Electronic device for generating content by identifying user pattern and operation method thereof

Abstract

An electronic device for generating content by identifying a user pattern, and an operation method thereof are disclosed. The electronic device may comprise at least one memory for storing one or more instructions. The electronic device may comprise at least one processor for executing the one or more instructions. The one or more instructions, when executed by the at least one processor, may cause the electronic device to analyze an input pattern of a user who generates content. The one or more instructions, when executed by the at least one processor, may cause the electronic device to determine whether the input pattern is a generation request pattern for target content corresponding to a part of the content. The one or more instructions, when executed by the at least one processor, may cause the electronic device to determine a selection area for generating the target content and a reference area for reference when generating the target content, when the input pattern is the generation request pattern. The one or more instructions, when executed by the at least one processor, may cause the electronic device to display the target content generated on the basis of the selection area and the reference area.

Description

Electronic device for generating content by identifying user patterns and method of operating the same

[0001] An electronic device and a method of operating the same for generating content by identifying user patterns are disclosed.

[0002] Generative AI (Generative AI) refers to artificial intelligence technology that generates new data based on given input data. Generative AI can be utilized in various fields, for example, to generate various types of content, such as text, images, music, or video. Users can interact with generative AI through prompts. Prompts can represent input text for user-generative AI interaction. Prompts can directly influence the output of generative AI.

[0003] The background technology described above is possessed or acquired during the process of deriving the present disclosure, and cannot necessarily be said to be a publicly known technology disclosed to the general public prior to the filing of the present disclosure.

[0004] According to one embodiment, an electronic device may include at least one memory storing one or more commands. The electronic device may include at least one processor that executes the one or more commands. The one or more commands, when executed by the at least one processor, may cause the electronic device to analyze a user's input pattern for generating content. The one or more commands, when executed by the at least one processor, may cause the electronic device to determine whether the input pattern is a generation request pattern for target content corresponding to a portion of the content. The one or more commands, when executed by the at least one processor, may cause the electronic device to determine a selection area for generating the target content and a reference area for reference when generating the target content, if the input pattern is the generation request pattern. The one or more commands, when executed by the at least one processor, may cause the electronic device to display the target content generated based on the selection area and the reference area.

[0005] According to one embodiment, a method of operating an electronic device may include an operation of analyzing an input pattern of a user who generates content. The method of operating the electronic device may include an operation of determining whether the input pattern is a generation request pattern for target content corresponding to a portion of the content. If the input pattern is the generation request pattern, the method of operating the electronic device may include an operation of determining a selection area for generating the target content and a reference area for reference when generating the target content. The method of operating the electronic device may include an operation of displaying the target content generated based on the selection area and the reference area.

[0006] According to one embodiment, a non-transitory computer-readable recording medium can store computer programs including one or more commands capable of executing the above-described method of operation.

[0007] FIG. 1 is a block diagram of an electronic device within a network environment according to various embodiments.

[0008] FIG. 2 is a flowchart for explaining the operation of an electronic device according to one embodiment of the present disclosure.

[0009] FIG. 3 is a diagram illustrating the creation of target content according to one embodiment of the present disclosure.

[0010] FIG. 4 is a diagram illustrating generation of a prompt according to one embodiment of the present disclosure.

[0011] FIG. 5 is a diagram for explaining control of a selection area according to one embodiment of the present disclosure.

[0012] FIG. 6 is a diagram for explaining the display of multiple target contents according to one embodiment of the present disclosure.

[0013] FIG. 7 is a drawing for explaining the operation of an electronic device according to one embodiment of the present disclosure.

[0014] FIG. 8 is a diagram for explaining the creation of target content when drawing a picture according to one embodiment of the present disclosure.

[0015] FIG. 9 is a diagram for explaining the creation of target content when writing a message according to one embodiment of the present disclosure.

[0016] FIG. 10 is a drawing for explaining the operation of AR glasses according to one embodiment of the present disclosure.

[0017] FIG. 11 is a diagram for explaining the creation of target content when using a voice memo according to one embodiment of the present disclosure.

[0018] FIG. 12 is a drawing for explaining a system according to one embodiment of the present disclosure.

[0019] FIG. 13 is a flowchart for explaining an operation method of an electronic device according to one embodiment of the present disclosure.

[0020] Hereinafter, embodiments will be described in detail with reference to the attached drawings. In the description with reference to the attached drawings, identical components are assigned the same reference numerals regardless of the drawing numbers, and redundant descriptions thereof will be omitted.

[0021] FIG. 1 is a block diagram of an electronic device (101) within a network environment (100) according to various embodiments. Referring to FIG. 1, in the network environment (100), the electronic device (101) may communicate with the electronic device (102) via a first network (198) (e.g., a short-range wireless communication network), or may communicate with at least one of the electronic device (104) or the server (108) via a second network (199) (e.g., a long-range wireless communication network). In one embodiment, the electronic device (101) may communicate with the electronic device (104) via the server (108). According to one embodiment, the electronic device (101) may include a processor (120), a memory (130), an input module (150), an audio output module (155), a display module (160), an audio module (170), a sensor module (176), an interface (177), a connection terminal (178), a haptic module (179), a camera module (180), a power management module (188), a battery (189), a communication module (190), a subscriber identification module (196), or an antenna module (197). In some embodiments, the electronic device (101) may 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)).

[0022] 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.

[0023] The auxiliary processor (123) may control at least a portion of functions or states associated with at least one component (e.g., a display module (160), a sensor module (176), or a communication module (190)) of the electronic device (101), for example, on behalf of the main processor (121) while the main processor (121) is in an inactive (e.g., sleep) state, or together with the main processor (121) while the main processor (121) is in an active (e.g., application execution) state. In one embodiment, the auxiliary processor (123) (e.g., an image signal processor or a communication processor) may be implemented as a part of another functionally related component (e.g., a camera module (180) or a communication module (190)). In one embodiment, the auxiliary processor (123) (e.g., a neural network processing unit) may include a hardware structure specialized for processing artificial intelligence models. The artificial intelligence models may be generated through machine learning. This learning can be performed, for example, in the electronic device (101) itself where 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 a plurality of 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.

[0024] 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.

