Electronic device, method, and non-transitory computer-readable recording medium for generating visual content using different data sets

Abstract

An electronic device is disclosed. The electronic device may obtain one sequence of user inputs for requesting generation of visual content for a plurality of users. The electronic device may, on the basis of the user inputs, generate first visual content through a generative AI model by using first data that is permitted to be viewed by first users having a first privacy level among the plurality of users. The electronic device may generate second visual content through the generative AI model on the basis of second data that is permitted to be viewed by second users having a second privacy level higher than the first privacy level among the plurality of users. The second data may include the first data and other data not included in the first data.

Description

Electronic device, method, and non-transitory computer-readable recording medium for generating visual content using different data sets

[0001] The following descriptions relate to electronic devices, methods, and non-transitory computer-readable recording media for generating visual content using different data sets.

[0002] Artificial intelligence is a technology for simulating the neural activity of humans (or living things), such as perception and / or inference, and can be implemented by hardware, software, or a combination of these designed to perform computations for simulating neural activity.

[0003] The above information may be provided as background art to aid in understanding the present disclosure. No claim or determination is made as to whether any of the above is applicable as prior art related to the present disclosure.

[0004] An electronic device is disclosed. The electronic device may include at least one processor including a processing circuit and a memory storing instructions and including one or more storage media. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to obtain a sequence of user inputs for requesting the generation of visual content for a plurality of users. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to generate first visual content through the generative AI model based on first data that is permitted to be viewed by first users among the plurality of users having a first privacy level, based on the user input. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to generate second visual content through the generative AI model based on second data that is permitted to be viewed by second users among the plurality of users having a second privacy level higher than the first privacy level. The second data may include the first data and other data not included in the first data.

[0005] A method is disclosed. The method can be performed on an electronic device. The method can include obtaining a sequence of user inputs for requesting the generation of visual content for a plurality of users. The method can include generating first visual content using the generative AI model based on first data that is permitted to be viewed by first users among the plurality of users having a first privacy level based on the user input. The method can include generating second visual content using the generative AI model based on second data that is permitted to be viewed by second users among the plurality of users having a second privacy level higher than the first privacy level. The second data can include the first data and other data not included in the first data.

[0006] A non-transitory computer-readable storage medium is disclosed. The non-transitory computer-readable storage medium may store a program including instructions. The instructions, when individually or collectively executed by at least one processor of an electronic device, may cause the electronic device to obtain a sequence of user inputs for requesting the generation of visual content for a plurality of users. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to generate first visual content through the generative AI model based on first data that is permitted to be viewed by first users among the plurality of users having a first privacy level, based on the user input. The instructions, when executed individually or collectively by the at least one processor, may cause the electronic device to generate second visual content through the generative AI model based on second data that is permitted to be viewed by second users among the plurality of users having a second privacy level higher than the first privacy level. The second data may include the first data and other data not included in the first data.

[0007] In connection with the description of the drawings, the same or similar reference numerals may be used for the same or similar components.

[0008] FIG. 1 is a block diagram of an electronic device within a network environment according to various embodiments.

[0009] FIG. 2 is a block diagram of an electronic device according to one embodiment.

[0010] FIG. 3A is a diagram illustrating user input of a user according to one embodiment.

[0011] FIG. 3b is a diagram illustrating a user interface (UI) for selecting users according to one embodiment.

[0012] Figure 4 is a diagram illustrating data sets according to one embodiment.

[0013] FIG. 5 is a diagram illustrating generated visual contents according to one embodiment.

[0014] FIG. 6 is a diagram illustrating user input according to one embodiment.

[0015] FIG. 7 is a diagram illustrating data sets according to one embodiment.

[0016] FIG. 8A is a diagram illustrating generated visual content according to one embodiment.

[0017] FIG. 8b is a diagram illustrating generated visual content according to one embodiment.

[0018] FIG. 8c is a diagram illustrating generated visual content according to one embodiment.

[0019] FIG. 8d is a diagram illustrating generated visual content according to one embodiment.

[0020] FIG. 9a is a diagram illustrating a UI according to one embodiment.

[0021] FIG. 9b is a diagram illustrating generated visual content according to one embodiment.

[0022] FIG. 9c is a diagram illustrating generated visual content according to one embodiment.

[0023] FIG. 10 is a diagram illustrating an example of an operation in which an electronic device transmits data sets to different electronic devices, according to one embodiment.

[0024] FIG. 11A is a diagram illustrating an example of a UI displayed by an electronic device according to one embodiment.

[0025] FIG. 11b is a diagram illustrating an example of a UI displayed by an electronic device according to one embodiment.

[0026] FIG. 12 is a diagram illustrating user input according to one embodiment.

[0027] FIG. 13 is a diagram illustrating data sets according to one embodiment.

[0028] FIG. 14A is a diagram illustrating generated visual content according to one embodiment.

[0029] FIG. 14b is a diagram illustrating generated visual content according to one embodiment.

[0030] FIG. 15 is a flowchart illustrating an operation of an electronic device generating visual content according to one embodiment.

[0031] FIG. 16 is a flowchart illustrating an operation of an electronic device to identify data sets for generating visual content, according to one embodiment.

[0032] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings so that those skilled in the art can easily implement the present disclosure. However, the present disclosure may be implemented in various different forms and is not limited to the embodiments described herein. In connection with the description of the drawings, the same or similar reference numerals may be used for identical or similar components. Furthermore, in the drawings and related descriptions, descriptions of well-known functions and configurations may be omitted for clarity and conciseness.

[0033] FIG. 1 is a block diagram of an electronic device (101) within a network environment (100) according to various embodiments.

[0034] Referring to FIG. 1, in a network environment (100), an electronic device (101) may communicate with an electronic device (102) via a first network (198) (e.g., a short-range wireless communication network), or may communicate with at least one of an electronic device (104) or a server (108) via a second network (199) (e.g., a long-range wireless communication network). According to one embodiment, the electronic device (101) may communicate with the electronic device (104) via the server (108). According to one embodiment, the electronic device (101) may include a processor (120), a memory (130), an input module (150), an audio output module (155), a display module (160), an audio module (170), a sensor module (176), an interface (177), a connection terminal (178), a haptic module (179), a camera module (180), a power management module (188), a battery (189), a communication module (190), a subscriber identification module (196), or an antenna module (197). In some embodiments, the electronic device (101) may omit at least one of these components (e.g., the connection terminal (178)), or may have one or more other components added. In some embodiments, some of these components (e.g., the sensor module (176), the camera module (180), or the antenna module (197)) may be integrated into one component (e.g., the display module (160)).

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0051] The wireless communication module (192) can support 5G networks and next-generation communication technologies following the 4G network, such as NR access technology (new radio access technology). The NR access technology can support high-speed transmission of high-capacity data (eMBB (enhanced mobile broadband)), minimization of terminal power and connection of multiple terminals (mMTC (massive machine type communications)), or high reliability and low latency (URLLC (ultra-reliable and low-latency communications)). The wireless communication module (192) can support, for example, a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate. The wireless communication module (192) can support various technologies for securing performance in a high-frequency band, such as beamforming, massive multiple-input and multiple-output (MIMO), full dimensional MIMO (FD-MIMO), array antenna, analog beam-forming, or large scale antenna. The wireless communication module (192) can support various requirements specified in the electronic device (101), an external electronic device (e.g., the electronic device (104)), or a network system (e.g., the second network (199)). According to one embodiment, the wireless communication module (192) can support a peak data rate (e.g., 20 Gbps or more) for realizing eMBB, a loss coverage (e.g., 664 dB or less) for realizing mMTC, or a U-plane latency (e.g., 0.5 ms or less for downlink (DL) and uplink (UL), or 6 ms or less for round trip) for realizing URLLC.

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

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

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

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

[0056] FIG. 2 is a block diagram of an electronic device according to one embodiment.

[0057] Referring to FIG. 2, the electronic device (101) may include a processor (120), a memory (130), and an input module (150). In one embodiment, the electronic device (101) of FIG. 2 may correspond to the electronic device (101) of FIG. 1. In one embodiment, the processor (120), the memory (130), and the input module (150) of FIG. 2 may correspond to the processor (120), the memory (130), and the input module (150) of FIG. 1, respectively.

[0058] In one embodiment, the memory (130) may include a Gen AI (generative artificial intelligence) model interface (210), a GEN AI model (230), a data management module (240), a level determination module (245), a database (260), and level data (270). In one embodiment, each of the GEN AI model interface (210), the GEN AI model (230), the data management module (240), the level determination module (245), the database (260), and the level data (270) may be a program including one or more instructions.

[0059] In one embodiment, the GEN AI model interface (210) may be a user interface that can interact with a user. In one embodiment, the GEN AI model interface (210) may include an input handler (220) for obtaining user input, and an output interface (225) for providing output to the user. In one embodiment, each of the GEN AI model interface (210), the input handler (220), and the output interface (225) may be a program including one or more instructions. In one embodiment, the input handler (220) may provide a user with an interface for obtaining a user request (or query) to the GEN AI model (230) from the user.

[0060] In one embodiment, the GEN AI model interface (210) may obtain user input from a user through an input handler (220). For example, the user input may be input (e.g., voice input) obtained through an input module (150), but is not limited thereto. For example, the user input may be a touch input obtained through a display module (e.g., the display module (160) of FIG. 1).

[0061] In one embodiment, the user input may include, but is not limited to, an input for requesting the generation of visual content through the GEN AI model (230). For example, the user input may include an input for requesting the modification of visual content generated through the GEN AI model (230). For example, the user input may include an input for selecting (or determining) a target (or recipient) of the visual content generated through the GEN AI model (230) to be shared with.

[0062] In one embodiment, the user input may be a sequence of multiple user inputs. For example, the sequence of multiple user inputs may include a series of inputs for generating visual content through the GEN AI model (230).

[0063] For example, a sequence of multiple user inputs may include one or more user inputs for generating a prompt that is input to the GEN AI model (230).

[0064] For example, a sequence of multiple user inputs may include one or more user inputs for selecting multiple sharing targets.

[0065] For example, a sequence of multiple user inputs may include one or more user inputs for selecting a level (or privacy level) (or priority) of at least one of the multiple sharing targets.

[0066] For example, a sequence of multiple user inputs may include one or more user inputs that indicate the type of visual content to be generated. For example, the visual content may be content including text and / or images. For example, the visual content may be content for promoting (or introducing) a business (or individual) (e.g., a pamphlet, leaflet, catalog, or brochure). For example, the visual content may be content for promoting (or informing) an event (e.g., an invitation, wedding invitation, or poster). However, the present invention is not limited thereto. For example, the visual content may be content for conveying information (e.g., a list of events, a list of assets, or personal information).

[0067] For example, a sequence of multiple user inputs may include one or more user inputs for selecting data that can be used to generate visual content to be generated.

