input prompt (1151) that includes information about the appearance (e.g., size, shape, color) of a showerhead. For example, the electronic device may obtain a first input prompt (1151) such as "[Object] Image of a translucent showerhead with a filter on the handle, [Object property] cannot be changed."

[0185] According to one embodiment, the electronic device may obtain a second input prompt (1153) output from the input prompt generation module (1140) based on the second object (1133) and personalized information (1135). For example, the electronic device may obtain a second input prompt (1153) that includes information about the user's body. For example, the electronic device may obtain a second input prompt (1153) that includes information about clothes worn by the user. For example, the electronic device may obtain a second input prompt (1153) that includes information about the color of the background. For example, the electronic device may obtain a second input prompt (1153) such as "[Object] Generate an image of washing hands using an image of the user's hand among user images, [Object property] changeable pose, [Background] blue, [Background property] changeable."

[0186] According to one embodiment, the electronic device may provide a first input prompt (1151) and a second input prompt (1153) to a generative artificial intelligence model (1160). The generative artificial intelligence model (1160) may include an artificial intelligence model trained for generating user-customized content. The generative artificial intelligence model (960) may correspond to the generative artificial intelligence model described with reference to FIG. 4 (e.g., 470 of FIG. 4). For example, the electronic device may provide at least a portion of the first input prompt (1151), which includes information about the appearance (e.g., size, shape, color) of a water filter, to the generative artificial intelligence model (1160). For example, the electronic device may provide at least a portion of the second input prompt (1153), which includes information about the user's body, information about clothes worn by the user, and information about the user's favorite color, to the generative artificial intelligence model (1160). For example, the electronic device may provide input prompts such as “[Object 1] Image of a translucent shower head with a filter on the handle, [Object 1 property] cannot be changed, [Object 2] Generate an image of washing hands using an image of a user’s hand from among the user images, [Object 2 property] Changeable pose, [Background] Blue, [Background property] Changeable” to the generative artificial intelligence model (1160).

[0187] In one embodiment, the electronic device may obtain third content (1170) output from the generative artificial intelligence model (1160). For example, the electronic device may obtain third content (1170) output from the generative artificial intelligence model (1160) based on at least a portion of the first input prompt (1151) and at least a portion of the second input prompt (1153). For example, the electronic device may obtain third content (1170) including a shower head, a user's hand, and a background in a color preferred by the user.

[0188] According to one embodiment, the electronic device can output third content (1170). For example, the electronic device can output the third content (1170) using at least one of a display and an audio module of the electronic device. For example, the electronic device can transmit the third content (1170) to an external electronic device in order to output the third content (1170) using at least one of a display and an audio module of the external electronic device.

[0189] FIG. 12 is a diagram illustrating an electronic device that acquires content using a generative artificial intelligence model according to various embodiments. The operation of the electronic device illustrated in FIG. 12 may be performed by a processor (e.g., the processor 220 of FIG. 2) performing calculations or controlling components of the electronic device. In addition, the operation of the electronic device illustrated in FIG. 12 may be performed solely by the electronic device, or some operations may be performed through an external electronic device. The module of FIG. 12 may be implemented as hardware or software to perform a predetermined function. The artificial intelligence model of FIG. 12 may include hardware or software implemented to perform a predetermined function.

[0190] According to one embodiment, the electronic device may input first content (1210). For example, the electronic device may input first content (1210) including a product advertisement image. The electronic device may provide the first content (1210) to an object classification module (1220). The object classification module (1220) may correspond to the object classification module (420 of FIG. 4) described with reference to FIG. 4 and the object classification module (620 of FIG. 6) described with reference to FIG. 6. The first content (1210) may include a product (1211), a first text (1213), and a second text (1215). For example, the first content (1210) may include identifiers related to objects (1211, 1213, 1215) included in the first content (1210).

[0191] According to one embodiment, the electronic device can obtain information about each of the objects (1211, 1213, 1215) included in the first content (1210) output from the object classification module (1220). For example, the electronic device can obtain information about the appearance (e.g., size, shape, color) of each of the product (1211), the first text (1213), and the second text (1215) from the object classification module (1220). The electronic device can obtain information about the content of the first text (1213) and the second text (1215) from the object classification module (1220). For example, the electronic device can obtain the characteristics of the shoe located at the lower center of the screen as a result of the identification of the product (1211). The electronic device can identify an attribute of the product (1211) that is unchangeable. For example, the electronic device can identify the property that the position and / or size of the product (1211) cannot be changed, and the shape, appearance, and image of the product (1211) can be changed. For example, the electronic device can identify the property that the product (1211) cannot be changed within a certain frame of a video. For example, the electronic device can identify the property that the position and shape cannot be changed within a certain frame of a video, and the shape and design of an object obtained from personalized information or content other than the first content (1210) can be changed in frames other than the certain frame.