[0025] According to one embodiment, the memory (130) may include one or more memories. The instructions stored in the memory (130) may be stored in a single memory. The instructions stored in the memory (130) may be divided and stored in multiple memories. The instructions stored in the memory (130) may be individually or collectively executed by the processor (120) to cause the electronic device (101) to perform the operations described with reference to FIGS. 2 to 13. The instructions stored in the memory (130) may be individually or collectively executed by multiple processors to cause the electronic device (101) to perform the operations described with reference to FIGS. 2 to 13. According to one embodiment, the memory (130) may include a volatile memory (132) or a nonvolatile memory (134).

[0026] 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).

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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).

[0034] 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.

[0035] 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.

[0036] 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).

[0037] 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.

[0038] 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).

[0039] The wireless communication module (192) can support 5G networks and next-generation communication technologies following the 4G network, such as NR access technology (new radio access technology). The NR access technology can support high-speed transmission of high-capacity data (eMBB (enhanced mobile broadband)), minimization of terminal power and connection of multiple terminals (mMTC (massive machine type communications)), or high reliability and low latency (URLLC (ultra-reliable and low-latency communications)). The wireless communication module (192) can support, for example, a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate. The wireless communication module (192) can support various technologies for securing performance in a high-frequency band, such as beamforming, massive multiple-input and multiple-output (MIMO), full dimensional MIMO (FD-MIMO), array antenna, analog beam-forming, or large scale antenna. The wireless communication module (192) can support various requirements specified in the electronic device (101), an external electronic device (e.g., the electronic device (104)), or a network system (e.g., the second network (199)). According to one embodiment, the wireless communication module (192) can support a peak data rate (e.g., 20 Gbps or more) for eMBB realization, a loss coverage (e.g., 164 dB or less) for mMTC realization, or a U-plane latency (e.g., 0.5 ms or less for downlink (DL) and uplink (UL), or 1 ms or less for round trip) for URLLC realization.

[0040] 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).

[0041] 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.

[0042] 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)).

[0043] 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.

[0044] 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.

[0045] 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 (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.

[0046] 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).

[0047] 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.

[0048] According to one embodiment, the method according to various embodiments disclosed in this document may be provided as a computer program product. The computer program product may be traded between sellers and buyers as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)) or may be provided through an application store (e.g., Play Store). TM ) or directly between two user devices (e.g., smart phones), online distribution (e.g., downloading or uploading). In the case of online distribution, at least a portion of the computer program product may be at least temporarily stored or temporarily created in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0049] According to various embodiments, each component (e.g., a module or a program) of the above-described components may include one or more entities, and some of the entities may be separated and placed in other components. According to various embodiments, one or more components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In such a case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to the integration. According to various embodiments, the operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

[0050]

[0051] FIG. 2 is a flowchart for explaining the operation of an electronic device according to one embodiment of the present disclosure.

[0052] 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. Operations (201) to (223) may be performed by at least one component (e.g., the processor (120) of FIG. 1) of an electronic device (e.g., the electronic device (101) of FIG. 1). For example, when one or more instructions stored in at least one memory (e.g., the memory (130) of FIG. 1) are executed by at least one processor, the electronic device may perform the following operations.

[0053] In operation (201), the electronic device can identify a content creation event.

[0054] Electronic devices can provide content creation, such as document creation, drawing, composing, voice recording, message writing, or code creation. However, the aforementioned content is merely exemplary, and the present disclosure is not limited thereto. For example, the electronic device can identify a content creation event based on user input via an input module (e.g., input module (150)). Alternatively, the electronic device can identify a content creation event based on the execution of a specific application that provides content creation.

[0055] In operation (203), the electronic device can analyze the user's input pattern.

[0056] Electronic devices can analyze the input patterns of users who create content. By analyzing the user's input patterns, electronic devices can determine whether the user is generating content normally.

[0057] In operation (205), the electronic device can determine whether the user's input pattern is a generation request pattern. If the user's input pattern is determined to be a generation request pattern, the electronic device can perform operation (207). If the user's input pattern is determined not to be a generation request pattern, the electronic device can perform operation (201).

[0058] In one embodiment, the generation request pattern may be a pattern requesting modification or creation of a portion of content (hereinafter, "target content"). The electronic device may determine whether the pattern is a generation request pattern based on the results of analyzing the user's input pattern. For example, the electronic device may analyze the user's input pattern to determine whether it is a generation request pattern. If the user's input pattern is determined to be a generation request pattern, the electronic device may provide modification or creation of the target content. Even if the user does not explicitly request the creation of the target content, the electronic device may determine whether a nonverbal expression (e.g., the user's input pattern) is a generation request pattern.

[0059] According to one embodiment, an electronic device may determine that a deletion command for a portion of content exceeds a threshold number of times, as a generation request pattern. For example, if the electronic device receives repeated deletion commands for a portion of content and the number of deletion commands received exceeds a threshold number, the electronic device may determine the user's input pattern as a generation request pattern. For example, if a repeated deletion command is received at a specific location in a document being written and the number of deletion commands received exceeds a threshold number, the electronic device may determine the user's input pattern as a generation request pattern.

[0060] In one embodiment, the electronic device may determine a content creation request pattern if the user's input delay time for content creation exceeds a threshold time (e.g., 1 minute). For example, if the user's input for content creation is not obtained for a period exceeding the threshold time, the electronic device may determine the user's input pattern as a content creation request pattern. For example, if the user's input is not obtained for a period exceeding the threshold time for a document being written, the electronic device may determine the user's input pattern as a content creation request pattern.

[0061] In one embodiment, the electronic device may determine a part that should normally be present in a specific content, and if the part that should normally be present is absent, the electronic device may determine the user's input pattern as a generation request pattern. The part that should normally be present may be a part that is naturally identified as existing in the specific content. For example, if a picture contains only a human face shape but no eyes, nose, or mouth, the electronic device may determine that the face shape lacks the eyes, nose, and mouth that should normally be present, and determine the user's input pattern as a generation request pattern. For example, if a document contains no text between quotation marks or parentheses, the electronic device may determine that the text that should normally be present is absent, and determine the user's input pattern as a generation request pattern.

[0062] In one embodiment, when a proofreading symbol (e.g., line break, line break, etc.) is detected in a document, the electronic device may determine the user's input pattern as a generation request pattern.