[0068] For example, a series of inputs for generating visual content may not be temporally consecutive. For example, one or more user inputs for generating a prompt, one or more user inputs for selecting multiple sharing targets, one or more user inputs for selecting a level of at least one sharing target, one or more user inputs for selecting data that can be used to generate the visual content to be generated, and / or one or more user inputs for indicating the type of visual content to be generated may be obtained at different points in time.

[0069] In one embodiment, the GEN AI model interface (210) may input user input obtained through the input handler (220) into the GEN AI model (230). In one embodiment, the GEN AI model interface (210) may input a request for generation of visual content based on the user input obtained through the input handler (220) into the GEN AI model (230). The request for generation of visual content may include a prompt obtained based on the user input.

[0070] In one embodiment, the prompt may include words (or sentences) to guide the generation of visual content based on user input. In one embodiment, the prompt may be a task instruction for the GEN AI model (230). For example, the prompt may include at least a portion of the content (or text) (or information) contained in the user input.

[0071] For example, at least one sentence (or at least one word) included in the prompt may describe characteristics of visual content to be generated through the GEN AI model (230) (e.g., size, color, shape, format (e.g., whether an image is included, whether text is included), and / or characteristics (e.g., location, size) of an object (e.g., an image or text). For example, characteristics of visual content to be generated through the GEN AI model (230) that are not included in the prompt may be set as default characteristics.

[0072] For example, at least one sentence (or at least one word) included in the prompt may describe information (e.g., information about the sharing target, electronic device information of the sharing target, level (or privacy level) (or priority) of the sharing target, information about the application that requested the generation of the visual content) to be referenced when the GEN AI model (230) generates the visual content. For example, at least one sentence (or at least one word) included in the prompt may indicate data (e.g., data stored in the database (260)) to be referenced when the GEN AI model (230) generates the visual object. However, the present invention is not limited thereto. For example, at least one sentence (or at least one word) included in the prompt may provide information (e.g., information about the sharing target, information about the electronic device of the sharing target, the level (or privacy level) (or priority) of the sharing target, information about the application that requested the generation of the visual content) for identifying data (e.g., data stored in the database (260)) to be referenced when the GEN AI model (230) generates a visual object.

[0073] For example, at least one sentence (or at least one word) included in a prompt can be extracted from text included in the user input, text represented by the user input, and / or a shared object indicated by the user input. For example, the prompt can be extracted by the input handler (220), but is not limited thereto. For example, the prompt can be extracted by another AI model. For example, the prompt can be generated by another AI model based on a request from the input handler (220). For example, the other AI model can be an AI model (e.g., a stable diffusion model) for performing a task of extracting words (or sentences) (e.g., captioning) from text included in the user input, text represented by the user input, and / or a shared object indicated by the user input.

[0074] In one embodiment, the GEN AI model interface (210) can output visual content acquired (or generated) through the GEN AI model (230) to the user through the output interface (225). For example, the GEN AI model interface (210) can output visual content through the display module (160). However, the present invention is not limited thereto. For example, the GEN AI model interface (210) can output content by requesting an external electronic device (e.g., the electronic device (102, 104) of FIG. 1) connected by wires and / or wirelessly to output visual content through a communication module (e.g., the communication module (190) of FIG. 1). For example, the GEN AI model interface (210) can output audio signals included in the visual content through an audio output module (e.g., the audio output module (155) of FIG. 1).

[0075] In one embodiment, the GEN AI model (230) can generate visual content based on user input obtained through the input handler (220). For example, the GEN AI model (230) can generate visual content through a prompt based on the user input. For example, the GEN AI model (230) can generate visual content based on a data set stored in the database (260) to which access is permitted through the prompt. In one embodiment, the GEN AI model (230) can provide the generated visual content to the output interface (225).

[0076] In one embodiment, the GEN AI model (230) may include an AI model including multiple parameters related to a neural network having a structure based on an encoder and a decoder, such as a transformer. In one embodiment, the GEN AI model (230) may include a bi-directional model based on learning for an encoder (e.g., bidirectional encoder representations from transformers (BERT)) or an auto-encoding model (e.g., a diffusion model). In one embodiment, the GEN AI model (230) may include an auto-regressor model based on learning for a decoder (e.g., a generative pre-trained transformer (GPT)). In one embodiment, the GEN AI model (230) may include a sequence-to-sequence model (e.g., stable diffusion, DALL-E 2) based on learning for an encoder and a decoder. In one embodiment, the GEN AI model (230) may include a large language model (LLM) for processing natural language based on a massive number of parameters, but is not limited thereto. The GEN AI model (230) may include parameters for driving a neural network such as a convolutional neural network (CNN), a recurrent neural network (RNN), a feedforward neural network (FNN), and / or a long short-term memory (LSTM).

[0077] In one embodiment, the data management module (240) may manage a database (260) that stores data of a user of the electronic device (101). In one embodiment, the data management module (240) may classify data (e.g., photos, videos, personal information, application data) stored in the database (260) into accessible data sets according to the level (or, privacy level) (or, priority) of the sharing target. In one embodiment, personal information may include personal information of an individual (e.g., name, social security number, address, contact information, date of birth, place of birth, or gender), family relationship information, physical information (e.g., face, iris, voice, genetic information, fingerprints, height, or weight), medical information (or, health information), education information (e.g., academic background, grades, certificates, or licenses), property information (e.g., income information, credit information, asset information, or real estate information), and / or location information.

[0078] In one embodiment, the data management module (240) may identify (or determine) data to be used to generate visual content. In one embodiment, the data management module (240) may identify (or determine) data to be used to generate visual content based on the level of the sharing target.

[0079] For example, the data management module (240) may identify (or determine) first data to be used to generate visual content to be provided to a sharing target with a relatively low level of data. For example, the data management module (240) may identify (or determine) second data to be used to generate visual content to be provided to a sharing target with a relatively high level of data. In one embodiment, the second data may include the first data and other data not included in the first data. For example, the first data may not include information for identifying a designated individual. For example, the second data may include the first data and other data that includes information for identifying a designated individual. For example, the first data may include photos of the designated individual, excluding facial photos. For example, the second data may include photos of the designated individual and the first data, but is not limited thereto. For example, the first data may include low-level personal information among the information for identifying the designated individual. Low-level personal information may include name, date of birth, and / or gender. For example, the second data may include relatively high levels of personal information and the first data, among information for identifying a given individual. The relatively high level of personal information may include unique identifier information (e.g., social security number, physical information, credit information, and / or medical information).

[0080] In one embodiment, the database (260) may be a local database of the electronic device (101) stored in the memory (130) of the electronic device (101), but is not limited thereto. For example, the database (260) may be a remote database (or a cloud database) stored externally (e.g., on a server (108)) accessible through the communication module (190) of the electronic device (101).

[0081] In one embodiment, the level determination module (245) may identify (or determine) the level (or privacy level) (or priority) of the sharing target (or recipient) of visual content. In one embodiment, the level (or privacy level) (or priority) may not be distinguished by numbers (or steps). For example, the level (or privacy level) (or priority) may be classified by keywords, categories, and / or images.

[0082] In one embodiment, the level determination module (245) may identify (or determine) the level of a shared object stored in the level data (270). In one embodiment, the level of a shared object may be stored in the level data (270) based on one or more user inputs for selecting a level of at least one shared object.

[0083] In one embodiment, the level determination module (245) may identify (or determine) the level of the sharing target based on relationship information between the sharing target and the user of the electronic device (101). For example, the relationship information may include the number (or frequency) of contacts (e.g., phone calls, text messages), conversation content, and / or relationships (e.g., friends, coworkers, family) between the sharing target and the user, but is not limited thereto. For example, the relationship information may include the number of chat rooms participated in together, distance, and / or the number (or frequency) of visual content transmissions.

[0084] In one embodiment, the level determination module (245) may identify (or determine) a level corresponding to a range corresponding to the number of contacts (or frequency) among a plurality of ranges as the level of the sharing target. Here, each of the plurality of ranges may be assigned a different level. In one embodiment, the level determination module (245) may identify (or determine) a level corresponding to at least one keyword as the level of the sharing target when the context of the conversation content corresponds to at least one keyword among a plurality of keywords. Here, each of the plurality of keywords may be assigned a different level. In one embodiment, the context of the conversation content may include a combination of words representing a summary of the conversation content between the sharing target and the user. In one embodiment, the level determination module (245) may identify (or determine) a level corresponding to a relationship established for the sharing target as the level of the sharing target. However, the present invention is not limited thereto. In one embodiment, the level determination module (245) may identify (or determine) the level of the sharing target as a level corresponding to the number of chat rooms in which the user has participated. In one embodiment, the level determination module (245) may identify (or determine) the level of the sharing target as a level corresponding to the number of times (or frequency) of visual content transmissions.

[0085] In one embodiment, the level data (270) may store the level (or privacy level) (or priority) of the sharing target (or recipient). In one embodiment, the level of the sharing target stored in the level data (270) may be stored in the electronic device (101) before obtaining a user input of a current sequence (e.g., a user input of a current sequence for generating (and / or modifying) the current visual content through the GEN AI model (230). The level of the sharing target stored in the electronic device (101) before obtaining a user input of a current sequence may be a level of the sharing target determined through a user input of a previous sequence before obtaining the user input of the current sequence.

[0086] Hereinafter, an operation of generating visual content by an electronic device (101) (or a processor (120) of the electronic device (101)) using different data sets may be described. In one embodiment, the operation of generating visual content may be performed as the processor (120) of the electronic device (101) executes instructions included in the GEN AI model interface (210), the GEN AI model (230), the data management module (240), the level determination module (245), the database (260), and / or the level data (270). The processor (120) may control the operations of the electronic device (101) by executing instructions stored in the memory (130). For example, the processor (120) may correspond to a plurality of processors that collectively perform a plurality of operations by dividing them among the processors.

[0087] In one embodiment, the processor (120) may obtain user input from a user via the input module (150). In one embodiment, the user input may be a sequence of user inputs for requesting generation of visual content for multiple sharing targets (or recipients) (or users). In one embodiment, the sequence of user inputs may include one or more user inputs for generating a prompt that is input to the GEN AI model (230). For example, the sequence of user inputs may include one or more user inputs for generating a prompt, one or more user inputs for selecting multiple sharing targets, one or more user inputs for selecting a level of at least one sharing target, one or more user inputs for selecting data that can be used to generate the visual content to be generated, and / or one or more user inputs for indicating a type of visual content to be generated.

