Method and electronic device for supporting artificial intelligence-based ai content service, and recording medium therefor

Abstract

An electronic device according to one embodiment comprises a display, a processor, and a memory for storing instructions executable by the processor, wherein the instructions enable, on the basis of an AI content generation request, the electronic device to: identify an object included in first content displayed on the display; acquire first information related to the object and / or the first content, and second information related to the electronic device or a user; generate a prompt for an input to a generative artificial intelligence model on the basis of at least one of the first content, the first information and the second information; and generate second content related to the first content by using generative artificial intelligence (AI) using the generated prompt as an input.

Description

Method and electronic device supporting AI content service based on artificial intelligence, and recording medium thereof

[0001] The present invention relates to a method and an electronic device for supporting AI content services using generative artificial intelligence, and a recording medium thereof.

[0002] With the recent rise in interest in online education environments, interest in online education systems utilizing electronic devices is also growing. Online education systems offer the advantages of overcoming time and space constraints and offering low-cost education. They also offer the potential to provide customized services tailored to each learner's individuality and ability.

[0003] Current online education systems digitize pre-acquired or pre-existing educational materials, filtering and organizing these digitized materials to provide educational content tailored to the user's needs. While online education systems can leverage existing materials to select and provide content tailored to learner characteristics (e.g., age, learning level, etc.), they can struggle to provide new or personalized content not found in existing materials.

[0004] Artificial Intelligence (AI) technology is rapidly developing. In particular, generative AI technology is rapidly growing as AI capabilities evolve. Generative AI refers to AI technology that utilizes machine learning and deep learning to generate similar content based on existing content, such as text, audio, and / or images.

[0005] Various embodiments seek to provide methods and devices that can provide optimized, customized education to learners by using generative AI to generate new, personalized AI content based on the user's interests, moving away from standardized existing data.

[0006] Various embodiments propose methods and devices that can improve responsiveness to camera zoom performance.

[0007] However, the problem to be solved in this disclosure is not limited to the problem mentioned above, and may be expanded in various ways without departing from the spirit and scope of this disclosure.

[0008] An electronic device according to one embodiment may include a display, a processor, and a memory storing instructions executable by the processor. The instructions according to one embodiment may cause the electronic device to identify an object included in first content displayed on the display based on an AI content generation request. The instructions according to one embodiment may cause the electronic device to obtain first information related to at least one of the object or the first content, and second information related to the electronic device or a user. The instructions according to one embodiment may cause the electronic device to generate a prompt for input of a generative artificial intelligence model based on at least one of the first content, the first information, and the second information. The instructions according to one embodiment may cause the electronic device to generate second content related to the first content using generative artificial intelligence (AI) with the generated prompt as an input.

[0009] According to one embodiment, a method for supporting AI content services in an electronic device may include an operation for identifying an object included in first content displayed on the display based on an AI content generation request. According to one embodiment, a method for supporting AI content services in an electronic device may include an operation for obtaining first information related to at least one of the object or the first content, and second information related to the electronic device or a user. According to one embodiment, a method for supporting AI content services in an electronic device may include an operation for generating a prompt for input of a generative artificial intelligence model based on at least one of the first content, the first information, and the second information. According to one embodiment, a method for supporting AI content services in an electronic device may include an operation for generating second content related to the first content using generative artificial intelligence (AI) with the generated prompt as an input.

[0010] A non-transitory computer-readable medium storing instructions according to one embodiment may include instructions that, when executed by a processor of an electronic device, cause the processor to perform an operation of identifying an object included in first content displayed on the display based on an AI content generation request. The computer-readable medium according to one embodiment may include instructions that cause the processor to perform an operation of obtaining first information related to at least one of the object or the first content and second information related to the electronic device or a user. The computer-readable medium according to one embodiment may include instructions that cause the processor to generate a prompt for input of a generative artificial intelligence model based on at least one of the first content, the first information, and the second information. The computer-readable medium according to one embodiment may include instructions that cause the processor to generate second content related to the first content using generative artificial intelligence (AI) with the generated prompt as an input.

[0011] An electronic device according to one embodiment may include a computer-readable recording medium having recorded thereon a program for implementing an AI content service support method.

[0012] Electronic devices, methods, and recording media thereof according to various embodiments can generate personalized AI content by utilizing content selected by a user from among content displayed on a display of the electronic device, and provide customized education or learning services to the user by utilizing the generated AI content.

[0013] The effects that can be obtained from the present disclosure are not limited to the effects mentioned above, and various effects that are not mentioned can be provided, which can be directly or indirectly understood by a person having ordinary skill in the art to which the present disclosure belongs, from the description below.

[0014] In connection with the description of the drawings, the same or similar reference numerals may be used for identical or similar components. Furthermore, the above-described contents and other aspects, features, and advantages related to specific embodiments of the present disclosure will become more apparent from the following detailed description taken in conjunction with the drawings.

[0015] FIG. 1A is a block diagram of an electronic device within a network environment, according to one embodiment.

[0016] FIG. 1b illustrates an exemplary configuration of a generative AI (artificial intelligence) system according to various embodiments.

[0017] FIG. 2 illustrates exemplary configurations related to generative AI of an electronic device according to various embodiments.

[0018] FIG. 3 illustrates an exemplary method for generating AI content for an electronic device according to various embodiments.

[0019] FIG. 4 illustrates an exemplary method for operating an AI content service of an electronic device according to various embodiments.

[0020] FIG. 5 illustrates an exemplary method for providing AI content services based on artificial functions of an electronic device according to various embodiments.

[0021] FIG. 6 illustrates examples of a learning setting user interface screen of AI content of an electronic device according to various embodiments.

[0022] FIG. 7 illustrates examples of user interface screens for generating AI content of an electronic device according to various embodiments.

[0023] FIGS. 8A to 8D illustrate user display screens that support AI content services of electronic devices according to various embodiments.

[0024] FIG. 9 illustrates exemplary screens of a user interface for collecting an AI content DB of an electronic device according to various embodiments.

[0025] FIG. 10 illustrates exemplary screens of a user interface for collecting content DB of an electronic device and generating AI content according to various embodiments.

[0026] FIG. 11 illustrates exemplary screens of a user interface supporting AI content services of an electronic device according to various embodiments.

[0027] FIG. 12 illustrates an exemplary method for supporting AI content services of an electronic device according to various embodiments.

[0028] Electronic devices according to the 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 disclosed in this document are not limited to the aforementioned devices.

[0029] FIG. 1A is a block diagram of an electronic device (101) within a network environment (100), according to one embodiment.

[0030] Referring to FIG. 1A, 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). In one embodiment, the electronic device (101) may communicate with the electronic device (104) via the server (108). According to one embodiment, the electronic device (101) may include a processor (120), a memory (130), an input module (150), an audio output module (155), a display module (160), an audio module (170), a sensor module (176), an interface (177), a connection terminal (178), a haptic module (179), a camera module (180), a power management module (188), a battery (189), a communication module (190), a subscriber identification module (196), or an antenna module (197). In some embodiments, the electronic device (101) may omit at least one of these components (e.g., the connection terminal (178)), or may have one or more other components added. In some embodiments, some of these components (e.g., the sensor module (176), the camera module (180), or the antenna module (197)) may be integrated into one component (e.g., the display module (160)).

[0031] The processor (120) may include various processing circuits and / or multiple processors. For example, the term "processor" as used in this document and claims may refer to various processing circuits including at least one processor, one or more of which may be configured to perform various functions described herein, either individually or in a distributed manner. When "processor," "at least one processor," and "one or more processors" are described herein as being configured to perform multiple functions, this includes, but is not limited to, situations where one processor performs some of the listed functions and other processor(s) perform the remaining functions, and where a single processor performs all of the listed functions. Furthermore, at least one processor may include a combination of processors that perform the listed / disclosed functions in a distributed manner. At least one processor may execute program instructions to achieve or perform various functions. 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.