[0063] According to one embodiment, if the user's input pattern is determined to be a generation request pattern, the electronic device can determine the user's status information. The electronic device can determine whether to determine a selection area and a reference area based on the status information. For example, the electronic device can determine whether to perform operations below operation (207) based on the user's status information. If the input pattern is determined to be a generation request pattern, the electronic device can obtain external information through a module capable of obtaining external information of the electronic device, such as an input module, a sensor module (e.g., a sensor module (176) of FIG. 1), and a camera module (e.g., a camera module (180) of FIG. 1). The electronic device can determine the user's status information based on the external information. For example, an electronic device may determine user status information by analyzing user expressions, movements, voice, etc. based on sensor data obtained from modules included in the electronic device (e.g., a camera module, an audio module (e.g., an audio module (170) of FIG. 1, etc.)) and / or sensor data received from a device connected to the electronic device (e.g., a digital pen, a wearable device (e.g., a watch and a ring, etc.), wireless earphones, etc.).

[0064] For example, the electronic device can acquire an image through a front camera (e.g., the camera module (180) of FIG. 1) facing the same direction as the display module (e.g., the display module (160) of FIG. 1). For example, the electronic device can analyze the facial expression of the user included in the image to determine whether the user is in a state of worry. If the user is determined to be in a state of worry, the electronic device can perform operation (207). For example, if the user is determined not to be present in the image (e.g., the user is absent), the electronic device may not perform operation (207) even if a generation request pattern is identified.

[0065] In operation (207), the electronic device can determine whether the selection area has been selected by the user. If the selection area has been selected by the user, the electronic device can perform operation (211). If the selection area has not been selected by the user, the electronic device can perform operation (209).

[0066] The selection area may be an area for generating target content. For example, the selection area may indicate an area where target content generated based on an identified generation request pattern will be placed.

[0067] In action (209), the electronic device can predict the selection area.

[0068] If the selection area is not explicitly selected by the user, the electronic device can predict the selection area. Predicting the selection area will be described later in Fig. 4.

[0069] In operation (211), the electronic device can determine a selection area.

[0070] When a user selects a specific area as a selection area, the electronic device can determine that area as the selection area. For example, the electronic device can receive a command via an input module to determine a specific area of ​​content as the selection area. Based on the command, the electronic device can determine the specific area as the selection area.

[0071] If no selection area is selected by the user, the electronic device can determine the selection area based on the predicted selection area in operation (209).

[0072] In operation (213), the electronic device can determine a reference area.

[0073] A reference area may be an area containing reference content for reference when generating target content. For example, the reference area may contain reference content referenced to generate target content to be placed in a selected area. The method for determining the reference area will be described later in FIG. 4.

[0074] Electronic devices can display reference and selection areas on content. Users can intuitively identify the reference and selection areas.

[0075] In action (215), the electronic device may generate a prompt.

[0076] An electronic device can generate a prompt based on a selection area and a reference area. The electronic device can generate a prompt that instructs a generative AI model to generate target content to be included in the selection area based on the reference content included in the reference area. In other words, the electronic device can analyze the reference content included in the reference area. The electronic device can analyze the context and style of the reference content. The electronic device can generate a prompt based on the analysis results.

[0077] In one embodiment, the selection area may include the selected content. In other words, the selection area may be determined as a blank area containing no content or an area containing at least a portion of the content being written by the user. The electronic device may analyze the reference content and the selected content included in the reference area. The electronic device may analyze the context and style of the reference content and the selected content. Based on the analysis results of the reference content and the selected content, the electronic device may generate a prompt that commands the generative AI model to generate target content.

[0078] In operation (217), the electronic device can obtain target content.

[0079] In one embodiment, an electronic device may transmit a prompt to a server (e.g., server 108 of FIG. 1 ). The server may include a generative artificial intelligence model. In response to transmitting the prompt to the server, the electronic device may obtain target content generated based on the prompt from the server. The generative artificial intelligence model may generate multiple target contents based on the prompt.

[0080] In one embodiment, a generative AI model may be included in an electronic device. The electronic device may input a prompt into the generative AI model within the electronic device. The generative AI model, upon receiving the prompt, may generate multiple target contents based on the prompt.

[0081] In operation (219), the electronic device can determine whether multiple target contents have been acquired. If multiple target contents have not been acquired, the electronic device can perform operation (221). If multiple target contents have been acquired, the electronic device can perform operation (223).

[0082] In operation (221), the electronic device may display target content if multiple target contents are not acquired. For example, the electronic device may display target content in a selection area.

[0083] In operation (223), the electronic device may obtain a selection command for any one of a plurality of target contents. The electronic device may display the plurality of target contents and obtain a selection command for any one of the plurality of target contents. A method for displaying the plurality of target contents will be described later in FIG. 6.

[0084] In one embodiment, an electronic device can receive feedback from a user regarding target content. The electronic device can modify the target content based on the feedback. For example, the electronic device can regenerate a prompt that reflects the feedback and obtain modified target content based on the regenerated prompt.

[0085] Below, we will explain the creation of target content using specific examples.

[0086]

[0087] FIG. 3 is a diagram illustrating the creation of target content according to one embodiment of the present disclosure.

[0088] Referring to FIG. 3, a screen (310) and a screen (320) are illustrated that display content (e.g., a document) being created by a user. The screen (310) and the screen (320) may represent the screen of an electronic device (e.g., the electronic device (101) of FIG. 1).

[0089] Referring to screen (310), content (311) (e.g., a document) being created by a user is illustrated. According to one embodiment, an electronic device (e.g., electronic device (101) of FIG. 1) can analyze a user's input pattern for creating content (311). The electronic device can analyze the input pattern to determine whether the input pattern is a creation request pattern. For example, the electronic device can determine the input pattern as a creation request pattern if the number of delete commands for a word or phrase at a specific location exceeds a threshold number. For example, the electronic device can determine the input pattern as a creation request pattern if the input delay time exceeds a threshold time.

[0090] According to one embodiment, if the input pattern is determined to be a generation request pattern, the electronic device can determine a selection area (313). For example, the selection area (313) can be determined by a selection by the user. If there is no selection by the user, the electronic device can predict the selection area (313).

