Method for utilizing image tag by using ai, and electronic device therefor

Abstract

Various embodiments of the present invention may comprise a display (160), a memory (130) for storing instructions, and a processor (120), wherein the instructions, when executed by the processor, may cause the electronic device to: identify an object included in an image displayed on the display; generate a first tag on the basis of the identified object and / or location information about the image; display the generated first tag on the image; when the first tag is selected, generate, on the basis of at least one of the location information about the image, the identified object, and the first tag, a second tag to which a function of content or an application related to the image is linked; display the generated second tag on the image; and provide the function of the content or the application related to the image on the basis of the selection of the second tag. Various embodiments are possible.

Description

Method for utilizing image tagging using AI and electronic device thereof

[0001] Various embodiments of the present disclosure disclose a method for utilizing image tags using AI and an electronic device thereof.

[0002] With the advancement of digital technology, various types of electronic devices, such as mobile terminals, personal digital assistants (PDAs), electronic notebooks, smartphones, tablet PCs (personal computers), and wearable devices, are becoming widely used. These electronic devices are constantly undergoing improvements in their hardware and / or software to support and enhance their functionality.

[0003] Traditionally, tags embedded in images could be used to search for and provide all images containing the same tag within an electronic device. Here, tags are used solely for the purpose of linking only images containing the same tag.

[0004] In one embodiment, a method and device may be disclosed for generating a first tag based on an object included in an image (or content) and location information of the image, displaying the generated first tag on the image, and when the first tag is selected, generating a second tag linked to a function of content or an application related to the image based on at least one of the location information of the image, the identified object, and the first tag, displaying the generated second tag on the image, and providing a function of the related content or application based on selection of the second tag.

[0005] An electronic device (101) according to an embodiment of the present disclosure includes a display (160), a memory (130) for storing instructions, and a processor (120), wherein the instructions, when executed by the processor, cause the electronic device to identify an object included in an image displayed on the display, generate a first tag based on the identified object and location information of the image, display the generated first tag on the image, and when the first tag is selected, generate a second tag linked to a function of a content or application related to the image based on at least one of the location information of the image, the identified object, and the first tag, display the generated second tag on the image, and provide a function of the content or application related to the image based on selection of the second tag.

[0006] An operating method of an electronic device (101) according to an embodiment of the present disclosure may include an operation of identifying an object included in an image displayed on a display of the electronic device, an operation of generating a first tag based on the identified object and location information of the image, an operation of displaying the generated first tag on the image, an operation of generating a second tag linked to a function of a content or application related to the image based on at least one of the location information of the image, the identified object, and the first tag when the first tag is selected, an operation of displaying the generated second tag on the image, and an operation of providing a function of a content or application related to the image based on selection of the second tag.

[0007] In one embodiment, tag information can be obtained from content (e.g., images, videos) using a generative AI model, and additional information can be generated based on the tag information from the generative AI model.

[0008] According to one embodiment, personal information stored in an electronic device or additional data obtained from an external source (e.g., a cloud server or SNS) at the user's request may be used to obtain a result desired by the user through a generative AI model installed in the electronic device or a generative AI model driven by an intelligent server.

[0009] According to one embodiment, data in various formats such as images, videos, texts, and voices can be generated based on tag information, and when tag information is not used in a generative AI model, an application link that can search tag information online or directly connect to an application highly related to an application installed on an electronic device can be added to the tag information.

[0010] In one embodiment, data can be diversified and used by using tag information as input data for a generative AI model or as prior information for user personalization.

[0011] FIG. 1 is a block diagram of an electronic device within a network environment according to one embodiment.

[0012] FIG. 2 is a block diagram illustrating a generative artificial intelligence system according to one embodiment.

[0013] FIG. 3 is a diagram illustrating an example of providing information related to a tag of an image in an electronic device according to one embodiment.

[0014] Figure 4 is a flowchart illustrating an operating method of an electronic device according to one embodiment.

[0015] FIG. 5A is a diagram illustrating an example of adding a tag to an image in an electronic device according to one embodiment.

[0016] FIG. 5b is a diagram illustrating an example of providing a function of content or an application related to a selected tag in an electronic device according to one embodiment.

[0017] FIG. 6 is a diagram illustrating an example of adding an emotional tag to an image in an electronic device according to one embodiment.

[0018] FIG. 7 is a flowchart illustrating a method for adding and linking tags to an electronic device according to one embodiment.

[0019] FIGS. 8A and 8B are diagrams illustrating an example of generating tags and content in an electronic device according to one embodiment.

[0020] FIG. 9 is a flowchart illustrating a second tag generation method in an electronic device according to one embodiment.

[0021] FIGS. 10 and 11 are diagrams illustrating an example of adding tag information to an image in an electronic device according to one embodiment.

[0022] FIGS. 12 to 14 are drawings illustrating an example of utilizing an image tag in an electronic device according to one embodiment.

[0023] FIG. 1 is a block diagram of an electronic device (101) within a network environment (100) according to various embodiments.

[0024] Referring to FIG. 1, in a network environment (100), an electronic device (101) may communicate with an electronic device (102) via a first network (198) (e.g., a short-range wireless communication network), or may communicate with at least one of an electronic device (104) or a server (108) via a second network (199) (e.g., a long-range wireless communication network). According to one embodiment, the electronic device (101) may communicate with the electronic device (104) via the server (108). According to one embodiment, the electronic device (101) may include a processor (120), a memory (130), an input module (150), an audio output module (155), a display module (160), an audio module (170), a sensor module (176), an interface (177), a connection terminal (178), a haptic module (179), a camera module (180), a power management module (188), a battery (189), a communication module (190), a subscriber identification module (196), or an antenna module (197). In some embodiments, the electronic device (101) may omit at least one of these components (e.g., the connection terminal (178)), or may have one or more other components added. In some embodiments, some of these components (e.g., the sensor module (176), the camera module (180), or the antenna module (197)) may be integrated into one component (e.g., the display module (160)).

[0025] The processor (120) may, for example, execute software (e.g., a program (140)) to control at least one other component (e.g., a hardware or software component) of the electronic device (101) connected to the processor (120) and perform various data processing or operations. According to one embodiment, as at least a part of the data processing or operations, the processor (120) may store commands or data received from other components (e.g., a sensor module (176) or a communication module (190)) in a volatile memory (132), process the commands or data stored in the volatile memory (132), and store result data in a non-volatile memory (134). According to one embodiment, the processor (120) may include a main processor (121) (e.g., a central processing unit or an application processor) or an auxiliary processor (123) (e.g., a graphics processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor) that can operate independently or together with the main processor (121). For example, when the electronic device (101) includes the main processor (121) and the auxiliary processor (123), the auxiliary processor (123) may be configured to use less power than the main processor (121) or to be specialized for a given function. The auxiliary processor (123) may be implemented separately from the main processor (121) or as a part thereof.

[0026] The auxiliary processor (123) may control at least a portion of functions or states associated with at least one component (e.g., a display module (160), a sensor module (176), or a communication module (190)) of the electronic device (101), for example, on behalf of the main processor (121) while the main processor (121) is in an inactive (e.g., sleep) state, or together with the main processor (121) while the main processor (121) is in an active (e.g., application execution) state. In one embodiment, the auxiliary processor (123) (e.g., an image signal processor or a communication processor) may be implemented as a part of another functionally related component (e.g., a camera module (180) or a communication module (190)). In one embodiment, the auxiliary processor (123) (e.g., a neural network processing unit) may include a hardware structure specialized for processing artificial intelligence models. The artificial intelligence models may be generated through machine learning. This learning can be performed, for example, on the electronic device (101) itself where the artificial intelligence model is executed, or can be performed through a separate server (e.g., server (108)). The learning algorithm can include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but is not limited to the examples described above. The artificial intelligence model can include multiple artificial neural network layers.The artificial neural network may be one of a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), a deep Q-network, or a combination of two or more of the above, but is not limited to the examples described above. In addition to, or alternatively to, a hardware structure, an artificial intelligence model may include a software structure.

[0027] The memory (130) can store various data used by at least one component (e.g., processor (120) or sensor module (176)) of the electronic device (101). The data can include, for example, software (e.g., program (140)) and input data or output data for commands related thereto. The memory (130) can include volatile memory (132) or non-volatile memory (134).

[0028] The program (140) may be stored as software in the memory (130) and may include, for example, an operating system (142), middleware (144), or an application (146).