[0192] For example, as a result of identifying the first text (1213), the electronic device can obtain the characteristics that the text is located at the upper right corner of the screen, has a size of 10, and the content is about "50% off online promotion on October 25th." The electronic device can identify the attributes of the first text (1213) that the size and color can be changed, and the content cannot be changed. For example, as a result of identifying the second text (1215), the electronic device can obtain the characteristics that the text is located at the upper left corner of the screen, has a size of 15, and the content is about "NEW ARRIVAL," and the text is 12, and the content is about "LIMITED SHOES." The electronic device can identify the attribute of the second text (1215) that the text is "changeable."

[0193] According to one embodiment, the electronic device can identify a first object (1231) and a second object (1233) among the objects included in the first content (1210). For example, the electronic device can identify a product (1211) and a first text (1213) as the first object (1231). For example, the electronic device can identify a second text (1215) as the second object (1233).

[0194] According to one embodiment, the electronic device may provide a first object (1231), a second object (1233), and personalized information (1235) to an input prompt generation module (1240). The personalized information (1235) may include information acquired based on the second content from an artificial intelligence model trained to acquire weights for each of the preset types from the content. The artificial intelligence model may correspond to the artificial intelligence model described with reference to FIG. 4 (e.g., 430 of FIG. 4) and the artificial intelligence model described with reference to FIG. 7 (e.g., 720 of FIG. 7). For example, the personalized information (1235) may include information relevant to the user according to the user's interests, preferences, needs, and circumstances. For example, the personalized information (1235) may include information regarding sneakers used by the user.

[0195] According to one embodiment, the electronic device may obtain an input prompt output from an input prompt generation module (1240). The input prompt generation module (1240) may correspond to the input prompt generation module described with reference to FIG. 4 (e.g., 450 of FIG. 4) and the input prompt generation module described with reference to FIG. 8 (e.g., 820 of FIG. 8).

[0196] According to one embodiment, the electronic device may obtain a first input prompt (1251) output from the input prompt generation module (1240) based on the first object (1231). For example, the electronic device may obtain a first input prompt (1251) that includes information about the appearance (e.g., size, shape, color) and location of the product (1211). For example, the electronic device may obtain a first input prompt (1251) that includes information about the appearance (e.g., size, shape, color), content, and location of the first text (1213). For example, the electronic device may obtain a first input prompt (1251) such as "[object] image of a shoe located at the center bottom of the screen, [object property] electronic device cannot change position and shape within one frame of the video and can change shape and design of the object in frames other than one frame, [text] 50% discount for online promotion on October 25, [text property] size and color can be changed, content cannot be changed."

[0197] According to one embodiment, the electronic device may obtain a second input prompt (1253) output from the input prompt generation module (1240) based on the second object (1233) and personalized information (1235). For example, the electronic device may obtain a second input prompt (1253) including information related to the appearance (e.g., size, shape, color), purchase date, and model of the shoes the user is wearing. For example, the electronic device may obtain a second input prompt (1253) including at least a portion of the content of the second text (1215). For example, the electronic device may obtain a second input prompt (1253) such as "[Object] Shoes worn by the user included in personalized information are located at the lower center of the screen. [Object property] Model cannot be changed, can be changed to an old look, [Text] LIMITED SHOES, [Text property] Size and color can be changed."

[0198] According to one embodiment, the electronic device may provide a first input prompt (1251) and a second input prompt (1253) to a generative artificial intelligence model (1260). The generative artificial intelligence model (1260) may include an artificial intelligence model trained for generating user-customized content. The generative artificial intelligence model (1260) may correspond to the generative artificial intelligence model described with reference to FIG. 4 (e.g., 470 of FIG. 4). For example, the electronic device may provide at least a portion of the first input prompt (1251), which includes information about the appearance (e.g., size, shape, color) and location of the product (1211), to the generative artificial intelligence model (1260). For example, the electronic device may provide at least a portion of the second input prompt (1253), which includes information about the appearance (e.g., size, shape, color), purchase date, and model of a shoe being worn by the user, and the content of the second text (1215), to the generative artificial intelligence model (1260). For example, the electronic device may provide an input prompt such as "Generate a video composed of a first frame and a second frame, [First frame object] Shoes worn by the user included in personalized information located at the bottom center of the screen, [First frame object property] Model cannot be changed, can be changed to an old look, [First frame text] LIMITED SHOES, [First frame text property] Size and color can be changed, [Second frame object] Image of shoes of model XX located at the bottom center of the screen, [Second frame object property] cannot be changed, [Second frame text] 50% discount for online promotion on October 25, [Second frame text property] Size and color can be changed, content cannot be changed" to the generative artificial intelligence model (1060).