[0088] In one embodiment, the processor (120) may identify (or determine) the level (or privacy level) (or priority) of sharing targets of visual content through the level determination module (245). For example, the processor (120) may identify (or determine) the level of sharing targets based on one or more user inputs for selecting the level of at least one sharing target among the sharing targets. For example, the processor (120) may identify (or determine) the level of sharing targets stored in the level data (270). For example, the processor (120) may identify (or determine) the level of sharing targets based on relationship information between the sharing target and the user of the electronic device (101). For example, if the level of the sharing target is not identified through a user input, the processor (120) may identify (or determine) the level of the sharing target based on the level of the sharing target stored in the level data (270). For example, if the level of the shared target stored in the level data (270) is not identified, the processor (120) can identify (or determine) the level of the shared target based on the relationship information.

[0089] In one embodiment, the processor (120) may classify the shared objects into multiple groups based on their levels. For example, the processor (120) may classify first shared objects having the same first level into a first group, and second shared objects having the same second level into a second group. However, the present invention is not limited thereto. In one embodiment, the processor (120) may classify shared objects having the same relationship into the same group based on relationship information. For example, the processor (120) may identify the lowest level among the levels of shared objects classified in the same group as the representative level of the group.

[0090] In one embodiment, the processor (120) may identify (or determine) data to be used to generate visual content through the data management module (240). For example, the processor (120) may identify (or determine) first data to be used to generate visual content to be provided to a sharing target with a relatively low level among data stored in the database (260). For example, the processor (120) may identify (or determine) second data to be used to generate visual content to be provided to a sharing target with a relatively high level among data stored in the database (260).

[0091] In one embodiment, the processor (120) may generate a prompt to be input to the GEN AI model (230). In one embodiment, the processor (120) may generate a prompt to be input to the GEN AI model (230) based on a sequence of user input. In one embodiment, the processor (120) may generate a single prompt to be input to the GEN AI model (230). In one embodiment, the single prompt may be generated based on a sequence of user input. In one embodiment, the single prompt may be a single prompt for the generation of two or more visual contents. However, the present invention is not limited thereto. For example, the processor (120) may generate two or more prompts to be input to the GEN AI model (230). In one embodiment, the two or more prompts may be generated based on a sequence of user input. In one embodiment, the two or more prompts may be two or more prompts for the generation of two or more visual contents. For example, each of two or more prompts may be a prompt for the creation of one piece of visual content.

[0092] For example, a prompt may include one or more words that indicate characteristics (e.g., size, color, shape, format (e.g., whether it contains an image, whether it contains text), and / or characteristics (e.g., location, size) of an object (e.g., an image or text) and / or type (e.g., invitation, wedding invitation, or poster) of the visual content to be generated.

[0093] For example, a prompt may include one or more words that indicate information to reference when generating visual content (e.g., the sharing target, information about the sharing target's electronic device, information about the application that requested the generation of the visual content).

[0094] For example, a prompt may include one or more words indicating the level of the sharing target and / or data to be referenced when generating a visual object. In one embodiment, the processor (120) may generate a prompt indicating data that is permitted to be viewed for sharing targets having a specified privacy level among a plurality of sharing targets. In one embodiment, the processor (120) may generate a prompt indicating data corresponding to the level of the sharing target (e.g., data to be referenced when generating a visual object). For example, the prompt may include words for requesting generation of visual content using data corresponding to the level of the sharing target.

[0095] In one embodiment, the processor (120) may generate visual content through the GEN AI model (230). For example, the processor (120) may generate visual content by inputting a prompt to the GEN AI model (230). In one embodiment, the processor (120) may generate at least one visual content by inputting one prompt to the GEN AI model (230). For example, the number of at least one visual content may correspond to the number of levels of the shared objects. For example, if the levels of the shared objects all have the same level of 1, the at least one visual content generated by inputting one prompt to the GEN AI model (230) may be 1. For example, if the levels of the shared objects have different n levels (n is an integer), the at least one visual content generated by inputting one prompt to the GEN AI model (230) may be n (or less than n). However, the present invention is not limited thereto. For example, the processor (120) can generate two or more visual contents by inputting two or more prompts into the GEN AI model (230). For example, the processor (120) can generate two or more visual contents by inputting a number of prompts corresponding to the number of levels of shared objects into the GEN AI model (230). For example, the number of prompts may correspond to the number of levels of shared objects.

[0096] In one embodiment, the processor (120) may output visual content generated by the GEN AI model (230) through the output interface (225). For example, the processor (120) may output visual content through the display module (160).

[0097] As described above, the electronic device (101) can determine the data to be used to generate visual content for multiple sharing targets based on the levels of the multiple sharing targets without any user intervention. Accordingly, the number of user input steps required to generate visual content through the GEN AI model (230) can be reduced. Furthermore, based on the relationship between the user of the electronic device (101) and the multiple sharing targets, the use of the user's personal information, which is not permitted to be viewed by the sharing targets, in generating visual content through the GEN AI model (230) can be reduced.

[0098] FIG. 3A is a diagram illustrating user input according to an embodiment. FIG. 3B is a diagram illustrating a user interface (UI) for selecting users according to an embodiment. FIG. 4 is a diagram illustrating data sets according to an embodiment. FIG. 5 is a diagram illustrating generated visual content according to an embodiment.

[0099] FIGS. 3A to 5 may be described with reference to the electronic device (101) of FIG. 2 (or components of the electronic device (101)). The operations described with reference to FIGS. 3A to 5 may be performed as instructions included in the GEN AI model interface (210), the GEN AI model (230), the data management module (240), the level determination module (245), the database (260), and / or the level data (270) of FIG. 2 are executed by the processor (120) of the electronic device (101).

[0100] Referring to FIG. 3A, a user (300) may input a user input (310) requesting the generation of visual content (e.g., an invitation) to an electronic device (101). For example, the electronic device (101) may obtain the user's (300) speech (or voice input) as the user input (310) through an input module (150).

[0101] In one embodiment, the electronic device (101) may identify (or determine) sharing targets of visual content based on obtaining user input (310). For example, the electronic device (101) may identify (or determine) sharing targets of visual content through the output interface (225) of the GEN AI model interface (210) for interacting with the user (300). For example, referring to FIG. 3B, the electronic device (101) may identify (or determine) sharing targets of visual content based on additional user input for an area (320) for selecting sharing targets on an output interface (225) output through a display module (e.g., the display module (160) of FIG. 1). For example, the electronic device (101) may identify (or determine) sharing targets of visual content based on a user input for selecting at least some of the visual objects within the area (320). For example, the electronic device (101) may identify, based on user input, sharing targets corresponding to a visual object (321) indicating that a sharing target is selected. For example, the electronic device (101) may identify, based on user input, sharing targets corresponding to a visual object (325) indicating that a sharing target is not selected.

[0102] In one embodiment, the electronic device (101) may identify (or determine) the privacy level of the sharing targets of the visual content based on obtaining a user input (310). For example, the electronic device (101) may identify (or determine) the privacy level of the sharing targets of the visual content through the output interface (225) of the GEN AI model interface (210) for interacting with the user (300). For example, referring to FIG. 3B, the electronic device (101) may identify (or determine) the privacy level of the sharing targets of the visual content based on an additional user input for an area (330) for determining the privacy level of the sharing targets on the output interface (225) output through the display module (160). For example, the electronic device (101) may identify (or determine) the privacy level of sharing targets of visual content based on a user input that determines a privacy level for at least some of the visual objects within the area (330). For example, the electronic device (101) may identify the privacy level of sharing targets corresponding to a visual object (331) indicating that the privacy level of the sharing target is not selected. For example, the electronic device (101) may identify the privacy level of sharing targets corresponding to a visual object (335) indicating that the privacy level of the sharing target is selected. For example, the electronic device (101) may not determine the privacy level of sharing targets corresponding to a visual object (339) indicating that selection of a privacy level is disabled because the sharing target is not a sharing target.

[0103] In one embodiment, the electronic device (101) can identify (or determine) data to be used to generate visual content. In one embodiment, the electronic device (101) can identify (or determine) data to be used to generate visual content based on the privacy level of the sharing target.

[0104] In one embodiment, referring to FIG. 4, the electronic device (101) may identify (or determine) a photo (400) as data to be used for generating visual content based on a user input (310). For example, the electronic device (101) may identify (or determine) a photo (400) related to "Jieun," the host of the invitation, as data to be used for generating visual content based on the user input (310). However, the present invention is not limited thereto. For example, the electronic device (101) may identify (or determine) other data (e.g., videos or personal information) other than the photo (400) as data to be used for generating visual content based on the user input (310).

[0105] In one embodiment, the electronic device (101) may classify data (e.g., photos) stored in the database (260) into accessible data sets according to the privacy level of the sharing target through the level determination module (245). In one embodiment, the electronic device (101) may identify (or determine) a first set of photos (410) to be used for generating visual content to be provided to a sharing target with a relatively low privacy level among the photos (400). For example, the electronic device (101) may identify (or determine) a second set of photos (420) to be used for generating visual content to be provided to a sharing target with a relatively high privacy level among the photos (400). In one embodiment, the first set of photos (410) may be a subset of the second set of photos (420). For example, the second photo set (420) may include the first photo set (410) and other data not included in the first photo set (410). However, the present invention is not limited thereto. For example, the first photo set (410) may include a photo set (431) that is in an intersection relationship with the second photo set (420) and a photo set (411) that is in a difference relationship with the second photo set (420). For example, the second photo set (420) may include a photo set (431) that is in an intersection relationship with the first photo set (410) and a photo set (421) that is in a difference relationship with the first photo set (410).

[0106] For example, the first set of photos (410) may not include information for identifying a designated individual. For example, the second set of photos (420) may include the first set of photos (410) and other data containing information for identifying a designated individual. For example, the first set of photos (410) may include photos of a designated individual (e.g., “Ji-eun”), excluding facial photos. For example, the second set of photos (420) may include photos of a designated individual (e.g., “Ji-eun”) and the first set of photos (410). However, this is not limited thereto. For other types of data (e.g., personal information) other than photos (400), the first data set (410) may include low-level personal information among the information for identifying a designated individual. Low-level personal information may include name, date of birth, and / or gender. For example, in the case of other types of data (e.g., personal information) other than photographs (400), the second data set (420) may include a relatively high level of personal information and the first data set (410) among information for identifying a given individual. The relatively high level of personal information may include unique identification information (e.g., social security number, physical information, credit information, and / or medical information).

[0107] In one embodiment, the electronic device (101) may generate a prompt to be input to the GEN AI model (230). In one embodiment, the electronic device (101) may generate a prompt to be input to the GEN AI model (230) based on a sequence of user input. In one embodiment, the electronic device (101) may generate one prompt to be input to the GEN AI model (230). However, the present invention is not limited thereto. For example, the electronic device (101) may generate two or more prompts to be input to the GEN AI model (230).