[0029] The input module (150) can receive commands or data to be used in a component of the electronic device (101) (e.g., a processor (120)) from an external source (e.g., a user) of the electronic device (101). The input module (150) can include, for example, a microphone, a mouse, a keyboard, a key (e.g., a button), or a digital pen (e.g., a stylus pen).

[0030] The audio output module (155) can output audio signals to the outside of the electronic device (101). The audio output module (155) can include, for example, a speaker or a receiver. The speaker can be used for general purposes, such as multimedia playback or recording playback. The receiver can be used to receive incoming calls. In one embodiment, the receiver can be implemented separately from the speaker or as part of the speaker.

[0031] The display module (160) can visually provide information to an external party (e.g., a user) of the electronic device (101). The display module (160) may include, for example, a display, a holographic device, or a projector and a control circuit for controlling the device. According to one embodiment, the display module (160) may include a touch sensor configured to detect a touch, or a pressure sensor configured to measure the intensity of a force generated by the touch.

[0032] The audio module (170) can convert sound into an electrical signal, or vice versa, convert an electrical signal into sound. According to one embodiment, the audio module (170) can acquire sound through the input module (150), output sound through the sound output module (155), or an external electronic device (e.g., electronic device (102)) (e.g., speaker or headphone) directly or wirelessly connected to the electronic device (101).

[0033] The sensor module (176) can detect the operating status (e.g., power or temperature) of the electronic device (101) or the external environmental status (e.g., user status) and generate an electrical signal or data value corresponding to the detected status. According to one embodiment, the sensor module (176) can include, for example, a gesture sensor, a gyro sensor, a barometric pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biometric sensor, a temperature sensor, a humidity sensor, or an illuminance sensor.

[0034] The interface (177) may support one or more designated protocols that may be used to directly or wirelessly connect the electronic device (101) with an external electronic device (e.g., the electronic device (102)). In one embodiment, the interface (177) may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

[0035] The connection terminal (178) may include a connector through which the electronic device (101) may be physically connected to an external electronic device (e.g., electronic device (102)). According to one embodiment, the connection terminal (178) may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (e.g., a headphone connector).

[0036] The haptic module (179) can convert electrical signals into mechanical stimuli (e.g., vibration or movement) or electrical stimuli that a user can perceive through tactile or kinesthetic sensations. According to one embodiment, the haptic module (179) can include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

[0037] The camera module (180) can capture still images and videos. According to one embodiment, the camera module (180) may include one or more lenses, image sensors, image signal processors, or flashes.

[0038] The power management module (188) can manage power supplied to the electronic device (101). According to one embodiment, the power management module (188) can be implemented as, for example, at least a part of a power management integrated circuit (PMIC).

[0039] A battery (189) may power at least one component of the electronic device (101). In one embodiment, the battery (189) may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0040] The communication module (190) may support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between the electronic device (101) and an external electronic device (e.g., electronic device (102), electronic device (104), or server (108)), and the performance of communication through the established communication channel. The communication module (190) may operate independently from the processor (120) (e.g., application processor) and may include one or more communication processors that support direct (e.g., wired) communication or wireless communication. According to one embodiment, the communication module (190) may include a wireless communication module (192) (e.g., a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module (194) (e.g., a local area network (LAN) communication module, or a power line communication module). Among these communication modules, the corresponding communication module can communicate with an external electronic device (104) via a first network (198) (e.g., a short-range communication network such as Bluetooth, wireless fidelity (WiFi) direct, or infrared data association (IrDA)) or a second network (199) (e.g., a long-range communication network such as a legacy cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (e.g., a LAN or WAN)). These various types of communication modules can be integrated into a single component (e.g., a single chip) or implemented as multiple separate components (e.g., multiple chips). The wireless communication module (192) can verify or authenticate the electronic device (101) within a communication network such as the first network (198) or the second network (199) by using subscriber information (e.g., an international mobile subscriber identity (IMSI)) stored in the subscriber identification module (196).

[0041] The wireless communication module (192) can support 5G networks and next-generation communication technologies following the 4G network, such as NR access technology (new radio access technology). The NR access technology can support high-speed transmission of high-capacity data (eMBB (enhanced mobile broadband)), minimization of terminal power and connection of multiple terminals (mMTC (massive machine type communications)), or high reliability and low latency (URLLC (ultra-reliable and low-latency communications)). The wireless communication module (192) can support, for example, a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate. The wireless communication module (192) can support various technologies for securing performance in a high-frequency band, such as beamforming, massive multiple-input and multiple-output (MIMO), full dimensional MIMO (FD-MIMO), array antenna, analog beam-forming, or large scale antenna. The wireless communication module (192) can support various requirements specified in the electronic device (101), an external electronic device (e.g., the electronic device (104)), or a network system (e.g., the second network (199)). According to one embodiment, the wireless communication module (192) can support a peak data rate (e.g., 20 Gbps or more) for eMBB realization, a loss coverage (e.g., 164 dB or less) for mMTC realization, or a U-plane latency (e.g., 0.5 ms or less for downlink (DL) and uplink (UL), or 1 ms or less for round trip) for URLLC realization.

[0042] The antenna module (197) can transmit or receive signals or power to or from an external device (e.g., an external electronic device). In one embodiment, the antenna module (197) may include an antenna including a radiator formed of a conductor or a conductive pattern formed on a substrate (e.g., a PCB). In one embodiment, the antenna module (197) may include a plurality of antennas (e.g., an array antenna). In this case, at least one antenna suitable for a communication method used in a communication network, such as the first network (198) or the second network (199), may be selected from the plurality of antennas, for example, by the communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device via the at least one selected antenna. In some embodiments, in addition to the radiator, another component (e.g., a radio frequency integrated circuit (RFIC)) may be additionally formed as a part of the antenna module (197).

[0043] According to various embodiments, the antenna module (197) may form a mmWave antenna module. In one embodiment, the mmWave antenna module may include a printed circuit board, an RFIC disposed on or adjacent a first side (e.g., a bottom side) of the printed circuit board and capable of supporting a designated high-frequency band (e.g., a mmWave band), and a plurality of antennas (e.g., an array antenna) disposed on or adjacent a second side (e.g., a top side or a side side) of the printed circuit board and capable of transmitting or receiving signals in the designated high-frequency band.

[0044] At least some of the above components can be interconnected and exchange signals (e.g., commands or data) with each other via a communication method between peripheral devices (e.g., a bus, GPIO (general purpose input and output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface)).

[0045] According to one embodiment, commands or data may be transmitted or received between the electronic device (101) and an external electronic device (104) via a server (108) connected to a second network (199). Each of the external electronic devices (102 or 104) may be the same or a different type of device as the electronic device (101). According to one embodiment, all or part of the operations executed in the electronic device (101) may be executed in one or more of the external electronic devices (102, 104, or 108). For example, when the electronic device (101) is to perform a certain function or service automatically or in response to a request from a user or another device, the electronic device (101) may, instead of or in addition to executing the function or service itself, request one or more external electronic devices to perform the function or at least a part of the service. One or more external electronic devices that receive the request may execute at least a portion of the requested function or service, or an additional function or service related to the request, and transmit the result of the execution to the electronic device (101). The electronic device (101) may process the result as is or additionally and provide it as at least a portion of a response to the request. For this purpose, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used, for example. The electronic device (101) may provide an ultra-low latency service by using distributed computing or mobile edge computing, for example. In another embodiment, the external electronic device (104) may include an Internet of Things (IoT) device. The server (108) may be an intelligent server utilizing machine learning and / or a neural network. According to one embodiment, the external electronic device (104) or the server (108) may be included in the second network (199).The electronic device (101) can be applied to intelligent services (e.g., smart home, smart city, smart car, or healthcare) based on 5G communication technology and IoT-related technology.

[0046] Electronic devices according to the various embodiments disclosed in this document may take various forms. Electronic devices may include, for example, portable communication devices (e.g., smartphones), computer devices, portable multimedia devices, portable medical devices, cameras, wearable devices, or home appliances. Electronic devices according to the embodiments of this document are not limited to the aforementioned devices.