[0199] According to one embodiment, the electronic device can obtain third content output from the generative artificial intelligence model (1260). For example, the electronic device can obtain third content (1270) output from the generative artificial intelligence model (1260) based on at least a portion of the first input prompt (1251) and at least a portion of the second input prompt (1253). For example, the electronic device can obtain third content (1270) generated as a video. For example, the electronic device can obtain video content including a first frame (1271) that includes a sneaker worn by a user as an object and a second frame (1273) that includes a product (1211) as an object as the third content (1270).

[0200] According to one embodiment, the electronic device may output third content (1270). For example, the electronic device may output the third content (1270) using at least one of a display and an audio module of the electronic device. For example, the electronic device may transmit the third content (1270) to an external electronic device in order to output the third content (1270) using at least one of a display and an audio module of the external electronic device.

[0201] FIG. 13 is a diagram illustrating an electronic device that acquires content using a generative artificial intelligence model according to various embodiments. The operation of the electronic device illustrated in FIG. 13 may be performed by a processor (e.g., the processor 220 of FIG. 2) performing calculations or controlling components of the electronic device. In addition, the operation of the electronic device illustrated in FIG. 13 may be performed solely by the electronic device, or some operations may be performed through an external electronic device. The module of FIG. 13 may be implemented as hardware or software to perform a predetermined function. The artificial intelligence model of FIG. 13 may include hardware or software implemented to perform a predetermined function.

[0202] According to one embodiment, the electronic device may input first content (1310). For example, the electronic device may input first content (1310) including product advertising text and product images. The electronic device may provide the first content (1310) to an object classification module (1320). The object classification module (1320) may correspond to the object classification module (420 of FIG. 4) described with reference to FIG. 4 and the object classification module (620 of FIG. 6) described with reference to FIG. 6. The first content (1310) may include text (1311), a product (1313), and a background (1315). For example, the first content (1310) may include identifiers related to objects (1311, 1313, 1315) included in the first content (1310).

[0203] According to one embodiment, the electronic device can obtain information about each of the objects included in the first content (1310) output from the object classification module (1320). For example, the electronic device can obtain information about the text (1311), the appearance (e.g., size, shape, color) of each of the products (1313), and the background (1315) from the object classification module (1320). For example, as a result of identifying the text (1311), the electronic device can obtain a feature that "TRANSFORM YOUR SPACE INQUIRE TODAY!" is located at the center of the first content (1310), and that the size of "TRANSFORM YOUR SPACE" is 20 and the size of "INQUIRE TODAY!" is 10. The electronic device can identify an attribute of the text that the size and font can be changed. For example, the electronic device may, upon identifying the product (1313), obtain the characteristics of an open five-story display cabinet located on both sides of the first content (1310). The electronic device may identify an attribute of the product (1313) that cannot be changed. For example, the electronic device may, upon identifying the background (1315), obtain the characteristics of the appearance of the walls, floor, ceiling, and pillars. The electronic device may identify an attribute of the background (1315) that the positions of the walls and pillars cannot be changed, and the rest can be changed.

[0204] According to one embodiment, the electronic device can identify a first object (1331) and a second object (1333) among the objects included in the first content (1310). For example, the electronic device can identify text (1311) and a product (1313) as the first object (1331). For example, the electronic device can identify a background (1315) as the second object (1333).

[0205] According to one embodiment, the electronic device may provide a first object (1331), a second object (1333), and personalized information (1335) to an input prompt generation module (1340). The personalized information (1335) may include information acquired based on the second content from an artificial intelligence model trained to acquire weights for each of the preset types from the content. The artificial intelligence model may correspond to the artificial intelligence model described with reference to FIG. 4 (e.g., 430 of FIG. 4) and the artificial intelligence model described with reference to FIG. 7 (e.g., 720 of FIG. 7). For example, the personalized information (1335) may include information relevant to the user according to the user's interests, preferences, needs, and circumstances. For example, the personalized information (1335) may include information regarding the user's living space. For example, the personalized information (1335) may include information regarding a product being used by the user.

[0206] In one embodiment, personalized information (1335) may be obtained from images captured at locations determined to be where the user resides or frequently visits. For example, the characteristics of a subject recognized from an image captured at the user's residence may be included in personalized information (1335). In one embodiment, personalized information (1335) may be obtained from images captured by the user. For example, the characteristics of a subject recognized from an image captured by the user or the appearance of the user recognized from an image captured by the user may be included in personalized information (1335).

[0207] According to one embodiment, the electronic device may obtain an input prompt output from an input prompt generation module (1340). The input prompt generation module (1340) may correspond to the input prompt generation module described with reference to FIG. 4 (e.g., 450 of FIG. 4) and the input prompt generation module described with reference to FIG. 8 (e.g., 820 of FIG. 8).