[0032] The auxiliary processor (123) may control at least a portion of functions or states associated with at least one component (e.g., a display module (160), a sensor module (176), or a communication module (190)) of the electronic device (101), for example, on behalf of the main processor (121) while the main processor (121) is in an inactive (e.g., sleep) state, or together with the main processor (121) while the main processor (121) is in an active (e.g., application execution) state. In one embodiment, the auxiliary processor (123) (e.g., an image signal processor or a communication processor) may be implemented as a part of another functionally related component (e.g., a camera module (180) or a communication module (190)). In one embodiment, the auxiliary processor (123) (e.g., a neural network processing unit) may include a hardware structure specialized for processing artificial intelligence models. The artificial intelligence models may be generated through machine learning. This learning can be performed, for example, in the electronic device (101) itself where artificial intelligence is performed, or can be performed through a separate server (e.g., server (108)). The learning algorithm can include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but is not limited to the examples described above. The artificial intelligence model can include multiple artificial neural network layers.The artificial neural network may be one of a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), a deep Q-network, or a combination of two or more of the above, but is not limited to the examples described above. In addition to, or alternatively to, a hardware structure, an artificial intelligence model may include a software structure.

[0033] 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).

[0034] 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).

[0035] 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).

[0036] 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.

[0037] The display module (160) can visually provide information to an external party (e.g., a user) of the electronic device (101). The display module (160) may include, for example, a display, a holographic device, or a projector and a control circuit for controlling the device. In one embodiment, the display module (160) may include a touch sensor configured to detect a touch, or a pressure sensor configured to measure the intensity of a force generated by the touch.

[0038] 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).

[0039] 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.

[0040] 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.

[0041] 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).

[0042] A 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. In one embodiment, the haptic module (179) can include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

[0043] 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.

[0044] 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, for example, as at least a part of a power management integrated circuit (PMIC).

[0045] 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.

[0046] 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).

[0047] 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.

[0048] The antenna module (197) can transmit or receive signals or power to or from an external device (e.g., an external electronic device). In one embodiment, the antenna module (197) may include an antenna including a radiator formed of a conductor or a conductive pattern formed on a substrate (e.g., a PCB). In one embodiment, the antenna module (197) may include a plurality of antennas (e.g., an array antenna). In this case, at least one antenna suitable for a communication method used in a communication network, such as the first network (198) or the second network (199), may be selected from the plurality of antennas by, for example, the communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device through the selected at least one antenna. In some embodiments, in addition to the radiator, another component (e.g., a radio frequency integrated circuit (RFIC)) may be additionally formed as a part of the antenna module (197).

[0049] In one embodiment, the antenna module (197) may form a mmWave antenna module. In one embodiment, the mmWave antenna module may include a printed circuit board, an RFIC disposed on or adjacent a first side (e.g., a bottom side) of the printed circuit board and capable of supporting a designated high-frequency band (e.g., a mmWave band), and a plurality of antennas (e.g., an array antenna) disposed on or adjacent a second side (e.g., a top side or a side side) of the printed circuit board and capable of transmitting or receiving signals in the designated high-frequency band.

[0050] 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)).

[0051] 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.

[0052] An electronic device (101) according to one embodiment may support a generative AI (or on-device AI) function / service. The generative AI function may refer to a technology that generates new content based on previously learned data and can generate new types of AI content by utilizing given input data or information. For example, generative AI may generate new content based on previously learned data and may also be applied to operations such as improving image quality or editing videos.

[0053] An electronic device (101) according to one embodiment may support a generative AI function (or AI service) in conjunction with a server (108). At least one of the electronic device (101) or the server (108) according to one embodiment may include the configuration of the generative AI system illustrated in FIG. 1B.

[0054] For example, FIG. 1B illustrates the configuration of a generative AI system according to one embodiment. As illustrated in FIG. 1B, the generative AI system may include a user interface (10100), an AI framework (10200), a generative AI model (10300), an application and service component (10400), and a database component (10500).

[0055] A user interface (e.g., a user query / response interface) (10100) according to one embodiment may receive a user query. The user query input may be in the form of natural language, images, and videos. The user interface (10100) may transmit not only data regarding the user query input but also context information to the AI ​​framework (10200). The context information may include various additional information at the time of user input. In addition, the user query input may be in a form that mixes the above-described natural language, images, sounds, and context information. In addition, the user query input may be in a non-natural language form that does not generate natural language, such as a menu selection (e.g., a creation request or a modification request). The user interface (10100) may output the results of a generative artificial intelligence system to the user. The output may be in the form of natural language or specific content, and may also be provided in the form of an action requested by the user.

[0056] An AI framework (10200) according to one embodiment can receive a user query input and coordinate and control each component necessary to perform the user's intention based on the user's query input. The AI ​​framework (10200) can include a prompt design component (10210), an application and plug-in management component (APIs / Plugins Management component) (10230), and an output modification component (10250).

[0057] A user query or action entered in a user interface (10100) according to one embodiment may be transmitted to a prompt design component (10210). The prompt design component (10210) may be used to generate prompts suitable for input into a large language model (LLM) or a large multimodal model (LMM). The prompt design component (10210) 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 (10210) may access a database component (10500) (e.g., a knowledge component) containing user preference data, a prompt library, and prompt examples to generate prompts and pass them to the large language model (LLM) or the large multimodal model (LMM).

[0058] According to one embodiment, the application and plugin management component (10230) can communicate with external information when there is a request for additional information when passing user input as input to a generative model. The application and plugin management component (10230) establishes a channel for communicating with the external application and service component (10400) (e.g., AI Interface) through an application programming interface (API), thereby enabling access to various data sources. In addition, the application and plugin management component (10230) can request an action through the API to perform a final user query rather than an intermediate result when the application or service needs to perform the action. Information obtained from an external source can be passed as input to the generative model along with the user input.

[0059] An output modification component (10250) according to one embodiment can fine-tune the output of a generative model. For example, the output modification component (10250) can verify that content generated through a language model (LLM) or a large-scale multi-modal model (LMM) is not irrelevant, does not contain biased content, or does not contain harmful content. In addition, the output modification component (10250) can determine to what extent the content matches the result desired by the user and can perform additional processing if necessary. Additionally, the output modification component (10250) can configure and provide hints to the user to avoid undesired output.

[0060] A generative AI model (10300) according to one embodiment generally refers to an artificial intelligence neural network that generates new types of data based on user input information. Representative examples of image-generating models include generative adversarial networks (GANs) and variational autoencoders (VAEs). For example, a generative AI model may be a Diffusion-based generative model that uses VAE and a Transformer structure. Furthermore, a language-generating model may refer to a model trained to statistically generate the most appropriate output based on input values. Among generative AI models (10300), language-generating models may be, for example, models such as CHAT-GPT 3 and CHAT-GPT 4. As another example, large multimodal models (LMMs) may be models that recognize various types of data input, such as text, images, and voice, and generate corresponding new data.

[0061] According to one embodiment, the memory (130) may store instructions executable by the processor (120) or the electronic device (101). Such instructions may include control commands such as arithmetic and logical operations, data movement, or input / output that may be processed by the processor (120).

[0062] According to one embodiment, the processor (120) (e.g., including a processing circuit) may be operatively, functionally, and / or electrically connected to a display (e.g., a display module (160), a touchscreen display), and / or a memory (130). The processor (120) may be configured to perform operations or data processing related to control and / or communication of each component of the electronic device (101), and may be formed of one or more processors. The operations and data processing functions that the processor (120) may implement on the electronic device (201) are not limited, but in the present disclosure, various operations related to AI content services for education or learning may be processed. For example, the electronic device (101) according to one embodiment may be implemented to provide an AI content service by using a part of the AI ​​system of FIG. 1B.

[0063] Referring to FIG. 1A, an electronic device (101) according to one embodiment may include a display (e.g., a display module (160)), a processor (120), and a memory (130) that stores instructions executable by the processor (120). The terms "instructions may cause" and "processor configured to" in this document may be used interchangeably to refer to a situation where an instruction causes a task to be performed when executed, or where at least one processor is configured to individually and / or collectively perform a task. The instructions according to one embodiment may cause the electronic device (101) or the processor (120) to identify an object included in first content displayed on the display based on an AI content generation request. The instructions according to one embodiment may cause the electronic device (101) or the processor (120) to obtain first information related to at least one of the object or the first content, and second information related to the electronic device (101) or the user. The instructions according to one embodiment may cause the electronic device (101) or the processor (120) to generate a prompt for input of a generative artificial intelligence model based on at least one of the first content, the first information, and the second information. The instructions according to one embodiment may cause the electronic device (101) or the processor (120) to generate second content related to the first content and personalized using generative artificial intelligence (AI) with the generated prompt as input.

[0064] According to one embodiment, the second content may include artificial intelligence (AI) content, education content, or learning content.

[0065] The instructions according to one embodiment may cause the electronic device (101) or the processor (120) to extract at least one of object identification information, content description keywords analyzed for the first content or the identified object, and additional information based on metadata of the content as the first information.