[0047] The various embodiments of this document and the terminology used therein are not intended to limit the technical features described in this document to specific embodiments, but should be understood to include various modifications, equivalents, or substitutes of the embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of the items, unless the context clearly indicates otherwise. In this document, each of the phrases "A or B", "at least one of A and B", "at least one of A or B", "A, B, or C", "at least one of A, B, and C", and "at least one of A, B, or C" can include any one of the items listed together in the corresponding phrase among those phrases, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used merely to distinguish the corresponding component from other corresponding components and do not limit the corresponding components in any other respect (e.g., importance or order). When a component (e.g., a first) is referred to as "coupled" or "connected" to another (e.g., a second) component, with or without the terms "functionally" or "communicatively," it means that the component can be connected to the other component directly (e.g., wired), wirelessly, or through a third component.

[0048] The term "module" used in various embodiments of this document may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be an integral component, or a minimum unit or part of such a component that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0049] Various embodiments of the present document may be implemented as software (e.g., a program (140)) including one or more instructions stored in a storage medium (e.g., an internal memory (136) or an external memory (138)) readable by a machine (e.g., an electronic device (101)). For example, a processor (e.g., a processor (120)) of the machine (e.g., an electronic device (101)) may call at least one instruction among the one or more instructions stored from the storage medium and execute it. This enables the machine to operate to perform at least one function according to the at least one called instruction. The one or more instructions may include code generated by a compiler or code executable by an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' simply means that the storage medium is a tangible device and does not contain signals (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently or temporarily on the storage medium.

[0050] According to one embodiment, the method according to various embodiments disclosed in this document may be provided as a computer program product. The computer program product may be traded between sellers and buyers as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)) or may be provided through an application store (e.g., Play Store). TM ) or directly between two user devices (e.g., smart phones), online distribution (e.g., downloading or uploading). In the case of online distribution, at least a portion of the computer program product may be at least temporarily stored or temporarily created in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0051] According to various embodiments, each component (e.g., a module or a program) of the above-described components may include one or more entities, and some of the entities may be separated and placed in other components. According to various embodiments, one or more components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In such a case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to the integration. According to various embodiments, the operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

[0052] FIG. 2 is a block diagram illustrating a generative artificial intelligence system according to one embodiment.

[0053] Referring to FIG. 2, a generative artificial intelligence system (200) according to one embodiment may include a user interface (210), a database (220), an application and service component (230), an AI framework (250), and a generative AI model (270). According to one embodiment, the generative artificial intelligence system (200) may be included in an electronic device (e.g., the electronic device (101) of FIG. 1) or an external server (e.g., an intelligent server (e.g., the server (108) of FIG. 1)).

[0054] The user interface (210) can receive a user query. The user query can be in the form of natural language, images, or videos. Additionally, context information can be transmitted along with the user query. As another example, the user query can also be a non-natural language input that does not generate natural language, such as a design request or modification. Furthermore, the query can be a mixed form of natural language, images, sounds, and context information as described above. Furthermore, the user interface (210) can output the results of the generative artificial intelligence system to the user. The output can be in the form of natural language or specific content, and can also be provided in the form of an action requested by the user.

[0055] The AI ​​framework (250) can receive a user query and coordinate and control each component necessary to carry out the user's intent. The AI ​​framework (250) may include a prompt design component (251), an application and plug-in management component (APIs / Plugins Management component) (253), and an output modification component (255).

[0056] A user query or action entered in the user interface (210) may be transmitted to a prompt design component (251). The prompt design component (251) may be used to generate prompts suitable for input into a large language model (LLM) or a large multimodal model. The prompt design component (251) may be an AI component that uses a machine learning algorithm or a neural network to develop better prompts over time. The prompt design component (251) may access a knowledge component containing user preference data, a prompt library, and prompt examples to generate prompts and transmit them to the large language model (LLM) or the large multimodal model (LMM).

[0057] The application and plugin management component (253) can communicate with external information when a request for additional information is made when user input is passed as input to the generative model. The application and plugin management component (253) establishes a channel for communication with the AI ​​Interface externally via an application programming interface (API), thereby enabling access to various data sources. Furthermore, if the application or service needs to perform an action that ultimately fulfills a user query, rather than an intermediate result, the application and plugin management component (253) can request such an action via the API. Information obtained from external sources can be passed as input to the generative model along with user input.

[0058] The output modification component (255) can fine-tune the output from the generative model. For example, the output modification component (255) can verify that content generated through a language model (LLM) or a large-scale multimodal model (LMM) is not irrelevant, does not contain biased content, or does not contain harmful content. In addition, the output modification component (255) can determine the degree to which the content matches the user's desired result and, if necessary, can proceed with additional processing. Additionally, the output modification component (255) can configure and provide hints to the user to avoid undesired output.

[0059] Generative AI models (270) generally refer to artificial intelligence neural networks that create new forms of data based on user input information. Representative models that generate images include generative adversarial networks (GANs) and variational autoencoders (VAEs). Recently, diffusion-based generative models that use VAE and transformer structures are also called generative models. In addition, language models are models trained to statistically output the most appropriate output based on input values, and representative examples include models such as CHAT-GPT 3 and CHAT-GPT 4. In addition, since they can recognize various types of data input, such as text, images, and voice, and generate new data corresponding to them, they are called large multimodal models (LMMs).

[0060] FIG. 3 is a diagram illustrating an example of providing information related to a tag of an image in an electronic device according to one embodiment.

[0061] Referring to FIG. 3, a processor (e.g., a processor (120) of FIG. 1) of an electronic device (e.g., an electronic device (101) of FIG. 1) according to an embodiment may display an image (301) on a display (e.g., a display module (160) of FIG. 1). A first user interface (310) may include an image (301) and a first graphical user interface (UI) element (311). The image (301) may be obtained (or photographed) from a camera (e.g., a camera module (180) of FIG. 1) (e.g., a preview image), stored in a memory of the electronic device (101) (e.g., a memory (130) of FIG. 1), or received (or downloaded) from an external device (or server). According to an embodiment, the image (301) may mean an image included in a screen (e.g., a web page) that may be displayed through the display module (160). Hereinafter, although the description is expressed as an image, the present invention can be equally applied to videos. Therefore, images can be interpreted as content. The first graphical UI element (311) may set whether to display (e.g., enable / disable) tags related to the image (301). The first user interface (310) may be in a state where the first graphical UI element (311) is disabled.

[0062] When a first graphic UI element (311) is selected in the first user interface (310), the processor (120) may provide a second user interface (330) that displays a tag related to the image (301) (e.g., display the tag on the display module (160)). The second user interface (330) may display a first tag (333) on the image (301). The first tag (333) may be text related to the image (301). The processor (120) may identify an object included in the image (301) and extract location information of the image (301). The object may include at least one of a person (or person), an animal, an object, or a background. The number of identified objects may be one or more. The location information of the image (301) may be extracted from metadata of the image (301).

[0063] The processor (120) may generate a first tag (333) (e.g., a place name) based on the location information of the identified object and / or image (301). If the image (301) includes text, the processor (120) may recognize and extract the text included in the image (301). The processor (120) may further consider the extracted text to generate the first tag (333). When generating the first tag (333), the first tag (333) may be generated through a generative AI included in the electronic device (101) (e.g., the generative artificial intelligence system (200) of FIG. 2) or an intelligent server including the generative artificial intelligence system (200) (e.g., the server (108) of FIG. 1). After generating the first tag (333), the processor (120) may display the first tag (333) on the image (301).

[0064] When a first tag (333) is selected in the second user interface (330), the processor (120) may provide (e.g., display on the display module (160)) a third user interface (350) including a second tag (351). The third user interface (350) may display the first tag (333) and the second tag (351) on the image (301). The processor (120) may generate a second tag (351) linked to a function of a content or application related to the image (301) based on at least one of the location information of the image (301), the identified object, and the first tag (333). When generating the second tag (351), the second tag (351) may be generated through the generating AI included in the electronic device (101) or the server (108). After generating the second tag (351), the processor (120) may display the first tag (333) and the second tag (351) on the image (301). According to one embodiment, when the first tag (333) is selected, the processor (120) may link the function of the content or application related to the image (301) to the first tag based on at least one of the location information of the image (301), the identified object, and the first tag (333).

[0065] According to one embodiment, the processor (120) may determine feature information based on a representative object of the image (301) and / or location information of the image (301), search for content and functions of an application based on the feature information, group the searched content by tag, and generate a second tag in which the grouped content and the function of the searched application are linked. Alternatively, the processor (120) may search for content stored in a memory (130) or a cloud server (e.g., server (108) of FIG. 1) connected to the electronic device (101) based on the context (e.g., context and user intention) of the image (301), group the searched content by tag, and generate a representative tag of the grouped content as a second tag. For example, the second tag (351) may be an Everland map, an Everland QR admission ticket, or an Everland restaurant.

