Electronic device using personal ai model and operating method thereof

Abstract

According to an embodiment, an electronic device (201) may include a memory (230), a communication circuit (250), and a processor (220). According to an embodiment, a processor may be configured to confirm a usage pattern of specified media among all media stored in a memory, and determine a score for each specified media based on the usage pattern. According to an embodiment, a processor may be configured to confirm features corresponding to features of each specified media by using a primary AI model stored in a memory. According to an embodiment, a processor may be configured to obtain a personalized first AI model trained based on scores and features. According to an embodiment, a processor may be configured to determine a first preference for each of a plurality of first media based on a first AI model. According to an embodiment, a processor may be configured to perform a function related to a plurality of first media based on a first preference. Other various embodiments are feasible.

Description

Technical Field

[0001] The present disclosure relates to an electronic device using a personal AI model and an operating method thereof. Background Art

[0002] For many people in modern times, portable digital communication devices have become necessary items. Consumers want to obtain various high-quality services that consumers want anytime and anywhere by using portable digital communication devices.

[0003] Recognition services using artificial intelligence (AI) technology can be services that use AI models trained using deep learning to identify various types of media based on an interface implemented by a portable digital communication device, and then use the results of this identification to provide consumers with various content services. Providing high-quality AI recognition services to consumers requires technology that accurately identifies user preferences or interests and provides appropriate content services that match the identified user's intentions. Summary of the Invention

[0004] Problem Solution According to an embodiment, an electronic device 201 may include a memory 230, a communication circuit 250, and a processor 220. The processor according to the embodiment may be configured to confirm a usage pattern of a specified media item among all media items stored in the memory, and determine a score for each specified media item based on the usage pattern. The processor according to the embodiment may be configured to confirm features corresponding to characteristics of each specified media item by using a main AI model stored in the memory. The processor according to the embodiment may be configured to obtain a personalized first AI model trained based on scores and features. The processor according to the embodiment may be configured to determine a first preference for each of a plurality of first media items based on the first AI model. The processor according to the embodiment may be configured to execute functions related to the plurality of first media items based on the first preference.

[0005] An operating method of an electronic device 201 according to an embodiment may include confirming a usage pattern of a specified media item among all media items stored in the electronic device, and determining a score for each specified media item based on the usage pattern. The operating method of an electronic device according to an embodiment may include extracting features corresponding to the characteristics of each specified media item by using a main AI model stored in the electronic device. The operating method of an electronic device according to an embodiment may include acquiring a personalized first AI model trained based on scores and features. The operating method of an electronic device according to an embodiment may include determining a first preference for each of a plurality of first media items based on the first AI model. The operating method of an electronic device according to an embodiment may include executing functions related to a plurality of first media items based on the first preference.

[0006] A non-transitory recording medium 130 according to an embodiment may store instructions capable of performing the following operations: confirming a usage pattern of a specified media item among all media items stored in the electronic device 201, and determining a score for each specified media item based on the usage pattern; extracting features corresponding to characteristics of each specified media item by using a main AI model stored in the electronic device; obtaining a personalized first AI model trained based on the scores and features; determining a first preference for each of a plurality of first media items based on the first AI model; and performing functions related to the plurality of first media items based on the first preferences. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 is a block diagram illustrating electronic devices in a network environment according to various embodiments.

[0008] Figure 2a is a block diagram illustrating a system including an electronic device, a plurality of external electronic devices, and a server according to an embodiment.

[0009] Figure 2b is a flowchart illustrating an operating method of an electronic device according to an embodiment.

[0010] Figure 3 is a block diagram illustrating an AI service manager executed in an electronic device according to an embodiment.

[0011] Figure 4a is a flowchart illustrating a method for training a personal AI model by an electronic device according to an embodiment.

[0012] Figure 4b is a flowchart illustrating a method in which an electronic device trains a personal AI model by using information about media received from the outside according to an embodiment.

[0013] Figure 5A method for training a personal AI model by an electronic device according to an embodiment is illustrated.

[0014] Figure 6 A method in which an electronic device obtains features and scores of media for training a personal AI model according to an embodiment is illustrated.

[0015] Figure 7 is a flowchart illustrating a method of training a personal AI model by an electronic device when a state of the electronic device satisfies a specified condition according to an embodiment.

[0016] Figure 8a is a flowchart illustrating a method in which an electronic device performs a function related to a media item by using a personal AI model according to an embodiment.

[0017] Figure 8b is a flowchart illustrating a method of classifying, by an electronic device, media items by using a personal AI model according to an embodiment.

[0018] Figure 9a An operation of confirming a preference for a media item by using a personal AI model by an electronic device according to an embodiment is illustrated.

[0019] Figure 9b An operation of confirming a preference for a media item by using an AI model of another person by an electronic device according to an embodiment is illustrated.

[0020] Figure 9c An operation of confirming a preference of a media item by using an AI model for each group by an electronic device according to an embodiment is illustrated.

[0021] Figure 10 An AI service manager for managing multiple AI models according to an embodiment is shown.

[0022] Figure 11a is a flowchart illustrating a method of performing functions related to a media item by using another person's AI model according to an embodiment.

[0023] Figure 11b is a flowchart illustrating a method of performing a function related to a media item by using a specific group of AI models according to an embodiment.

[0024] Figure 12a is a flowchart illustrating a method of performing a function related to a media item by using an AI model of a specific person according to an embodiment.

[0025] Figure 12b is a flowchart illustrating a method of providing guidance to media by using an AI model of a specific person according to an embodiment.

[0026] Figure 13a A method of confirming an image preferred by a user among a plurality of images by using a personal AI model according to an embodiment is illustrated.

[0027] Figure 13b A method of confirming an image preferred by another person among a plurality of images by using an AI model of another person according to an embodiment is shown.

[0028] Figure 13c A method of classifying images according to attributes of a plurality of images by using a personal AI model according to an embodiment is illustrated.

[0029] Figure 14 A method of sharing an image for each corresponding group using a group-specific AI model according to an embodiment is illustrated.

[0030] Figure 15a A method of confirming an image preferred by an expert among a plurality of images by using an expert AI model according to an embodiment is illustrated.

[0031] Figure 15b A method of providing guidance on an image by using an expert AI model according to an embodiment is illustrated. DETAILED DESCRIPTION

[0032] Figure 1 1 is a block diagram illustrating an electronic device 101 in a network environment 100 according to various embodiments. Figure 1 In the network environment 100, the electronic device 101 can communicate with the electronic device 102 via a first network 198 (e.g., a short-range wireless communication network), or can communicate with at least one of the electronic device 104 and the server 108 via a second network 199 (e.g., a long-range wireless communication network). Depending on the embodiment, the electronic device 101 can communicate with the electronic device 104 via the server 108. Depending on the 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 (SIM) 196, or an antenna module 197. In some embodiments, at least one of the aforementioned components (e.g., the connection terminal 178) may be omitted from the electronic device 101, or one or more other components may be added to the electronic device 101. In some embodiments, some of the above-described components (eg, sensor module 176 , camera module 180 , or antenna module 197 ) may be implemented as a single component (eg, display module 160 ).

[0033] The processor 120 may execute, for example, software (e.g., program 140) to control at least one other component of the electronic device 101 coupled to the processor 120 (e.g., a hardware component or a software component), and may perform various data processing or calculations. According to one embodiment, as at least part of the data processing or calculations, the processor 120 may store commands or data received from another component (e.g., sensor module 176 or communication module 190) in the volatile memory 132, process the commands or data stored in the volatile memory 132, and store the resulting data in the non-volatile memory 134. Depending on the embodiment, the processor 120 may include a main processor 121 (e.g., a central processing unit (CPU) or an application processor (AP)) or an auxiliary processor 123 (e.g., a graphics processing unit (GPU), a neural processing unit (NPU), an image signal processor (ISP), a sensor hub processor, or a communication processor (CP)) that is independent of or integrated with the main processor 121. For example, when the electronic device 101 includes a main processor 121 and an auxiliary processor 123, the auxiliary processor 123 may be adapted to consume less power than the main processor 121 or be adapted to be dedicated to a specific function. The auxiliary processor 123 may be implemented separately from the main processor 121 or as part of the main processor 121.

[0034] When the main processor 121 is inactive (e.g., sleeping), the auxiliary processor 123 (rather than the main processor 121) may control at least some of the functions or states associated with at least one of the components of the electronic device 101 (e.g., the display module 160, the sensor module 176, or the communication module 190). Alternatively, when the main processor 121 is active (e.g., running an application), the auxiliary processor 123 may work with the main processor 121 to control at least some of the functions or states associated with at least one of the components of the electronic device 101 (e.g., the display module 160, the sensor module 176, or the communication module 190). Depending on the embodiment, the auxiliary processor 123 (e.g., an image signal processor or a communication processor) may be implemented as part of another component functionally related to the auxiliary processor 123 (e.g., the camera module 180 or the communication module 190). Depending on the embodiment, the auxiliary processor 123 (e.g., a neural processing unit) may include hardware structures dedicated to artificial intelligence model processing. The artificial intelligence model may be generated through machine learning. For example, such learning can be performed by the electronic device 101 where the artificial intelligence is executed or via a separate server (e.g., server 108). The learning algorithm may include, but is not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning. The artificial intelligence model may include multiple artificial neural network layers. The artificial neural network may be a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), or a deep Q network, or a combination of two or more thereof, but is not limited thereto. Additionally or alternatively, the artificial intelligence model may include a software structure in addition to a hardware structure.