[0208] According to one embodiment, the electronic device may obtain a first input prompt (1351) output from the input prompt generation module (1340) based on the first object (1331). For example, the electronic device may obtain the first input prompt (1351) including information about the appearance (e.g., size, shape, color) and location of the text (1311) and the product (1313). For example, the electronic device may obtain the first input prompt (1351) such as "[Text] Place TRANSFORM YOUR SPACE INQUIRE TODAY! in the center of the image, [Text Attribute] Size and font can be changed, [Product] Place the open 5-tier display case on both sides of the image, and [Product Attribute] Cannot be changed."

[0209] According to one embodiment, the electronic device may obtain a second input prompt (1353) output from the input prompt generation module (1340) based on the second object (1333) and personalized information. For example, the electronic device may obtain a second input prompt (1353) including information (1335) about the user's living space. For example, the electronic device may obtain a second input prompt (1353) including information about a product being used by the user. For example, the electronic device may obtain a second input prompt (1353) such as "[Floor] Rug, sofa, and round table are arranged, [Floor property] is changeable, [Wall] color is stone gray, the front wall is white with a framed configuration, [Wall property] is changeable, [Column] color is stone gray, arranged in a form that harmonizes with the wall, [Column property]: changeable."

[0210] According to one embodiment, the electronic device may provide a first input prompt (1351) and a second input prompt (1353) to a generative artificial intelligence model (1360). The generative artificial intelligence model (1360) may include an artificial intelligence model trained for generating user-customized content. The generative artificial intelligence model (1360) may correspond to the generative artificial intelligence model described with reference to FIG. 4 (e.g., 470 of FIG. 4). For example, the electronic device may provide at least a portion of the first input prompt (1351), which includes information about text (1311) and the appearance (e.g., size, shape, color) and location of a product (1313), to the generative artificial intelligence model (1360). For example, the electronic device may provide at least a portion of the second input prompt (1353), which includes information about a user's living space and information about a product being used by the user, to the generative artificial intelligence model (1360). For example, the electronic device may provide the generative artificial intelligence model (1360) with input prompts such as "[Text] Place TRANSFORM YOUR SPACE INQUIRE TODAY! in the center of the image, [Text Attributes] Size and font can be changed, [Product] Place an open 5-tier display case on both sides of the image, [Product Attributes] cannot be changed, [Floor] Place a rug, a sofa, and a round table, [Floor Attributes] can be changed, [Wall]: Color is stone gray, the front wall is white with a framed configuration, [Wall Attributes]: can be changed, [Column] Color is stone gray, Place in a form that harmonizes with the wall, [Column Attributes]: can be changed."

[0211] According to one embodiment, the electronic device may obtain third content (1370) output from the generative artificial intelligence model (1360). For example, the electronic device may obtain third content (1370) output from the generative artificial intelligence model (1360) based on at least a portion of the first input prompt (1351) and at least a portion of the second input prompt (1353). For example, the electronic device may obtain text and an image including the appearance of a product within the user's living space as the third content (1370).

[0212] According to one embodiment, the electronic device can output third content (1370). For example, the electronic device can output the third content (1370) using at least one of a display and an audio module of the electronic device. For example, the electronic device can transmit the third content (1370) to an external electronic device in order to output the third content (1370) using at least one of a display and an audio module of the external electronic device.

[0213] FIG. 14 is a diagram illustrating an electronic device that acquires content using a generative artificial intelligence model according to various embodiments. The operation of the electronic device illustrated in FIG. 14 may be performed by a processor (e.g., the processor (220) of FIG. 2) performing calculations or controlling components of the electronic device. In addition, the operation of the electronic device illustrated in FIG. 14 may be performed by the electronic device alone, or some operations may be performed through an external electronic device. The module of FIG. 14 may be implemented as hardware or software to perform a predetermined function. The artificial intelligence model of FIG. 14 may include hardware or software implemented to perform a predetermined function.

[0214] According to one embodiment, the electronic device may input a plurality of contents (1410). For example, the electronic device may input one or more images from among a first image (1411) and a second image (1413) that include a key visual of the brand.

[0215] According to one embodiment, the electronic device may provide a plurality of contents (1410) to an object classification module (1420). The object classification module (1420) may correspond to the object classification module described with reference to FIG. 4 (e.g., 420 of FIG. 4) and the object classification module described with reference to FIG. 6 (e.g., 620 of FIG. 6). The plurality of contents (1410) may include objects that are related to each other. For example, a first image (1411) and a second image (1413) may include color patterns of a brand as objects that are related to each other. Each of the first image (1411) and the second image (1413) may include identifiers related to objects included in the first image (1411) and the second image (1413).