[0066] According to one embodiment, the processor (120) may learn the usage pattern of the user of the electronic device (101) and search for content related to the image using a key feature keyword based on the user's preference. Alternatively, the processor (120) may identify the history of application function usage or input keyword at the location where the image was captured, and search for content related to the image using a key feature keyword based on the identified history of application function usage or input keyword.

[0067] The processor (120) may provide (e.g., display on the display module (160)) a fourth user interface (370) based on a user input (353) of selecting a second tag (351) in the third user interface (350). The fourth user interface (370) may display content (371) related to the second tag selected on the image (301). For example, if the user selects an Everland QR ticket among the second tags (351), the processor (120) may display content (371) (e.g., an image) including the Everland QR ticket on the display module (160). When the processor (120) selects the content (371), the processor (120) may provide the Everland QR ticket on the full screen of the display module (160).

[0068] An electronic device (101) according to an embodiment of the present disclosure includes a display (160), a memory (130) for storing instructions, and a processor (120), wherein the instructions, when executed by the processor, cause the electronic device to identify an object included in an image displayed on the display, generate a first tag based on location information of the identified object and / or the image, display the generated first tag on the image, and when the first tag is selected, generate a second tag linked to a function of a content or application related to the image based on at least one of the location information of the image, the identified object, and the first tag, display the generated second tag on the image, and provide a function of the content or application related to the image based on selection of the second tag.

[0069] The instructions, when executed by the processor, may cause the electronic device to determine feature information based on a representative object of the image and / or location information of the image, search for content and / or a function of an application based on the feature information, group the searched content by tag, and generate a second tag in which the grouped content and the function of the searched application are linked.

[0070] The above instructions, when executed by the processor, may cause the electronic device to search for content stored in the memory or a server connected to the electronic device based on the context of the image, group the searched content by tag, and generate a representative tag of the grouped content as a second tag.

[0071] The instructions, when executed by the processor, may cause the electronic device to display a first graphic UI element providing a function for adding a tag when the first tag is displayed, display a second graphic UI element for inputting tag information when the first graphic UI element is selected, receive tag addition information from a user through the second graphic UI element, generate a new image and a third tag related to the tag addition information through a generative AI model based on the tag addition information and information related to the image, and display the third tag on the generated image.

[0072] The above instructions, when executed by the processor, may cause the electronic device to display an image associated with the third tag when the third tag is selected.

[0073] The above instructions, when executed by the processor, may cause the electronic device to provide a function of content or an application related to the selected second tag when the second tag is selected.

[0074] The above instructions, when executed by the processor, may cause the electronic device to display a graphical UI element related to tag display on the image, and, when the graphical UI element is selected, to delete the first tag or the second tag displayed on the image.

[0075] The above instructions, when executed by the processor, cause the electronic device to search for content related to the image using the first tag as a feature keyword related to the image, and the feature keyword may be a keyword specified by location information within the electronic device or may be obtained using an AI model trained to output a major feature keyword according to location information.

[0076] The above instructions, when executed by the processor, may cause the electronic device to learn a usage pattern of a user of the electronic device and search for content related to the image with a key feature keyword based on the user's preference, or to identify a history of function usage of an application or a history of input keywords at a location where the image was taken and search for content related to the image with a key feature keyword based on the identified history of function usage of the application or the history of input keywords.

[0077] The above instructions, when executed by the processor, may cause the electronic device to display tags selected by the user and tags not selected by the user on the image.

[0078] Figure 4 is a flowchart (400) illustrating an operating method of an electronic device according to one embodiment.

[0079] Referring to FIG. 4, in operation 401, a processor (e.g., the processor (120) of FIG. 1) of an electronic device (e.g., the electronic device (101) of FIG. 1) according to an embodiment may display an image on a display (e.g., the display module (160) of FIG. 1). The image may be obtained (or photographed) from a camera (e.g., the camera module (180) of FIG. 1) (e.g., a preview image), stored in a memory of the electronic device (101) (e.g., the memory (130) of FIG. 1), or received (or downloaded) from an external device (or server). Depending on the embodiment, the image may refer to an image included in a screen (e.g., a web page) that can be displayed through the display module (160). Although the description below refers to an image, the present invention can be equally applied to a video. Therefore, the image can be interpreted as content.

[0080] According to one embodiment, the processor (120) may display a graphical UI element that sets whether to display (e.g., activate / deactivate) a tag related to an image. The graphical UI element may be activated or deactivated by default in the electronic device (101). The processor (120) may determine whether to display a tag related to an image based on whether the graphical UI element is selected by a user. Operation 403 may be performed in a state where the graphical UI element is activated.

[0081] In operation 403, the processor (120) may identify an object included in the image. The object may include at least one of a person (or persons), an animal, an object, or a background. For example, if the object is a person, it may include a person's face, upper body (e.g., from head to waist), or full body (e.g., from head to feet). If the object is an object, it may include, for example, a car, a desk, or a building (e.g., a view of the Louvre Museum). The image may include one or more objects. If the image includes multiple objects, the processor (120) may perform image segmentation to recognize each object.

[0082] AI-based image segmentation models can be trained using pairs of RGB-based three-channel images and labeled image types for each image. Among the most recent AI-based segmentation methods, SAM (Segment Anything Model, MetaAI) boasts excellent performance. It may be that the segmentation model was trained using a training database called SA-1B. This training database is constructed by obtaining sudo-labeling results for foreground objects from an AI model that performs auto-labeling, and then verifying these results with humans. Through this training, the AI ​​model can segment even very small objects within an image.

[0083] In operation 405, the processor (120) may generate a first tag based on the identified object and the location information of the image. The location information of the image may be extracted from metadata of the image (e.g., resolution, capacity, location, etc.). According to one embodiment, the generative AI included in the electronic device (101) (e.g., the generative artificial intelligence system (200) of FIG. 2) may generate the first tag based on the location information of the identified object and / or the image. Alternatively, the processor (120) may transmit the image to an intelligent server (e.g., the server (108) of FIG. 1) including the generative artificial intelligence system (200) to request generation of a first tag, and receive the first tag from the server (108) in response to the request. According to one embodiment, when the image includes text, the processor (120) may recognize and extract text included in the image, and generate the first tag by further considering the extracted text.

[0084] For example, when object recognition is performed on the image using a segmentation AI model, the AI ​​model can output information on the location of the object in a coordinate system composed of a bounding box and information on the approximate type (person, animal, object) of the object. The image and the location information of the object included in the image are transmitted as inputs to the LLM model, and the processor (120) can use the information obtained from the LLM model as object tag information. For example, when utilizing a multi-modal LLM AI model, the first tag can be generated by transmitting image information segmenting the main object and the location information of the object as inputs to the LLM. The LLM model can generate the first tag based on the input image and the location information of the object by using information retrieved externally through RAG.

[0085] In operation 407, the processor (120) may display the first tag (e.g., the generated first tag) on ​​the image. For example, if there is one first tag, the processor (120) may display the first tag in the center of the image, or display the first tag around the object included in the image so as not to overlap with a major portion of the object. Even if there are multiple objects included in the image, there may be only one first tag. Alternatively, if there are multiple objects included in the image, there may be multiple first tags corresponding to the objects.

[0086] In operation 409, the processor (120) may detect a user input selecting the first tag. The user may touch (e.g., tap, long press) the first tag displayed on the image.

[0087] In operation 411, the processor (120) may generate a second tag linked to a function of content or an application related to the image in response to selection of the first tag. The processor (120) may determine feature information based on a representative object of the image and location information of the image, and search for functions of content and applications based on the feature information. For example, feature information of the location information may be a location-related category, such as an amusement park, a convenience store, or a movie theater. Keywords related to the location information of the image may be, for example, tickets, restaurants, or rides in the case of an amusement park. The content may refer to multimedia content such as an image or video. The content may include not only content stored in the memory (130), but also content stored in a cloud server linked to the electronic device (101). The processor (120) may group the searched content by tag, and generate a second tag linked to the grouped content and the function of the searched application. The function of the above application may include, for example, a specific image in a gallery application, a map of the current location in a map application, or a specific function of a specific application (e.g., a searched page or a specific URL). The second tag may be generated as text.