[0108] For example, a prompt may include one or more words that indicate characteristics (e.g., size, color, shape, format (e.g., whether it contains an image, whether it contains text), and / or characteristics (e.g., location, size) of an object (e.g., an image or text) and / or type (e.g., invitation, wedding invitation, or poster) of the visual content to be generated.

[0109] For example, a prompt may include one or more words that indicate information to reference when generating visual content (e.g., the sharing target, information about the sharing target's electronic device, information about the application that requested the generation of the visual content).

[0110] For example, a prompt may include one or more words indicating a level of a sharing target and / or data to be referenced when generating a visual object. In one embodiment, the electronic device (101) may generate a prompt indicating data that is permitted to be viewed for sharing targets having a specified privacy level among a plurality of sharing targets. In one embodiment, the electronic device (101) may generate a prompt indicating data corresponding to the level of the sharing target (e.g., data to be referenced when generating a visual object). For example, the prompt may include words for requesting generation of visual content using data corresponding to the level of the sharing target.

[0111] In one embodiment, the electronic device (101) can generate visual content through the GEN AI model (230). For example, the electronic device (101) can generate visual content by inputting a prompt to the GEN AI model (230). In one embodiment, the electronic device (101) can generate at least one visual content by inputting one prompt to the GEN AI model (230). For example, the number of at least one visual content may correspond to the number of levels of the shared objects.

[0112] For example, referring to FIG. 5, the electronic device (101) may generate visual content (510) for sharing targets with the lowest privacy level. For example, the visual content (510) may take the form of a birthday party invitation. For example, the visual content (510) may not include personal information (e.g., name) about the birthday party host. For example, the visual content (510) may not include a photo of the birthday party host. For example, instead of a photo of the birthday party host, the visual content (510) may include an image (515) related to the birthday party host.

[0113] For example, referring to FIG. 5, the electronic device (101) may generate visual content (530) for sharing targets with the next highest privacy level. For example, the visual content (530) may take the form of a birthday party invitation. For example, the visual content (530) may include some personal information (e.g., name) about the host of the birthday party. For example, the visual content (530) may include a photo (535) of the host of the birthday party, excluding facial photos. For example, the phrases and / or words included in the visual content (530) may differ from those in the visual contents (510 and 550). For example, the phrases included in the visual content (530) may have a formal tone.

[0114] For example, referring to FIG. 5, the electronic device (101) may generate visual content (550) for sharing targets with the highest privacy level. For example, the visual content (550) may take the form of a birthday party invitation. For example, the visual content (550) may include some personal information (e.g., name) about the host of the birthday party. For example, the visual content (550) may include facial photos (551, 553, 555) among photos of the host of the birthday party. For example, the phrases and / or words included in the visual content (550) may differ from those in the visual contents (510 and 530). For example, the phrases included in the visual content (550) may have an informal tone.

[0115] In one embodiment, the visual contents (510, 530, and 550) of FIG. 5 are illustrated as having the form of a pamphlet, but this is merely an example. The type of the visual contents (510, 530, and 550) may not be limited to images and / or videos.

[0116] In one embodiment, the electronic device (101) can output visual contents (510, 530, and 550) generated through the GEN AI model (230) through the output interface (225). For example, the electronic device (101) can output visual contents (510, 530, and 550) through the display module (160).

[0117] Thereafter, the electronic device (101) may modify the visual contents (510, 530, and 550) generated by the GEN AI model (230) through additional user input from the user. In one embodiment, the additional user input may be included as a sequence of user input.

[0118] Thereafter, the electronic device (101) can transmit visual contents (510, 530, and 550) generated through the GEN AI model (230) to the electronic devices of the sharing targets through additional user input. For example, the electronic device (101) can transmit visual contents (510, 530, and 550) corresponding to the level of the sharing targets to the electronic devices of the sharing targets.

[0119] According to an embodiment, the electronic device (101) may generate visual content based on inputting the privacy levels of the sharing targets of the visual content into the GEN AI model (230). For example, the electronic device (101) may generate visual content based on inputting a prompt indicating the privacy levels of the sharing targets of the visual content into the GEN AI model (230). For example, the electronic device (101) may generate visual content based on inputting the privacy levels of the sharing targets of the visual content into the GEN AI model (230) without determining data to be used for generating the visual content based on the privacy levels of the sharing targets. For example, the electronic device (101) may generate visual content including different contents based on inputting a prompt indicating the privacy levels of the sharing targets of the visual content into the GEN AI model (230) without limiting the accessible data sets according to the privacy levels of the sharing targets to the GEN AI model (230). For example, the GEN AI model (230) can generate visual content with varying degrees of personal information exposure, depending on the privacy level of the subjects being shared. Accordingly, visual content generated based on the same data set (e.g., photo (400)) may have varying degrees of personal information exposure, depending on the privacy level of the subjects being shared.

[0120] FIG. 6 is a diagram illustrating user input according to an embodiment. FIG. 7 is a diagram illustrating data sets according to an embodiment. FIG. 8a is a diagram illustrating generated visual content according to an embodiment. FIG. 8b is a diagram illustrating generated visual content according to an embodiment. FIG. 8c is a diagram illustrating generated visual content according to an embodiment. FIG. 8d is a diagram illustrating generated visual content according to an embodiment.

[0121] FIGS. 6 to 8D may be described with reference to the electronic device (101) of FIG. 2 (or components of the electronic device (101)). The operations described with reference to FIGS. 6 to 8D may be performed as instructions included in the GEN AI model interface (210), the GEN AI model (230), the data management module (240), the level determination module (245), the database (260), and / or the level data (270) of FIG. 2 are executed by the processor (120) of the electronic device (101).

[0122] Referring to FIG. 6, a user (600) may input a user input (610) requesting the generation of visual content (e.g., asset information) to an electronic device (101). For example, the electronic device (101) may obtain the user's (600) speech (or voice input) as the user input (610) through an input module (150).

[0123] In one embodiment, the electronic device (101) can identify (or determine) sharing targets of visual content based on obtaining user input (610). In one embodiment, the electronic device (101) can identify (or determine) the privacy level of sharing targets of visual content based on obtaining user input (610).

[0124] In one embodiment, the electronic device (101) can identify (or determine) data to be used to generate visual content. In one embodiment, the electronic device (101) can identify (or determine) data to be used to generate visual content based on the privacy level of the sharing target.

[0125] In one embodiment, referring to FIG. 7, the electronic device (101) may identify (or determine) asset data (700) as data to be used for generating visual content based on user input (610). For example, the electronic device (101) may identify (or determine) asset data (700) as data to be used for generating visual content based on user input (610). However, the present invention is not limited thereto. For example, the electronic device (101) may identify (or determine) other data (e.g., other personal information) other than asset data (700) as data to be used for generating visual content based on user input (610).

[0126] In one embodiment, the electronic device (101) may classify data (e.g., asset data (700)) stored in the database (260) into accessible data sets according to the privacy level of the sharing target through the level determination module (245). In one embodiment, the electronic device (101) may identify (or determine) a first asset data set (710) to be used for generating visual content to be provided to a sharing target with a relatively low privacy level among the asset data (700). For example, the electronic device (101) may identify (or determine) a second asset data set (720) to be used for generating visual content to be provided to a sharing target with a relatively high privacy level among the asset data (700). In one embodiment, the first asset data set (710) may be a subset of the second asset data set (720), but is not limited thereto. For example, a first asset data set (710) may include an asset data set (731) that is in an intersection relationship with a second asset data set (720) and an asset data set (711) that is in a difference relationship with the second asset data set (720). For example, a second asset data set (720) may include an asset data set (731) that is in an intersection relationship with the first asset data set (710) and an asset data set (721) that is in a difference relationship with the first asset data set (710).

[0127] For example, the first asset data set (710) may include low-level personal information (or, property information) among information for identifying a designated individual. Low-level personal information may include name, date of birth, gender, and / or simplified property information. For example, the second asset data set (720) may include relatively high-level personal information among information for identifying a designated individual and the first asset data set (710). The relatively high-level personal information may include unique identifiers (e.g., Social Security Number) and / or non-simplified property information.

[0128] In one embodiment, the electronic device (101) may generate a prompt to be input to the GEN AI model (230). In one embodiment, the electronic device (101) may generate a prompt to be input to the GEN AI model (230) based on a sequence of user input. In one embodiment, the electronic device (101) may generate one prompt to be input to the GEN AI model (230). However, the present invention is not limited thereto. For example, the electronic device (101) may generate two or more prompts to be input to the GEN AI model (230).

[0129] For example, a prompt may include one or more words indicating a level of a sharing target and / or data to be referenced when generating a visual object. In one embodiment, the electronic device (101) may generate a prompt indicating data that is permitted to be viewed for sharing targets having a specified privacy level among a plurality of sharing targets. In one embodiment, the electronic device (101) may generate a prompt indicating data corresponding to the level of the sharing target (e.g., data to be referenced when generating a visual object). For example, the prompt may include words for requesting generation of visual content using data corresponding to the level of the sharing target.

[0130] In one embodiment, the electronic device (101) can generate visual content through the GEN AI model (230). For example, the electronic device (101) can generate visual content by inputting a prompt to the GEN AI model (230). In one embodiment, the electronic device (101) can generate at least one visual content by inputting one prompt to the GEN AI model (230). For example, the number of at least one visual content may correspond to the number of levels of the shared objects.

[0131] For example, referring to FIG. 8A, the electronic device (101) can generate visual content for sharing targets with the lowest privacy level. For example, the visual content of FIG. 8A may have a table format in which data is entered into entries separated by rows and columns. For example, the visual content of FIG. 8A may include simplified personal information and simplified real estate information. For example, the visual content of FIG. 8A may include simplified financial goals.

[0132] For example, referring to FIG. 8B, the electronic device (101) can generate visual content for sharing targets with the highest privacy level. For example, the visual content of FIG. 8B may have a table format in which data is entered into entries separated by rows and columns. For example, the visual content of FIG. 8B may include detailed personal information and detailed real estate information. For example, the visual content of FIG. 8B may include detailed financial goals.

[0133] For example, referring to FIG. 8C, the electronic device (101) can generate visual content for sharing targets with the lowest privacy level. For example, the visual content of FIG. 8C may have a table format in which data is entered into entries distinguished by rows and columns. For example, the visual content of FIG. 8C may include simplified personal information, simplified family relationship information, and simplified asset information (e.g., simplified income information, simplified credit information, and simplified asset information). For example, the visual content of FIG. 8C may include simplified financial goals.

[0134] For example, referring to FIG. 8D , the electronic device (101) can generate visual content for sharing targets with the highest privacy level. For example, the visual content of FIG. 8D may have a table format in which data is entered into entries separated by rows and columns. For example, the visual content of FIG. 8D may include detailed personal information, detailed family relationship information, and detailed financial information (e.g., detailed income information, detailed credit information, and detailed asset information). For example, the visual content of FIG. 8D may include detailed financial goals.