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

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

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

[0038] The sound output module 155 can output sound signals to the outside of the electronic device 101. The sound output module 155 can include, for example, a speaker or a receiver. The speaker can be used for general purposes such as playing multimedia or playing records. The receiver can be used to receive incoming calls. Depending on the embodiment, the receiver can be implemented separately from the speaker or as part of the speaker.

[0039] The display module 160 can visually provide information to the outside of the electronic device 101 (e.g., a user). The display module 160 may include, for example, a display, a holographic device, or a projector, and a control circuit for controlling a corresponding one of the display, the holographic device, and the projector. Depending on the embodiment, the display module 160 may include a touch sensor adapted to detect a touch or a pressure sensor adapted to measure the strength of the force caused by the touch.

[0040] The audio module 170 can convert sound into an electrical signal, and vice versa. According to an embodiment, the audio module 170 can obtain sound via the input module 150, or output sound via the sound output module 155 or an earphone of an external electronic device (e.g., electronic device 102) directly (e.g., wired) coupled to the electronic device 101 or wirelessly coupled.

[0041] The sensor module 176 can detect the operating state of the electronic device 101 (e.g., power or temperature) or the environmental state outside the electronic device 101 (e.g., the state of the user), and then generate an electrical signal or data value corresponding to the detected state. Depending on the embodiment, the sensor module 176 may include, for example, a gesture sensor, a gyro sensor, an atmospheric pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor, an infrared (IR) sensor, a biometric sensor, a temperature sensor, a humidity sensor, or an illumination sensor.

[0042] The interface 177 may support one or more specific protocols for directly (e.g., wired) or wirelessly coupling the electronic device 101 to an external electronic device (e.g., the electronic device 102). Depending on the embodiment, the interface 177 may include, for example, a High-Definition Multimedia Interface (HDMI), a Universal Serial Bus (USB) interface, a Secure Digital (SD) card interface, or an audio interface.

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

[0044] The haptic module 179 may convert the electric signal into mechanical stimulation (eg, vibration or movement) or electric stimulation that can be recognized by the user via his sense of touch or kinesthetic sense. According to an embodiment, the haptic module 179 may include, for example, a motor, a piezoelectric element, or an electric stimulator.

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

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

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

[0048] The communication module 190 can support establishing 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 perform communication via the established communication channel. The communication module 190 may include one or more communication processors capable of operating independently from the processor 120 (e.g., application processor (AP)) and support direct (e.g., wired) communication or wireless communication. According to an 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 (PLC) module). A corresponding one of these communication modules can communicate via a first network 198 (e.g., a short-range communication network such as Bluetooth TM , Wireless Fidelity (Wi-Fi) Direct, or Infrared Data Association (IrDA)) or a second network 199 (for example, a long-distance communication network such as a traditional cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (for example, a LAN or a wide area network (WAN)))). These various types of communication modules may be implemented as a single component (for example, a single chip), or may be implemented as multiple components (for example, multiple chips) separated from each other. The wireless communication module 192 may identify and authenticate the electronic device 101 in a communication network (such as the first network 198 or the second network 199) using user information (for example, an International Mobile Subscriber Identity (IMSI)) stored in the user identification module 196.

[0049] The wireless communication module 192 can support 5G networks, which are subsequent to 4G networks, as well as next-generation communication technologies (e.g., New Radio (NR) access technologies). NR access technologies can support enhanced mobile broadband (eMBB), massive machine-type communications (mMTC), or ultra-reliable low-latency communications (URLLC). The wireless communication module 192 can support high-frequency bands (e.g., millimeter-wave bands) to achieve, for example, high data transmission rates. The wireless communication module 192 can support various technologies for ensuring performance in high-frequency bands, such as beamforming, massive multiple-input multiple-output (massive MIMO), full-dimensional MIMO (FD-MIMO), array antennas, analog beamforming, or massive antennas. The wireless communication module 192 can support various requirements specified in the electronic device 101, an external electronic device (e.g., electronic device 104), or a network system (e.g., the second network 199). According to an embodiment, the wireless communication module 192 may support a peak data rate for implementing eMBB (e.g., 20 Gbps or greater), loss coverage for implementing mMTC (e.g., 164 dB or less), or U-plane latency for implementing URLLC (e.g., 0.5 ms or less for each of the downlink (DL) and uplink (UL), or 1 ms or less round trip).

[0050] Antenna module 197 can transmit or receive signals or power to or from an external device (e.g., an external electronic device) outside electronic device 101. Depending on the embodiment, antenna module 197 may include an antenna comprising a radiating element formed of a conductive material or conductive pattern formed in or on a substrate (e.g., a printed circuit board (PCB)). Depending on the embodiment, antenna module 197 may include multiple antennas (e.g., an array antenna). In this case, at least one antenna suitable for the communication scheme used in a communication network (e.g., first network 198 or second network 199) may be selected from the multiple antennas by, for example, communication module 190 (e.g., wireless communication module 192). Signals or power can then be transmitted or received between communication module 190 and the external electronic device via the selected at least one antenna. Depending on the embodiment, another component other than the radiating element (e.g., a radio frequency integrated circuit (RFIC)) may also be formed as part of antenna module 197.

[0051] According to various embodiments, antenna module 197 may form a millimeter wave antenna module. According to embodiments, the millimeter wave antenna module may include a printed circuit board, an RFIC, and multiple antennas (e.g., array antennas), wherein the RFIC is disposed on or adjacent to a first surface (e.g., bottom surface) of the printed circuit board and is capable of supporting a specified high frequency band (e.g., millimeter wave band), and the multiple antennas are disposed on or adjacent to a second surface (e.g., top surface or side surface) of the printed circuit board and are capable of transmitting or receiving signals in the specified high frequency band.

[0052] At least some of the above components may be coupled to each other via an inter-peripheral communication scheme (e.g., a bus, general purpose input output (GPIO), a serial peripheral interface (SPI), or a mobile industry processor interface (MIPI)) and communicatively transfer signals (e.g., commands or data) therebetween.

[0053] According to an embodiment, commands or data may be transmitted or received between the electronic device 101 and the external electronic device 104 via the server 108 coupled to the second network 199. Each of the electronic device 102 or the electronic device 104 may be a device of the same type as the electronic device 101, or a device of a different type than the electronic device 101. According to an embodiment, all or some operations to be executed on the electronic device 101 may be executed on one or more of the external electronic device 102, the external electronic device 104, or the server 108. For example, if the electronic device 101 should automatically execute a function or service or should execute a function or service in response to a request from a user or another device, the electronic device 101 may request the one or more external electronic devices to execute at least part of the function or service instead of executing the function or service, or the electronic device 101 may request the one or more external electronic devices to execute at least part of the function or service in addition to executing the function or service. The one or more external electronic devices that receive the request may execute at least a portion of the requested function or service, or execute another function or service related to the request, and transmit the results of the execution to the electronic device 101. The electronic device 101 may provide the results as at least a partial response to the request, either with or without further processing. To this end, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technologies may be used. The electronic device 101 may use distributed computing or mobile edge computing to provide ultra-low latency services. In another embodiment, the external electronic device 104 may include an Internet of Things (IoT) device. The server 108 may be an intelligent server that utilizes machine learning and / or neural networks. Depending on the embodiment, the external electronic device 104 or the server 108 may be included in the second network 199. The electronic device 101 may be used for intelligent services based on 5G communication technology or IoT-related technologies (e.g., smart homes, smart cities, smart cars, or healthcare).

[0054] Figure 2a is a block diagram illustrating a system including an electronic device, a plurality of external electronic devices, and a server according to an embodiment.

[0055] Reference Figure 2a , the system 200 according to the embodiment may include an electronic device 201, a plurality of external electronic devices 202 and 203, and a server 208. For example, the electronic device 201 may be implemented as Figure 1 The plurality of external electronic devices 202 and 203 may be implemented as Figure 1The electronic devices 102 and 104 are the same or similar. In addition, the server 208 can be implemented as Figure 1 The server 108 is the same or similar.

[0056] The electronic device 201 according to an embodiment may transmit data to or receive data from a plurality of external electronic devices 202 and 203 and a server 208. For example, the electronic device 201 may receive data of media and / or AI models from the plurality of external electronic devices 202 and 203. In addition, the electronic device 201 may receive data of media and / or AI models from the server 208.

[0057] According to an embodiment, the electronic device 201 may include a processor 220 , a memory 230 , a battery 240 , a communication module 250 , and a display 260 .

[0058] According to an embodiment, the processor 220 may control the overall operation of the electronic device 201. The processor 220 may be implemented as Figure 1 The processor 220 may be the same or similar to the processor 120 of FIG. Figure 1 a main processor 121 or an application processor) or an auxiliary processor (e.g., Figure 1 Auxiliary processor 123 or neural processing unit (NPU)).