[0216] According to one embodiment, the electronic device can obtain information about each of the objects included in each of the plurality of contents (1410) output from the object classification module (1420). For example, the electronic device can obtain information about the appearance (e.g., size, shape, color) of each of the color patterns, people, text, and background included in each of the first image (1411) and the second image (1413) from the object classification module (1420). For example, the electronic device can obtain features about stripes in which red, white, and blue are sequentially arranged from the first image (1411) and the second image (1413). The electronic device can identify attributes of the color pattern such as unchangeable, unchangeable in ratio, and changeable in size.

[0217] According to one embodiment, the electronic device can identify a first object (1431) and a second object (1433) among objects included in each of the plurality of contents (1410). For example, the electronic device can identify a color pattern (1411a) included in a bag in the first image (1411) as the first object (1431). For example, the electronic device can identify a color pattern (1413a) included in a muffler in the second image (1413) as the first object (1431). For example, the electronic device can identify a person and a background in the first image (1411) as the second object (1433). For example, the electronic device can identify a person and a background in the second image (1413) as the second object (1433).

[0218] According to one embodiment, the electronic device may provide a first object (1431), a second object (1433), and personalized information (1435) to an input prompt generation module (1440). The personalized information (1435) may include information obtained based on the second content from an artificial intelligence model trained to obtain weights for each of the preset types from the content. The artificial intelligence model may correspond to the artificial intelligence model described with reference to FIG. 4 (e.g., 430 of FIG. 4) and the artificial intelligence model described with reference to FIG. 7 (e.g., 720 of FIG. 7). For example, the personalized information (1435) may include information relevant to the user according to the user's interests, preferences, needs, and circumstances.

[0219] According to one embodiment, the electronic device may obtain an input prompt output from an input prompt generation module (1440). The input prompt generation module (1440) may correspond to the input prompt generation module described with reference to FIG. 4 (e.g., 450 of FIG. 4) and the input prompt generation module described with reference to FIG. 8 (e.g., 820 of FIG. 8).

[0220] According to one embodiment, the electronic device may obtain a first input prompt (1451) output from the input prompt generation module (1440) based on a first object (1431) included in a plurality of contents (1410). For example, the electronic device may obtain the first input prompt (1451) based on a first object that has a relationship among the first objects (1431) included in each of the plurality of contents (1410). For example, the electronic device may obtain a first input prompt (1451) that includes information about a color pattern. For example, the electronic device may obtain a first input prompt (1451) such as "[Pattern] Image including a color pattern composed of stripes in which red, white, and blue are arranged in sequence, [Pattern Attribute] cannot be changed, ratio cannot be changed, size can be changed."

[0221] According to one embodiment, the electronic device may obtain a second input prompt (1453) output from the input prompt generation module (1440) based on the second object (1433) and personalized information (1435). For example, the electronic device may obtain a second input prompt (1453) that includes information about the user's interests and preferences. For example, the electronic device may obtain a second input prompt (1453) that includes information about a color scheme (e.g., black & white) preferred by the user. For example, the electronic device may obtain a second input prompt (1453) such as "Create a theme for a mobile terminal in a black & white style."

[0222] According to one embodiment, the electronic device may provide a first input prompt (1451) and a second input prompt (1453) to a generative artificial intelligence model (1460). The generative artificial intelligence model (1460) may include an artificial intelligence model trained for generating user-customized content. The generative artificial intelligence model (1460) may correspond to the generative artificial intelligence model described with reference to FIG. 4 (e.g., 470 of FIG. 4). For example, the electronic device may provide at least a portion of the first input prompt (1451), which includes information about a key color pattern of the brand, to the generative artificial intelligence model (1460). For example, the electronic device may provide at least a portion of the second input prompt (1453), which includes information about a color arrangement preferred by the user, to the generative artificial intelligence model (1460). For example, the electronic device may provide an input prompt to the generative artificial intelligence model (1460) such as "Generate a theme for a mobile terminal with a color pattern and a black & white style, [Pattern] Color pattern consisting of stripes arranged in order of red, white, and blue, [Pattern properties] Cannot be changed, ratio cannot be changed, size can be changed."

[0223] In one embodiment, the electronic device may obtain third content (1470) output from the generative artificial intelligence model (1460). For example, the electronic device may obtain third content (1470) output from the generative artificial intelligence model (1460) based on at least a portion of the first input prompt (1451) and at least a portion of the second input prompt (1453). For example, the electronic device may obtain a theme for a mobile terminal that includes a brand's key color pattern and a user's preferred color style as the third content (1470).

[0224] According to one embodiment, the electronic device may output third content (1470). For example, the electronic device may output the third content (1470) using at least one of a display and an audio module of the electronic device. For example, the electronic device may transmit the third content (1470) to an external electronic device in order to output the third content (1470) using at least one of a display and an audio module of the external electronic device.

[0225] According to the disclosed embodiment, an electronic device can easily generate and provide customized content to a user by generating a prompt based on a result of classifying the type of object included in the content and personalized information related to the user, and applying the prompt to a generative artificial intelligence model.