[0066] The instructions according to one embodiment may cause the electronic device (101) or the processor (120) to extract at least one of user learning setting information, user app usage information, user profile information, and context information as the second information.

[0067] The instructions according to one embodiment may cause the electronic device (101) or the processor (120) to select and extract the second information associated with the first information.

[0068] The instructions according to one embodiment may be characterized in that the electronic device (101) or the processor (120) identifies the object by performing an operation for selecting the object included in the first content or by recognizing the object within the first content.

[0069] The instructions according to one embodiment may cause the electronic device (101) or the processor (120) to display the second content on a display.

[0070] According to one embodiment, the second content may include a content or object image, object identification information, a type of generated AI content, and a content description.

[0071] The instructions according to one embodiment may cause the electronic device (101) or the processor (120) to display the second content in the form of a pop-up window overlapping the first content or to display it in a foreground form.

[0072] The instructions according to one embodiment may cause the electronic device (101) or the processor (120) to display texts of the content by applying different visual effects so that the texts of the content are visually distinguished according to the source information when the source information of the content description is different.

[0073] The instructions according to one embodiment may enable the electronic device (101) or the processor (120) to obtain edit information regarding modified or changed AI content related to the second content or feedback information regarding learning results of the second content.

[0074] The instructions according to one embodiment may cause the electronic device (101) or the processor (120) to update the second content based on the acquired editing information or the feedback information.

[0075] Instructions according to one embodiment may cause the electronic device (101) or the processor (120) to display a second content creation item and a data collection item on at least a portion of the display based on selection of the first content displayed on the display, and to receive the AI ​​content creation request based on selection of the second content creation item or recognition of an object included in the first content.

[0076] In the description of the electronic device (101) according to the embodiments of the present invention disclosed below, the same reference numbers are given to components that are substantially the same as those disclosed in the embodiments disclosed in FIGS. 1A and 1B described above, and redundant descriptions of their functions may be omitted.

[0077] FIG. 2 illustrates exemplary configurations related to generative AI of an electronic device according to various embodiments.

[0078] Referring to FIG. 2, an electronic device (101) according to one embodiment may include components that support AI content services using generative AI. For example, a processor (120) of the electronic device (101) may include at least one of a DB management unit (210), a content data management unit (220), a personalized data management unit (230), an AI content type determination unit (240), a prompt generation unit (250), an AI content generation model unit (260), an AI content provision unit (270), and a feedback management unit (280), and each of these elements may include various circuits and / or executable program instructions.

[0079] According to one embodiment, the DB management unit (210) can control to manage and update a universal (common) content DB (211) and a personalized AI content DB (212). The DB management unit (210) can store educational contents created in advance or previously in the universal content DB (211). The DB management unit (210) can store or update AI contents (e.g., AI educational contents) created according to a user request in the personalized AI content DB (212). For example, the personalized AI content DB can include at least one of AI contents (or educational contents, second contents), content data (or first information), and personalized data (or second information).

[0080] According to one embodiment, the DB management unit (210) can store (or update) first information (e.g., analysis information (221), additional information (222)) transmitted from the content data management unit (220) and second information (e.g., user's learning setting information (231), user's app usage information (232), user profile information (233), and context information (234)) transmitted from the personalized data management unit (230) in the personalized AI content DB (212).

[0081] According to one embodiment, the DB management unit (210) may store images and / or analysis information of test papers or question papers that the user has solved directly in the personalized AI content DB (212).

[0082] According to one embodiment, the electronic device (101) may communicate with a server to update a universal content DB (211) or transmit AI contents stored in a personalized AI content DB (212) to the server.

[0083] According to one embodiment, the content data management unit (or first information management unit) (220) can extract first information (e.g., analysis information (221) of content or object and / or additional information (222) based on metadata of content). The content data management unit (220) can transmit the first information to the prompt generation unit (250) or to the DB management unit (210). The analysis information (221) can include at least some of object identification information and content description keywords. The additional information (222) can mean information based on metadata of content or object (e.g., date, time, location, etc.).

[0084] Although not illustrated in the drawing, the content information management unit (220) may further include a content analysis unit (not illustrated). The content analysis unit may analyze designated content (e.g., content selected by user input) to recognize at least one object within the content and confirm identification information of the object.

[0085] According to one embodiment, the personalized data management unit (or second information management unit) (230) may extract second information (e.g., at least one of user learning setting information (231), user app usage information (232), user profile information (233), and context information (234)) related to the first information, and transmit the second information to the prompt generation unit (250). The user learning setting information (231) may include, for example, at least one of a learning mode, a learning language, an AI content type, an AI content field, a learning level, and an app that can support the learning mode. The user app usage information (232) may refer to application information running on the electronic device (e.g., a browser app, a music app, a movie app, etc.). The user profile information (233) may include at least one of user age, gender, learning pattern, learning grade, and learning level information based on a learning result. Context information (234) may refer to information extracted through recognition of the situation of an electronic device or / and a user (e.g., a connection situation between an electronic device and another electronic device, a meeting situation, a situation in which the user is at home, etc.).

[0086] According to one embodiment, the AI ​​content type determination unit (240) may determine at least one of the type of AI content and / or the user interface (UI) configuration based on at least one of user learning setting information, learning pattern, and second information. For example, the AI ​​content type determination unit (240) may recognize a situation of an electronic device or a user (e.g., a situation in which an electronic device is connected to a speaker device and is located inside a house) based on context information, and determine the type and / or UI configuration of customized AI content suitable for the situation (e.g., a content in which a question sound is output through a speaker device and the electronic device displays candidate correct answers).

[0087] According to one embodiment, the prompt generation unit (250) may generate a prompt for AI content generation based on at least one of content, first information, and second information, and transmit the generated prompt to the AI ​​content generation model unit (260). For example, the prompt generation unit (250) may list the information extracted during prompt generation and transmit it to the AI ​​content generation model, or may transmit a prompt converted into a natural language form using the extracted information as input to the AI ​​content generation model.

[0088] According to one embodiment, the AI ​​content generation model unit (260) may use at least one of the prompt transmitted from the prompt generation unit (250), the DB (e.g., the general content DB (211), the personalized AI content DB (212)), and the content selected by the user (e.g., the first content) as input data of the AI ​​content generation model (or AI model, AI engine). The AI ​​content generation model unit (260) may generate AI content using the AI ​​content generation model (or AI model, AI engine). For example, the AI ​​content generation model may include at least one of an incorrect answer note generation model (261), an educational content generation model (263), and a concept organization generation model (265). Although not shown in the drawing, the AI ​​content generation model may further include a user pattern generation model (not shown) that records a user's learning pattern for AI content and is modeled by learning the learning pattern or feedback information. The user pattern generation model may refer to a generation model that is modeled to generate AI content that reflects personal characteristics. For example, the educational content generation model (263) may utilize at least one of a text generation model, an image generation model, and a video generation model, and similar content of educational content may also be generated through the above-described models.

[0089] In one embodiment, the AI ​​content generation model unit (260) can generate AI content by selecting an AI content generation model that matches the content type determined by the AI ​​content type determination unit. For example, if a prompt for creating a video lecture is input for first content consisting of images, the electronic device (101) can generate AI video lecture content based on the first content.

[0090] According to one embodiment, the AI ​​content provider (270) can control the display to display the generated AI content according to the UI configuration. For example, the UI configuration of the AI ​​content may include a content or object image, object identification information, the type of the generated AI content, and the content description. If the source information of the content description is different, the AI ​​content provider (270) can display the text of the content description by applying different visual effects so that the text is visually distinguished according to the source information. For example, text generated by AI among the content descriptions may be displayed in black, text based on the first information may be displayed in purple, or text based on the second information may be displayed in blue.

[0091] According to one embodiment, when the AI ​​content is edited (or modified, changed) by the user after the user has learned the AI ​​content, or feedback information is received, the feedback management unit (280) may transmit the edit information and / or feedback information to the DB management unit (210) to update the general content DB (211) or the personalized AI content DB (212).

[0092] In the following embodiments, each operation is performed through the interaction of the processor (120) and the memory (130), and may be operated through software modules implemented in relation to each operation (e.g., configurations implemented on the framework). Hereinafter, each operation may be performed sequentially, but is not necessarily performed sequentially. For example, the order of each operation may be changed, and at least two operations may be performed in parallel.

[0093] FIG. 3 illustrates an exemplary method for generating AI content for an electronic device according to various embodiments.