[0091] According to one embodiment, the electronic device can predict a selection area (313) based on a portion of the content (311) for which a repetitive delete command has been obtained. The electronic device can predict the selection area (313) based on the size and location of the content (311) for which the repetitive delete command has been obtained. For example, if a repetitive delete command has been obtained for 5 or more words in the 10th line of a document being written, the electronic device can determine an area that can include 5 or more words in the 10th line of the document as the selection area (313).

[0092] According to one embodiment, if there is no user input for a threshold period of time, the electronic device may predict a selection area (313) based on previously written content based on the point at which the user's input stopped. For example, if the user's input stopped at the 10th line and the previously written sentences based on the 10th line contain 15 or more words, the electronic device may determine the area that may contain 15 or more words in the 10th line as the selection area (313).

[0093] Referring to a screen (320) according to one embodiment, a reference area (315) determined based on a selection area (313) is illustrated. The electronic device can determine the reference area (315) based on the selection area (313). The electronic device can determine the reference area (315) based on the position and / or size of the selection area (313).

[0094] According to one embodiment, the electronic device may determine the size of the reference area (315) based on the determined size. For example, if the determined size is 100 sentences, the electronic device may determine the size of the reference area (315) to be 100 or more sentences. According to one embodiment, the determined size may change based on the size of the selection area (313). For example, the larger the size of the selection area (313), the larger the determined size may change. According to one embodiment, the electronic device may determine the size of the reference area (315) to be larger as the size of the selection area (313) is larger. For example, the size of the reference area (315) may be determined to be larger when the size of the selection area (313) can include 20 words than when the size of the selection area (313) can include 10 words. For example, the size here may also be interpreted as the amount of content.

[0095] According to one embodiment, the electronic device may determine the location of the reference area (315) based on the location of the selection area (313). For example, if the selection area (313) is located at the end of the content (311), the electronic device may determine a portion of the front part of the selection area (313) as the location of the reference area (315). For example, if the selection area (313) is located at the beginning of the content (311), the electronic device may determine a portion of the back part of the selection area (313) as the location of the reference area (315). For example, if the selection area (313) is located in the middle of the content (311), the electronic device may determine a portion of the front part and a portion of the back part of the selection area (313) as the reference area (315).

[0096] According to one embodiment, the electronic device can determine the reference area (315) based on a selection command for the reference area (315) obtained from the user.

[0097] In one embodiment, the reference area (315) may be determined for a separate content other than the content being generated (311). For example, the electronic device may determine the reference area (315) for another previously generated content.

[0098] Referring to screen (330), the electronic device can acquire target content generated based on the selection area (313) and the reference area (315). For example, the size of the target content may be smaller than or equal to the size of the selection area (313). The electronic device can display the acquired target content in the selection area (313). According to one embodiment, the electronic device can acquire multiple target contents. A case where the electronic device acquires multiple target contents will be described later with reference to FIG. 6.

[0099] Additionally, according to one embodiment, the selection area (313) and the reference area (315) may be determined based on one or more artificial intelligence models. For example, the electronic device may determine the selection area (313) using a first artificial intelligence model. The first artificial intelligence model may be a model trained to determine the selection area (313) based on a user's input pattern. The electronic device may determine the reference area (315) using a second artificial intelligence model. The second artificial intelligence model may be a model trained to determine the reference area (315) based on the selection area (313).

[0100] Below, we will explain the prompt generated based on the selection area (313) and the reference area (315).

[0101]

[0102] FIG. 4 is a diagram illustrating generation of a prompt according to one embodiment of the present disclosure.

[0103] Referring to FIG. 4, a screen (400) is shown in which a selection area (413) (e.g., selection area (313) of FIG. 3) and a reference area (415) (e.g., selection area (315) of FIG. 3) are determined.

[0104] According to one embodiment, an electronic device (e.g., electronic device (101) of FIG. 1) may generate a prompt (420) when a selection area (413) and a reference area (415) are determined. The electronic device may generate a prompt (420) that commands a generative artificial intelligence model to generate target content included in the selection area (413) based on reference content included in the reference area (415).

[0105] In one embodiment, the prompt (420) may include reference content (421), selection content (423), and a command (425). The reference content (421) may be content included in the reference area (415). The reference content (421) may be referenced when generating target content. The selection content (423) may be content included in the selection area (413). Depending on the embodiment, the selection content (423) may not be present. The command (425) may include a command that causes the generative artificial intelligence model to change the expression of the selection content (423) by referring to the reference content (421) or to generate target content to be placed in the selection area (413). For example, the command (425) may include a command that causes the target content to be generated such that the size of the target content is smaller than or equal to the size of the selection area (413).

[0106] In one embodiment, the command (425) may include a statement that causes the style of the reference content (421) to be reflected in the target content. Target content generated based on the prompt including the statement that causes the style of the reference content (421) to be reflected in the target content may reflect the style of the reference content (421). For example, the style may include various characteristics such as font, font size, and tone in the case of a document. The style may include various characteristics such as brush type, brush stroke, and color in the case of an image.

[0107] An electronic device may transmit a prompt (420) to a server (e.g., server (108) of FIG. 1). The server may include a generative artificial intelligence model. The server may input the prompt (420) into the generative artificial intelligence model. The server may obtain target content generated based on the prompt (420) from the generative artificial intelligence model. The server may transmit the target content to the electronic device.

[0108] In one embodiment, the electronic device may input a prompt (420) into a generative artificial intelligence model stored in a memory (e.g., memory (130) of FIG. 1). The electronic device may obtain target content generated based on the prompt (420) from the generative artificial intelligence model.

[0109] Below, we will explain the control of the selection area (413).

[0110]

[0111] FIG. 5 is a diagram for explaining control of a selection area according to one embodiment of the present disclosure.

[0112] Referring to FIG. 5, a screen (500) is shown in which a selection area (513) (e.g., selection area (313) of FIG. 3 and selection area (413) of FIG. 4) is displayed.

[0113] According to one embodiment, an electronic device (e.g., electronic device (101) of FIG. 1) may provide an object (510) that can control the size of the selection area (513) along with a selection area (513). The electronic device may provide control over the position and / or size of the selection area (513) via the object (510).