[0088] The processor (110) may search for images in the electronic device (101) based on the first tag, and may filter out images that match the context related to the image among the searched images. According to one embodiment, a context that may be used when filtering the search results using the first tag may use a feature keyword related to location information related to the image. At this time, the feature keyword related to the location may be a major keyword that is predefined for each location in the electronic device (101), or may use an AI model that has been trained to output major feature keywords according to input location information. According to one embodiment, a context that may be used when filtering the search results using the first tag may use major feature keywords based on the user's preference by learning the device user's usage pattern. The processor (110) (or generative AI) may use, in the electronic device (101), an application function that the user frequently used at the location or a major keyword that the user frequently inputs through the keyboard at the location as a major keyword.

[0089] In operation 413, the processor (120) may display the second tag (e.g., the generated second tag) on ​​the image. In operation 413, the tags displayed on the image may include the first tag and the second tag. The processor (120) may determine the placement position (or display position) of the second tag based on its relevance to the image. For example, the processor (120) may determine that a second tag with a high relevance is displayed on top of the image, and a second tag with a low relevance is displayed on bottom of the image. If the second tag is displayed on top of the image, the user can recognize the second tag more easily than the second tag displayed on bottom. Or vice versa.

[0090] In operation 415, the processor (120) may provide content or application functions based on the selection of the second tag. If multiple second tags are displayed as the second tags, for example, Everland map, Everland QR admission ticket, and Everland restaurant, the user may select the second tag, which is the Everland map. In this case, the processor (120) may provide a map image of a map application displaying the location of Everland.

[0091] FIG. 5A is a diagram illustrating an example of adding a tag to an image in an electronic device according to one embodiment.

[0092] Referring to FIG. 5A, a processor (e.g., a processor (120) of FIG. 1) of an electronic device (e.g., an electronic device (101) of FIG. 1) according to an embodiment may display a first user interface (510) including an add tag menu (511) on a display (e.g., a display module (160) of FIG. 1) in an image (501). The first user interface (510) may display a first tag (e.g., Everland) and a second tag (e.g., Everland map, Everland QR admission ticket, Everland restaurant) related to the image (501). The add tag menu (511) may be provided when a graphic UI element (e.g., a cross shape) provided together with the display of the first tag is selected. The add tag menu (511) may include an add tag, add link, or create item. The add tag menu (511) may be displayed first before the first tag is displayed (i.e., in the original image state). A second tag or third tag can be added without creating a first tag through the tag addition menu (511).

[0093] When a first item (e.g., 'Create') is selected by the user in the tag addition menu (511), the processor (120) may display a second user interface (520) on the display module (160). According to one embodiment, the second user interface (520) may include a keypad (523) for receiving input of a tag to be created. The user may input a tag to be created through the keypad (523). The processor (120) may display tag creation information (527) received through the keypad (523) and provide a tag creation button (521) including the tag creation information. When the tag creation button (521) is selected, the processor (120) may provide a third user interface (530) including a new image (531) and a third tag (533) based on the image (501) and the tag creation information.

[0094] According to one embodiment, a generative AI (e.g., a generative artificial intelligence system (200) of FIG. 2) included in an electronic device (101) may generate a new image (531) and a third tag (533) based on an image (501) and the tag generation information. The generative AI may analyze the image (501) and generate a new image (531) and a third tag (533) based on the image analysis result and the text of the tag generation information. For example, the generative AI may generate only an area corresponding to the sky in the image (501) and superimpose the sky area on the image (501) to generate a new image (531). Alternatively, the generative AI may generate the entire image including the area corresponding to the sky as a new image (531).

[0095] Alternatively, the processor (120) may transmit the image (501) and tag generation information to an intelligent server (e.g., server (108) of FIG. 1) including a generative artificial intelligence system (200) to request generation of a tag, and receive a third tag (533) from the server (108) based on the request. The processor (120) may transmit coordinate information of an area corresponding to the sky (e.g., a masking area) in the image (501) to the server (108), and receive an image of the sky area from the server (108) to provide a new image (531) to the image (501). Alternatively, the processor (120) may transmit the image (501) and tag generation information to the server (108), and receive a new image (531) from the server (108).

[0096] According to one embodiment, the processor (120) may display the third tag (533) differently from the first tag or the second tag. For example, the processor (120) may display the area border of the third tag (533) differently (e.g., bold or shiny) to indicate that the third tag (533) is activated, or may display the third tag (533) in a shaded or blinking manner. The third tag (533) may display a graphic object (e.g., three stars) indicating that it is related to the new image (531). When storage of the new image (531) is requested, the processor (120) may store the new image (531) in association with the image (501). Alternatively, the processor (120) may store location information where the new image (531) is stored in the metadata of the image (501).

[0097] When an area where no tags are displayed is selected in the third user interface (530), the processor (120) may provide a fourth user interface (540). The fourth user interface (540) may display a first tag, a second tag, and a third tag on the original image (541). Here, the third tag may be displayed in the same manner as the first tag and the second tag, indicating that the third tag is deactivated, unlike what is displayed in the third user interface (530). When an area where no tags are displayed is selected, the processor (120) may stop displaying the new image (531) on the screen and display the original image (541) on the screen.

[0098] FIG. 5b is a diagram illustrating an example of providing a function of content or an application related to a selected tag in an electronic device according to one embodiment.

[0099] Referring to FIG. 5B, the processor (120) may provide a fifth user interface (550) including a first tag (553) and a second tag (551) to an image (501). The image (501) may be a preview image acquired by a user through a camera application at the main gate of Everland. The fifth user interface (550) may be activated to display tags related to the image (501), and the processor (120) may analyze the user's intention to obtain meaningful information necessary for the user and provide the first tag (553) and the second tag (551). The second tag (551) may be linked to a function of a content or application related to the image (501). When a user input for selecting the second tag (551) is detected in the fifth user interface (550), the processor (120) may provide a sixth user interface (560).

[0100] The sixth user interface (560) may include content (561, 563) and / or graphic UI elements (567) related to the selected second tag. For example, when the tag 'Everland Restaurant' is selected, if a restaurant photo is linked, the processor (120) may provide the restaurant photo as the first content (563). In addition, the processor (120) may analyze the context for the keyword 'Everland Restaurant', extract text from the first content (563), extract a map location corresponding to the text extracted from the map application, and then provide a map image indicating the user's current location (e.g., the current location of the electronic device (101)) and / or the location of the restaurant as the second content (561).

[0101] Alternatively, the processor (120) may extract location information from metadata of the first content (563), extract map information (e.g., map content, map image content, etc.) corresponding to the extracted location information from a map application, and then provide the extracted map information as the second content (561). Additionally, the processor (120) may display a graphic UI element (567) such as an arrow indicating the direction in which a restaurant is located based on the current location of the electronic device (101). The processor (120) may display a graphic object that simply indicates the direction, or, as in the form of 3D navigation route guidance, may identify a floor or road area within the current image in a camera preview and display a route guidance graphic object (e.g., an arrow, a route guidance element) that allows the user to move to the corresponding area by overlaying it on the screen.

[0102] FIG. 6 is a diagram illustrating an example of adding an emotional tag to an image in an electronic device according to one embodiment.

[0103] Referring to FIG. 6, a processor (e.g., a processor (120) of FIG. 1) of an electronic device (e.g., an electronic device (101) of FIG. 1) according to an embodiment may display a first user interface (610) including an add tag menu (611) on a display (e.g., a display module (160) of FIG. 1) in an image (601). The first user interface (610) may display a first tag (e.g., Everland) and / or a second tag (e.g., Everland map, Everland QR admission ticket, Everland restaurant) related to the image (601). For example, the add tag menu (611) may be provided when a user input is generated to activate display of a tag or a graphic UI element (613) is selected. The add tag menu (611) may include items such as add tag, add link, or create.

[0104] When an add tag item is selected from an add tag menu (611), the processor (120) may provide a second user interface (630). The second user interface (630) may include a tag input area in which a tag can be input through user input (e.g., text, voice, etc.). The second user interface (630) may include a tag input item (631) to be added. When the tag input area or the tag input item (631) is touched, the processor (120) provides a keypad, and the user can input desired tag information through the keypad. According to one embodiment, when an add emotion tag item is selected from the tag input item (631), the processor (120) may provide a third user interface (650). The third user interface (650) may include a menu (651) including a designated emotion tag. In the third user interface (650), the user can select an emotion tag called 'excited' (653) from the designated emotion tag menu (651). When excitement (653) is selected, the processor (120) may provide a fourth user interface (670) with an emotion tag (671) called "excitement" added. The user may add a desired tag to the image (601). The added tag may be stored as metadata of the image (601).