[0094] Referring to FIG. 3, according to one embodiment, the electronic device (101) may support an AI education content service (or AI education content function, AI learning mode) that generates AI education content related to the user's interests (e.g., selected content) using AI and supports learning.

[0095] In operation 310, the processor (120) of the electronic device (101) may receive an input requesting AI content generation through at least one of an application, a task, or a widget. For example, the processor (120) may display a UI menu (e.g., an AI content generation item) related to AI content based on a user input selecting content (e.g., first content) displayed on the display based on at least one of the application, the task, or the widget, or based on object recognition included in the content. The processor (120) may receive an input selecting an AI content generation item displayed on the display (e.g., an input requesting AI content generation).

[0096] In operation 315, the processor (120) can analyze the content and identify objects included in the content.

[0097] For example, the processor (120) may analyze first content selected by a user or first content in which an object is recognized to extract first information (or content data) and identify an object included in the content. The processor (120) may extract second information (or personalized data) related to the first information and transmit at least one of the content, the first information, and the second information to the prompt generation unit (250). The first information may include analysis information (221) of the content or object and / or additional information (222) based on metadata of the content. The second information may include at least one of user learning setting information (231), user app usage information (232), user profile information (233), and context information (234).

[0098] In operation 320, the processor (120) may generate a prompt for AI content generation. The processor (120) may generate a prompt for AI content generation based on at least one of content, first information (or content data), and second information (or personalized data).

[0099] In operation 325, the processor (120) may generate AI content (e.g., AI educational content, second content) using an AI model (or an AI content generation model). For example, the AI ​​model (e.g., AI content generation model) may include at least one of an incorrect answer note generation model (261), an educational content generation model (263), a concept organization generation model (265), or a user pattern generation model (not shown).

[0100] The processor (120) can determine the type of AI content that matches learning setting information or personalized characteristics, and select an AI model corresponding to the determined type to generate AI content.

[0101] According to one embodiment, the processor (120) can generate AI content related to and personalized with content by using the generated prompt and educational service-related DB (e.g., general content DB (211) and personalized AI content DB (212)) as input values ​​of the AI ​​model.

[0102] The processor (120) can display the generated AI content on a display.

[0103] In operation 330, the processor (120) can obtain user editing information for the generated AI content.

[0104] For example, the processor (120) switches to an editing UI screen that can edit AI content based on an editing request for AI content displayed on the display, and obtains editing information (or editing data) in which AI content content is modified or changed through the editing UI.

[0105] In one embodiment, operation 330 may be omitted.

[0106] In operation 335, the processor (120) can update the universal content DB (211) or / and the personalized AI content DB (212) with editing information or user learning results (or feedback information).

[0107] In operation 340, the processor (120) may receive a request for generating complementary AI content.

[0108] According to one embodiment, the processor (120) may receive an input requesting a change in type for AI content or requesting a supplement to AI content in relation to feedback (e.g., problem solving) for previously generated AI content.

[0109] For example, the processor (120) may recognize that a request for creating supplementary AI content has been received when educational content for explanation is required based on incorrect answer information based on the user's problem-solving results for AI content, or when a new problem needs to be created in consideration of the process required for learning.

[0110] In operation 345, the processor (120) may generate a prompt for generating complementary AI content.

[0111] For example, the processor (120) may extract second information that matches the supplementary characteristics in relation to a request for creation of supplementary AI content among the second information, and may change the input of the second information to generate an updated prompt.

[0112] In operation 350, the processor (120) can generate complementary AI content (e.g., AI training content, third content) using an AI model (e.g., AI content generation model).

[0113] For example, the processor (120) can generate complementary AI content corresponding to previously generated AI content.

[0114] In operation 360, the processor (120) analyzes the learning pattern of a user who has learned the supplementary AI content, and in operation 370, the processor (120) can update the universal content DB (211) or / and the personalized AI content DB (212) with the user learning results.

[0115] FIG. 4 illustrates an exemplary method for operating an AI content service of an electronic device according to various embodiments.

[0116] Referring to FIG. 4, the processor (120) of the electronic device (101) according to one embodiment may display first content on the display in operation 410. For example, the processor (120) may execute an application / task / function (e.g., gallery, camera, screen capture, AR app, book app, video viewer app, fashion app, SNS app) capable of supporting AI services based on user input, and display the first content (e.g., text, image, or video).

[0117] In operation 420, the processor (120) may receive an AI content generation request related to the first content displayed on the display.

[0118] For example, the processor (120) may display a menu item for generating AI content (or AI training content, second content, or learning content) related to the first content based on an input for selecting the first content. When an input for selecting the AI ​​content generation menu item is received, the processor (120) may recognize that an AI content generation request has been received.

[0119] An electronic device (101) according to one embodiment can receive a request for AI content creation related to an image (or object) currently displayed on a display through a user's voice using an artificial intelligence secretary or text input using various interfaces.

[0120] In operation 430, the processor (120) may identify at least one object included in the first content displayed on the display. For example, the processor (120) may identify at least one object included in the first content when a user selects an object included in the first content or when an application capable of supporting AI services recognizes (e.g., automatically recognizes) an object included in the first content.

[0121] In operation 440, the processor (120) may obtain first information (or content data) based on analysis of first content and objects. For example, the first information may include analysis information (221) of the content and objects and additional information (222) based on metadata. The analysis information (221) may include at least some of object identification information and content description keywords. The processor (120) may extract additional information (222) based on metadata of the selected content or object. The additional information (222) may refer to information based on metadata (e.g., date, time, location, etc.) of the content or object.

[0122] In operation 450, the processor (120) may obtain second information (or personalized data) related to the user and the electronic device, which is associated with the first information. For example, the second information may include at least one of the user's learning setting information (231), the user's app usage information (232), user profile information (233), and context information (234).

[0123] In operation 460, the processor (120) can generate personalized AI content based on the first content based on at least one of the first content, the first information, and the second information.

[0124] For example, the processor (120) may generate a prompt for AI content generation based on at least one of the first content, the first information, and the second information. The processor (120) may use the prompt and the DB (e.g., the general content DB (211) or the personalized AI content DB (212)) as input values ​​for an AI content generation model to generate AI content related to the first content and personalized. The processor (120) may determine a content type based on learning setting information or personal characteristics and generate AI content that matches the determined type.

[0125] In operation 470, the processor (120) can display the generated AI content on the display.

[0126] For example, the processor (120) may display a UI screen (hereinafter, referred to as an AI content UI screen) that provides AI content by overlaying at least a portion of the content displayed on the display. For example, the AI ​​content may include an object image recognized by a user or automatically, object identification information, type information of the generated AI content, and content description. As another example, the processor (120) may display the content on a portion of the display (e.g., a first display area) according to the form factor of the electronic device (101) (e.g., a foldable device) or a split screen, and display the AI ​​content generated based on the content on another portion of the display (e.g., a second display area).

[0127] According to one embodiment, the processor (120) may display the content description (834) by applying different visual effects (e.g., color, size, shape, font, etc.) so as to visually distinguish the source of the information.

[0128] In operation 480, the processor (120) may edit the AI ​​content or update the AI ​​content or data related to the AI ​​content based on the feedback information.

[0129] For example, the processor (120) supports a function of editing AI content and / or a function of recording feedback information, and can update a personalized AI content DB (212) based on editing information and feedback information edited by the user.

[0130] According to one embodiment, the electronic device (101) may be implemented as a wearable device. For example, the wearable device may include at least one of a watch type, glasses type, or ring type that can be worn on the body.

[0131] According to one embodiment, a wearable device may support AI content services based on at least one of virtual reality, augmented reality, mixed reality, or extended reality devices. For example, the wearable device may identify an object in an image or scene provided through the display of the wearable device and generate AI content related to the identified object to provide an AI content service. Alternatively, if the wearable device is implemented as a VST (video see-through) type, the wearable device may analyze an object or scene within an area selected by a user from a preview image or video captured through a camera and generate AI content related to the analyzed object or scene to provide an AI content service.

[0132] FIG. 5 illustrates an example of an AI content service method based on an artificial function of an electronic device according to various embodiments.

[0133] Referring to FIG. 5, the processor (120) of the electronic device (10) according to one embodiment may receive a request for selecting an object and generating learning content from content (e.g., first content) in operation 510.