[0226] FIG. 15 is a diagram showing an example of a configuration of a system including a generative artificial intelligence model according to various embodiments.

[0227] According to one embodiment, the electronic device of FIGS. 1 to 14 (e.g., 101 of FIG. 1) may be configured to include at least a portion of the User Query / Response Interface (1510), the AI ​​framework (1520), the application / service component (1530), the knowledge repositories (1540), or the Generative AI Model (1550) of FIG. 15. According to one embodiment, at least a portion of the User Query / Response Interface (1510), the AI ​​framework (1520), the application / service component (1530), the knowledge repositories (1540), or the Generative AI Model (1550) of FIG. 15 may be included in an external electronic device (e.g., 102 of FIG. 1).

[0228] Referring to FIG. 15, the User Query / Response Interface (1510) can receive a user's input. The user's input can be in the form of natural language, images, and / or videos. Additionally, context information can also be transmitted when the user's input is transmitted. The context information can include various additional information at the time of the user's input. For example, it can include information on the application the user is currently using or information on the user's location. Additionally, the user's input can be in the form of a mixture of the aforementioned natural language, images, sounds, and context information. Additionally, the user's input can also be in the form of a non-natural language, such as selecting a menu. The User Query / Response Interface (1510) can output the results of the generative artificial intelligence system to the user. The output can be in the form of natural language or specific content, and can also be provided in the form of an action requested by the user. The User Query / Response Interface (1510) can output the results of the generative artificial intelligence system to the user. The output can be in natural language form, in the form of specific content, or in the form of actions requested by the user.

[0229] The AI ​​framework (1520) can receive user input and coordinate and control each component necessary to perform the user's intention based on the user's query.

[0230] User input received from the User Query / Response Interface (1510) can be transmitted to the Prompt design component (1521). The Prompt design component (1521) can be used to generate prompts suitable for inputting the user input into a Large Language Model (LLM) or a Large Multimodal Model (LMM). The Prompt design component (1521) can be an AI component that uses a machine learning algorithm or a neural network to develop better prompts over time. The Prompt design component (1521) can access a knowledge component (e.g., knowledge repositories (1540)) containing user preference data, a prompt library, and prompt examples based on the user input to generate a prompt, and transmit the generated prompt to the LLM or LMM.

[0231] The API / Plug-in management component (1523) can communicate with external information when there is a request for additional information when passing user input as input to a generative model. The API / Plug-in management component (1523) can establish a channel for communicating with the outside of the AI ​​Interface through the API, and can enable access to various data sources (e.g., knowledge repositories (1540)) through the established channel. In addition, if the API / Plug-in management component (1523) needs to perform an action that performs the user input as a final result rather than an intermediate result in an application or service, it can request the action to the application / service component (1530) through the API. Information obtained from an external source can be used to generate a prompt in the prompt design component (1521) together with the user input, or can be passed as input to the generative model.

[0232] The Refiner component (e.g., the output modification component (1525)) can fine-tune the output from a generative model. For example, the Refiner component can verify that the content generated by the LLM and / or LMM is not irrelevant, biased, or harmful. Furthermore, the Refiner component can determine the degree to which the output matches the user's desired result and, if necessary, perform additional processing. The Refiner component can also include and provide hints to the user to avoid undesirable output.

[0233] Generative AI Model (1550) can generally refer to an artificial intelligence neural network that creates new types of data based on user input information. Generative AI Model (1550) can include an image-generating model and / or a language-generating model. Representative models for generating images include a generative adversarial network (GAN) and a variational autoencoder (VAE), and examples include a diffusion-based generative model that uses a VAE and a transformer structure. A language-generating model is a model trained to statistically output the most appropriate output value based on input values, and representative examples include models such as CHAT-GPT 3 and CHAT-GPT 4. In addition, there is also an LMM that can recognize various types of data input, such as text, images, and voice, and generate new data corresponding to them.

[0234] An electronic device according to one embodiment may include at least one processor including a processing circuit and a memory storing instructions. The at least one processor may individually and / or collectively execute instructions. The electronic device may identify a first object corresponding to a primary object and a second object corresponding to an additional object among a plurality of objects included in a first content. The electronic device may obtain personalized information related to a user from the second content. The electronic device may obtain at least one input prompt based on the first object, the second object, and the personalized information. The electronic device may provide at least one input prompt to a first artificial intelligence model so as to provide third content output from the first artificial intelligence model through a user interface. The third content may include a first object and a third object in which at least a portion of the second object is modified.

[0235] According to one embodiment, the electronic device may identify a second object as an additional object that can be modified using personalized information based on identification information received in association with the first content.

[0236] According to one embodiment, the second content includes an image taken at a location associated with the user, and the electronic device can identify information related to an object included in the image as at least part of the personalized information.