[0135] In one embodiment, the visual contents of FIGS. 8A and 8B may be content to be provided to a real estate manager. In one embodiment, the visual contents of FIGS. 8C and 8D may be content to be provided to a property manager.

[0136] In one embodiment, the electronic device (101) may output visual contents (e.g., the visual contents of FIGS. 8A to 8D) generated through the GEN AI model (230) through the output interface (225). For example, the electronic device (101) may output visual contents (e.g., the visual contents of FIGS. 8A to 8D) through the display module (160).

[0137] Thereafter, the electronic device (101) may modify the visual contents generated by the GEN AI model (230) (e.g., the visual contents of FIGS. 8A to 8D ) through additional user input from the user. In one embodiment, the additional user input may be included as a sequence of user input.

[0138] Thereafter, the electronic device (101) may transmit visual contents generated by the GEN AI model (230) (e.g., the visual contents of FIGS. 8A to 8D ) to the electronic devices of the sharing targets through additional user input. For example, the electronic device (101) may transmit visual contents corresponding to the level of the sharing targets (e.g., the visual contents of FIGS. 8A to 8D ) to the electronic devices of the sharing targets.

[0139] According to an embodiment, the electronic device (101) may generate visual content based on inputting the privacy levels of the sharing targets of the visual content into the GEN AI model (230). For example, the electronic device (101) may generate visual content including different contents based on inputting a prompt indicating the privacy levels of the sharing targets of the visual content into the GEN AI model (230), without limiting the accessible data sets according to the privacy levels of the sharing targets. For example, the GEN AI model (230) may generate visual content in which the degree of personal information exposure varies depending on the privacy levels of the sharing targets. Accordingly, visual content generated based on the same data set (e.g., asset data (700)) may have different degrees of personal information exposure depending on the privacy levels of the sharing targets.

[0140] FIG. 9A is a diagram illustrating a UI according to an embodiment. FIG. 9B is a diagram illustrating generated visual content according to an embodiment. FIG. 9C is a diagram illustrating generated visual content according to an embodiment.

[0141] FIGS. 9A to 9C may be described with reference to the electronic device (101) of FIG. 2 (or components of the electronic device (101)). The operations described with reference to FIGS. 9A to 9C may be performed as instructions included in the GEN AI model interface (210), the GEN AI model (230), the data management module (240), the level determination module (245), the database (260), and / or the level data (270) of FIG. 2 are executed by the processor (120) of the electronic device (101).

[0142] Referring to FIG. 9, a user may input a user input (910) requesting the generation of visual content (e.g., an invitation) to an electronic device (101). For example, the electronic device (101) may obtain a user's text input as a user input (910) from the user through a screen (900) generated through a GEN AI model interface (210).

[0143] In one embodiment, the electronic device (101) can identify (or determine) sharing targets of visual content based on obtaining user input (910). In one embodiment, the electronic device (101) can identify (or determine) the privacy level of sharing targets of visual content based on obtaining user input (910).

[0144] In one embodiment, the electronic device (101) can identify (or determine) data to be used to generate visual content. In one embodiment, the electronic device (101) can identify (or determine) data to be used to generate visual content based on the privacy level of the sharing target.

[0145] In one embodiment, the electronic device (101) may identify (or determine) a photo as data to be used to generate visual content based on user input (910). For example, the electronic device (101) may identify (or determine) a photo associated with a user who is the host of the invitation as data to be used to generate visual content based on user input (910).

[0146] In one embodiment, the electronic device (101) may classify data (e.g., photos) stored in the database (260) into accessible data sets according to the privacy level of the sharing target through the level determination module (245). In one embodiment, the electronic device (101) may identify (or determine) a first set of photos to be used to generate visual content to be provided to a sharing target with a relatively low privacy level among photos. For example, the data management module (240) may identify (or determine) a second set of photos to be used to generate visual content to be provided to a sharing target with a relatively high privacy level among photos. In one embodiment, the first set of photos may be a subset of the second set of photos, but is not limited thereto. For example, the first set of photos may include a set of photos that is an intersection with the second set of photos and a set of photos that is a difference with the second set of photos. For example, the second photo set may include a photo set that is in an intersection relationship with the first photo set and a photo set that is in a difference relationship with the first photo set.

[0147] For example, the first set of photos may not include information for identifying a specific individual. For example, the second set of photos may include the first set of photos and other data containing information for identifying a specific individual. For example, the first set of photos may include photos of a specific individual (e.g., a user) excluding facial photos. For example, the second set of photos may include photos of a specific individual (e.g., a user) and the first set of photos.

[0148] In one embodiment, the electronic device (101) may generate a prompt to be input to the GEN AI model (230). In one embodiment, the electronic device (101) may generate a prompt to be input to the GEN AI model (230) based on a sequence of user input. In one embodiment, the electronic device (101) may generate one prompt to be input to the GEN AI model (230). However, the present invention is not limited thereto. For example, the electronic device (101) may generate two or more prompts to be input to the GEN AI model (230).

[0149] In one embodiment, the electronic device (101) may output visual contents generated through the GEN AI model (230) on the screen (900) through the output interface (225). For example, referring to FIG. 9A, the electronic device (101) may include a guide text (920) indicating that the generation of visual contents is complete through the display module (160), visual objects (930, 940) that can confirm the visual contents, and lists (950, 960) of sharing targets that receive the visual contents.

[0150] For example, referring to FIG. 9B, the electronic device (101) may display visual content (970) in response to a user input selecting a visual object (930). In one embodiment, the electronic device (101) may display visual content (970) for sharing targets with the highest privacy level in response to the user input selecting the visual object (930). For example, the visual content (970) may take the form of a wedding invitation. For example, the visual content (970) may include some personal information (e.g., name) of the invitees to the wedding. For example, the visual content (970) may include facial photos (975) among photos of the invitees to the wedding.

[0151] For example, referring to FIG. 9C, the electronic device (101) may display visual content (980) in response to a user input selecting a visual object (940). In one embodiment, the electronic device (101) may display visual content (980) for sharing targets with the lowest privacy level. For example, the visual content (980) may take the form of a wedding invitation. For example, the visual content (980) may not include personal information (e.g., name) about the invitees to the wedding. For example, the visual content (980) may not include a photo of the invitees to the wedding. For example, the visual content (980) may include a picture (985) related to the invitees to the wedding instead of a photo of the invitees to the wedding.

[0152] Thereafter, the electronic device (101) can modify the visual contents (970 and 980) generated by the GEN AI model (230) through additional user input from the user. In one embodiment, the additional user input can be included as a sequence of user input.

[0153] Thereafter, the electronic device (101) may transmit visual contents (970 and 980) generated through the GEN AI model (230) to the electronic devices of the sharing targets through additional user input. For example, the electronic device (101) may transmit visual contents (970 and 980) corresponding to the level of the sharing targets to the electronic devices of the sharing targets.

[0154] FIG. 10 is a diagram illustrating an example of an operation in which an electronic device transmits data sets to different electronic devices, according to one embodiment.

[0155] FIG. 10 may be described with reference to the electronic device (101) of FIG. 2 (or components of the electronic device (101)). The operations described with reference to FIG. 10 may be performed as instructions included in the GEN AI model interface (210), the GEN AI model (230), the data management module (240), the level determination module (245), the database (260), and / or the level data (270) of FIG. 2 are executed by the processor (120) of the electronic device (101).

[0156] In one embodiment, the electronic device (101) may obtain user input requesting the generation of visual content. In one embodiment, the electronic device (101) may identify (or determine) sharing targets of the visual content based on obtaining the user input.

[0157] In one embodiment, the electronic device (101) can identify (or determine) electronic devices (1001, 1003, 1005) of the sharing targets of visual content based on obtaining user input.

[0158] In one embodiment, the electronic device (101) may identify (or determine) a privacy level corresponding to the electronic devices (1001, 1003, 1005) of the sharing targets of the visual content based on obtaining a user input (310). For example, the electronic device (101) may identify (or determine) a privacy level based on a user input determining a privacy level for the electronic devices (1001, 1003, 1005) of the sharing targets. However, the present invention is not limited thereto. For example, the electronic device (101) may identify a privacy level for the electronic devices (1001, 1003, 1005) of the sharing targets for which a privacy level is not selected based on data stored in the database (260). For example, the privacy level for electronic devices (1001, 1003, 1005) may be determined based on the type of electronic devices (1001, 1003, 1005). For example, a tablet PC (personal computer) may have the highest sharing level. For example, a smartphone may have the next highest sharing level. For example, a laptop may have the lowest sharing level. However, this is not limited thereto. For example, the privacy level for electronic devices (1001, 1003, 1005) may be determined based on the privacy levels of the sharing targets using the electronic devices (1001, 1003, 1005). For example, even when using the same type of electronic device, the privacy level may change depending on the privacy level of the sharing target as the sharing target using the electronic device changes.

[0159] In one embodiment, the electronic device (101) can identify (or determine) data to be used to generate visual content. In one embodiment, the electronic device (101) can identify (or determine) data to be used to generate visual content based on the privacy levels of the electronic devices (1001, 1003, 1005) with which it is to be shared.

[0160] For example, the electronic device (101) may identify (or determine) data to be used for generating visual content based on the privacy levels of the electronic devices (1001, 1003, 1005) that will receive the user's personal data (e.g., game play video and / or play history). For example, the electronic device (101) may identify (or determine) the entire game play video and the entire play history as data to be used for generating visual content for the electronic device (1001) with the highest privacy level. For example, the electronic device (101) may identify (or determine) the game highlight video and the play summary as data to be used for generating visual content for the electronic device (1003) with the next highest privacy level. For example, the electronic device (101) may identify (or determine) the game video summary as data to be used to generate visual content for the electronic device (1005) with the lowest privacy level.

[0161] In one embodiment, the electronic device (101) may generate a prompt to be input to the GEN AI model (230). In one embodiment, the electronic device (101) may generate a prompt to be input to the GEN AI model (230) based on a sequence of user input. In one embodiment, the electronic device (101) may generate one prompt to be input to the GEN AI model (230). However, the present invention is not limited thereto. For example, the electronic device (101) may generate two or more prompts to be input to the GEN AI model (230).

[0162] For example, a prompt may include one or more words indicating the level of the sharing target and / or data to be referenced when generating a visual object. In one embodiment, the electronic device (101) may generate a prompt indicating data that is permitted to be viewed for sharing targets having a specified privacy level among a plurality of sharing targets.

[0163] In one embodiment, the electronic device (101) can generate visual content through the GEN AI model (230). For example, the electronic device (101) can generate visual content by inputting a prompt to the GEN AI model (230).