[0134] For example, the electronic device (101) can display first content on the display through an application that supports AI services (e.g., camera, gallery, Bixby Vision, screen capture, AR app, book app, video viewer app, fashion app, SNS app) when the AI ​​learning mode (or AI service training mode) is activated. The processor (120) can display an AI content creation menu item related to the selected first content based on an input that selects the first content displayed on the display or an object included in the first content. The processor (120) can perform operations for creating AI content (e.g., AI training content, second content) based on the selection of the AI ​​content creation menu item.

[0135] In operation 520, the processor (120) may analyze the selected content (e.g., the first content) and transmit first information (or content data) related to the content or an object included in the content to the prompt generation unit (250). The first information may include analysis information (221) of the content and the object and additional information (222) based on metadata. The analysis information (221) may include at least some of object identification information and content description keywords. The additional information (222) may refer to information based on metadata (e.g., date, time, location, etc.) of the content or the object.

[0136] According to one embodiment, the processor (120) may extract analysis information (221) obtained by analyzing selected content and objects identified within the content, and additional information (222) based on metadata of the selected content or object. For example, the processor (120) may automatically recognize objects within the content, extract object identification information for objects selected by a user, and extract descriptive keywords representing the characteristics of the content.

[0137] According to one embodiment, the processor (120) may transmit content (e.g., first content) and / or first information to the prompt generation unit (250).

[0138] According to some embodiments, the processor (120) may update the personalized AI content DB (212) with the selected content and / or first information extracted from the selected content (e.g., additional information (222)).

[0139] According to one embodiment, the processor (120) may update the selected content and / or first information extracted from the selected content to the personalized AI content DB (212).

[0140] In operation 530, the processor (120) can control, through the DB management unit (210), at least one of the personalized AI content DB (212) and / or the universal content DB (211) to be used as input for the AI ​​content creation model.

[0141] In operation 540, the processor (120) may transmit second information (e.g., second information related to the first content (or first information)) stored in the personalized data management unit (230) to the prompt generation unit (250). The second information may include at least one of user learning setting information (231), user app usage information (232), user profile information (233), and context information (234). The user learning setting information (231) may include, for example, at least one of a learning mode, a learning language, an AI content type, an AI content field, a learning level, and an app that can support the learning mode. The user app usage information (232) may refer to application information running on the electronic device (e.g., a browser app, a music app, a movie app, etc.). The user profile information (233) may include at least one of user age, gender, learning pattern, learning grade, and learning level information based on a learning result. Context information (234) may refer to information extracted through recognition of the situation of an electronic device or / and a user (e.g., a connection situation between an electronic device and another electronic device, a meeting situation, a situation in which the user is at home, etc.).

[0142] For example, the type of AI content or screen UI configurations may be determined based on learning setting information or contextual information. Alternatively, the training level of AI content may be determined based on user app (application) usage information and user profile information.

[0143] In operation 550, the processor (120) may generate a prompt for AI content generation based on at least one of the content, the first information, and the second information, and transmit the generated prompt to the AI ​​content generation model.

[0144] According to one embodiment, the processor (120) may list information (e.g., text, images, etc.) extracted when generating a prompt and pass it to the AI ​​content generation model, or may generate a prompt converted into a natural language form using the extracted information and pass it as input to the AI ​​content generation model.

[0145] In operation 560, the processor (120) can generate AI content (e.g., AI education content, second content) related to the selected content and personalized by using an AI content generation model that inputs data and prompts stored in a DB (e.g., universal, common content DB (211) and personalized AI content DB (212)).

[0146] In operation 570, the processor (120) can output (or display) the generated AI content on a display.

[0147] For example, the processor (120) may display a UI screen (hereinafter, “AI content UI screen”) that provides AI content by overlaying at least a portion of the content displayed on the display. The AI ​​content UI screen may be displayed as a pop-up window, but is not limited thereto. As another example, the processor (120) may display content on a portion of the display (e.g., a first display area) according to the form factor of the electronic device (101) (e.g., a foldable device) or a split screen, and display AI content generated based on the content on another portion of the display (e.g., a second display area).

[0148] In operation 580, the processor (120) can obtain editing information or feedback information for AI content by user input.

[0149] According to one embodiment, when displaying AI content on a display, the processor (120) may display editing items that can enter the editing function (or editor mode) of the AI ​​content upon a user request. The processor (120) may switch to a UI screen (hereinafter, “edit UI screen”) for editing the AI ​​content based on a user input for selecting an editing item, and may obtain editing information about the AI ​​content based on editing information modified / changed by the user through the edit UI screen. Alternatively, the processor (120) may provide a function for recording feedback data about the AI ​​content and may obtain feedback information recorded by the user.

[0150] For example, editing information may refer to information about AI content data edited / modified through the user's editing function. Feedback information may refer to evaluation / feedback information about AI content after the user has learned about the AI ​​content (e.g., whether the learning level is appropriate, whether the content is recognized as suitable for the user, etc.).

[0151] According to one embodiment, the processor (120) may store or update AI content or edited AI content in the personalized AI content DB (212). If information edited by the user is related to content data (or first information), the processor (120) may control the updating of analysis information or additional information of the image.

[0152] In operation 590, the processor (120) can update AI content by recording learning results for AI content based on editing information or feedback information. The processor (120) can update and manage AI content stored in the personalized AI content DB (212).

[0153] According to one embodiment, the processor (120) may update (or adjust, fine tune) the personalized AI content DB (212) and / or user personalized data based on the results of user learning (e.g., problem solving, speaking answers) for AI content and / or information analyzed from the learning results. For example, if the electronic device (101) determines that the content edited by the user is related to image analysis information, the electronic device (101) may transmit the user edited content to a component that processes image analysis to adjust the image analysis so that more personalized keywords can be extracted or analysis results can be output. Alternatively, if the content edited by the user is related to application usage information, the electronic device (101) may transmit the user edited content to the personalized AI DB so that more personalized results can be output when analyzing personalized data.

[0154] In some embodiments, operation 580 or operation 590 may be omitted.

[0155] FIG. 6 illustrates examples of a learning setting user interface screen of AI content of an electronic device according to various embodiments.

[0156] Referring to FIG. 6, an electronic device (101) according to one embodiment may provide an AI content service function when executing a specific application / task / function (e.g., gallery, camera, screen capture, AR app, book app, video viewer app, fashion app, SNS app) that supports AI services. For example, the electronic device (101) may be designed to automatically support AI content (or AI education content) regardless of setting options.

[0157] According to one embodiment, the electronic device (101) may support setting options for AI content. For example, the electronic device (101) may support changing setting information related to AI content through the learning setting UI screens (610) illustrated in FIG. 6.

[0158] In one embodiment, if the electronic device (101) only supports on / off and language setting of learning mode, as an example, <601> As illustrated, a learning setting UI screen (610) including an on / off setting item (620) and a language setting item (630) may be provided. The language setting item (630) may be an item for setting a language to be used in generating AI content (or AI education content) for foreign language education.

[0159] According to one embodiment, the electronic device (101) <601> If additional settings and type settings are supported as shown in <602> As illustrated, a learning setting UI screen (610) further including a type setting item (640) may be provided. The type setting item (640) is an item for setting the type of AI content, and at least one of OPIC, TOEFL, TOEIC, JLPT, JPT, HSK, news, conversation, elementary, middle, and high school English problems, Scholastic Ability Test problems, speaking examples, writing, and journal may be selected, but is not limited thereto.

[0160] According to one embodiment, the electronic device (101) <603> If additional settings and field settings are supported as shown in <603> As illustrated, a learning setting UI screen (610) further including a field setting item (650) may be provided. The field setting item (650) is an item for setting the field of AI content, and at least one of society, history, economy, politics, daily life, science, trends, or mathematics may be selected, but is not limited thereto.

[0161] According to one embodiment, if the electronic device (101) is designed to allow the user to set AI content support functions in a widget or a specific app, <604> As illustrated, the learning setting UI screen (610) may include, for example, a learning mode on / off setting item (620), a language setting item (630), a type setting item (640), a field setting item (650), an AI content widget setting item (660), a gallery app support setting item (670), and a screen capture support setting item (680).

[0162] The learning setting UI screens illustrated in Figure 6 are examples only and are not limited thereto.

[0163] FIG. 7 illustrates examples of user interface screens for generating AI content of an electronic device according to various embodiments.

[0164] Referring to FIG. 7, according to one embodiment, the electronic device (101) may perform a function of generating AI content in conjunction with a function supported by a specific application. For example, the electronic device (101) may provide a menu UI (hereinafter, "AI content menu UI") related to an AI content service in conjunction with a function of identifying objects within the content.