[0059] According to an embodiment, the processor 220 may run an AI service manager (or an AI service manager module) for managing services or functions using artificial intelligence (AI) or an AI model. For example, the AI ​​service manager may be run in the foreground or the background.

[0060] According to an embodiment, the memory 230 (eg, Figure 1 The memory 230 can store media-related data. For example, media can refer to data related to images, videos, and audio that can be executed in the electronic device 201. Furthermore, the memory 230 can store media-related applications (e.g., photo viewing applications, video playback applications, audio playback applications, file explorer applications, background settings applications, and file sharing applications).

[0061] According to an embodiment, the processor 220 may identify usage patterns of multiple media items among the media items stored in the memory 230 (e.g., all media items stored in the memory 230). For example, the processor 220 may confirm or monitor a user's interaction with a media-related application to view, share, edit, set favorites, set background settings, and / or delete the media. The processor 220 may determine or confirm a score for the corresponding media based on the usage pattern of the media. For example, the score may refer to a score or value based on the usage pattern of the media. For example, the processor 220 may convert the usage pattern of the media into a score by using a specified formula. For example, the processor 220 may determine that the higher the score of the media, the more frequently the user uses the corresponding media or the more interested they are in it.

[0062] According to an embodiment, the memory 230 may store a master AI model. For example, the master AI model may be an AI model pre-stored in the electronic device 201. For example, the master AI model may be an AI model that serves as a reference for an AI model (hereinafter referred to as a personal AI model) personalized for the user of the electronic device 201 based on the user's usage pattern. For example, the processor 220 may refer to the master AI model to train media that the user is determined to use more frequently or is of greater interest to obtain (or generate or update) a personal AI model. For example, the processor 220 may store the trained personal AI model in the memory 230. For example, the master AI model and the personal AI model may be implemented as deep learning-type (e.g., convolutional neural network (CNN)-type) AI models. For example, the processor 220 may perform on-device AI model training and utilization.

[0063] According to an embodiment, the processor 220 may extract or confirm features of each of the plurality of media items by using the main AI model stored in the memory 230. For example, when media is input, the main AI model may output features corresponding to the media. Features may be data representing characteristics of the media recognized by the main AI model. For example, features may be represented as a series of floating point numbers (e.g., 4-byte floating point numbers). ), and may have values ​​that vary depending on the attributes used to classify the media (e.g., color, hue, color temperature, or composition). However, a feature may have a value that does not allow the characteristics of the media to be traced back even if the feature is analyzed.

[0064] According to an embodiment, the processor 220 may train an AI model based on the score and features of each of the plurality of media items. As a result of the training, the processor 220 may obtain (or generate or update) a personal AI model personalized for the user of the electronic device 201. For example, the processor 220 may train an AI model when the electronic device 201 is idle or the battery 240 (e.g., Figure 1 Train personal AI models while the battery 189) is charging.

[0065] According to an embodiment, the processor 220 may confirm or determine the first preference of each first media stored in the memory 230 by using a personal AI model. For example, the first preference may refer to a preference score or preference value of each first media determined by a personal AI model personalized for the user of the electronic device 201. For example, the first media may be all media items stored in the memory 230, or media items for which the user has requested confirmation among all media items. Alternatively, the first media may be media that meets preconfigured criteria (for example, media generated at a specific point in time, media generated within a specific time interval, media generated at a specific location, or media obtained from a specific person or specific device) among all media items stored in the memory 230. The processor 220 may store the first preference of each first media in the memory 230.

[0066] According to an embodiment, the processor 220 may perform a function related to the first media based on the first preference. For example, the processor 220 may recommend at least one media item among the first media items based on the first preference. For example, the processor 220 may recommend media with higher preference to the user. For example, the processor 220 may also categorize the first media based on the first preference. For example, the processor 220 may categorize the first media in order of the first preference.

[0067] Depending on the embodiment, the processor 220 may further classify the first media according to a specific person, a specific role, a specific location, or a specific time interval using a personal AI model. For example, the processor 220 may separately classify media that includes a specific person (or a specific role), may separately classify media obtained at a specific location, or may separately classify media obtained during a specific time interval.

[0068] Depending on the embodiment, the processor 220 may use a personal AI model to identify the attributes of each first medium (e.g., color, hue, color temperature, or composition). For example, the processor 220 may classify the first media based on the identified attributes. For example, the processor 220 may classify the first media into at least one media item based on composition, and further classify the first media into at least one media item based on hue or color temperature.

[0069] According to an embodiment, the processor 220 may receive information regarding a personalized AI model of a user of the corresponding external electronic device (hereinafter referred to as an "other person's AI model") from at least one of the plurality of external electronic devices 202 and 203 via the communication module 250. The processor 220 may store the "other person's AI model" in the memory 230. The processor 220 may use the "other person's AI model" to confirm preferences for media stored in the memory 230. The processor 220 may execute functions related to the corresponding media based on the confirmed preferences. For example, the processor 220 may transmit media stored in the memory 230 that are preferred by the other person to the external electronic device.

[0070] According to an embodiment, the electronic device 201 may receive information about a specific personal AI model of a specific person (e.g., an expert or a celebrity) from the server 208 through the communication module 250. The processor 220 may store the specific AI model in the memory 230. The processor 220 may confirm a preference for the media stored in the memory 230 by using the specific AI model. The processor 220 may perform a function related to the corresponding media based on the confirmed preference. For example, the processor 220 may confirm a media preferred by a specific person among the media stored in the memory 230. Alternatively, the processor 220 may compare the preferences of the specific person with the preferences of the user to display the preference of the specific person through the display 260 (e.g., Figure 1 The display module 160 provides guidance on the media.

[0071] As described above, the electronic device 201 can use the personalized personal AI model to recommend media that matches preferences or interests or classify media that matches the user's preferences among all media items stored in the memory 230. In addition, the electronic device 201 can easily confirm media that matches the preferences of others or the preferences of experts among all media items stored in the memory 230.

[0072] Figure 2b is a flowchart illustrating an operating method of an electronic device according to an embodiment.

[0073] Reference Figure 2b , by electronic devices (e.g. Figure 2a At least a portion of the operations performed by the electronic device 201) may be performed by a processor (eg, Figure 2a However, for the convenience of description, the electronic device 201 will be described as performing the corresponding operation.

[0074] According to an embodiment, in operation 211, the electronic device 201 may confirm that the memory (eg, Figure 2aThe usage pattern of the designated media item among all media items stored in the memory 230 of the memory 230 is determined, and the score of each designated media item is determined based on the determined usage pattern. For example, the designated media item may be selected by the user, or may be selected by the processor (e.g., Figure 2a The processor 220 of the electronic device 201 may automatically select the specified media item. For example, the specified media item may be at least a portion of all media items. For example, the electronic device 201 may confirm the usage mode by considering at least one of viewing, sharing, editing, deleting, favorite settings, or background settings for the specified media item.

[0075] According to an embodiment, in operation 213 , the electronic device 201 may extract features corresponding to characteristics of each designated media item by using the main AI model stored in the memory 230 .

[0076] According to an embodiment, the electronic device 201 may obtain a personalized first AI model trained based on the score and the feature in operation 215. For example, the first AI model may be an AI model personalized by the user of the electronic device 201.

[0077] According to an embodiment, in operation 217, the electronic device 201 may determine a first preference for each of the plurality of first media items based on the first AI model. For example, the plurality of first media items may be designated media items directly selected by the user, or may be selected by the processor (e.g., Figure 2a Processor 220 (e.g., processor 220) automatically selects a designated media item to determine preference. For example, the plurality of first media items may be at least a portion of all media items stored in memory 230. Furthermore, the plurality of first media items may include newly acquired media items (e.g., newly acquired externally or newly captured or photographed by a camera). Depending on the implementation, operations 215 and 217 may be separated in time. For example, operation 217 may not be performed immediately after the first AI model is acquired through operation 215.

[0078] According to an embodiment, in operation 219, the electronic device 201 may perform a function related to the plurality of first media items based on the first preference. For example, the electronic device 201 may recommend at least some of the plurality of first media items. Alternatively, the electronic device 201 may classify the plurality of first media items by category based on the first preference.

[0079] Figure 3 is a block diagram illustrating an AI service manager executed in an electronic device according to an embodiment.

[0080] Reference Figure 3 According to an embodiment, the processor 220 (eg, Figure 2aThe processor 220 of the electronic device 201 may run the AI ​​service manager 301. For example, the AI ​​service manager 301 may be a module that uses an AI model to manage services (or functions). Figure 2a The AI ​​service manager 301 runs in the foreground or background of the electronic device 201).

[0081] According to an embodiment, the AI ​​service manager 301 may include an event processor 310 , a recorder 320 , and an AI framework 340 .

[0082] According to an embodiment, the event processor 310 may confirm or monitor an event generated in the electronic device 201. The AI ​​service manager 301 may confirm the event generated in the electronic device 201 through the event processor 310, and may perform a specified operation based on the confirmed event. For example, when the electronic device 201 is confirmed to be in an idle state, the AI ​​service manager 301 may perform an operation of training a personal AI model. When it is confirmed that the electronic device 201 enters a specific location or generates a specific group, the AI ​​service manager 301 may perform an operation of obtaining an AI model for the group. In addition, when the electronic device 201 performs a specific service or a specific function, the AI ​​service manager 301 may perform an operation of obtaining an expert AI model. The detailed method for the electronic device 201 (or the AI ​​service manager 301) to perform the corresponding operation will be described below.