[0164] For example, the electronic device (101) may generate visual contents (1010, 1030, 1050) based on the privacy levels of the electronic devices (1001, 1003, 1005) that will receive the user's personal data (e.g., game play footage and / or play history). For example, the visual contents (1010) may be generated based on the entire game play footage and the entire play history for the electronic device (1001) with the highest privacy level. For example, the visual contents (1030) may be generated based on the game highlight footage and play summary for the electronic device (1003) with the next highest privacy level. For example, the visual contents (1050) may be generated based on the game video summary for the electronic device (1005) with the lowest privacy level.

[0165] In one embodiment, the electronic device (101) can transmit visual contents (1010, 1030, 1050) generated through the GEN AI model (230) to the electronic devices (1001, 1003, 1005). For example, the electronic device (101) can transmit the visual contents (1010, 1030, 1050) to the electronic devices (1001, 1003, 1005) through a communication module (e.g., the communication module (190) of FIG. 1).

[0166] Thereafter, the electronic device (101) can modify the visual contents (1010, 1030, 1050) generated by the GEN AI model (230) through additional user input from the user. In one embodiment, the additional user input can be included as a sequence of user input.

[0167] Thereafter, the electronic device (101) can transmit visual contents (1010, 1030, 1050) generated through the GEN AI model (230) to the electronic devices of the sharing targets through additional user input. For example, the electronic device (101) can transmit visual contents (1010, 1030, 1050) corresponding to the level of the sharing targets to the electronic devices of the sharing targets.

[0168] FIG. 11a is a diagram illustrating an example of a UI displayed by an electronic device according to an embodiment. FIG. 11b is a diagram illustrating an example of a UI displayed by an electronic device according to an embodiment.

[0169] FIGS. 11A and 11B may be described with reference to the electronic device (101) of FIG. 2 (or components of the electronic device (101)). For example, the electronic device (1101) of FIGS. 11A and 11B may be described with reference to the electronic device (101) of FIG. 2. The operations described with reference to FIGS. 11A and 11B may be performed as instructions included in the GEN AI model interface (210), the GEN AI model (230), the data management module (240), the level determination module (245), the database (260), and / or the level data (270) of FIG. 2 are executed by the processor (120) of the electronic device (101).

[0170] The electronic device (1101) of FIGS. 11A and 11B may be a wearable device worn by a user (1100). For example, the electronic device (1101) may be a head mounted display (HMD). For example, the electronic device (1101) may be a device for augmented reality (AR), virtual reality (VR), mixed reality (MR), and / or extended reality (XR).

[0171] Referring to FIG. 11A, a user (1100) may wear an electronic device (1101). The user (1100) may view at least one visual object (1120) within a field of view (FOV) (1110) through the electronic device (1101). Here, the FOV (1110) may refer to an area that the user (1100) can view. The FOV (1110) may refer to a display area through a display module (e.g., the display module (160) of FIG. 1) of the electronic device (1101) that the user (1100) can view. For example, when the user (1100) views a visual object (1120), it may mean that the user's (1100) gaze (1105) is directed toward the visual object (1120).

[0172] In one embodiment, the electronic device (1101) can process the gaze (1105) of the user (1100). In one embodiment, the electronic device (1101) can process the gaze (1105) (or user input) based on the visual object (1120) where the gaze (1105) of the user (1100) is located. For example, the electronic device (1101) can display visual content (1130) including controllable elements for the visual object (1120) according to the privacy level of the user (1101). In one embodiment, the visual content (1130) can be generated through the GEN AI model (230). For example, visual content (1130) can be generated based on prompts based on gaze (1105), privacy level of the user (1100), and visual object (1120) input into the GEN AI model (230).

[0173] For example, referring to FIG. 11A, the electronic device (101) may display visual content (1130) including controllable elements (e.g., turning a light on and turning a light off) for a visual object (1120) around the visual object (1120) within the FOV (1110). For example, referring to FIG. 11B, the electronic device (101) may display visual content (1140) including controllable elements (e.g., turning a light on, turning a light off, and controlling the color of a light) for a visual object (1120) around the visual object (1120) within the FOV (1110). However, the present invention is not limited thereto. For example, the electronic device (101) may have different shapes, contents, and uses of the visual contents (1130, 1140) depending on the privacy level of the user (1100) wearing the electronic device (101).

[0174] FIG. 12 is a diagram illustrating user input according to an embodiment. FIG. 13 is a diagram illustrating data sets according to an embodiment. FIG. 14a is a diagram illustrating generated visual content according to an embodiment. FIG. 14b is a diagram illustrating generated visual content according to an embodiment.

[0175] FIGS. 12 to 14B may be described with reference to the electronic device (101) of FIG. 2 (or components of the electronic device (101)). The operations described with reference to FIGS. 12 to 14B may be performed as instructions included in the GEN AI model interface (210), the GEN AI model (230), the data management module (240), the level determination module (245), the database (260), and / or the level data (270) of FIG. 2 are executed by the processor (120) of the electronic device (101).

[0176] Referring to FIG. 12, a user (1200) may input a user input (1210) requesting the creation of visual content (e.g., a schedule record) to an electronic device (101). For example, the electronic device (101) may obtain the user's (1200) speech (or voice input) as the user input (1210) through an input module (150).

[0177] In one embodiment, the electronic device (101) may identify (or determine) the sharing targets of visual content (or the applications to which the visual content will be recorded) (hereinafter, “applications”) based on obtaining user input (1210). In one embodiment, the electronic device (101) may identify (or determine) the privacy level of the applications of the visual content based on obtaining user input (1210).

[0178] In one embodiment, the electronic device (101) can identify (or determine) data to be used to generate visual content. In one embodiment, the electronic device (101) can identify (or determine) data to be used to generate visual content based on the privacy level of the applications.

[0179] In one embodiment, referring to FIG. 13, the electronic device (101) may identify (or determine) a record (1300) as data to be used for generating visual content based on a user input (1210). For example, the electronic device (101) may identify (or determine) the record (1300) as data to be used for generating visual content based on the user input (1210). However, the present invention is not limited thereto. For example, the electronic device (101) may identify (or determine) other data (e.g., a photo, a video, or personal information) other than the record (1300) as data to be used for generating visual content based on the user input (1210).

[0180] In one embodiment, the electronic device (101) may classify data (e.g., records (1300)) stored in the database (260) into accessible data sets according to the privacy level of the application through the level determination module (245). In one embodiment, the electronic device (101) may identify (or determine) a first category of records (1310) among the records (1300) as a first data set to be used for generating visual content to be provided to an application with a relatively low privacy level. For example, the electronic device (101) may identify (or determine) a second category of records (1320) among the records (1300) as a second data set to be used for generating visual content to be provided to an application with a relatively high privacy level. In one embodiment, a subset between the first category of records (1310) and the second category of records (1320) may be an empty set. In one embodiment, the records of the first category (1310) and the records of the second category (1320) may not overlap each other. However, this is not limited thereto. For example, the records of the first category (1310) may include a data set (1331) that is in an intersection relationship with the records of the second category (1320) and a data set (1311) that is in a difference relationship with the records of the second category (1320). For example, the records of the second category (1320) may include a data set (1331) that is in an intersection relationship with the records of the first category (1310) and a data set (1321) that is in a difference relationship with the records of the first category (1310).

[0181] For example, records of the first category (1310) may include records related to personal schedules. For example, records of the second category (1320) may include records related to work schedules.

[0182] In one embodiment, the electronic device (101) may generate a prompt to be input to the GEN AI model (230). In one embodiment, the electronic device (101) may generate a prompt to be input to the GEN AI model (230) based on a sequence of user input. In one embodiment, the electronic device (101) may generate one prompt to be input to the GEN AI model (230). However, the present invention is not limited thereto. For example, the electronic device (101) may generate two or more prompts to be input to the GEN AI model (230).

[0183] For example, a prompt may include one or more words indicating the level of an application and / or data to be referenced when generating a visual object. In one embodiment, the electronic device (101) may generate a prompt indicating data that is permitted to be viewed for applications having a specified privacy level among a plurality of applications. In one embodiment, the electronic device (101) may generate a prompt indicating data corresponding to the level of an application (e.g., data to be referenced when generating a visual object). For example, the prompt may include words for requesting generation of visual content using data corresponding to the level of the application.

[0184] In one embodiment, the electronic device (101) can generate visual content through the GEN AI model (230). For example, the electronic device (101) can generate visual content by inputting a prompt to the GEN AI model (230). In one embodiment, the electronic device (101) can generate at least one visual content by inputting one prompt to the GEN AI model (230). For example, the number of at least one visual content may correspond to the number of levels of the applications.

[0185] For example, referring to FIG. 14A, the electronic device (101) can generate visual content for applications with the lowest privacy level. For example, the visual content of FIG. 14A may have a table format in which data is entered into entries separated by rows and columns. For example, the visual content of FIG. 14A may include work hours, work activities, and details of work activities.

[0186] For example, referring to FIG. 14B, the electronic device (101) can generate visual content for applications with the highest privacy level. For example, the visual content of FIG. 14B may have a table format in which data is entered into entries separated by rows and columns. For example, the visual content of FIG. 14B may include personal time, personal activities, and personal activity content.

[0187] In one embodiment, the electronic device (101) may output visual contents (e.g., the visual contents of FIGS. 14A and 14B) generated through the GEN AI model (230) through the output interface (225). For example, the electronic device (101) may output visual contents (e.g., the visual contents of FIGS. 14A and 14B) through the display module (160).

[0188] FIG. 15 is a flowchart illustrating an operation of an electronic device generating visual content according to one embodiment.

[0189] FIG. 15 may be described with reference to the electronic device (101) of FIG. 2. The operations of FIG. 15 may be performed by the electronic device (101) (or the processor (120) of the electronic device (101). For example, the operations of FIG. 15 may be performed by the electronic device (101) when the instructions are individually or collectively executed by at least one processor (120). In one embodiment, the instructions may be included in the GEN AI model interface (210), the GEN AI model (230), the data management module (240), the level determination module (245), the database (260), and / or the level data (270). In the following embodiments, the operations may be performed sequentially, but are not necessarily performed sequentially. For example, the order of the operations may be changed, and at least two operations may be performed in parallel.

[0190] Referring to FIG. 15, in operation 1510, the electronic device (101) may obtain a user input. For example, the user input may be an input (e.g., a voice input) obtained through an input module (150). However, the present invention is not limited thereto. For example, the user input may be a touch input obtained through a display module (e.g., the display module (160) of FIG. 1). In one embodiment, the user input may include an input for requesting generation of visual content through a GEN AI model (230).

[0191] In operation 1520, the electronic device (101) may identify a data set that can be used to generate visual content based on user input. For example, the electronic device (101) may identify a data set that can be used to generate visual content for a plurality of shared objects identified based on user input. For example, the electronic device (101) may identify a data set that can be used to generate visual content corresponding to the levels of the plurality of shared objects identified based on user input.