[0114] For example, the electronic device may reduce the size of the selection area (513) based on a control command to swipe the object (510) to the left. For example, the electronic device may expand the size of the selection area (513) based on a control command to swipe the object (510) to the right. For example, the electronic device may control the position of the selection area (513) based on a selection command and a movement command for more than a threshold time for the object (510).

[0115] According to one embodiment, the reference area (515) (e.g., the reference area (315) of FIG. 3 and the reference area (415) of FIG. 4) may be determined based on the selection area (513). For example, the reference area (515) may be determined based on the position and / or size of the selection area (513). For example, if the size of the selection area (513) is reduced based on a user's control command, the size of the reference area (515) may be reduced based on the size of the reduced selection area (513). For example, if the size of the selection area (513) is expanded based on a user's control command, the size of the reference area (515) may be expanded based on the size of the expanded selection area (513). For example, if the position of the selection area (513) is moved based on a user's control command, the position of the reference area (515) may be moved based on the position of the selection area (513).

[0116] Accordingly, the electronic device can control the selection area (513) and the reference area (515) based on the control command through the user's object (510).

[0117] Below, we will explain how to display multiple target contents.

[0118]

[0119] FIG. 6 is a diagram for explaining the display of multiple target contents according to one embodiment of the present disclosure.

[0120] Referring to FIG. 6, a screen (600) and a screen (610) of an electronic device (e.g., the electronic device (101) of FIG. 1) are illustrated.

[0121] According to one embodiment, an electronic device may obtain a plurality of target contents (620) generated based on a prompt (e.g., prompt (420) of FIG. 4). The electronic device may display the plurality of target contents (620) to obtain a selection command for any one of the plurality of target contents (620). A user may select any one of the plurality of target contents (620) to be displayed in a selection area (613) (e.g., selection area (313) of FIG. 3, selection area (413) of FIG. 4, and selection area (513) of FIG. 5).

[0122] For example, referring to the screen (600), the electronic device can display a plurality of target contents (620). For example, the electronic device can display the plurality of target contents (620) in a pop-up form. The electronic device can receive a selection command from the user for any one of the plurality of target contents (620). Upon receiving the selection command, the electronic device can display the selected target contents in a selection area (613) on the screen (610).

[0123] According to one embodiment, on the screen (610), the electronic device may further display an indicator (630). For example, the indicator (630) may indicate the number of the plurality of target contents (620). The electronic device may receive a selection command for the indicator (630). Upon receiving the selection command for the indicator (630), the electronic device may display a screen (600) providing a selection command for one of the plurality of target contents (620).

[0124] Below, we will describe the operation of the electronic device based on the user's status information.

[0125]

[0126] FIG. 7 is a drawing for explaining the operation of an electronic device according to one embodiment of the present disclosure.

[0127] Referring to FIG. 7, a screen (700) of an electronic device (701) (e.g., electronic device (101) of FIG. 1) generating content (711) (e.g., content (311) of FIG. 3) by a user (720) is illustrated.

[0128] According to one embodiment, the electronic device (701) can analyze the input pattern of a user (720) who creates content (711). The electronic device (701) can determine whether the input pattern of the user (720) is a creation request pattern. If the input pattern of the user (720) is determined to be a creation request pattern, the electronic device (701) can determine status information of the user (720).

[0129] According to one embodiment, the electronic device (701) can obtain external information through modules such as an input module (e.g., input module (150) of FIG. 1), a sensor module (e.g., sensor module (176) of FIG. 1), and a camera module (e.g., camera module (180) of FIG. 1). The electronic device can analyze the external information to determine status information of the user (720).

[0130] For example, the electronic device can analyze sounds acquired through a microphone to determine whether the user (720) is absent. For example, the electronic device can analyze the facial expression of the user (720) included in an image acquired through a front camera and determine whether the user (720) is thinking. For example, the electronic device can analyze the gestures of the user (720) included in an image acquired through the front camera and store a list of actions that the user (720) unconsciously performs when thinking. If the acquired actions of the user (720) are included in the list, the electronic device can determine that the user (720) is thinking. If a specific action of the user (720) is repeatedly acquired with a generation request pattern, the electronic device can add the specific action to the list.

[0131] According to one embodiment, the electronic device (701) may further determine whether to determine a selection area (713) (e.g., selection area (313) of FIG. 3 , selection area (413) of FIG. 4 , selection area (513) of FIG. 5 , and selection area (613) of FIG. 6 ) and a reference area (715) (e.g., reference area (315) of FIG. 3 , reference area (415) of FIG. 4 , and reference area (515) of FIG. 5 ) based on the status information of the user (720).

[0132] For example, if the electronic device determines that the user (720) is absent, the electronic device may not determine the selection area (713) and the reference area (715) even if a generation request pattern is identified. For example, if the electronic device does not determine that the user (720) is in distress, the electronic device may not determine the selection area (713) and the reference area (715) even if a generation request pattern is identified. For example, if the electronic device determines that the user (720) is in distress, the electronic device may determine the selection area (713) and the reference area (715).

[0133] The method for determining the selection area (713) and the reference area (715) and the method for generating target content based on the selection area (713) and the reference area (715) will be omitted as described above.

[0134] Below, we will explain a case where the content according to one embodiment of the present disclosure is a picture.

[0135]

[0136] FIG. 8 is a diagram for explaining the creation of target content when drawing a picture according to one embodiment of the present disclosure.

[0137] Referring to FIG. 8, a screen (800) of an electronic device (e.g., the electronic device (101) of FIG. 1 and the electronic device (701) of FIG. 7) displaying a drawing drawn by a user (e.g., the user (720) of FIG. 7) is illustrated. For example, the user may be drawing a second object (802) based on a first object (801).

[0138] In one embodiment, the electronic device can analyze the user's input pattern. For example, if a delete command for a second object (802) exceeds a threshold number of times, the electronic device can determine the user's input pattern as a generation request pattern. For example, the electronic device can obtain a delete command for the face portion of the second object (802) exceeding a threshold number of times.

[0139] According to one embodiment, the electronic device can determine a selection area (813) (e.g., selection area (313) of FIG. 3, selection area (413) of FIG. 4, selection area (513) of FIG. 5, selection area (613) of FIG. 6, and selection area (713) of FIG. 7) and a reference area (815) (e.g., reference area (315) of FIG. 3, reference area (415) of FIG. 4, reference area (515) of FIG. 5, and reference area (715) of FIG. 7). For example, the electronic device can determine a face portion of the second object (802) that has obtained a delete command as the selection area (813). The electronic device can determine a face portion of the first object (801) corresponding to the face portion of the second object (802) as the reference area (815). According to one embodiment, the position and / or size of the reference area (815) and the selection area (813) can be controlled based on a user's control command.