[0083] According to an embodiment, the event handler 310 may include a device event handler 311 and an action event handler 312. For example, the device event handler 311 may obtain the status of the electronic device 201 and new media items, and / or may confirm or monitor events related to media functions. The action event handler 312 may confirm or monitor events such as the electronic device 201 entering a specific location or forming a group with at least one external electronic device.

[0084] According to an embodiment, a logger 320 may identify usage patterns of a specific media item 305. For example, the usage patterns of a specific media item may be based on interactions with the specific media item 305 (e.g., viewing, sharing, background settings, favorite settings, indexing, editing, and deletion). For example, the logger 320 may identify the time and / or number of times the specific media item 305 has been viewed. The logger 320 may also identify the number of times the specific media item 305 has been transferred, the location where it has been uploaded, and / or the location where it has been copied. The logger 320 may also identify whether a tag has been assigned to the specific media item 305, whether background settings have been made, or whether it has been made a favorite. The logger 320 may also identify the number of times and / or the level of edits made to the specific media item 305. The logger 320 may also identify whether the specific media item 305 has been deleted and / or hidden.

[0085] According to an embodiment, recorder 320 may determine a score based on the usage pattern of specific media item 305. For example, the score may indicate the user's level of interest (or interest value) in specific media item 305. Recorder 320 may provide the score of specific media item 305 to AI framework 340.

[0086] According to an embodiment, the AI ​​framework 340 may execute and manage a main AI model 350 and a personal AI model 360 .

[0087] According to an embodiment, the main AI model 350 may extract features of the specific media item 305. Depending on the implementation, the main AI model 350 may extract (or determine) an aesthetic score for the specific media item 305. For example, the aesthetic score may be a score or value indicating a characteristic of the specific media item 305 (e.g., perspective, composition, color, or color temperature).

[0088] According to an embodiment, the AI ​​framework 340 may train a personal AI model using the score and features of a specific media item 305. For example, the AI ​​framework 340 may train the personal AI model with reference to a master AI model, such that when the features of the specific media item 305 are input, the score of the specific media item 305 is output. Depending on the implementation, the AI ​​framework 340 may further train the personal AI model using the aesthetic score. For example, the AI ​​framework 340 may train the personal AI model 360 with reference to the master AI model 350, such that when the features and aesthetic score of the specific media item 305 are input, the score of the specific media item 305 is output.

[0089] According to an embodiment, as a result of training, the AI ​​framework 340 may obtain and store a personal AI model 360. The AI ​​framework 340 may store information about the personal AI model 360 in a personal database (DB) 330. For example, the personal DB may store data used to train the personal AI model (e.g., usage patterns, scores, features, and aesthetic scores of a specific media item 350). For example, the personal database 330 may be implemented as a memory (e.g., Figure 2a memory 230).

[0090] According to the above method, the AI ​​framework 340 can obtain a score, feature, and / or aesthetic score for each of the plurality of media items stored in the memory 230. The AI ​​framework 340 can train a personal AI model based on the obtained score, feature, and / or aesthetic score.

[0091] According to an embodiment, the AI ​​framework 340 may extract or confirm the preference score of the media by using the personal AI model 360. For example, the preference score may be a value indicating the degree of preference of the user determined by the personal AI model 360. The AI ​​framework 340 may extract or confirm the preference score of each of all media items stored in the memory 230 by using the personal AI model 360. Alternatively, the personal AI model 360 may extract or confirm the preference score of the media for which the user requested confirmation by using the personal AI model 360.

[0092] Even if all users have different preferences, conventional electronic devices may recommend the same media. For example, when a user inputs the title of a specific movie, the device may recommend movies with similar titles or ratings, regardless of whether the user likes or dislikes the movie. To improve this, AI models can be used.

[0093] Electronic devices using traditional AI models can query individuals for their preferences for specific media items or provide a score indicating their preferences. However, in this case, the electronic device requires additional UI / UX to receive information from the user. Furthermore, the electronic device requires more logic to select the appropriate media to query the user for their preferences. Alternatively, the electronic device can obtain personal information from the user, such as a user profile. In this case, the security of the user's personal information may be compromised.

[0094] According to an embodiment, the electronic device 201 can use the media stored in the electronic device 201 to train an AI model that reflects the user's preferences, and can provide various media-related functions (e.g., media curation services, media sharing services, media recommendation services, and media classification services) through the trained AI model.

[0095] In addition, the electronic device 201 according to an embodiment can use user-preferred media or media in which the user has high interest as data for AI model training to recommend content among various media stored in the electronic device 201. For this purpose, the electronic device 201 can effectively select media for AI model training.

[0096] In addition, the electronic device 201 according to the embodiment can share the personalized AI model with other electronic devices. In this case, even when personal information such as user profiles is not shared, the electronic device 201 can share the user's preferences by sharing the personalized AI model.

[0097] At least a portion of the operations of the electronic device 201 described below may be performed by the processor 220. However, for convenience of description, the operations performed by the electronic device 201 will be described.

[0098] Figure 4a is a flowchart illustrating a method for training a personal AI model by an electronic device according to an embodiment.

[0099] Reference Figure 4a According to an embodiment, in operation 401, an electronic device (eg, Figure 2a The electronic device 201 may confirm the request to generate a personal AI model. For example, the electronic device 201 may confirm the request to generate a personal AI model based on a specified event (e.g., a media preference confirmation request or a media classification request event) or user input (e.g., an input requesting the generation of a personal AI model).

[0100] According to an embodiment, in operation 403, the electronic device 201 may store the data in a memory (eg, Figure 2a A media collection for training a personal AI model is determined from a plurality of media items (e.g., all media items) stored in the memory 230 . For example, the media collection may include specified media items from among all media items. For example, the specified media items may include a specified number of media items. For example, the specified media items may be determined to be media items with a high usage frequency from among all media items.

[0101] According to an embodiment, in operation 405, the electronic device 201 may record the Figure 3 The recorder 320 ) obtains (or confirms) a score of the usage pattern of each media included in the media set.

[0102] According to an embodiment, in operation 407, the electronic device 201 can use the main AI model (eg, Figure 3 The main AI model 350 of the electronic device 201 obtains the characteristics of each media included in the media collection. According to the implementation, the electronic device 201 can further obtain the aesthetic score of each media included in the media collection.

[0103] According to an embodiment, the electronic device 201 may train a personal AI model based on the score and the feature in operation 409. According to an implementation, the electronic device 201 may train the personal AI model by using the aesthetic score.

[0104] According to an embodiment, in operation 411 , the electronic device 201 may obtain a personal AI model as a result of training and store the obtained personal AI model.

[0105] Figure 4b is a flowchart illustrating a method in which an electronic device trains a personal AI model by using information about media received from the outside according to an embodiment.

[0106] Reference Figure 4bAccording to an embodiment, in operation 431, an electronic device (eg, Figure 2a The electronic device 201 can be connected to an external electronic device (eg, Figure 2a The external electronic device 202 or 203) can obtain information about at least one media item. In addition, the electronic device 201 can obtain information about at least one media item from a server (e.g., Figure 2a The server 208 of the embodiment of the present invention obtains information about at least one media item. For example, the information about at least one media item may include information about at least one media item or a feature of the at least one media item.

[0107] In an embodiment, in operation 433, electronic device 201 may train a personal AI model based on the acquired information. For example, when the personal AI model is trained using features of a specific character (or a specific object), the personal AI model can more accurately identify media that includes the specific character. Depending on the implementation, even if the electronic device does not directly obtain the media from external electronic device 202 or 203 or server 208, electronic device 201 may train the personal AI model using features of the acquired media.

[0108] Therefore, the electronic device 201 can enhance the performance of the personal AI model (eg, recognition of a specific role or a specific object).

[0109] According to an embodiment, the electronic device 201 may obtain another person's AI model trained for a specific character or a specific object from the external electronic device 202 or 203 or the server 208. The electronic device 201 may more accurately recognize media including a specific character by using the other person's AI model.

[0110] Figure 5 A method for training a personal AI model by an electronic device according to an embodiment is illustrated.

[0111] Reference Figure 5 Part (a), according to an embodiment, when a specific media item 305 is input, the main AI model (e.g., Figure 3 The main AI model 350 of the electronic device 201 may extract or output features 306 corresponding to the specific media item 305. Depending on the implementation, when the specific media item 305 is input, the electronic device 201 may extract or output features 306 corresponding to the specific media item 305 and an aesthetic score 307.

[0112] Reference Figure 5 Part (b), according to an embodiment, when a specific media item 305 is input, the recorder (e.g., Figure 3 The recorder 320 ) may extract or output a score 308 based on usage patterns of a particular media item 305 .

[0113] Reference Figure 5 Part (c), according to an embodiment, may be performed by training a personal AI model (e.g., Figure 3 Depending on the implementation, the operation of training the personal AI model 360 by using the aesthetic score 307 may be performed.