[0165] In one embodiment, the gallery application may display a first image (e.g., first content) (711), provide a function for identifying and separating an object (712) within the first image (711) (e.g., object outline extraction), and provide an AI content service function. For example, <701> As illustrated, the electronic device (101) may display an image-related menu UI (720) based on an input (or automatic object recognition) for selecting a first image (711) displayed on the execution screen (710) of the gallery application. For example, the image-related menu UI (720) may further include an AI item (721), an image sharing item, an image copy item, and an image save item, but this is merely an example.

[0166] When the electronic device (101) receives an input for selecting an AI item (721) from an image-related menu UI (720), the electronic device (101) may display an AI content menu UI (730). The electronic device (101) may generate AI content (e.g., AI educational content) related to the first image (711) and / or object (712) based on the input for selecting the AI ​​content generation item (731).

[0167] In one embodiment, a camera application (or AR application) may support the function of recognizing objects in images or videos (e.g., content) captured by the camera and AI content service functions. For example, <702> As illustrated, the electronic device (101) can automatically recognize an object (741) in an image or video (740) captured through a camera function (e.g., Bixby Vision) that supports object identification, or display an AI content menu UI (730) based on an input of a user selecting an object (741). <702> On the screen, the electronic device (101) can generate AI content (e.g., AI educational content) related to an image or video (740) and / or object (741) based on an input for selecting an AI content generation item (731).

[0168] According to one embodiment, the screen capture application may support the function of recognizing an object after capturing the screen of the electronic device (101) and the AI ​​content service function. For example, <703> As illustrated, the electronic device (101) can display a screen capture image (750) on the display based on a user request. The electronic device (101) can recognize an object area (751) and an object (752) within the screen capture image (750). The electronic device (101) can display an AI content menu UI (730) based on the object (752) being recognized. <703> On the screen, the electronic device (101) can generate AI content (e.g., AI educational content) related to a recognized object (752) in a screen capture image (750) based on an input of selecting an AI content generation item (731).

[0169] Figures 8a to 8d illustrate user display screens supporting AI content services of electronic devices according to various embodiments. Figures 8a to 8d illustrate examples of AI content services supported through a gallery application. However, these are merely examples, and the embodiments applied to the present disclosure can also be applied to other applications.

[0170] Referring to FIGS. 8A to 8E, an electronic device (101) according to one embodiment executes a gallery application. <8001> As illustrated, a first image (or first content) (810) can be displayed on a display. The electronic device (101) can receive a user input (812) for selecting an object (e.g., a Christmas tree object) (811) included in the first image (810).

[0171] Electronic device (101) <8002> As illustrated, based on a user input (812) for selecting an object (811), an object separation function may be used to separate and display the object (e.g., display an outline) on a first image (810) displayed on a display, and an image-related menu UI (815) may be displayed. The electronic device (101) may display an AI content menu UI (820) based on an input for selecting an AI item (816) in the image-related menu UI (815).

[0172] The electronic device (101) can receive an input (821) for selecting an AI content creation item in the AI ​​content menu UI (820).

[0173] According to one embodiment, the electronic device (101) may omit the image-related menu UI (815) and provide only the AI ​​content menu UI (820) in response to an input for selecting an object within an image.

[0174] The electronic device (101) can generate AI content (e.g., AI educational content) related to the first image (810) and / or object (811) based on an input (821) for selecting an AI content generation item. The electronic device (101) <8003> As shown in , information (825) indicating that AI content is being generated can be displayed on the display.

[0175] The electronic device (101) can analyze the first image (810) and the object (811) to extract first information (or content data). For example, the electronic device (101) can extract analysis information (or analysis keywords) representing the characteristics of the first image (810) as the first information (e.g., Christmas tree, red ball ornament, a large number of small-sized LED bulbs, indoor, living room, etc.), and extract additional information based on metadata of the first image (e.g., December 24, 2022, 8:30 PM, location information, focal length, magnification information, etc.) or / and metadata of the identified object (e.g., object identification information).

[0176] The electronic device (101) can extract second information (or personalized data) associated with the first information. For example, the electronic device (101) can extract, as second information, date and time information (e.g., December 24, 2022, 8:30 PM) from among the additional information extracted from the first image, user app usage information (e.g., Music, SNS-Instagram app usage on a smartphone device, etc.), user profile information, or user learning setting information associated with the second information. Alternatively, the electronic device (101) may extract context information based on location identification (e.g., location identification such as my home / work), information about various external devices (e.g., TV, refrigerator, speaker, etc.) present at a location (e.g., my home) connected to or identified with the electronic device (101), usage information of applications used in the external devices (e.g., Netflix app on a TV device, Music app on a speaker device, etc.) (e.g., watching Last Christmas movie at 10 PM on December 24, 2022 on Netflix app, playing multiple carols such as Andy Williams' Happy Holiday and Peggy Lee's The Christmas Waltz on Music app on December 24, 2022).

[0177] According to one embodiment, the electronic device (101) can generate a prompt for AI content generation using at least one of a first image, first information, and second information. The electronic device (101) can transmit a prompt and a DB (e.g., a general content DB (211) or / and a personalized AI content DB (212)) as inputs to an AI content generation model, and can generate AI content related to the first image and personalized using the AI ​​content generation model.

[0178] Electronic device (101) <8004> As illustrated, the generated AI content (830) can be displayed on the display. For example, the AI ​​content (830) can include an object image (831) recognized by a user or automatically, object identification information (832), a type of generated AI content (833), and content description (834).

[0179] According to one embodiment, the electronic device (101) <8004> Display AI content (830) in a pop-up window as shown in <8005> As shown in , AI content (830) can be converted to full screen (e.g., foreground).

[0180] According to one embodiment, the electronic device (101) may display texts by applying different visual effects (e.g., color, size, shape, font, etc.) to visually distinguish them based on the source information of the content description (834). For example, AI content may include data such as the following [Table 1].

[0181] 객체 식별 정보Christmas TreeAI 컨텐츠 언어EnglishAI 컨텐츠 유형OPIC TEST컨텐츠 내용(description)Q. tell me about what you did during your last vacation. how did your vacation start and did it end? what did you do on each day?A. Hello, I'm happy to tell you about my last vaction.I had a wonderful time with my family at home.My vacation started on december 24th,which was christmas eve.In the morning,we set up our christmas tree in the living room. We had a beautiful tall tree. We wrapped a lot of small LED lights areound it and made it shine brightly, We also hung some ormanents of red balls and small dolls on the branches.it was a festive and lovelysight.Wetook some pictures and posted them on social media.And then, we had a special dinner together.Welistened to some carol musicand exchanged gifts in front of the Chreitmas tree. we also watched a movie on Netflix and evjoyed some hot chocolate. It was a cozy and warm night.

[0182] The content description may include text generated by an AI content generation model, text generated by first information extracted in relation to the content, and text generated by second information extracted in relation to a user or electronic device.

[0183] For example, the electronic device (101) may display content generated by the AI ​​model (e.g., Hello, I'm happy to tell you about my last vacation. I had a wonderful time with my family at home, which was Christmas Eve, etc.) in black, content generated by the first information (e.g., My vacation started on December 24th, We set up our Christmas tree in the living room. We had a beautiful tall tree, etc.) in purple (or bold), and content generated by the second information (e.g., We took some pictures and posted them on social media, We listened to some carol music, etc.) in blue (or italic), but this is only an example.

[0184] According to one embodiment, the electronic device (101) <8005> When some text is selected from the content description (834) as shown in FIG. 1 , a UI (not shown) may be provided that provides source information about what information (e.g., first information or second information) the selected text was generated from. For example, when a user selects “We set up our Christmas tree in the living room,” the electronic device (101) may additionally display a UI indicating that the content is based on “object identification information of the image.” For another example, when a user selects “We listened to some carol music,” the electronic device (101) may additionally display a UI indicating that the content is based on “app (music) information of the electronic device used on the same date as the image.”

[0185] Electronic device (101) <8004> Based on an input for selecting an additional function display item (835) for the AI ​​content (830) shown in FIG. 1 , an additional function menu UI (836) related to AI content may be displayed. For example, the additional function menu UI (836) may include at least one of a content content editing item, a word learning item, a grammar learning item, a similar AI content creation item, a speaking practice item, and a different type of content creation item, but this is only an example.