[0237] According to one embodiment, the electronic device may display an updated first object on a user interface via third content based on personalized information.

[0238] According to one embodiment, the electronic device can identify a first object and a second object classified by the second artificial intelligence model from the first content by providing the first content to the second artificial intelligence model.

[0239] According to one embodiment, at least one input prompt may include a plurality of input prompts, including a first input prompt and a second input prompt. The first input prompt may include a feature about a first object, and the second input prompt may include a feature about a second object and at least a portion of personalized information.

[0240] According to one embodiment, the electronic device can obtain personalized information output from the third artificial intelligence model by providing second content to the third artificial intelligence model.

[0241] According to one embodiment, the electronic device can obtain personalized information by identifying content being provided through the electronic device as second content.

[0242] According to one embodiment, the electronic device can obtain personalized information by identifying content to be provided through the electronic device as second content after third content is provided.

[0243] In one embodiment, the instructions of a non-transitory computer-readable recording medium having recorded thereon instructions, when executed individually and / or collectively by at least one processor including a processing circuit, may cause an electronic device to perform at least one operation. The operation performed by the processor may include an operation of identifying, among a plurality of objects included in a first content, a first object and a second object designated to be changeable through the electronic device. The operation performed by the processor may include an operation of obtaining personalized information related to a user from the second content. The operation performed by the processor may include an operation of providing, through a user interface, third content generated based on the first object, the second object, and the personalized information. The third content may include a first object and a third object in which at least a portion of the second object is changed based on the personalized information.

[0244] In one embodiment, the second content may include an image captured by the user. The processor's operation of obtaining personalized information may include obtaining the user's facial region from the image as at least part of the personalized information.

[0245] According to one embodiment, the actions provided by the processor through the user interface may include an action of displaying an updated first object through third content based on object information provided by a provider of the first content.

[0246] A method performed by an electronic device according to one embodiment may include an operation of identifying, among a plurality of objects included in a first content, a first object corresponding to a primary object and a second object corresponding to an additional object. The method performed by the electronic device may include an operation of obtaining personalized information related to a user. The method performed by the electronic device may include an operation of providing, through a user interface, second content generated based on the first object, the second object, and the personalized information. The second content may include the first object and a third object in which at least a portion of the second object is modified.

[0247] According to one embodiment, the method performed by the electronic device may further include an action of obtaining second content by inputting an input prompt generated based on the first object, the second object, and personalized information into an artificial intelligence model.

[0248] In one embodiment, the second content may include an updated first object.

[0249] In one embodiment, the first object may be updated based on object information generated by a provider of the first content.

[0250] According to one embodiment, the action of identifying the electronic device may include an action of identifying a first object among a plurality of objects as a primary object based on identification information received in association with the first content.

[0251] According to one embodiment, the action of identifying the electronic device may include an action of identifying an object that satisfies a specified condition among objects included in a plurality of objects and not identified as a primary object as an additional object.

[0252] In one embodiment, the specified condition may be related to the type of object. The action of identifying the electronic device may include identifying a second object, whose type corresponds to a person, as an additional object among a plurality of objects.

[0253] In one embodiment, the personalized information may include information related to third content being provided via the electronic device. The method performed by the electronic device may include an operation of changing a second object into a third object using at least a portion of the third content.

[0254] Electronic devices according to various embodiments disclosed in this document may take various forms. Electronic devices may include, for example, portable communication devices (e.g., smartphones), computer devices, portable multimedia devices, portable medical devices, cameras, wearable devices, or home appliances. Electronic devices according to embodiments of this document are not limited to the aforementioned devices.

[0255] 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” may 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 the corresponding component from other corresponding components and do not limit the corresponding components in any other respect (e.g., importance or order). When a component (e.g., a first) is referred to as “coupled” or “connected” to another (e.g., a second) component, with or without the terms “functionally” or “communicatively,” it means that the component can be connected to the other component directly (e.g., wired), wirelessly, or through a third component.

[0256] The term "module" used in various embodiments of this document may include a unit implemented by hardware, software, firmware, or a combination thereof, 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).

[0257] Various embodiments of the present document may be implemented as software (e.g., a program (140)) including one or more instructions stored in a storage medium (e.g., an internal memory (136) or an external memory (138)) readable by a machine (e.g., an electronic device (101)). For example, a processor (e.g., a processor (120)) of the machine (e.g., an electronic device (101)) may call at least one instruction among the one or more instructions stored from the storage medium and execute it. This enables the machine to operate to perform at least one function according to the at least one called instruction. The one or more instructions may include code generated by a compiler or code executable by an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' 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.