[0114] Figure 6 A method in which an electronic device obtains features and scores of media for training a personal AI model according to an embodiment is illustrated.

[0115] Reference Figure 6 ,According to an embodiment, an electronic device (e.g. Figure 2a electronic device 201 or Figure 3 The recorder 320 of the image 601 may confirm the usage pattern of the image 601. The electronic device 201 may obtain usage pattern information 610 based on the usage pattern of the image 601. For example, the usage pattern information 610 may include at least a portion of information regarding the number of times the image 601 was viewed, the number of times the image was shared, whether the image was set as a background, whether the image was edited, or whether the image was deleted.

[0116] According to an embodiment, the electronic device 201 may normalize the usage pattern information 610 to obtain normalized usage pattern information 620. For example, the electronic device 201 may normalize the usage pattern information 610 according to a specified rule. For example, the normalized usage pattern information 620 may include a value of the usage pattern of the media 601.

[0117] According to an embodiment, the electronic device 201 may convert the value included in the normalized usage pattern information 620 into a score 630 using a specified formula. For example, the score 630 may be a score or value based on the usage pattern of the image 601. For example, the specified formula may be determined by the sum (e.g., total) of the values ​​of the usage pattern of the media 601.

[0118] According to an embodiment, the electronic device 201 may obtain the features 640 corresponding to the image 601 by using the main AI model 350 .

[0119] According to the above method, the electronic device 201 can obtain the score 630 and features 640 for training the personal AI model.

[0120] Figure 7 is a flowchart illustrating a method of training a personal AI model by an electronic device when a state of the electronic device satisfies a specified condition according to an embodiment.

[0121] Reference Figure 7 According to an embodiment, in operation 701, an electronic device (eg, Figure 2a The electronic device 201) can confirm the status of the electronic device 201.

[0122] According to an embodiment, in operation 703, the electronic device 201 may confirm whether the state of the electronic device 201 is an idle state. For example, the idle state may refer to a state in which the user is not disturbed when using the electronic device 201. For example, the idle state may refer to a state in which the electronic device 201 is not in use or is being charged. The electronic device 201 may confirm whether the electronic device 201 is in an idle state (for example, a state in which no motion is detected) through a sensor included in the electronic device 201. Alternatively, the electronic device 201 may be based on a battery (for example, Figure 2a Whether the electronic device 201 is in an idle state is confirmed by determining whether the battery 240 of the electronic device 201 is charging.

[0123] According to an embodiment, when the state of the electronic device 201 is confirmed to be an idle state (for example, if yes in operation 703), the electronic device 201 may confirm whether a specified condition for updating the personal AI model is satisfied in operation 705. For example, the electronic device 201 may determine that the specified condition is satisfied when a predetermined number of media items are newly acquired, a specified time has passed after a previous update, a specific period based on a user's usage pattern (for example, a new media generation period and / or an idle state entry period) has passed, or when a request is made to execute a media-related function (for example, a request to confirm media preferences or a request to generate a personal AI model for media).

[0124] According to an embodiment, in operation 707, the electronic device 201 may update the personal AI model. For example, the electronic device 201 may adjust the weights applied to the personal AI model to update the personal AI model. For example, the electronic device 201 may obtain a score based on the usage pattern of each newly acquired media item and obtain the features of each newly acquired media item. Hereinafter, the electronic device 201 may additionally train the personal AI model by using the score and features of each newly acquired media item. The electronic device 201 may obtain a new weight value applied to the personal AI model as a result of the additional training.

[0125] According to an embodiment, when both the conditions of operation 703 and operation 705 are not satisfied, the electronic device 201 may not update the personal AI model. However, depending on the implementation, when either the conditions of operation 703 or operation 705 are satisfied, the electronic device 201 may update the personal AI model.

[0126] According to the above method, the electronic device 201 can update the personal AI model so that the user's preferences and interests match.

[0127] Figure 8a is a flowchart illustrating a method in which an electronic device performs a function related to a media item by using a personal AI model according to an embodiment.

[0128] Reference Figure 8a According to an embodiment, in operation 801, the electronic device 201 may detect a request to confirm a preference for a specific media item.

[0129] According to an embodiment, in operation 803, the electronic device 201 may Figure 3 For example, the electronic device 201 may input media into the main AI model 350 to obtain features corresponding to the media.

[0130] According to an embodiment, in operation 805, the electronic device 201 may Figure 3 The electronic device 201 may input features corresponding to the media into the personal AI model 360 to obtain the preferences of the media.

[0131] According to an embodiment, in operation 807, the electronic device 201 may perform a function related to media items based on the preferences obtained using the personal AI model 360. For example, the electronic device 201 may recommend at least one media item to the user based on the preferences (e.g., recommend at least one media item that matches the user's preferences). Alternatively, the electronic device 201 may categorize the media items by category based on the preferences. Alternatively, the electronic device 201 may categorize the media items by category based on the attributes of the media items.

[0132] Figure 8b is a flowchart illustrating a method of classifying, by an electronic device, a media item by using a personal AI model according to an embodiment.

[0133] Reference Figure 8b According to an embodiment, in operation 831, an electronic device (eg, Figure 2a The electronic device 201 may select some media items according to a score based on a usage pattern of each of all media items stored in the memory 230 .

[0134] Depending on the embodiment, in operation 833, the electronic device 201 may confirm the attributes of each selected media item. For example, the attributes may include the composition (e.g., horizontal, vertical, or diagonal), hue (e.g., blue, red, green, or white), and / or color temperature (e.g., hot, warm, mild, or cool) of the media (e.g., an image). The electronic device 201 may determine a score or value for the corresponding attribute for each selected media item.

[0135] According to an embodiment, the electronic device 201 may classify the media items based on the confirmed attributes in operation 835. For example, the electronic device 201 may classify all media items with high scores in terms of composition as media items focused on composition, and may classify all media items with high scores in terms of hue / color temperature as media items focused on hue / color temperature.

[0136] Through the above method, the electronic device 201 can provide curation services for media projects.

[0137] Figure 9a An operation of confirming a preference for a media item by using a personal AI model by an electronic device according to an embodiment is illustrated.

[0138] Reference Figure 9a According to an embodiment, the AI ​​framework 340 can extract or confirm the first preference scores 910 of the plurality of first media items 905 respectively by using the personal AI model 360. The AI ​​framework 340 can generate a personal AI model or use a personal AI model stored in the memory 230 (e.g., Figure 3 For example, the first preference score 910 may be an indication of a preference score assigned to an electronic device (eg, Figure 2a The preference scores of the corresponding media items determined by the personal AI model 360 personalized by the user of the electronic device 201. For example, the plurality of first media items 950 may be at least some of all the media items stored in the memory 230.

[0139] According to an embodiment, the electronic device 201 may select and recommend at least one media item among the plurality of first media items 905 by using the preference score confirmed using the personal AI model. Therefore, the electronic device 201 may automatically recommend a media item that matches the user's preference among the plurality of first media items.

[0140] Figure 9b An operation of confirming a preference for a media item by using an AI model of another person by an electronic device according to an embodiment is illustrated.

[0141] Reference Figure 9b According to an embodiment, the AI ​​framework 340 can use the data from an external electronic device (e.g., Figure 2a 202, 203 or 208) received or downloaded AI models from others, rather than Figure 9a For example, the AI ​​framework 340 may extract or confirm the second preference scores 920 of the plurality of first media items 905 by using the AI ​​model 370 of others. For example, the second preference scores 920 may be indicative of the preference scores of the first media items 905 for the electronic device (e.g., Figure 2a Alternatively, the second preference score 920 may be a score indicating the preference of the corresponding media item determined by the AI ​​model 370 of the other person personalized by the user (e.g., the other person) of the external electronic device 202 or 203. Figure 2a The preference score of the corresponding media item determined by the AI ​​model 307 of others personalized by an expert or a specific person (eg, a celebrity) stored in the server 208 ).

[0142] According to an embodiment, the electronic device 201 can select and recommend at least one of the plurality of first media items 905 by using the preference scores determined by the AI ​​model of others. For example, the electronic device 201 can provide information about media that matches the preferences of others or experts among the plurality of first media items. Therefore, the user can easily confirm the media that matches the preferences of others or experts through the electronic device 201.

[0143] Figure 9c An operation of confirming a preference of a media item by using an AI model for each group by an electronic device according to an embodiment is illustrated.

[0144] Reference Figure 9c According to an embodiment, the AI ​​framework 340 can use group-specific AI models. For example, the AI ​​framework 340 can manage and / or run AI models 381, 382, ​​and 383 for multiple groups.

[0145] According to an embodiment, the AI ​​framework 340 may extract or confirm preferences for media items associated with the corresponding group from among the plurality of first media items 905 by using a group AI model 381, 382, ​​or 383 for each of the plurality of groups. For example, the first AI model 381 may output a first set of preferences 921 for at least one media item A 911 associated with the first group from among the plurality of first media items 905. For example, the first set of preferences 921 may be a score indicating the preference for at least one media item A 911 determined by the first AI model 381. For example, the second AI model 382 may output a second set of preferences 922 for at least one media item B 912 associated with the second group from among the plurality of first media items 905. For example, the second set of preferences 922 may be a score indicating the preference for at least one media item B 912 determined by the second AI model 382. For example, the third AI model 383 may output a third set of preferences 923 for at least one media item C 913 associated with the third group from among the plurality of first media items 905. For example, third set of preferences 923 may be scores indicating preferences for at least one media item C 913 determined by third set of AI models 383 .