[0140] The electronic device may generate a prompt (820) (e.g., prompt (420) of FIG. 4) based on the reference area (815) and the selection area (813). In one embodiment, the prompt (820) may instruct a generative artificial intelligence model to generate target content (823) to be included in the selection area (813) based on the reference content of the reference area (815) (e.g., reference content (421) of FIG. 4).

[0141] The electronic device can obtain target content (823) generated based on the prompt (820). The electronic device can display the target content (823) in the selection area (813). A description of the method for generating the target content (823) based on the prompt (820) is omitted here.

[0142] Hereinafter, a case in which content (e.g., content (311) of FIG. 7 and content (711) of FIG. 7) according to one embodiment of the present disclosure is a message will be described.

[0143]

[0144] FIG. 9 is a diagram for explaining the creation of target content when writing a message according to one embodiment of the present disclosure.

[0145] Referring to FIG. 9, a screen (900) of an electronic device (e.g., electronic device (101) of FIG. 1 and electronic device (701) of FIG. 7) is shown displaying a message being written by a user (e.g., user (720) of FIG. 7). For example, the screen (900) may be displaying a chat room.

[0146] In one embodiment, the electronic device can analyze the user's input patterns. For example, if a delete command exceeds a threshold number of times for a message, the electronic device can determine the user's input patterns as a generation request pattern.

[0147] According to one embodiment, the electronic device can determine a selection area (913) (e.g., selection area (313) of FIG. 3 , selection area (413) of FIG. 4 , selection area (513) of FIG. 5 , selection area (613) of FIG. 6 , selection area (713) of FIG. 7 , and selection area (813) of FIG. 8 ) and a reference area (915) (e.g., reference area (315) of FIG. 3 , reference area (415) of FIG. 4 , reference area (515) of FIG. 5 , reference area (715) of FIG. 7 , and reference area (815) of FIG. 8 ). For example, the reference area (915) can be determined to include the contents of a previous message of the user and / or the contents of a previous message of another user. For example, at least a portion of a message for which a delete command has been repeatedly obtained can be determined as the reference area (913). According to one embodiment, the reference area (915) and the selection area (913) can be positioned and / or sized based on a user's control command.

[0148] According to one embodiment, the electronic device may generate a prompt (e.g., prompt (420) of FIG. 4 and prompt (820) of FIG. 8) based on a reference area (915) and a selection area (913). According to one embodiment, the prompt may instruct a generative artificial intelligence model to generate target content (e.g., target content (823) of FIG. 8) to be included in the selection area (913) based on reference content (e.g., reference content (421) of FIG. 4) of the reference area (915).

[0149] According to one embodiment, the electronic device may obtain a plurality of target contents (923) generated based on a prompt (e.g., a plurality of target contents (620)). The electronic device may display the plurality of target contents (923) to provide a selection for any one of the plurality of target contents (923). The electronic device may display any one of the plurality of target contents (923) for which a selection command has been received in a selection area (913).

[0150] Hereinafter, a case in which an electronic device according to one embodiment of the present disclosure is a head mounted display (HMD) will be described.

[0151]

[0152] FIG. 10 is a drawing for explaining the operation of an HMD according to one embodiment of the present disclosure.

[0153] According to one embodiment, an electronic device (e.g., electronic device (101) of FIG. 1 and electronic device (701) of FIG. 7) may be an HMD (1001). The HMD (1001) may provide a visual see-through (VST) function. For example, the HMD (1001) may be AR glasses. However, this is merely an example and the present disclosure is not limited thereto.

[0154] In one embodiment, the HMD (1001) can acquire an input pattern of a user (e.g., a user (720) of FIG. 7) who is generating content (e.g., content (311) of FIG. 3 and content (711) of FIG. 7). For example, the HMD (1001) can acquire an input pattern (e.g., an action) of a user who is writing on paper.

[0155] In one embodiment, the HMD (1001) can analyze the user's input pattern to determine whether it is a generation request pattern. For example, the HMD (1001) can determine the user's input pattern as a generation request pattern if it identifies the action of erasing words and / or sentences at a specific location with an eraser more than a threshold number of times. For example, the HMD (1001) can determine the user's input pattern as a generation request pattern if it identifies the action of drawing two lines with a pen at a specific location more than a threshold number of times.

[0156] According to one embodiment, the HMD (1001) can determine a selection area (1013) (e.g., selection area (313) of FIG. 3, selection area (413) of FIG. 4, selection area (513) of FIG. 5, selection area (613) of FIG. 6, selection area (713) of FIG. 7, selection area (813) of FIG. 8, and selection area (913) of FIG. 9) and a reference area (1015) (e.g., reference area (315) of FIG. 3, reference area (415) of FIG. 4, reference area (515) of FIG. 5, reference area (715) of FIG. 7, reference area (815) of FIG. 8, and reference area (915) of FIG. 9)). The HMD (1001) can display the selection area (1013) and the reference area (1015) through augmented reality.

[0157] In one embodiment, the HMD (1001) may generate a prompt (1020) (e.g., prompt (420) of FIG. 4 and prompt (820) of FIG. 8) based on a selection area (1013) and a reference area (1015). In one embodiment, the prompt may instruct a generative artificial intelligence model to generate target content (e.g., target content (823) of FIG. 8) to be included in the selection area (913) based on reference content (e.g., reference content (421) of FIG. 4) of the reference area (1015).

[0158] According to one embodiment, the HMD (1001) can obtain a plurality of target contents (1023) (e.g., a plurality of target contents (620)) generated based on a prompt. The electronic device can display the plurality of target contents (1023) through augmented reality to provide a selection for any one of the plurality of target contents (1023). The electronic device can display any one of the plurality of target contents (1023) for which a selection command has been received in a selection area (1013).

[0159] Below, we will explain a case where the content according to one embodiment of the present disclosure is a voice memo.