[0258] According to one embodiment, the method according to various embodiments disclosed in this document may be provided as a computer program product. The computer program product may be traded between sellers and buyers as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)) or may be provided through an application store (e.g., Play Store). TM ) or directly between two user devices (e.g., smart phones), online distribution (e.g., downloading or uploading). In the case of online distribution, at least a portion of the computer program product may be at least temporarily stored or temporarily created in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0259] According to various embodiments, each component (e.g., a module or a program) of the above-described components may include one or more entities, and some of the entities may be separated and arranged in other components. According to various embodiments, one or more components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In such a case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to the integration. According to various embodiments, the operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

[0260] While the present disclosure has been illustrated and described with reference to various embodiments, it will be understood by those skilled in the art that the various embodiments are illustrative and not limiting. It will be further understood by those skilled in the art that various changes in form and detail may be made without departing from the true spirit and scope of the present disclosure, including the appended claims and their corresponding claims. It will also be understood that any of the embodiments described herein may be used in conjunction with any other embodiment described herein.

Claims

1. In electronic devices, At least one processor comprising a processing circuit; and a memory for storing instructions; The at least one processor, individually and / or collectively, executes the instructions, thereby causing the electronic device to: Among the multiple objects included in the first content, identify a first object corresponding to the primary object and a second object corresponding to the additional object, Obtain personalized information related to the user from the second content, Obtaining at least one input prompt based on the first object, the second object and the personalized information, By providing at least one input prompt to the first artificial intelligence model, third content output from the first artificial intelligence model is provided through a user interface, The third content comprises a third object in which at least a part of the second object has been changed and the first object. Electronic devices.

2. In paragraph 1, The at least one processor, individually and / or collectively, executes the instructions, thereby causing the electronic device to: Based on the identification information received in connection with the first content, identifying the second object as the additional object that can be changed using the personalized information. Electronic devices.

3. In paragraph 1, The second content includes an image taken at a location associated with the user, The at least one processor, individually and / or collectively, executes the instructions, thereby causing the electronic device to: To identify information related to an object included in said image as at least a part of said personalized information; Electronic devices.

4. In paragraph 1, The at least one processor, individually and / or collectively, executes the instructions, thereby causing the electronic device to: Displaying the first object updated based on the personalized information on the user interface through the third content; Electronic devices.

5. In paragraph 1, The at least one processor, individually and / or collectively, executes the instructions, thereby causing the electronic device to: By providing the first content to the second artificial intelligence model, the first object and the second object classified by the second artificial intelligence model are identified from the first content. Electronic devices.

6. In paragraph 1, wherein said at least one input prompt comprises a plurality of input prompts including a first input prompt and a second input prompt, The first input prompt includes features about the first object, and the second input prompt includes features about the second object and at least a portion of the personalized information. Electronic devices.

7. In paragraph 1, The at least one processor, individually and / or collectively, executes the instructions, thereby causing the electronic device to: By providing the second content to the third artificial intelligence model, the personalized information output from the third artificial intelligence model is obtained. Electronic devices.

8. In paragraph 1, The at least one processor, individually and / or collectively, executes the instructions, thereby causing the electronic device to: By identifying the content being provided through the electronic device as the second content, the personalized information is obtained. Electronic devices.

9. In paragraph 1, The at least one processor, individually and / or collectively, executes the instructions, thereby causing the electronic device to: By identifying the content to be provided through the electronic device after the third content is provided as the second content, the personalized information is obtained. Electronic devices.

10. In a computer-readable, non-transitory recording medium having instructions recorded thereon, the instructions, when individually and / or collectively executed by at least one processor including a processing circuit, cause the electronic device to perform at least one operation, wherein the at least one operation is: An operation of identifying, among a plurality of objects included in the first content, a first object and a second object designated to be changeable via the electronic device; An action to obtain personalized information related to the user from the second content; and Including an action of providing third content generated based on the first object, the second object, and the personalized information through a user interface; The third content includes the first object and a third object in which at least a part of the second object has been changed based on the personalized information. Recording medium.

11. In clause 10, The second content includes an image taken by the user, and the action of obtaining the personalized information is: An operation comprising obtaining a face area of the user from the image as at least a part of the personalized information, Recording medium.

12. In paragraph 10, The actions provided through the above user interface are: An operation of displaying the first object updated based on object information provided by the provider of the first content through the third content, Recording medium.

13. In a method performed by an electronic device, An operation of identifying a first object corresponding to a primary object and a second object corresponding to an additional object among a plurality of objects included in the first content; Actions to obtain personalized information related to the user; and Including an action of providing second content generated based on the first object, the second object, and the personalized information through a user interface, The second content comprises the first object and a third object in which at least a part of the second object has been changed. method.

14. In paragraph 13, Further comprising an action of obtaining the second content by inputting an input prompt generated based on the first object, the second object, and the personalized information into an artificial intelligence model. method.

15. In paragraph 13, The second content includes the updated first object, method.

Images