[0146] According to an embodiment, the electronic device 201 can share at least one of the plurality of first media items 905 with the corresponding group by using the preference score determined by the group-specific AI model 381, 382, ​​or 383. Therefore, the electronic device 201 can easily share media that matches the preferences of each group with external electronic devices included in the corresponding group. In addition, the user can easily confirm and manage the media that matches the preferences of each group through the electronic device 201.

[0147] Figure 10 An AI service manager for managing multiple AI models according to an embodiment is shown.

[0148] Reference Figure 10 According to an embodiment, the AI ​​service manager 1060 (e.g., Figure 3 The AI ​​service manager 301 of the electronic device 201 can manage multiple AI models 1061, 1062, 1063 and 1064. For example, the first AI model 1061 can be a personal AI model personalized by the user of the electronic device 201. The second AI model 1062 can be a personal AI model personalized by an external electronic device (e.g., Figure 2a The expert AI model 1063 may be an AI model of another person that is personalized by a user (eg, another person) of the external electronic device 202 or 203. Figure 2a The group AI model 1064 may be an expert AI model personalized by an expert obtained from a server 208 (e.g., a server 208). The group AI model 1064 may be a group AI model for a group (e.g., a family group, a friends group, or a specific group) including multiple external electronic devices that are connected to the electronic device 201 via a communication technology. For example, the group AI model 1064 may include a separate group AI model for each group generated by the electronic device 201.

[0149] According to an embodiment, the AI ​​service manager 1060 may manage training DBs 1071, 1072, 1073, and 1074 for training a plurality of AI models 1061, 1062, 1063, and 1064. For example, the training DBs 1071, 1072, 1073, and 1074 may store data (e.g., features, scores, or aesthetic scores of media) for training corresponding AI models.

[0150] Figure 11a is a flowchart illustrating a method of performing functions related to a media item by using an AI model of another person according to an embodiment.

[0151] Reference Figure 11a According to an embodiment, in operation 1101, an electronic device (eg, Figure 2a The electronic device 201 can be connected to an external electronic device (eg, Figure 2aThe external electronic device 202 or 203 of the external electronic device 202 or 203 obtains the AI ​​model of another person. For example, the AI ​​model of another person may be an AI model personalized by the user of the external electronic device 202 or 203 (eg, another person).

[0152] According to an embodiment, in operation 1103, the electronic device 201 may use a main AI model (eg, Figure 3 The main AI model 350 of the embodiment of the present invention can be used to obtain the characteristics of the media item for which the preference is to be confirmed. For example, the main AI model can receive media and output the characteristics of the media.

[0153] According to an embodiment, in operation 1105, the electronic device 201 may use the AI ​​model of another person to confirm preferences for the media item for which preference confirmation is desired. For example, the AI ​​model of another person may receive features of the media item obtained by the main AI model and output preferences for the corresponding media item. For example, the output preferences may be values ​​indicating the other person's interest in or preference for the corresponding media item.

[0154] According to an embodiment, the electronic device 201 may perform a function related to the media item based on the confirmed preference in operation 1107. For example, the electronic device 201 may transmit a specified number of media items with high preference among the media items stored in the memory 230 to the external electronic device 202 or 204. Alternatively, the electronic device 201 may classify the specified number of media items with high preference among the media items stored in the memory 230 into one category.

[0155] According to an embodiment, the electronic device 201 may search for at least one external electronic device that can share its AI model with the electronic device. In this case, when multiple external electronic devices are found, the electronic device 201 may provide a list of external electronic devices. For example, the list of external electronic devices may include representative images of AI models shared between external electronic devices. The electronic device 201 may obtain an AI model of another person personalized by the corresponding external electronic device from the selected external electronic device.

[0156] Figure 11b is a flowchart illustrating a method of performing a function related to a media item by using a specific group of AI models according to an embodiment.

[0157] Reference Figure 11b According to an embodiment, in operation 1131, an electronic device (eg, Figure 2a The electronic device 201) can communicate with an external electronic device (e.g., Figure 2a 202 and 203) form a group.

[0158] According to an embodiment, in operation 1133, the electronic device 201 may share an AI model with an external electronic device included in the group. For example, the electronic device 201 may send a personal AI model to the external electronic device. In addition, the electronic device 201 may also obtain an AI model from the external electronic device. Alternatively, the electronic device 201 may generate a group AI model for the group separately.

[0159] According to an embodiment, the electronic device 201 may confirm preferences for media items related to the group by using a shared AI model in operation 1135. The electronic device 201 may share the confirmed preferences with external electronic devices included in the group.

[0160] According to an embodiment, in operation 1137 , the electronic device 201 may select at least one media item to be shared with the external electronic device from among media items related to the group based on the confirmed preference.

[0161] According to an embodiment, the electronic device 201 may share the selected at least one media item with the external electronic device included in the group in operation 1139. For example, the electronic device 201 may transmit the at least one media item selected from the external electronic device included in the group.

[0162] Figure 12a is a flowchart illustrating a method of performing a function related to a media item by using an AI model of a specific person according to an embodiment.

[0163] Reference Figure 12a According to an embodiment, in operation 1201, an electronic device (eg, Figure 2a The electronic device 201 can obtain the Figure 2a The AI ​​model for a specific person is obtained from server 208. For example, the specific person may include, but is not limited to, an expert or celebrity. In this case, the AI ​​model for the specific person may be an AI model personalized by the expert or celebrity. The AI ​​model for the specific person may be an AI model that has been stored or registered in advance by the specific person in server 208.

[0164] According to an embodiment, the electronic device 201 may obtain features of a media item by using a master AI model in operation 1203. For example, the master AI model may receive input of media and output features of the corresponding media.

[0165] According to an embodiment, in operation 1205, the electronic device 201 may confirm preferences for a media item using a specific person's AI model. For example, the specific person's AI model may receive features of the media item obtained by the main AI model and output preferences for the corresponding media item. For example, the output preferences may be a value indicating the specific person's interest in or preference for the corresponding media item.

[0166] According to an embodiment, the electronic device 201 may perform a function related to the media item based on the confirmed preference in operation 1207. For example, the electronic device 201 may classify a specified number of media items with high preference among the media items stored in the memory 230 into a separate category. Alternatively, the electronic device 201 may recommend at least one media item with high preference among the media items stored in the memory 230 as expert-preferred media or celebrity-preferred media.

[0167] Figure 12b is a flowchart illustrating a method of providing guidance to media by using an AI model of a specific person according to an embodiment.

[0168] Reference Figure 12b According to an embodiment, in operation 1231, an electronic device (eg, Figure 2a The electronic device 201) can confirm the first preference of the specific media item by using the AI ​​model of the specific person. For example, the first preference of the specific media item can be confirmed by the server (e.g., Figure 2a The server 208 of the specific person obtains the AI ​​model of the specific person. For example, the first preference can be a score or value indicating the preference for the specific media item determined by the AI ​​model of the specific person.

[0169] According to an embodiment, the electronic device 201 may confirm a second preference for a specific media item by using a personal AI model in operation 1233. The second preference may be a score or value indicating a preference for a specific media item determined by the personal AI model.

[0170] According to an embodiment, in operation 1235, the electronic device 201 may compare the first preference and the second preference to provide guidance for a specific media item. For example, the electronic device 201 may identify a difference between the first preference and the second preference. The electronic device 201 may confirm the difference between the first preference and the second preference with reference to the first preference, and may provide guidance for the specific media item based on the identified difference. For example, the guidance may include whether the specific media item is preferred (e.g., information indicating whether the media is preferred or non-preferred), the degree of preference (e.g., a preference score for the media), and / or correction information (e.g., whether the media needs to be corrected and information about the correction method for the media). For example, when the AI ​​model of the specific person is an AI model of a photography expert and the media is an image, the electronic device 201 may provide guidance on the perspective, exposure, focus, and / or white balance of the corresponding image. For example, based on the difference between the first preference and the second preference, the electronic device 201 may provide guidance on a correction method for at least one of the perspective, exposure, focus, and white balance of the corresponding media.

[0171] Figure 13aA method of confirming an image preferred by a user among a plurality of images by using a personal AI model according to an embodiment is illustrated.

[0172] Reference Figure 13a ,According to an embodiment, an electronic device (e.g. Figure 2a The electronic device 201) can be configured to generate a signal by using a personal AI model 1350 (e.g., Figure 3 The electronic device 201 may use a personal AI model 360 to respectively confirm preferences of the plurality of images 1310, 1320, and 1330. The electronic device 201 may determine the image A 1310 having the highest preference among the plurality of images 1310, 1320, and 1330 as a recommended image.

[0173] Therefore, the electronic device 201 can efficiently confirm an image matching the user's preference among a plurality of images.

[0174] Figure 13b A method of confirming an image preferred by another person among a plurality of images by using an AI model of another person according to an embodiment is shown.