[0186] The electronic device (101) is based on an input (837) that selects a content content editing item. <8006> As shown in , the screen can be switched to an AI content editing UI screen (840) that provides a text input area (840) and a keyboard area (845). The user can edit / modify the contents of the AI ​​content (830) by entering text through the keyboard area (845). For example, the user can additionally enter "180cm, that we bought online, and it's called French skirt tree." into the AI ​​content. <8007> It shows AI content (830) whose content has been modified by the user.

[0187] According to one embodiment, the electronic device (101) may apply different visual effects (e.g., red highlighting or underlining) to text whose content has been modified or added by the user to visually distinguish it from other text. For example, the result data edited by the user for AI content may be as shown in [Table 2] below.

[0188] Q. tell me about what you did during your last vacation. how did your vacation start and did it end? what did you do on each day?A. Hello, I'm happy to tell you about my last vaction.I had a wonderful time with my family at home.My vacation started on december 24th,which was christmas eve.In the morning,we set up our christmas tree in the living room. We had a beautiful 180 cm tall treethat we bought online and it's called French skirt tree. We wrapped2000 (a lot of)small LED lights areound it and made it shine brightly, We also hung some ormanents of red ballsof 3.5 cn duaneterand5small dolls on the branches.it was a festive and lovelysight.Wetook some pictures and posted them on (social media)my instagram.And then, we had a special dinner together.Welistened to some1960s jazzcarol musicand exchanged gifts in front of the Chreitmas tree. we also watched a movie" Last Christmas"on Netflix and evjoyed some hot chocolate. It was a cozy and warm night.

[0189] According to one embodiment, the electronic device (101) can generate and provide different types of AI content depending on the set learning type. For example, the electronic device (101) of FIG. 8d <8008> As shown in , generate AI content (830-1) of a news type related to the first image (810), or <8009> As shown in , AI content (830-2) of a historical type related to the first image (810) can be generated. Or the electronic device (101) <8010> As shown in , generate AI content (830-3) of a conversation type related to the first image (810), or <8011> As shown in , AI content (830-4) of the TOEFL type can be created.

[0190] In one embodiment, the electronic device (101) may randomly select a type of AI content and generate and provide AI content if there is no type setting information for the AI ​​content. Alternatively, if the electronic device (101) is analyzed to have a preferred type of AI content based on a user learning pattern, the electronic device (101) may be configured to generate AI content of the preferred type first.

[0191] An electronic device (101) according to one embodiment may select an AI content type suitable for the situation of a user or / and the electronic device based on second information or personalized data (e.g., user profile information, situation information, user app usage information), and generate AI content with the selected type.

[0192] According to one embodiment, when an input for selecting a “creation item of another type of content” is received through an additional function menu UI while a specific type of AI content is displayed, the electronic device (101) may generate another type of AI content and display another type of AI content.

[0193] FIG. 9 illustrates user interface screens for collecting AI content DB of an electronic device according to various embodiments.

[0194] Referring to FIG. 9, according to one embodiment, the electronic device (101) may support an AI data gathering function for creating personalized AI content.

[0195] For example, the electronic device (101) <901> As illustrated, an image-related menu UI (920) may be displayed based on a user input for selecting a first image (910) or an object within the first image (910), and an AI content menu UI (930) may be displayed based on an input for selecting an AI item (921) from the image-related menu UI (920).

[0196] The electronic device (101) may extract first information (e.g., analysis information and additional information) related to the first image (910) or / and an object within the first image (910) based on an input (931) for selecting an AI data collection item, or may extract memory location information where the image is located and store the extracted information in a personalized AI content DB. For example, <901> The first image (910) shown in <902> The second image (940) illustrated may be contents captured at different times on the same date and at the same location (e.g., December 10, 2019, Salzburg Christmas Market, Austria). The electronic device (101) may collect the first image (910) and the second image (920) through an AI data collection item.

[0197] According to one embodiment, the electronic device (101) can store contents collected through AI data collection items in a personalized AI content DB.

[0198] According to one embodiment, the electronic device (101) can extract analysis information (e.g., key object identification information, keywords indicating a location, keywords indicating an atmosphere) or additional information (e.g., seasonal information based on date, etc.) by analyzing the first image and the second image and store the extracted information in a personalized AI content DB.

[0199] FIG. 10 illustrates user interface screens for collecting content DB of an electronic device and generating AI content according to various embodiments.

[0200] Referring to FIG. 10, an electronic device (101) according to one embodiment <1001> As illustrated in FIG. 9, the AI ​​data collection items described in FIG. 9 can be utilized to collect a first image (1010), a second image (1011), a third image (1012), a fourth image (1013), and a fifth image (1014). The first image (1010), the second image (1011), the third image (1012), the fourth image (1013), and the fifth image (1014) may be content captured on the same date (e.g., December 10, 2019) and at the same location (e.g., the Christmas market in Salzburg, Austria).

[0201] After the user performs the "Collect AI Data" action on four images excluding the fifth image (1014), the user can select the AI ​​content creation menu while the fifth image (1014) is displayed on the display.

[0202] For example, the electronic device (101) can identify an object (e.g., boots) for the fifth image (10114), extract a shooting date (e.g., December 10, 2019) and location information (e.g., Salzburg, Austria) from metadata information of the image, and then extract four images (e.g., a first image (1010), a second image (1011), a third image (1012), a fourth image (1013)) previously stored from a personalized data or personalized AI content DB and information related thereto (e.g., second information) using the extracted date information and location information. The electronic device (101) can generate AI content (1020) based on the four previously stored images and the fifth image (1014) selected by the user, and first information (e.g., analysis information and additional information) for each image.

[0203] Electronic device (101) <1002> As illustrated, the generated AI content can be displayed on a display. For example, an example of the content of AI content generated using multiple collected images may be as shown in [Table 3] below.

[0204] Q.Tell me about a memorable or unforgettable experience you had while traveling abroad. what happen and why was the experience memorable?A.One of the most memorable experiences I had whiletraveling abroad was when I visited Salzburg, Austria about three years ago. It was a snowy day in December, and I decided to go to the Hohensalzburg Fortress. I took a funicular up to the castle and explored its history and architecture. I also enjoyed the panoramic view of the city and the mountains from the castle.When I came down from the castle, it was almost sunset and themain square was filled with a beautiful Christmas market. There was a big Christmas tree in the center covered with snow. It was a magical scene that made me feel like I was in a fairy tale.One of the things that caught my eye wasa pair of warm Ugg bootsthat were on sale. I decided to buy the boots, which were very cozy and comfortable.I think buying the Ugg boots was the highlight of my trip, because they reminded me of the wonderful experience I had in Salzburg.

[0205] The text marked in underline in the contents of [Table 3] may be related to the first information (image analysis information and additional information).

[0206] FIG. 11 illustrates user interface screens supporting AI content services of electronic devices according to various embodiments.

[0207] Referring to FIG. 11, an electronic device (101) according to one embodiment may support a function of generating AI content or displaying AI content using a widget.

[0208] The electronic device (101) can display various types of widget objects related to AI content creation on a home screen (1110) on which icon objects (1120) corresponding to applications or functions are displayed. <1101> The screen may be an example that displays a first widget (1130) containing multiple images (or thumbnails) collected through an AI data gathering function, and provides a function to create AI content by adding an AI content creation item (1140) to the first widget (1130). <1102> The screen may be an example of displaying a second widget (1150) for checking the generated AI content, and providing a function for calling the AI ​​content using the widget by adding an AI content check item (1160) to the second widget (1150). <1130> The screen may be an example of providing a third widget (1170) in a form that can check the content of the generated AI content on the home screen (1110).

[0209] Figure 12 illustrates a method for supporting AI content services in an electronic device according to various embodiments. The diagram in Figure 12 may be a diagram illustrating a process in which AI content (e.g., AI educational content) is analyzed for learning outcomes and, based on the analyzed results, the AI ​​content evolves into personalized or customized content based on individual characteristics.

[0210] Referring to FIG. 12, an electronic device (101) according to one embodiment may support a function of updating AI content (or evolving it into customized AI content) according to the user's personal characteristics by reflecting the user's learning results on the generated AI content (e.g., AI education content).

[0211] For example, in operation 1210, the electronic device (101) may generate a prompt for generating AI content related to the first content. Prior to generating the prompt, in operation 1215, the electronic device (101) may transmit at least one of the first content, first information related to the first content or an object included in the first content, and second information related to the user / electronic device to the prompt generation unit.