[0105] According to one embodiment, when a user has experienced learning at a specific location (e.g., Everland), the processor (120) may collect content desired by the user using tags in images taken at the specific location (e.g., Everland) based on the operation of the present invention, and may generate content such as a report or diary related to the experiential learning using the collected content and data and provide the content to the user. For example, information linked using tags in the image and / or content type information (e.g., report, diary, video, journal, etc.) may be input to a generative AI model to generate content in a form desired by the user. The generative AI model may be a model trained to generate content based on multimodal input data based on various forms of data.

[0106] FIG. 7 is a flowchart (700) illustrating a method for adding and linking tags to an electronic device according to one embodiment.

[0107] Referring to FIG. 7, in operation 701, a processor (e.g., processor 120 of FIG. 1) of an electronic device (e.g., electronic device 101 of FIG. 1) according to an embodiment may display a first graphical UI element that provides a function for adding a tag. The processor (120) may display the first graphical UI element together when a first tag or a second tag is displayed on an image (e.g., an original image). For example, the processor (120) may perform operation 701 at 407 of FIG. 4.

[0108] In operation 703, the processor (120) may detect a user input selecting the first graphical UI element. The user may touch (e.g., tap, long press) the first graphical UI element displayed on the image.

[0109] In operation 705, the processor (120) may display a second graphical UI element for inputting tag information in response to selection of the first graphical UI element. The second graphical UI element may include a tag addition menu or a keypad for tag input. The tag addition menu may include an item for adding a tag, adding a link, or creating a tag. The following operation may be exemplified by a case where the 'create' item is selected. For example, when the 'add tag' item is selected, at least one tag may be selected from among the specified tags by the user.

[0110] In operation 707, the processor (120) may receive tag addition information. The tag addition information may be directly input by the user via the keypad. That is, the tag addition information may be text input. However, depending on the embodiment, the tag addition information may include an image, video, or audio.

[0111] In operation 709, the processor (120) may generate a third tag related to a new image and tag additional information. A generative AI (e.g., a generative artificial intelligence system (200) of FIG. 2) included in the electronic device (101) may generate a new image (or content) and the third tag based on the original image and the tag generation information. The generative AI may analyze the original image and generate a new image and the third tag based on the original image analysis result and / or the text of the tag generation information. For example, the generative AI may generate only a portion of the original image related to the tag additional information and overlay it on the original image to generate a new image. Alternatively, the generative AI may generate the entire image including the portion of the original image related to the tag additional information as a new image.

[0112] Alternatively, the processor (120) may transmit the original image and the tag generation information to an intelligent server (e.g., server (108) of FIG. 1) including a generative artificial intelligence system (200) to request generation of a tag, and receive the third tag from the server (108) based on the request. The processor (120) may transmit coordinate information of an area corresponding to the sky (e.g., a masking area) in the original image to the server (108), and receive an image for the partial area from the server (108) to provide a new image to the original image. Alternatively, the processor (120) may transmit the original image and the tag generation information to the server (108), and receive the new image from the server (108).

[0113] In operation 711, the processor (120) may display the third tag on the generated image (e.g., a new image). The processor (120) may display the third tag differently from other tags (e.g., a first tag or a second tag). When storage of the generated image is requested, the processor (120) may store the generated image in association with the original image. Alternatively, the processor (120) may store location information where the new image is stored in the metadata of the original image.

[0114] FIGS. 8A and 8B are diagrams illustrating an example of generating tags and content in an electronic device according to one embodiment.

[0115] Referring to FIG. 8A, a processor (e.g., the processor (120) of FIG. 1) of an electronic device (e.g., the electronic device (101) of FIG. 1) according to an embodiment may display a first user interface (810) on which a first tag (811) or a second tag (813) is displayed on an image (801) on a display (e.g., the display module (160) of FIG. 1). The first tag (811) may be generated based on an object (e.g., a panda) included in the image (801) displayed on the display module (160) and / or location information (e.g., Everland) of the image (801). Alternatively, the second tag (813) may be linked to a function of a content or application related to the image (801) based on the first tag (811).

[0116] According to one embodiment, when a second tag (813) is selected in the first user interface (810), the processor (120) may provide a second user interface (820). The second user interface (820) may include a function menu (821) of an application related to the second tag (813). When a create (823) item is selected in the function menu (821) of the application, the processor (120) may provide a third user interface (830). The third user interface (830) illustrates an example of receiving a request (831) from a user. The request (831) may be received through a keypad displayed in the image (801) or may be a voice input through a microphone (e.g., an audio output module (155) of FIG. 1) converted into text.

[0117] Referring to FIG. 8B, the processor (120) may provide a fourth user interface (850) that identifies an object (851) in an image (801) based on a request (831). The processor (120) may display the identified object (851) to be distinct from other areas within the image. The processor (120) may generate a new object (861) (or a new image) based on the request (831) and the object (851). The generative AI model may generate a new object (861) (or a new image) and a third tag (863) based on an area of ​​the object (861) within the image (801) and the request (831). The processor (120) may provide a fifth user interface (860) that includes the third tag (863) and the new object (861). The fifth user interface (860) may include a third tag (863) and a new object (861) in the image (801).

[0118] When an area where no tags are displayed is selected in the fifth user interface (860), the processor (120) may provide a sixth user interface (870). The sixth user interface (870) may display a first tag (e.g., Everland Panda), a second tag (e.g., Fubao), and a third tag (e.g., Baby Fubao) on the original image (801). The third tag may be displayed in the same manner as the first and second tags, indicating that the third tag is deactivated, unlike what is displayed in the fifth user interface (860). When an area where no tags are displayed is selected, the processor (120) may delete a new image (e.g., a new object (861)) and display the original image (601) on the screen.

[0119] According to one embodiment, when a user has experienced learning at a specific location (e.g., Everland), the processor (120) can collect content desired by the user using tags within images taken at the specific location (e.g., Everland), and can use the collected content and data to create content such as a report or diary related to the experiential learning and provide it to the user.

[0120] FIG. 9 is a flowchart (900) illustrating a second tag generation method in an electronic device according to one embodiment.

[0121] Referring to FIG. 9, in operation 901, a processor (e.g., the processor 120 of FIG. 1) of an electronic device (e.g., the electronic device 101 of FIG. 1) according to an embodiment may determine feature information based on a main object and / or location information of an image. The image may be displayed on a display (e.g., the display module (160) of FIG. 1). The feature information may be a context of the image, describing the main object or indicating the user's intention. When a first tag displayed together with the image is selected, the processor (120) may perform operation 901. The first tag may be generated based on an object identified from the image and / or location information of the image.

[0122] In operation 903, the processor (120) may search for an image (or content) based on the feature information. The processor (120) may search for an image related to an image displayed on the display module (160) based on the feature information. Here, searching for an image may refer to searching for content such as an image or video. The processor (120) may search for content stored in a memory of the electronic device (101) (e.g., memory (130) of FIG. 1) or a cloud server connected to the electronic device (101) (e.g., server (108) of FIG. 1).

[0123] In operation 905, the processor (120) may group the searched images by tag. The processor (120) may generate or extract tags based on metadata of each of the searched images, and group (or cluster) images having the same tag.

[0124] In operation 907, the processor (120) may search for a function of the application based on the feature information. The function of the application may include a searched page, a URL including a specific image, and a specific function of a specific application. Although the operations of searching for an image, grouping images, and searching for a function of the application are illustrated as separate operations in the drawing, the operations of searching for an image, grouping images, and searching for a function of the application may be performed at once. That is, operations 903, 905, and 907 may be performed as a single operation. According to one embodiment, the processor (120) may learn a user's usage pattern of the electronic device (101) and search for content related to the image using a key feature keyword based on the user's preference. Alternatively, the processor (120) may search for content related to the image using a key feature keyword based on a function usage history of the application or an input keyword history from the location information of the image.

[0125] In operation 909, the processor (120) may generate a second tag that links the image and the function of the application. The processor (120) may generate the second tag based on an image related to the image among the grouped images. Additionally, the processor (120) may generate the second tag in relation to the function of the searched application.