[0175] Reference Figure 13b ,According to an embodiment, an electronic device (e.g. Figure 2a The electronic device 201 may use the AI ​​model 1355 of another person (e.g., the AI ​​model 370 of another person in FIG. 9 ) to confirm the preferences of the multiple images 1310, 1320, and 1330. The electronic device 201 may determine the image B 1320 having the highest preference among the multiple images 1310, 1320, and 1330 as a recommended image.

[0176] Therefore, the electronic device 201 can effectively confirm an image that matches the preferences of others among multiple images. In addition, even if the personal information of others is not obtained, the electronic device 201 can confirm information about the preferences, interests or tastes of others through the AI ​​model of others.

[0177] Figure 13c A method of classifying images according to attributes of a plurality of images by using a personal AI model according to an embodiment is illustrated.

[0178] Reference Figure 13c ,According to an embodiment, an electronic device (e.g. Figure 2a The electronic device 201) can be implemented by using the personal AI model 1355 (e.g., Figure 3The electronic device 201 may use the personal AI model 360 of the plurality of images 1310, 1320, and 1330 to obtain attributes (e.g., composition, hue, or color temperature) of each of the plurality of images 1310, 1320, and 1330. The electronic device 201 may determine a score for each attribute of each of the plurality of images 1310, 1320, and 1330 by using the personal AI model 1355. The electronic device 201 may classify the plurality of images 1310, 1320, and 1330 according to the attributes. For example, the electronic device 201 may classify images 1310 and 1320, both of which have high scores in terms of composition, as images focused on composition. Furthermore, the electronic device 201 may classify images 1320 and 1330, both of which have high scores indicating hue / color temperature, as images focused on hue / color temperature.

[0179] According to the above method, the electronic device 201 can classify multiple images according to each attribute. In addition, the electronic device 201 can also provide information about the attribute and classify the images accordingly. Therefore, the electronic device 201 can provide a curation service to the user.

[0180] Figure 14 A method of sharing an image for each corresponding group using a group-specific AI model according to an embodiment is illustrated.

[0181] Reference Figure 14 ,According to an embodiment, an electronic device (e.g. Figure 2a The electronic device 201) can be implemented by using the group AI models 1450 and 1460 (e.g., Figure 9c The group of AI models 381, 382 and 383) are used to confirm the preferences of multiple images 1410, 1420, 1430 and 1440 respectively.

[0182] According to an embodiment, the electronic device 201 may confirm preferences of images 1410, 1420, and 1430 related to the first group among the plurality of images 1410, 1420, 1430, and 1440, respectively, by using the first group AI model 1450. For example, the electronic device 201 may share image A 1410 and image C 1430 among the images 1410, 1420, and 1430 with an external electronic device included in the first group based on the confirmed preferences.

[0183] According to an embodiment, the electronic device 201 may confirm preferences of images 1420, 1430, and 1440 related to the second group among the plurality of images 1410, 1420, 1430, and 1440, respectively, by using the second group AI model 1460. For example, the electronic device 201 may share image B 1420 and image D 1440 among the images 1420, 1430, and 1440 with the external electronic device included in the second group based on the confirmed preferences.

[0184] According to the above method, the electronic device 201 can share an image of interest among multiple images with an external electronic device included in the corresponding group according to the group. In addition, even if the personal information of the users included in the group is not obtained, the electronic device 201 can confirm information about the preferences, interests, or tastes of the group through the group AI model.

[0185] Figure 15a A method of confirming an image preferred by an expert among a plurality of images by using an expert AI model according to an embodiment is illustrated.

[0186] Reference Figure 15a ,According to an embodiment, an electronic device (e.g. Figure 2a The electronic device 201 may use an expert AI model 1550 (e.g., the other person's AI model 370 of FIG. 9 ) to confirm preferences for each of the multiple images 1510, 1520, and 1530. The electronic device 201 may determine the image C 1530 having the highest preference among the multiple images 1510, 1520, and 1530 as the expert-recommended image.

[0187] Therefore, the electronic device 201 can effectively confirm an image that matches the expert's preference among multiple images. In addition, the electronic device 201 can confirm information about the expert's preferences, interests, or tastes through the expert AI model without directly meeting the expert or obtaining the expert's personal information.

[0188] Figure 15b A method of providing guidance on an image by using an expert AI model according to an embodiment is illustrated.

[0189] Reference Figure 15b ,According to an embodiment, an electronic device (e.g. Figure 2aThe electronic device 201 may confirm the first preference for the specific image 1540 by using the expert AI model 1550 (e.g., the other person's AI model 370 of FIG. 9 ). The electronic device 201 may confirm the second preference for the specific image 1540 by using the personal AI model 1560. The electronic device 201 may provide guidance information for the specific image 1540 by comparing the first preference and the second preference. For example, the electronic device 201 may provide guidance information for the specific image 1540 based on the difference between the first preference and the second preference. For example, the electronic device 201 may provide a method for improving at least one of the perspective, exposure, focus, and white balance of the specific image 1540 based on the difference between the first preference and the second preference.

[0190] By utilizing the above-described method, the electronic device 201 can provide educational services or entertainment services by using an expert AI model.

[0191] The electronic device 201 according to an embodiment may include a memory 230, a communication circuit 250, and a processor 220. The processor according to an embodiment may be configured to confirm a usage pattern of a specified media item among all media items stored in the memory, and determine a score for each specified media item based on the usage pattern. The processor according to an embodiment may be configured to confirm features corresponding to the characteristics of each specified media item by using a main AI model stored in the memory. The processor according to an embodiment may be configured to obtain a personalized first AI model trained based on scores and features. The processor according to an embodiment may be configured to determine a first preference for each of a plurality of first media items based on the first AI model. The processor according to an embodiment may be configured to execute functions related to a plurality of first media items based on the first preference.

[0192] The processor according to an embodiment may be configured to, as at least part of the function related to the plurality of first media items, recommend at least one media item among the plurality of first media items based on the first preference.

[0193] The processor according to an embodiment may be configured to categorize the plurality of first media items based on the first preference.

[0194] The processor according to an embodiment may be configured to determine a second preference for each of the plurality of first media items by using the second AI model when acquiring a second AI model of another person from the external electronic device 202 or 203. The processor according to an embodiment may be configured to execute a function related to at least one media item among the plurality of first media items based on the second preference.

[0195] The processor according to an embodiment may be configured to determine a third preference for at least one media item among the plurality of first media items by using the third AI model, when a third AI model of the specific person is obtained from server 208. The processor according to an embodiment may be configured to compare the first preference with the third preference to provide guidance including at least one of whether the at least one media item is preferred, a degree of preference, or correction information.

[0196] The processor according to an embodiment may be configured to confirm whether the electronic device is in an idle state. The processor according to an embodiment may be configured to train the first AI model based on the score and the feature based on the electronic device being in the idle state.

[0197] The processor according to an embodiment may be configured to determine, based on the scores, designated media items among all media items stored in the memory as a media set for training the first AI model.

[0198] The processor according to the embodiment may be configured to acquire weights related to the first AI model as a result of training the first AI model. The processor according to the embodiment may be configured to apply the weights to the main AI model to acquire the first AI model.

[0199] The processor according to an embodiment may be configured to confirm an aesthetic score indicating characteristics of each designated media item by using the main AI model.The processor according to an embodiment may be configured to further use the aesthetic score in addition to using the score and features to train the first AI model.

[0200] The processor according to an embodiment may be configured to: when forming a group with multiple external electronic devices via a communication circuit, obtain an AI model from each of the multiple external electronic devices. The processor according to an embodiment may be configured to confirm preferences for multiple media items related to the group by using the AI ​​model. The processor according to an embodiment may be configured to send at least one media item from the multiple media items to the multiple external electronic devices based on the preferences.

[0201] The processor according to an embodiment may be configured to acquire information about at least one media item from an external electronic device or a server. The processor according to an embodiment may be configured to train a first AI model by using the information about at least one media item.

[0202] The processor according to an embodiment may be configured to confirm an attribute of each of the plurality of first media items by using the first AI model.The processor according to an embodiment may be configured to classify the plurality of first media items based on the attribute.

[0203] The operating method of the electronic device 201 according to the embodiment may include: confirming the usage pattern of a specified media item among all media items stored in the electronic device, and determining the score of each specified media item based on the usage pattern. The operating method of the electronic device according to the embodiment may include extracting features corresponding to the characteristics of each specified media item by using a main AI model stored in the electronic device. The operating method of the electronic device according to the embodiment may include obtaining a personalized first AI model trained based on the score and the feature. The operating method of the electronic device according to the embodiment may include determining a first preference for each of a plurality of first media items based on the first AI model. The operating method of the electronic device according to the embodiment may include executing functions related to the plurality of first media items based on the first preference.

[0204] According to an embodiment, performing a function related to the plurality of first media items may include recommending at least one media item among the plurality of first media items based on the first preference.

[0205] According to an embodiment, performing a function related to the plurality of first media items may include categorizing the plurality of first media items based on the first preference.