[0160]

[0161] FIG. 11 is a diagram for explaining the creation of target content when using a voice memo according to one embodiment of the present disclosure.

[0162] Referring to FIG. 11, an electronic device (1101) (e.g., electronic device (101) of FIG. 1, electronic device (701) of FIG. 7) performing a voice memo by a user (e.g., user (720) of FIG. 7) is illustrated.

[0163] According to one embodiment, the electronic device (1101) can analyze the input pattern based on the user's acquired voice memo. For example, if a silence exceeding a threshold time is acquired, the electronic device (1101) can determine the user's input pattern as a generation request pattern. The electronic device (1101) can determine whether the user's input pattern is a generation request pattern based on the user's voice. For example, the electronic device can determine the user's input pattern as a generation request pattern if the tone of the voice changes. For example, the electronic device can determine the user's input pattern as a generation request pattern if it acquires a specific word (e.g., "no," "again," etc.) or a specific sentence (e.g., "I misspoke").

[0164] According to one embodiment, the electronic device (1101) can determine a selection section and a reference section in a voice memo. The selection section may be a section to which acquired target content is added. The reference section may be a section referenced to generate target content.

[0165] In one embodiment, the electronic device (1101) may generate a prompt based on a selection section and a reference section. In one embodiment, the prompt may instruct a generative artificial intelligence model to generate target content (e.g., target content (823) of FIG. 8) to be included in the selection section based on reference content (e.g., reference content (421) of FIG. 4) of the reference area.

[0166]

[0167] FIG. 12 is a drawing for explaining a system according to one embodiment of the present disclosure.

[0168] Referring to FIG. 12, a system (1200) of the present disclosure is illustrated. The system (1200) may include a plurality of modules. It will be apparent to those skilled in the art that the plurality of modules may be implemented in software and / or hardware.

[0169] According to one embodiment, an event identification module (1201) can identify a content creation event. The event identification module (1210) can identify a content creation event based on the execution of a specific application that provides the creation of content (e.g., content (311) of FIG. 3 and content (711) of FIG. 7). However, this is merely an example and the present disclosure is not limited thereto.

[0170] According to one embodiment, when a content creation event is identified, a user input handler module (1203) may analyze an input pattern of a user (e.g., a user (720) of FIG. 7) based on input through an input module (e.g., an input module (150) of FIG. 1). The user input handler module (1203) may analyze the user's input pattern to determine whether the user's input pattern is a creation request pattern. For example, the user input handler module (1203) may calculate a statistical value for the time taken to input a word, phrase, or sentence, etc., to determine whether the user is performing input according to an existing pattern. For example, the user input handler module (1203) may calculate a statistical value for the user's input time, and determine whether the user is performing input according to an existing pattern by determining whether the user's current input time is included in the statistical value.

[0171] In one embodiment, the user input processing module (1203) may determine the user's input pattern as a generation request pattern if the user is not performing input according to an existing pattern. For example, the user input processing module (1203) may determine the user's input pattern as a generation request pattern if a repetitive deletion command for a portion of content is obtained.

[0172] According to one embodiment, the user state tracker module (1207) may determine the user's state information based on external information acquired based on a sensor module (1205) (e.g., the sensor module (176) of FIG. 1). In addition, the user state tracker module (1207) may determine the user's state information based on external information acquired based on a camera module (e.g., the camera module (180) of FIG. 1) and / or an input module (e.g., the input module (150) of FIG. 1).

[0173] For example, the user status tracker module (1207) can analyze an image acquired from the front camera. For example, if the user is not included in the image, the user status tracker module (1207) can determine the user's status information as absent. For example, the user status tracker module (1207) can determine the user's status information by analyzing the user's facial expression included in the image. The user's status information can include whether the user is contemplating content creation. For example, if the user's facial expression is a frown, the user status tracker module (1207) can determine that the user is contemplating content creation.

[0174] According to one embodiment, the state manager module (1209) may determine whether to transmit a prompt generation signal to the prompt generator module (1211) based on the generation request pattern and the user's state information. For example, if the user's input pattern is a generation request pattern and the user's state information is determined to be considering content generation, the prompt generation signal may be transmitted to the prompt generator module (1211).

[0175] According to one embodiment, the prompt generation module (1211) may request information necessary for prompt generation from the reference area manager module (1213), the selection area manager module (1215), and the style manager module (1217).

[0176] According to one embodiment, the selection area manager module (1215) may determine a specific area provided by a user as a selection area when the user provides a specific area as a selection area (e.g., selection area (313) of FIG. 3, selection area (413) of FIG. 4, selection area (513) of FIG. 5, selection area (613) of FIG. 6, selection area (713) of FIG. 7, selection area (813) of FIG. 8, selection area (913) of FIG. 9, and selection area (1013) of FIG. 10).

[0177] In one embodiment, if the user does not provide a specific area as a selection area, the selection area manager module (1215) can predict the selection area. For example, the selection area manager module (1215) can predict the selection area based on the user's input.

[0178] For example, the selection area manager module (1215) can obtain an average value for previously generated content from the contents manager module (1219). The contents manager module (1219) can store content previously generated by a user and content generated by a generative artificial intelligence model (e.g., target content). If the content is a document, the selection area manager module (1215) can receive an average value for the length of previously generated sentences from the contents manager module (1219). The selection area manager module (1215) can determine a selection area based on the average value. For example, if the average value for the length of previously generated sentences is 20 words and the sentence currently being written has 5 words, the selection area manager module (1215) can determine a length corresponding to 15 words as the selection area.

[0179] According to one embodiment, the reference area manager module (1213) can determine a reference area (e.g., reference area (315) of FIG. 3, reference area (415) of FIG. 4, reference area (515) of FIG. 5, reference area (715) of FIG. 7, reference area (815) of FIG. 8, reference area (915) of FIG. 9, and reference area (1015) of FIG. 10) based on the selected area. The reference area manager module (1213) can determine a reference area from previously generated content based on the selected area. A description of a method for determining a reference area will be omitted as it has been described above with reference to FIGS. 2 and 3. According to one embodiment, data deleted from content stored in a history manager module (1223) can be used to determine a reference area.