[0126] In operation 911, the processor (120) may display the second tag on the image. In operation 911, the tag displayed on the image may include the first tag and the second tag.

[0127] FIGS. 10 and 11 are diagrams illustrating an example of adding tag information to an image in an electronic device according to one embodiment.

[0128] Referring to FIG. 10, a processor (e.g., a processor (120) of FIG. 1) of an electronic device (e.g., an electronic device (101) of FIG. 1) according to an embodiment may detect a user input (1011) in an image (1001) (or video) displayed on a display (e.g., a display module (160) of FIG. 1). A first user interface (1010) may be a first tag (1013) displayed on an image (1001). The first tag (1013) may be a location name of the image (1001). The original image (1001) is an aquarium image taken from a distance, and if the user has not performed a separate pinch zoom operation, the processor (120) can transmit the original image (1001) to a generative AI included in the electronic device (e.g., the generative artificial intelligence system (200) of FIG. 2) or an intelligent server (e.g., the generative artificial intelligence system (200) of FIG. 2) to perform scene analysis. The processor (120) can obtain only rough information, such as the situation and location of the original image (1001), from the generative AI. The generative AI can generate a first tag from a result obtained through Retrieval Augmented Generation (RAG) based on data learned in advance or location information of metadata of an image taken by the user. For example, if there is no prior information about the original image (1001), the generative AI can search for the location of the original image (1001) on an external server (online) based on metadata (e.g., GPS information) of the original image (1001) and identify that the location is 'Churaumi Aquarium'.

[0129] The user input (1011) may be to zoom in / out the image (1001). If the original image (1001) is zoomed in through a pinch-zoom operation, segmentation may be performed using a segmentation AI model learned in advance for object recognition and classification. The processor (120) may display a second user interface (1030) based on the user input (1013) for zooming in. The processor (120) may provide information that is tagged differently depending on the change in the size of the original image (1001). The second user interface (1030) may be to enlarge the location where the user input is detected in the original image (1001). The generative AI may generate information called 'whale shark' as a first tag or a second tag (1033) through the image (1031) zoomed in through pinch-zoom and the location coordinates of the whale in the original image (1001). The second user interface (1030) may display a zoomed-in image (1031) and a first tag or a second tag (1033).

[0130] When the second tag (1033) is selected, the processor (120) may provide a third user interface (1050). The processor (120) may search for whale sharks online based on the second tag (1033). Alternatively, the processor (120) may provide a function menu (1051) of an application related to the second tag (1033) and select a "Create" item from the function menu (1051) of the application. The third user interface (1050) may include text (1053) corresponding to a user input requesting additional information about whale sharks from the user through a "Create" button of the function menu (1051) of the application. The text (1053) may be a text converted from a voice requesting additional information about whale sharks through a voice assistant application. The text (1053) may be displayed as a graphical UI element in the form of a speech bubble around the second tag (1033) selected by the user.

[0131] The generative AI can generate detailed information about a whale shark based on a zoomed-in image (1031) and text (1053). The processor (120) can provide a fourth user interface (1070) including the detailed information (1071). While the detailed information (1071) is displayed as text in the fourth user interface (1070), the detailed information (1071) can also include images or videos related to the text as well as text. For example, a user can select the tag "whale shark" and input a voice command or text such as "Show me a video of the whale shark's growth process" through a voice assistant application. The generative AI can generate and provide a video of the whale shark's growth process from a juvenile state to an adult based on the user input. The processor (120) can transmit the user input and the object area (whale shark) within the image to the generative AI, thereby preventing the generative AI from generating a video of the whale shark's growth process of a different species or habitat.

[0132] Detailed information (1071) may be stored together with the original image (1001) or the zoomed-in image (1031) at the user's request. The detailed information (1071) may be stored as metadata of the original image (1001), or may be stored in a separate storage location, and the storage location where the detailed information (1071) is stored may be stored in the metadata of the original image (1001). Accordingly, the present invention may include various information (e.g., tags, detailed information) added by the user in the original image (1001).

[0133] Referring to FIG. 11, a processor (e.g., a processor (120) of FIG. 1) of an electronic device (e.g., an electronic device (101) of FIG. 1) according to an embodiment may provide a first user interface (1110) including a second tag (1113) in an enlarged image (1101). The processor (120) may detect a user input (1111) for zooming out in the first user interface (1110). The processor (120) may display a second user interface (1130) based on the user input (1111) for zooming out. The second user interface (1130) may be an original image (1101) in which a first tag (1131) and a second tag (1133) are displayed. When the second tag (1133) is selected, the processor (120) may display a third user interface (1150). The third user interface (1150) may include detailed information (1151) related to the second tag (1153). Since the detailed information added at the user's request is included as metadata of the original image (1101), when the second tag (1033) is selected, the processor (120) may provide content or application functions related to the second tag (1133). The detailed information (1151) may be displayed as content related to the second tag (1135).

[0134] When a user input for zooming out on an enlarged image (1101) is detected, a second tag (1153) acquired during the zoom-in process and detailed information (1151) related to the second tag may be displayed next to the recognized object together with the first tag of the original image (1001). The processor (120) may display a graphic UI element (e.g., an AI assistant mark) to indicate that the second tag (1131) was generated through the generative AI. The detailed information (1151) acquired through the generative AI may be provided with a function to be searched separately by classifying it when performing a search in the memory of the electronic device (101) (e.g., the memory (130) of FIG. 1), thereby preventing the generative AI from having to request necessary information again when searching data in the future.

[0135] In addition, the processor (120) can provide a clustering result that is more improved than the existing image-based clustering by clustering the detailed information (1151) based on tags through the second tag (1133). For example, in the case of the current image-based clustering, it may be difficult to analyze various correlations between images during the clustering process because the clustering is performed limited to the location such as an aquarium, the shooting time, or the objects in the original image (1001). However, when the clustering is performed based on the second tag (1133) or the detailed information (1151) related to the second tag (1133), clustering can be performed based on the correlations such as the relationship between contents included in the data provided by the generative AI (e.g., education, document writing, etc.), the relationship between tags in the image (e.g., deep-sea fish [whale shark-blue whale-fin whale]), etc.

[0136] The processor (120) can generate and provide content in a content format (e.g., report, experiential learning log, diary, report) selected by the user by using the first tag, the second tag, and the functions of the content and application linked to each tag included in the original image (1001).

[0137] FIGS. 12 to 14 are drawings illustrating an example of utilizing an image tag in an electronic device according to one embodiment.

[0138] Referring to FIG. 12, a first user interface (1210) may display an image (1211) to which a 'dynamic image tagging' function is applied through a widget (e.g., a gallery application widget) of a home screen. According to an embodiment, a processor (e.g., a processor (120) of FIG. 1) of an electronic device (e.g., an electronic device (101) of FIG. 1) may display a second user interface (1230) on a display (e.g., a display module (160) of FIG. 1) when an image (1211) of a widget is selected (e.g., a user input for moving to an image detail display page). The second user interface (1230) may be an execution screen of a gallery application and may include an original image (1201) and various tags (1231) added to the original image.

[0139] The processor (120) may provide a third user interface (1250) when a second tag (1231) (e.g., #clear weather tag with an AI generation mark) is selected in the second user interface (1230) to which an image edited by a generative AI of the original image (1201) is linked. The third user interface (1250) may have a graphic effect (e.g., change in border color of a graphic UI element) applied to the graphic UI element (1251) of the selected tag to indicate a selected state. The third user interface (1250) may be an example in which the display area of ​​the original image (1201) is changed to an edited image and displayed when a tag is selected.

[0140] The fourth user interface (1270) may include an image (1271) linked to a selected second tag (e.g., #EverlandQRTicket) when a different second tag is selected from the original image (1201). When a different second tag is selected, the edited image (1251) displayed in the area of ​​the original image (1201) may be changed back to the original image and displayed, and multiple images (1271) linked to the different second tags selected by the user may be displayed.

[0141] The fifth user interface (1290) shows an example in which tag information displayed in the original image (1201) disappears when a graphic UI element (1273) displayed in the upper right corner of the original image (1201) in the fourth user interface (1270) is selected.