[0212] In operation 1220, the electronic device (101) may generate AI content (e.g., AI content of the OPIC problem type) by transmitting a prompt requesting generation of AI content of the OPIC problem type in relation to the first content to an AI model (e.g., AI content generation model).

[0213] For example, AI content for the OPIC exam question type may include questions and answer examples. The electronic device (101) may extract second information related to the first content through personalized data, and based on the extracted second information, generate content for example answers based on information the user has experienced or is expected to experience.

[0214] In operation 1230, the electronic device (101) can display AI content of the OPIC problem type on the display.

[0215] In operation 1240, the electronic device (101) may obtain user modification information (e.g., editing information) regarding AI content. For example, if the generated AI content includes information regarding user experience, the user may use the AI ​​content editing function to correct or modify any incorrect or desired content.

[0216] The electronic device (101) can generate customized OPIC questions or examples by reflecting (or providing feedback) on the user's changes or edits.

[0217] In operation 1250, the electronic device (101) can input user learning results (example answer data or speaking data) for AI content and analyze learning patterns.

[0218] In operation 1260, the electronic device (101) generates new AI content by reflecting the analyzed learning pattern (e.g., detecting sounds or words that the user has difficulty pronouncing) according to the learning result, and in operation 1270, the electronic device (101) can output the newly generated AI content to the display.

[0219] For example, the electronic device (101) can evaluate the user's learning level based on the learning results, analyze the user's speech data answering the OPIC questions, and create new AI content that changes the content of example answers (e.g., analyze the user's pronunciation to suggest words that are easier for the user to say).

[0220] Alternatively, the electronic device (101) may analyze the user's speech regarding examples of AI content, and if grammatical errors are repeated, generate AI content for grammar or speaking repetition training and provide it to the user. Alternatively, the electronic device (101) may generate AI content by adjusting the level of content (e.g., examples) of the AI ​​content to suit the user's learning level, reflecting the set educational objectives.

[0221] In operation 1280, the electronic device (101) can continuously perform updates on the AI ​​content by receiving and analyzing learning results for newly generated AI content.

[0222] In operation 1285, the electronic device (101) may receive input related to additional functions related to AI content (e.g., content content editing items, word learning items, grammar learning items, similar AI content generation items, speaking practice items, other types of content generation items, etc.). In operation 1289, the electronic device (101) may generate AI content corresponding to the additional functions.

[0223] According to one embodiment, the electronic device (101) may support a function of generating personalized AI content (or AI training content) according to user characteristics in relation to video content.

[0224] For example, when the electronic device (101) obtains information (e.g., second information) that a user frequently studies through video lectures, the electronic device may generate AI content of the video type based on data stored in the DB management unit. In this case, in the case of the video type, the electronic device may generate AI content by utilizing the user's avatar or a person image included in the stored image content in response to the person. When displaying AI content of the video type, the electronic device (101) may also provide a textual summary of the AI ​​content.

[0225] According to one embodiment, a method for supporting AI content services in an electronic device may include an operation for identifying an object included in first content displayed on the display based on an AI content generation request. According to one embodiment, a method for supporting AI content services in an electronic device may include an operation for obtaining first information related to at least one of the object or the first content, and second information related to the electronic device or a user. According to one embodiment, a method for supporting AI content services in an electronic device may include an operation for generating a prompt for input of a generative artificial intelligence model based on at least one of the first content, the first information, and the second information. According to one embodiment, a method for supporting AI content services in an electronic device may include an operation for generating second content that is personalized and related to the first content using generative artificial intelligence (AI) with the generated prompt as an input.

[0226] The embodiments of this document and the terminology used herein are not intended to limit the technical features described in this document to specific embodiments, but should be understood to include various modifications, equivalents, or substitutes of the embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of the items, unless the context clearly indicates otherwise. In this document, each of the phrases "A or B", "at least one of A and B", "at least one of A or B", "A, B, or C", "at least one of A, B, and C", and "at least one of A, B, or C" can include any one of the items listed together in the corresponding phrase among those phrases, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used merely to distinguish one component from another, and do not limit the components in any other respect (e.g., importance or order). When a component (e.g., a first component) is referred to as "coupled" or "connected" to another (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.

[0227] The term "module" used in the 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).

[0228] One embodiment 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.

[0229] According to one embodiment, the method according to one embodiment 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.

[0230] According to one embodiment, each component (e.g., a module or a program) of the above-described components may include one or more entities, and some of the entities may be separated and arranged in other components. According to one embodiment, 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 this 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 one embodiment, 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.

[0231] While the present disclosure has been described and illustrated with reference to various exemplary embodiments, it should be understood that these exemplary embodiments are illustrative and not limiting. Furthermore, those skilled in the art will appreciate that various changes in form and detail may be made therein without departing from the true spirit and scope of the present disclosure, which is encompassed by the appended claims and their equivalents. Furthermore, it should be understood that any embodiment described herein may be combined with any other embodiment described herein.

Claims

1. In electronic devices, display; At least one processor comprising a processing circuit; and A memory that stores instructions executable by at least one processor, The at least one processor individually and / or collectively executes instructions, causing the electronic device to: Based on the AI content generation request, identify an object included in the first content displayed on the display, Obtaining first information related to at least one of the above objects or the above first contents, and second information related to the electronic device or the user, Generate a prompt for input of a generative artificial intelligence model based on at least one of the first content, the first information, and the second information, An electronic device configured to generate second content related to the first content using generative AI (artificial intelligence) using the generated prompt as input.

2. In paragraph 1, The second content is an electronic device including AI (artificial intelligence) content, education content, or learning content.

3. In paragraph 1, The at least one processor individually and / or collectively causes the electronic device to: As the first information, at least one of object identification information, content description keywords that analyze the first content or the identified object, and additional information based on metadata of the content is extracted, An electronic device configured to extract at least one of user learning setting information, user app usage information, user profile information, and context information as the second information.

4. In paragraph 3, The at least one processor individually and / or collectively causes the electronic device to: An electronic device that selects and extracts the second information associated with the first information.

5. In paragraph 1, The at least one processor individually and / or collectively causes the electronic device to: An electronic device characterized in that the object is identified through a user input selecting the object included in the first content or through object recognition within the first content as an action for identifying the object.

6. In paragraph 1, The at least one processor individually and / or collectively causes the electronic device to: To display the second content generated above on the display, The second content is an electronic device including content or object images, object identification information, the type of generated AI content, and content description.

7. In paragraph 6, The at least one processor individually and / or collectively causes the electronic device to: An electronic device configured to display the second content in the form of a pop-up window overlapping the first content or to display it in the form of a foreground window.

8. In paragraph 6, The at least one processor individually and / or collectively causes the electronic device to: An electronic device configured to display texts of content by applying different visual effects so that they are visually distinguished according to the source information when the source information of the content (description) is different.

9. In paragraph 6, The at least one processor individually and / or collectively causes the electronic device to: Obtaining edit information on the AI content related to the second content that has been modified or changed or feedback information on the learning results of the second content, An electronic device configured to update the second content based on the acquired editing information or the feedback information.

10. In paragraph 1, The at least one processor individually and / or collectively causes the electronic device to: An electronic device configured to display a second content generation item and a data collection item on at least a portion of the display based on selecting the first content displayed on the display, and to receive the AI content generation request based on the second content generation item being selected or an object included in the first content being recognized.

11. In a method for supporting AI content services of electronic devices, An action to identify an object included in first content displayed on a display based on an AI content generation request; An operation of obtaining first information related to at least one of the object or the first content and second information related to the electronic device or the user; An operation of generating a prompt for input of a generative artificial intelligence model based on at least one of the first content, the first information, and the second information; and A method comprising an action of generating second content that is personalized and related to the first content using a generative AI (artificial intelligence) using the generated prompt as input.

12. In paragraph 11, The above second content includes AI (artificial intelligence) content, education content, or learning content, The first information includes at least one of object identification information, content description keywords analyzing the first content or the identified object, and additional information based on metadata of the content. A method wherein the second information includes at least one of user learning setting information, user app usage information, user profile information, and context information.

13. In paragraph 11, An operation of obtaining first information related to at least one of the above object or the above first content and second information related to the electronic device or the user, A method further comprising an action of selecting and extracting the second information associated with the first information.

14. In paragraph 11, The action of identifying the above object is, A method characterized in that the object is identified through user input selecting the object included in the first content or object recognition within the first content.

15. In paragraph 11, A method further comprising an action of displaying the generated second content on a display, wherein the second content includes a content or object image, object identification information, a type of generated AI content, and a content description.

Images