[0206] The operating method of the electronic device according to an embodiment may include: determining a second preference for each of the plurality of first media items by using the second AI model, when acquiring a second AI model of another person from the external electronic device 202 or 203. The operating method of the electronic device according to an embodiment may also include executing a function related to at least one media item among the plurality of first media items based on the second preference.

[0207] The operating method of the electronic device according to an embodiment may further include: determining a third preference for at least one media item among the plurality of first media items by using the third AI model, when a third AI model of the specific person is acquired from the server 208. The operating method of the electronic device according to an embodiment may include: comparing the first preference with the third preference to provide guidance including at least one of whether the at least one media item is preferred, a degree of preference, or correction information.

[0208] The operating method of the electronic device according to the embodiment may further include confirming whether the electronic device is in an idle state. The operating method of the electronic device according to the embodiment may further include training the first AI model based on the score and the feature based on the electronic device being in the idle state.

[0209] The operating method of the electronic device according to the embodiment may further include determining, based on the score, designated media items among all media items stored in the electronic device as a media set for training the first AI model.

[0210] The non-transitory recording medium 130 according to an embodiment may store instructions capable of executing: confirming a usage pattern of a specified media item among all media items stored in the electronic device 201, and determining a score for each specified media item based on the usage pattern; extracting features corresponding to the characteristics of each specified media item by using a main AI model stored in a memory; obtaining a personalized first AI model trained based on the scores and features; determining a first preference for each of a plurality of first media items based on the first AI model; and executing functions related to the plurality of first media items based on the first preferences.

[0211] The electronic device according to various embodiments may be one of various types of electronic devices. The electronic device may include, for example, a portable communication device (e.g., a smartphone), a computer device, a portable multimedia device, a portable medical device, a camera, a wearable device, or a household appliance. According to embodiments of the present disclosure, the electronic device is not limited to those described above.

[0212] It should be understood that the various embodiments of the present disclosure and the terms used therein are not intended to limit the technical features set forth herein to specific embodiments, but rather include various changes, equivalents, or alternative forms for the corresponding embodiments. For the description of the accompanying drawings, similar reference numerals may be used to refer to similar or related elements. It will be understood that nouns in the singular form corresponding to an item may include one or more things, unless the relevant context clearly indicates otherwise. As used herein, each of phrases such as "A or B," "at least one of A and B," "at least one of A or B," "A, B or C," "at least one of A, B and C," and "at least one of A, B or C" may include any one or all possible combinations of the items listed together with the corresponding phrase in the multiple phrases. As used herein, terms such as "first" and "second" or "first" and "second" may be used to simply distinguish a corresponding component from another component and do not limit the components in other respects (e.g., importance or order). It will be understood that if an element (e.g., a first element) is referred to as being “coupled to another element (e.g., a second element)”, “coupled to another element (e.g., a second element)”, “connected to another element (e.g., a second element)”, or “connected to another element (e.g., a second element)”, with or without the terms “operably” or “communicatively” being used, it means that the element may be directly (e.g., wired) coupled to the other element, wirelessly connected to the other element, or coupled to the other element via a third element.

[0213] As used in connection with various embodiments of the present disclosure, the term "module" may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with other terms (e.g., "logic," "logic block," "portion," or "circuit"). A module may be a single integrated component adapted to perform one or more functions, or the smallest unit or portion of the single integrated component. For example, depending on the embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0214] The various embodiments described herein can be implemented as software (e.g., program 140) comprising one or more instructions stored in a storage medium (e.g., internal memory 136 or external memory 138) that is readable by a machine (e.g., electronic device 101). For example, under the control of a processor (e.g., processor 120) of the machine (e.g., electronic device 101), the processor can invoke and execute at least one of the one or more instructions stored in the storage medium, with or without the use of one or more other components. This enables the machine to operate to perform at least one function in accordance with the invoked at least one 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. The term "non-transitory" simply means that the storage medium is a tangible device and does not include signals (e.g., electromagnetic waves), but does not distinguish between data being semi-permanently stored in the storage medium and data being temporarily stored in the storage medium.

[0215] According to an embodiment, the method according to various embodiments of the present disclosure may be included and provided in a computer program product. The computer program product may be traded as a product between a seller and a buyer. The computer program product may be distributed in the form of a machine-readable storage medium (e.g., a compact disc read-only memory (CD-ROM)), or may be downloaded via an application store (e.g., PlayStore). TM The computer program product may be distributed (e.g., downloaded or uploaded) online, or may be distributed (e.g., downloaded or uploaded) directly between two user devices (e.g., smartphones). If distributed online, at least part of the computer program product may be temporarily generated or at least temporarily stored in a machine-readable storage medium (such as a memory of a manufacturer's server, an application store's server, or a forwarding server).

[0216] According to various embodiments, each of the aforementioned components (e.g., a module or program) may comprise a single entity or multiple entities, and some of the multiple entities may be separately provided in different components. According to various embodiments, one or more of the aforementioned components may be omitted, or one or more additional components may be added. Alternatively or additionally, multiple components (e.g., modules or programs) may be integrated into a single component. In such a case, according to various embodiments, the integrated component may still perform the one or more functions of each of the multiple components in the same or similar manner as the corresponding one of the multiple components performed the one or more functions prior to integration. According to various embodiments, the operations performed by a module, program, or another component may be performed sequentially, in parallel, repeatedly, or in a heuristic manner, or one or more of the operations may be performed in a different order or omitted, or one or more additional operations may be added.

Claims

1. An electronic device (201), comprising: Memory (230); Communication circuit (250); as well as Processor (220), Wherein, the processor is configured to: identifying a usage pattern of designated media items among all media items stored in the memory, and determining a score for each of the designated media items based on the usage pattern; extracting features corresponding to characteristics of each of the specified media items by using a master AI model stored in the memory; Obtaining a personalized first AI model trained based on the score and the feature; determining a first preference for each of a plurality of first media items based on the first AI model; and A function associated with the plurality of first media items is performed based on the first preference.

2. The electronic device according to claim 1, wherein The processor is configured to, as at least part of the functionality associated with the plurality of first media items, recommend at least one media item from among the plurality of first media items based on the first preference.

3. The electronic device according to any one of claims 1 and 2, wherein The processor is configured to categorize the plurality of first media items based on the first preference.

4. The electronic device according to any one of claims 1 to 3, wherein The processor is configured to: When acquiring a second AI model of another person from an external electronic device ( 202 or 203 ), determining a second preference for each of the plurality of first media items by using the second AI model; and A function associated with at least one media item among the plurality of first media items is performed based on the second preference.

5. The electronic device according to any one of claims 1 to 4, wherein The processor is configured to: When a third AI model of the specific person is obtained from the server (208), determining a third preference of at least one media item among the plurality of first media items by using the third AI model; and The first preference is compared to the third preference to provide guidance including at least one of whether the at least one media item is preferred, a degree of preference, or correction information.

6. The electronic device according to any one of claims 1 to 5, wherein The processor is configured to: confirming whether the electronic device is in an idle state; and Based on confirming that the electronic device is in the idle state, the first AI model is trained based on the score and the feature.

7. The electronic device according to any one of claims 1 to 6, wherein: The processor is configured to determine, based on the score, the designated media item among all the media items stored in the memory as a media set for training the first AI model.

8. The electronic device according to any one of claims 1 to 7, wherein The processor is configured to: As a result of training the first AI model, obtaining weights associated with the first AI model; and The weights are applied to the primary AI model to obtain the first AI model.

9. The electronic device according to any one of claims 1 to 8, wherein The processor is configured to: determining an aesthetic score indicative of the characteristic of each of the specified media items by using the master AI model; and In addition to using the scores and the features, the aesthetic scores are further used to train the first AI model.

10. The electronic device according to any one of claims 1 to 9, wherein: The processor is configured to: when forming a group with a plurality of external electronic devices through the communication circuit, acquiring an AI model from each of the plurality of external electronic devices; identifying preferences for a plurality of media items associated with the group by using the AI ​​model; and At least one media item among the plurality of media items is transmitted to the plurality of external electronic devices based on the preference.

11. The electronic device according to any one of claims 1 to 10, wherein The processor is configured to: obtaining information about at least one media item from an external electronic device or server; and The first AI model is trained by using information about the at least one media item.

12. The electronic device according to any one of claims 1 to 11, wherein The processor is configured to: confirming an attribute of each of the plurality of first media items by using the first AI model; and The plurality of first media items are categorized based on the attributes.

13. The electronic device according to any one of claims 1 to 11, wherein: The processor is configured to confirm the usage pattern taking into account at least one of viewing, sharing, editing, deleting, favorite settings, or background settings of the designated media item.

14. A method for operating an electronic device (201), the method comprising: identifying a usage pattern of designated media items among all media items stored in the electronic device, and determining a score for each designated media item based on the usage pattern; extracting features corresponding to characteristics of each of the designated media items by using a master AI model stored in the electronic device; Obtaining a personalized first AI model trained based on the score and the feature; determining a first preference for each of a plurality of first media items based on the first AI model; as well as A function associated with the plurality of first media items is performed based on the first preference.

15. The method according to claim 14, wherein Performing a function related to the plurality of first media items includes recommending at least one media item among the plurality of first media items based on the first preference.

Images