[0142] Referring to FIG. 13, the first user interface (1310) may be an embodiment in which a first tag and a second tag are displayed on an image (1301), and when a second tag (1311) (e.g., #EverlandQRTicket) is selected, multiple images (1313) (e.g., two QR ticket images for each of two people) linked to the second tag (1311) are displayed on the screen. For example, the first user interface (1310) may display the first QR ticket image (1313) in the front, and a user input (1315) (e.g., a touch and drag in the left direction) for moving to another QR ticket image may be detected. The processor (120) may provide a second user interface (1330) in which an effect of the first QR ticket image (1331) moving to the left is displayed based on the user input (1315). In the second user interface (1330), the first QR ticket image (1331) may be moved and a portion of the second QR ticket image (1333) may be displayed. In the third user interface (1350), the first QR ticket image (1331) may be moved to the back and displayed in front of the second QR ticket image (1351) that was located at the back.

[0143] Referring to FIG. 14, the first user interface (1410) illustrates an example in which a user gesture (1401) is detected in a first QR ticket image (1411) while multiple images are displayed. Depending on the user gesture (1401), the second user interface (1430) may display the first QR ticket image (1411) enlarged and displayed in a large size like the second QR ticket image (1431). The third user interface (1450) illustrates an example in which a More item (1451) is selected while multiple images linked to the second tag are displayed. The fourth user interface (1470) may be an embodiment in which a list of all images (1471) linked to the second tag is overlaid and displayed on the image when the More item (1451) is selected.

[0144] An operating method of an electronic device (101) according to an embodiment of the present disclosure may include an operation of identifying an object included in an image displayed on a display of the electronic device, an operation of generating a first tag based on location information of the identified object and / or the image, an operation of displaying the generated first tag on the image, an operation of generating a second tag linked to a function of a content or application related to the image based on at least one of the location information of the image, the identified object, and the first tag when the first tag is selected, an operation of displaying the generated second tag on the image, and an operation of providing a function of a content or application related to the image based on selection of the second tag.

[0145] The operation of generating the second tag may include an operation of determining feature information based on a representative object of the image and / or location information of the image, an operation of searching for content and / or a function of an application based on the feature information, an operation of grouping the searched content by tag, and an operation of generating the second tag linked to the grouped content and the function of the searched application.

[0146] The operation of generating the second tag may include an operation of searching for content stored in the memory or a server connected to the electronic device based on the context of the image, an operation of grouping the searched content by tag, and an operation of generating a representative tag of the grouped content as the second tag.

[0147] The method may further include an operation of displaying a first graphic UI element that provides a function for adding a tag when the first tag is displayed, an operation of displaying a second graphic UI element for inputting tag information when the first graphic UI element is selected, an operation of receiving tag addition information from a user through the second graphic UI element, an operation of generating a new image and a third tag related to the tag addition information through a generative AI model based on the tag addition information and information related to the image, and an operation of displaying the third tag on the generated image.

[0148] The above method may further include an action of displaying an image related to the third tag when the third tag is selected.

[0149] The method may further include an operation of providing a function of content or an application related to the selected second tag when the second tag is selected.

[0150] The method may further include an action of displaying a graphic UI element related to tag display on the image, and an action of deleting the first tag or the second tag displayed on the image when the graphic UI element is selected.

[0151] The method includes an operation of searching for content related to the image by using the first tag as a feature keyword related to the image, wherein the feature keyword may be a keyword specified by location information within the electronic device or may be obtained by using an AI model trained to output a major feature keyword according to location information.

[0152] The method may include an operation of learning a user's usage pattern of the electronic device and searching for content related to the image with a key feature keyword based on the user's preference, or an operation of identifying a history of function usage of an application or a history of input keywords at a location where the image was taken, and searching for content related to the image with a key feature keyword based on the identified history of function usage of the application or the history of input keywords.

[0153] The method may further include an action of distinguishing and displaying tags selected by the user and tags not selected by the user on the image.

[0154] The various embodiments of the present invention disclosed in this specification and drawings are merely specific examples presented to facilitate easy explanation of the technical content of the present invention and aid understanding thereof, and are not intended to limit the scope of the present invention. Therefore, the scope of the present invention should be interpreted to include all modifications or variations derived based on the technical concept of the present invention, in addition to the embodiments disclosed herein.

Claims

1. In an electronic device (101), Display (160), Memory (130) for storing instructions; and A processor (120) is included, and the instructions, when executed by the processor, cause the electronic device to: Identifying an object contained in an image displayed on the above display, Generating a first tag based on the location information of the identified object and / or the image, Displaying the first tag generated above on the image, When the first tag is selected, a second tag is generated that is linked to a function of a content or application related to the image based on the location information of the image, the identified object, and at least one of the first tags, Display the second tag generated above on the image, An electronic device that provides a function of content or application related to the image based on selection of the second tag.

2. In the first paragraph, when the instructions are executed by the processor, the electronic device, Determine feature information based on the representative object of the image and / or location information of the image, Search for content and / or application features based on the above characteristic information, Group the searched content by tags, An electronic device that generates a second tag linked to the grouped content and the searched application's function.

3. In the first paragraph, when the instructions are executed by the processor, the electronic device, Retrieving content stored in the memory or a server connected to the electronic device based on the context of the image; Group the searched content by tags, An electronic device that generates a representative tag of the above grouped content as a second tag.

4. In the first paragraph, when the instructions are executed by the processor, the electronic device, When the first tag is displayed, a first graphic UI element providing a function for adding tags is displayed, When the first graphic UI element is selected, a second graphic UI element for entering tag information is displayed, Receive additional tag information from the user through the second graphic UI element, Generating a new image and a third tag related to the tag additional information through a generative AI model based on the tag additional information and information related to the image, An electronic device that displays the third tag on the generated image.

5. In the fourth paragraph, when the instructions are executed by the processor, the electronic device, An electronic device that displays an image related to the third tag when the third tag is selected.

6. In the first paragraph, when the instructions are executed by the processor, the electronic device, An electronic device that provides a function of content or application related to the selected second tag when the second tag is selected.

7. In the first paragraph, when the instructions are executed by the processor, the electronic device, Displaying graphic UI elements related to tag display on the image above, An electronic device that deletes the first tag or the second tag displayed on the image when the graphic UI element is selected.

8. In the first paragraph, when the instructions are executed by the processor, the electronic device, Search for content related to the image by using the first tag as a feature keyword related to the image, An electronic device wherein the above-mentioned feature keywords are keywords specified for each location information within the electronic device, or are acquired using an AI model learned to output major feature keywords according to location information.

9. In the first paragraph, when the instructions are executed by the processor, the electronic device, Learning the usage patterns of the user of the electronic device to search for content related to the image with key feature keywords based on the user's preferences, or An electronic device that identifies the history of application function usage or input keyword history at the location where the image was taken, and searches for content related to the image using a key feature keyword based on the identified application function usage history or input keyword history.

10. In the first paragraph, when the instructions are executed by the processor, the electronic device, An electronic device that displays tags selected by a user and tags not selected by the user on the image.

11. In the operating method of an electronic device (101), An action of identifying an object included in an image displayed on a display of the electronic device; An operation of generating a first tag based on location information of the identified object and / or the image; An action of displaying the generated first tag on the image; When the first tag is selected, an operation of generating a second tag linked to a function of a content or application related to the image based on location information of the image, the identified object, and at least one of the first tags; An operation of displaying the generated second tag on the image; and A method comprising an action of providing a function of content or an application related to the image based on selection of the second tag.

12. In the 11th paragraph, the operation of generating the second tag is: An operation of determining feature information based on a representative object of the image and / or location information of the image; An action to retrieve content and / or application functions based on the above characteristic information; An action of grouping the searched contents by tags; and A method comprising an action of generating the second tag linked to the grouped content and the function of the searched application.

13. In the 11th paragraph, the operation of generating the second tag is: An action of retrieving content stored in the memory or a server connected to the electronic device based on the context of the image; An action of grouping the searched contents by tags; and A method comprising an action of generating a representative tag of the above grouped content as a second tag.

14. In paragraph 11, An action of displaying a first graphic UI element that provides a function for adding a tag when the first tag is displayed; When the first graphic UI element is selected, an action of displaying a second graphic UI element for entering tag information; An action of receiving additional tag information from a user through the second graphic UI element; An operation of generating a new image and a third tag related to the tag additional information through a generative AI model based on the tag additional information and information related to the image; and A method further comprising an action of displaying the third tag on the generated image.

15. In paragraph 14, A method further comprising an action of displaying an image related to the third tag when the third tag is selected.

Images