[0192] In operation 1530, the electronic device (101) may generate data using the identified data set. In one embodiment, the electronic device (101) may generate visual content based on the identified data set through the GEN AI model (230). For example, the electronic device (101) may generate visual content based on the identified data set by inputting a prompt to the GEN AI model (230). For example, the prompt may be generated based on a user input. In one embodiment, the prompt may be one prompt for generating two or more visual contents. For example, the prompt may include one or more words that indicate characteristics (e.g., size, color, shape, format (e.g., whether an image is included, whether text is included), and / or characteristics (e.g., location, size) of an object (e.g., an image or text)) and / or type (e.g., invitation, wedding invitation, or poster) of the visual contents to be generated. For example, a prompt may include one or more words indicating information to be referenced when generating visual content (e.g., a sharing target, information on the electronic device of the sharing target, information on an application that requested generation of the visual content). For example, a prompt may include one or more words indicating a level of the sharing target and / or data to be referenced when generating a visual object. In one embodiment, the electronic device (101) may generate a prompt indicating data that is permitted to be viewed for sharing targets having a specified privacy level among a plurality of sharing targets. In one embodiment, the electronic device (101) may generate a prompt indicating data corresponding to the level of the sharing target (e.g., data to be referenced when generating a visual object). For example, a prompt may include words for requesting generation of visual content using data corresponding to the level of the sharing target.

[0193] Thereafter, the electronic device (101) can provide the generated visual content to the sharing target. For example, the electronic device (101) can transmit the generated visual content to the electronic device of the sharing target through a communication module (e.g., the communication circuit (190) of FIG. 1).

[0194] FIG. 16 is a flowchart illustrating an operation of an electronic device to identify data sets for generating visual content, according to one embodiment.

[0195] FIG. 16 may be described with reference to the electronic device (101) of FIG. 2. The operations of FIG. 16 may be performed by the electronic device (101) (or the processor (120) of the electronic device (101). For example, the operations of FIG. 16 may be performed by the electronic device (101) when the instructions are individually or collectively executed by at least one processor (120). In one embodiment, the instructions may be included in the GEN AI model interface (210), the GEN AI model (230), the data management module (240), the level determination module (245), the database (260), and / or the level data (270). In the following embodiments, the operations may be performed sequentially, but are not necessarily performed sequentially. For example, the order of the operations may be changed, and at least two operations may be performed in parallel.

[0196] The operations of FIG. 16 may be included in operation 1520 of FIG. 15.

[0197] Referring to FIG. 16, in operation 1610, the electronic device (101) may identify the priority of a user who will use the visual content to be generated. In one embodiment, the electronic device (101) may identify (or determine) the priority of the sharing targets of the visual content through the level determination module (245). For example, the electronic device (101) may identify (or determine) the priority of the sharing targets based on one or more user inputs for selecting the priority of at least one sharing target among the sharing targets. For example, the electronic device (101) may identify (or determine) the priority of the sharing targets stored in the level data (270). For example, the electronic device (101) may identify (or determine) the priority of the sharing targets based on relationship information between the sharing target and the user of the electronic device (101). For example, if the priority of the sharing target is not identified through user input, the electronic device (101) can identify (or determine) the priority of the sharing target based on the priorities of the sharing targets stored in the level data (270). For example, if the priority of the sharing target is not identified, the electronic device (101) can identify (or determine) the priority of the sharing target based on the relationship information.

[0198] In operation 1620, the electronic device (101) may determine whether the identified priority is a designated priority. For example, the electronic device (101) may identify a priority to which the priority of the shared object belongs among multiple priorities. For example, the designated priority may be the lowest priority among the multiple priorities. However, this is not a limitation. For example, the designated priority may be the highest priority among the multiple priorities.

[0199] For example, the electronic device (101) may perform operation 1630 based on determining that the priority of the sharing target is a specified priority. For example, the electronic device (101) may perform operation 1640 based on determining that the priority of the sharing target is different from the specified priority.

[0200] In operation 1630, the electronic device (101) may identify a first data set as a data set that can be used to generate visual content. For example, the electronic device (101) may identify (or determine) a first data set to be used to generate visual content to be provided to a sharing target with a relatively low level of data stored in the database (260). For example, the first data set may not include information for identifying a specific individual. For example, the first data set may include photos of the specific individual, excluding facial photos. However, the present invention is not limited thereto. For example, the first data set may include low-level personal information among the information for identifying the specific individual. Low-level personal information may include name, date of birth, and / or gender.

[0201] In operation 1640, the electronic device (101) may identify a second data set as a data set that can be used to generate visual content. For example, the electronic device (101) may identify (or determine) a second data set to be used to generate visual content to be provided to a relatively high-level sharing target among data stored in the database (260). In one embodiment, the second data set may include the first data set and other data not included in the first data set. For example, the second data set may include the first data set and other data that includes information for identifying a designated individual. For example, the second data set may include photos of the designated individual and the first data set, but is not limited thereto. For example, the second data set may include relatively high-level personal information among information for identifying the designated individual and the first data set. The relatively high-level personal information may include unique identification information (e.g., social security number, physical information, credit information, and / or medical information).

[0202] As described above, the electronic device (101) may include at least one processor (120) including a processing circuit and a memory (130) storing instructions and including one or more storage media. The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to obtain a sequence of user inputs for requesting generation of visual content (510, 530, 550) for a plurality of users. The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to generate first visual content (510, 530, 550) through the generative AI model (230) based on first data (410) that is permitted to be viewed by first users among the plurality of users having a first privacy level based on the user input. The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to generate second visual content (510, 530, 550) through the generative AI model (230) based on second data (420) that is permitted to be viewed by second users among the plurality of users having a second privacy level higher than the first privacy level. The second data (420) may include the first data (410) and other data (421) not included in the first data (410).

[0203] The user input of the above one sequence may include one or more user inputs for generating a prompt that is input to the generative AI model (230). The one or more user inputs may include a user input for selecting the plurality of users and a user input for indicating the type of visual content (510, 530, 550) to be generated.

[0204] The one or more user inputs may include a user input for specifying a privacy level of at least one user among the plurality of users. The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to identify privacy levels of other users than the at least one user among the plurality of users based on data stored in the electronic device (101) prior to obtaining the user input for specifying the privacy level. The data stored in the electronic device (101) prior to obtaining the user input for specifying the privacy level may include privacy levels of the other users specified through user input of another sequence prior to obtaining the user input of the one sequence.

[0205] The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to generate a first prompt indicating the first data (410) to generate the first visual content (510, 530, 550). The first prompt may include words for requesting generation of the first visual content (510, 530, 550) using the first data (410). The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to input the first prompt into the generative AI model (230). The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to generate a second prompt indicating the second data (420) to generate the second visual content (510, 530, 550). The second prompt may include words for requesting generation of the second visual content (510, 530, 550) using the second data (420). The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to input the second prompt to the generative AI model (230).

[0206] The user input of the one sequence may include one or more user inputs for selecting the second data (420). The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to identify the first data (410) corresponding to the first privacy level among the second data (420). The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to generate the first prompt based on identifying the first data (410). The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to generate the second prompt based on obtaining the one or more user inputs for selecting the second data (420).

[0207] The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to generate a prompt based on the user input. The prompt may include words for requesting generation of the visual content (510, 530, 550) for the plurality of users. The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to input the prompt into the generative AI model (230). The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to, based on inputting the one prompt to the generative AI model (230), identify first data (410) corresponding to the first privacy level in the second data (420). The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to, based on inputting the one prompt to the generative AI model (230), generate the first visual content (510, 530, 550) using the first data (410). The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to cause the generative AI model (230) to generate the second visual content (510, 530, 550) using the second data (420) based on the input of the one prompt to the generative AI model (230).

[0208] The first data (410) may not include information for identifying a designated individual. The second data (420) may include other data (421) that includes information for identifying the designated individual.

[0209] The first data (410) may include photos of the designated individual, excluding facial photos. The second data (420) may include photos of the designated individual. The first visual content (510, 530, 550) may include some of the photos, excluding facial photos. The second visual content (510, 530, 550) may include some of the facial photos.

[0210] The first data (410) includes a first level of personal information among the information for identifying a designated individual, and the personal information at the first level may include a name. The second data (420) includes a second level of personal information higher than the first level among the information for identifying the designated individual, and the personal information at the second level may include unique identification information.

[0211] The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to classify the plurality of users into a first group of first users and a second group of second users based on relationship information with users of the electronic device (101). The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to generate first visual content (510, 530, 550) through the generative AI model (230) based on a lowest privacy level among different privacy levels of the first users classified into the first group. The above instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to generate second visual content (510, 530, 550) through the generative AI model (230) based on the lowest privacy level among the different privacy levels of the second users classified in the second group.

[0212] As described above, the method may be performed in the electronic device (101). The method may include an operation of obtaining a sequence of user inputs for requesting generation of visual content (510, 530, 550) for a plurality of users. The method may include an operation of generating, based on the user input, a first visual content (510, 530, 550) through the generative AI model (230) based on first data (410) that is permitted to be viewed by first users among the plurality of users having a first privacy level. The method may include an operation of generating, based on second data (420) that is permitted to be viewed by second users among the plurality of users having a second privacy level higher than the first privacy level, a second visual content (510, 530, 550) through the generative AI model (230). The second data (420) may include the first data (410) and other data (421) not included in the first data (410).

[0213] The user input of the above one sequence may include one or more user inputs for generating a prompt that is input to the generative AI model (230). The one or more user inputs may include a user input for selecting the plurality of users and a user input for indicating the type of visual content (510, 530, 550) to be generated.

[0214] The one or more user inputs may include a user input for specifying a privacy level of at least one user among the plurality of users. The method may include an operation of identifying privacy levels of other users than the at least one user among the plurality of users based on data stored in the electronic device (101) before obtaining the user input for specifying the privacy level. The data stored in the electronic device (101) before obtaining the user input for specifying the privacy level may include privacy levels of the other users specified through user input of another sequence before obtaining the user input of the one sequence.

[0215] The method may include: generating a first prompt indicating the first data (410), wherein the first prompt includes words for requesting the creation of the first visual content (510, 530, 550) using the first data (410), and inputting the first prompt into the generative AI model (230) to generate the first visual content (510, 530, 550). The method may include: generating a second prompt indicating the second data (420), wherein the second prompt includes words for requesting the creation of the second visual content (510, 530, 550) using the second data (420), and inputting the second prompt into the generative AI model (230) to generate the second visual content (510, 530, 550).

[0216] The user input of the one sequence may include one or more user inputs for selecting the second data (420). The method may include an operation of identifying the first data (410) corresponding to the first privacy level among the second data (420). The method may include an operation of generating the first prompt based on identifying the first data (410). The method may include an operation of generating the second prompt based on obtaining the one or more user inputs for selecting the second data (420).

[0217] Based on the user input, a prompt may be generated, and the prompt may include words for requesting generation of the visual content (510, 530, 550) for the plurality of users. The method may include an operation of inputting the prompt into the generative AI model (230). The method may include an operation of identifying, by the generative AI model (230), first data (410) corresponding to the first privacy level in the second data (420), using the first data (410), generating the first visual content (510, 530, 550), and using the second data (420), generating the second visual content (510, 530, 550).

[0218] The first data (410) may not include information for identifying a designated individual. The second data (420) may include other data (421) that includes information for identifying the designated individual.

[0219] The first data (410) may include photos of the designated individual, excluding facial photos. The second data (420) may include photos of the designated individual. The first visual content (510, 530, 550) may include some of the photos, excluding facial photos. The second visual content (510, 530, 550) may include some of the facial photos.

[0220] The first data (410) includes a first level of personal information among the information for identifying a designated individual, and the personal information at the first level may include a name. The second data (420) includes a second level of personal information higher than the first level among the information for identifying the designated individual, and the personal information at the second level may include unique identification information.

[0221] The method may include an operation of classifying the plurality of users into a first group of first users and a second group of second users based on relationship information with the user of the electronic device (101). The method may include an operation of generating first visual content (510, 530, 550) through the generative AI model (230) based on a lowest privacy level among different privacy levels of the first users classified into the first group. The method may include an operation of generating second visual content (510, 530, 550) through the generative AI model (230) based on a lowest privacy level among different privacy levels of the second users classified into the second group.

[0222] A non-transitory computer readable storage medium as described above may store a program including instructions. The instructions, when individually or collectively executed by at least one processor (120) of the electronic device (101), may cause the electronic device (101) to obtain a sequence of user inputs for requesting generation of visual content (510, 530, 550) for a plurality of users. The instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to generate first visual content (510, 530, 550) through the generative AI model (230) based on first data (410) that is permitted to be viewed by first users among the plurality of users having a first privacy level, based on the user input. The above instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to generate second visual content (510, 530, 550) through the generative AI model (230) based on second data (420) that is permitted to be viewed by second users among the plurality of users having a second privacy level higher than the first privacy level. The second data (420) may include the first data (410) and other data (421) not included in the first data (410).

[0223] Electronic devices according to the various embodiments disclosed in this document may take various forms. Electronic devices may include, for example, portable communication devices (e.g., smartphones), computer devices, portable multimedia devices, portable medical devices, cameras, wearable devices, or home appliances. Electronic devices according to the embodiments of this document are not limited to the aforementioned devices.

[0224] The various embodiments of this document and the terminology used therein are not intended to limit the technical features described in this document to specific embodiments, but should be understood to include various modifications, equivalents, or substitutes of the embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of the items, unless the context clearly indicates otherwise. In this document, each of the phrases "A or B", "at least one of A and B", "at least one of A or B", "A, B, or C", "at least one of A, B, and C", and "at least one of A, B, or C" can include any one of the items listed together in the corresponding phrase among those phrases, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used merely to distinguish one component from another, and do not limit the components in any other respect (e.g., importance or order). When a component (e.g., a first component) is referred to as "coupled" or "connected" to another component (e.g., a second component), with or without the terms "functionally" or "communicatively," it means that the component can be connected to the other component directly (e.g., wired), wirelessly, or through a third component.

[0225] The term "module" used in various embodiments of this document may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be an integral component, or a minimum unit or part of such a component that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0226] Various embodiments of the present document may be implemented as software (e.g., a program (140)) including one or more instructions stored in a storage medium (e.g., an internal memory (136) or an external memory (138)) readable by a machine (e.g., an electronic device (101)). For example, a processor (e.g., a processor (120)) of the machine (e.g., an electronic device (101)) may call at least one instruction among the one or more instructions stored from the storage medium and execute it. This enables the machine to operate to perform at least one function according to the at least one called instruction. The one or more instructions may include code generated by a compiler or code executable by an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' simply means that the storage medium is a tangible device and does not contain signals (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently or temporarily on the storage medium.

[0227] According to one embodiment, the method according to various embodiments disclosed in this document may be provided as a computer program product. The computer program product may be traded between sellers and buyers as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., a compact disc read-only memory (CD-ROM)) or 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.

[0228] According to various embodiments, each component (e.g., a module or a program) of the above-described components may include one or more entities, and some of the entities may be separated and arranged in other components. According to various embodiments, one or more components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In such a case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to the integration. According to various embodiments, the operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

Claims

1. In an electronic device (101), At least one processor (120) comprising a processing circuit; and A memory (130) storing instructions and including one or more storage media, wherein the instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101) to: Obtaining a sequence of user inputs to request the generation of visual content (510, 530, 550) for multiple users, Based on the above user input, Generate first visual content (510, 530, 550) through the generative AI model (230) based on first data (410) that is permitted to be viewed by first users having a first privacy level among the plurality of users, Causing the generative AI model (230) to generate second visual content (510, 530, 550) based on second data (420) that is permitted to be viewed by second users among the plurality of users who have a second privacy level higher than the first privacy level, The second data (420) includes the first data (410) and other data (421) not included in the first data (410). Electronic devices.

2. In claim 1, The user input of the above one sequence includes one or more user inputs for generating a prompt that is input to the generative AI model (230), The one or more user inputs include a user input for selecting the plurality of users and a user input for indicating the type of visual content (510, 530, 550) to be generated. Electronic devices.

3. In claim 2, wherein said one or more user inputs include a user input for specifying a privacy level of at least one user among said plurality of users; The above instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101) to: Causing the privacy level of other users than the at least one user among the plurality of users to be identified based on data stored in the electronic device (101) before obtaining the user input for specifying the privacy level, The data stored in the electronic device (101) prior to obtaining the user input for specifying the privacy level includes the privacy levels of the other users specified through the user input of another sequence prior to obtaining the user input of the one sequence. Electronic devices.

4. In any one of claims 1 to 3, The above instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101) to: To generate the above first visual content (510, 530, 550): Generate a first prompt indicating the first data (410), wherein the first prompt includes words for requesting the generation of the first visual content (510, 530, 550) using the first data (410), Input the above first prompt into the generative AI model (230), To generate the above second visual content (510, 530, 550): Generating a second prompt indicating the second data (420), wherein the second prompt includes words for requesting the generation of the second visual content (510, 530, 550) using the second data (420), Causing the second prompt to be input into the generative AI model (230), Electronic devices.

5. In claim 4, The user input of the above one sequence includes one or more user inputs for selecting the second data (420), The above instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101) to: Identifying the first data (410) corresponding to the first privacy level among the second data (420), Based on identifying the first data (410), the first prompt is generated, Causing the second prompt to be generated based on obtaining one or more user inputs for selecting the second data (420). Electronic devices.

6. In any one of claims 1 to 5, The above instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101) to: Generating a prompt based on the user input, wherein the prompt includes words for requesting generation of the visual content (510, 530, 550) for the plurality of users, Inputting the above one prompt into the generative AI model (230), Based on inputting the above one prompt into the generative AI model (230), the generative AI model (230) Identifying the first data (410) corresponding to the first privacy level in the second data (420), Using the first data (410), the first visual content (510, 530, 550) is generated, Using the second data (420), causing the second visual content (510, 530, 550) to be generated, Electronic devices.

7. In any one of claims 1 to 6, The above first data (410) does not contain information for identifying a designated individual, The second data (420) includes the other data (421) including the information for identifying the designated individual. Electronic devices.

8. In claim 7, The above first data (410) includes photos of the designated individual, excluding facial photos, The above second data (420) includes photos of the designated individual, The above first visual content (510, 530, 550) includes some of the above photos excluding the above facial photos, The second visual content (510, 530, 550) includes some of the facial photos. Electronic devices.

9. In any one of claims 1 to 8, The above first data (410) includes a first level of personal information among the information for identifying a designated individual, and the first level of personal information includes a name, The second data (420) includes personal information of a second level higher than the first level among the information for identifying the designated individual, and the personal information of the second level includes unique identification information. Electronic devices.

10. In any one of claims 1 to 9, The above instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101) to: Classify the plurality of users into a first group of first users and a second group of second users based on relationship information with the users of the electronic device (101), Based on the lowest privacy level among the different privacy levels of the first users classified in the first group, the first visual content (510, 530, 550) is generated through the generative AI model (230), Causing the generative AI model (230) to generate second visual content (510, 530, 550) based on the lowest privacy level among the different privacy levels of the second users classified into the second group. Electronic devices.

11. In a method performed in an electronic device (101), An action to obtain a sequence of user inputs to request the generation of visual content (510, 530, 550) for multiple users; Based on the above user input, An operation of generating first visual content (510, 530, 550) through the generative AI model (230) based on first data (410) that is permitted to be viewed by first users having a first privacy level among the plurality of users, and An operation of generating second visual content (510, 530, 550) through the generative AI model (230) based on second data (420) that is permitted to be viewed by second users having a second privacy level higher than the first privacy level among the plurality of users is included. The second data (420) includes the first data (410) and other data (421) not included in the first data (410). method.

12. In claim 11, The user input of the above one sequence includes one or more user inputs for generating a prompt that is input to the generative AI model (230), The one or more user inputs include a user input for selecting the plurality of users and a user input for indicating the type of visual content (510, 530, 550) to be generated. method.

13. In claim 12, wherein said one or more user inputs include a user input for specifying a privacy level of at least one user among said plurality of users; The above method, An operation of identifying the privacy level of other users than the at least one user among the plurality of users based on data stored in the electronic device (101) before obtaining the user input for specifying the privacy level, The data stored in the electronic device (101) prior to obtaining the user input for specifying the privacy level includes the privacy levels of the other users specified through the user input of another sequence prior to obtaining the user input of the one sequence. method.

14. In any one of claims 11 to 13, To generate the above first visual content (510, 530, 550): An operation of generating a first prompt indicating the first data (410), wherein the first prompt includes words for requesting the generation of the first visual content (510, 530, 550) using the first data (410), and An operation of inputting the above first prompt into the generative AI model (230), and To generate the above second visual content (510, 530, 550): An operation of generating a second prompt indicating the second data (420), wherein the second prompt includes words for requesting the generation of the second visual content (510, 530, 550) using the second data (420), and An action including inputting the second prompt into the generative AI model (230). method.

15. In claim 14, The user input of the above one sequence includes one or more user inputs for selecting the second data (420), The above method, An operation of identifying the first data (410) corresponding to the first privacy level among the second data (420); An operation of generating the first prompt based on identifying the first data (410), and An operation of generating the second prompt based on obtaining one or more user inputs for selecting the second data (420) method.

Images