[0180] In one embodiment, the style manager module (1217) may determine the user's style based on previously generated content and transmit the determined style to the prompt generation module (1211). For example, if the content is a document, the user's style may include factors such as tone and sentence writing habits. For example, if the content is an illustration, the user's style may include brush strokes and colors. For example, if the content is a composition, the user's style may include the user's preferred melodies.

[0181] According to one embodiment, the prompt generation module (1211) can receive a reference region and reference content (e.g., reference content (421) of FIG. 4) from the reference region manager module (1213). The prompt generation module (1211) can receive a selection region from the selection region manager module (1215). According to an embodiment, the prompt generation module (1211) can receive a selection content (e.g., selection content (423) of FIG. 4). The prompt generation module (1211) can receive a user's style from the style manager module (1217). The prompt generation module (1211) can generate a prompt (e.g., prompt (420) of FIG. 4, prompt (820) of FIG. 8, and prompt (1020) of FIG. 10) based on information received from the reference region manager module (1213), the selection region manager module (1215), and the style manager module (1217).

[0182] The prompt generation module (1211) can transmit the generated prompt to the generative artificial intelligence module (1227) via the interaction handler module (1221). The generative artificial intelligence module (1227) can input the prompt into the generative artificial intelligence model to obtain target content.

[0183] The target content can be transmitted to the UI compositor module (1225) through the interaction processing module (1221). The UI compositor module (1225) can display the target content by compositing it into a selected area.

[0184]

[0185] FIG. 13 is a flowchart for explaining an operation method of an electronic device according to one embodiment of the present disclosure.

[0186] In the following embodiments, each operation may be performed sequentially, but is not necessarily performed sequentially. For example, the order of each operation may be changed, and at least two operations may be performed in parallel. Operations (1310) to (1340) may be performed by at least one component (e.g., the processor (120) of FIG. 1) of an electronic device (e.g., the electronic device (101) of FIG. 1, the electronic device (701) of FIG. 7, and the electronic device (1101) of FIG. 11). For example, when one or more instructions stored in at least one memory (e.g., the memory (130) of FIG. 1) are executed by at least one processor, the electronic device may perform the following operations.

[0187] In operation (1310), the electronic device can analyze an input pattern of a user (e.g., a user (720) of FIG. 7) who generates content (e.g., content (311) of FIG. 3 and content (711) of FIG. 7).

[0188] In operation (1320), the electronic device can determine whether the input pattern is a generation request pattern for target content corresponding to a portion of the content (e.g., target content (823) of FIG. 8).

[0189] In operation (1330), if the input pattern is a generation request pattern, the electronic device can determine a selection area for generating target content (e.g., selection area (313) of FIG. 3, selection area (413) of FIG. 4, selection area (513) of FIG. 5, selection area (613) of FIG. 6, selection area (713) of FIG. 7, selection area (813) of FIG. 8, selection area (913) of FIG. 9, and selection area (1013) of FIG. 10)) and a reference area for reference when generating target content (e.g., reference area (315) of FIG. 3, reference area (415) of FIG. 4, reference area (515) of FIG. 5, reference area (715) of FIG. 7, reference area (815) of FIG. 8, reference area (915) of FIG. 9, and reference area (1015) of FIG. 10)).

[0190] In operation (1340), the electronic device can display target content generated based on the selection area and the reference area.

[0191] Since the matters described above through FIGS. 1 to 12 are applied to each operation illustrated in FIG. 13, a more detailed description is omitted.

[0192] According to one embodiment, an electronic device (e.g., the electronic device 101 of FIG. 1, the electronic device 701 of FIG. 7, and the electronic device 1101 of FIG. 11) may include at least one memory (e.g., the memory 130 of FIG. 1) that stores one or more instructions. The electronic device may include at least one processor (e.g., the processor 120 of FIG. 1) that executes one or more instructions. The one or more instructions, when executed by the at least one processor, may cause the electronic device to analyze an input pattern of a user (e.g., the user 720 of FIG. 7) who generates content (e.g., the content 311 of FIG. 3 and the content 711 of FIG. 7). The one or more instructions, when executed by the at least one processor, may cause the electronic device to determine whether an input pattern is a generation request pattern for target content (e.g., the target content 823 of FIG. 8) corresponding to a portion of the content. One or more instructions, when executed by at least one processor, may cause the electronic device to determine a selection area for generating target content (e.g., a selection area (313) of FIG. 3, a selection area (413) of FIG. 4, a selection area (513) of FIG. 5, a selection area (613) of FIG. 6, a selection area (713) of FIG. 7, a selection area (813) of FIG. 8, a selection area (913) of FIG. 9, and a selection area (1013) of FIG. 10)) and a reference area for reference when generating the target content (e.g., a reference area (315) of FIG. 3, a reference area (415) of FIG. 4, a reference area (515) of FIG. 5, a reference area (715) of FIG. 7, a reference area (815) of FIG. 8, a reference area (915) of FIG. 9, and a reference area (1015) of FIG. 10)). One or more instructions, when executed by at least one processor, may cause the electronic device to display target content generated based on the selection region and the reference region.

[0193] According to one embodiment, one or more instructions, when executed by at least one processor, may cause the electronic device to determine a reference region based on a location and / or size of a selection region.

[0194] According to one embodiment, one or more instructions, when executed by at least one processor, may cause the electronic device to determine user status information. The one or more instructions, when executed by at least one processor, may cause the electronic device to determine whether to determine a selection area and a reference area based on the status information.

[0195] According to one embodiment, the one or more instructions, when executed by at least one processor, may cause the electronic device to generate a prompt (e.g., prompt (420) of FIG. 4, prompt (820) of FIG. 8, and prompt (1020) of FIG. 10) that instructs a generative artificial intelligence model to generate target content to be included in a selection area based on reference content included in a reference area (e.g., reference content (421) of FIG. 4). The one or more instructions, when executed by at least one processor, may cause the electronic device to transmit the prompt to a server (e.g., server (108) of FIG. 1) that includes the generative artificial intelligence model.

[0196] In one embodiment, the selection area and the reference area may be controllable based on user control commands.

[0197] In one embodiment, the target content may reflect the style of the reference content included in the reference area.

[0198] According to one embodiment, one or more instructions, when executed by at least one processor, may cause the electronic device to determine a generation request pattern when a user's input time for generating content exceeds a threshold time.

[0199] According to one embodiment, one or more instructions, when executed by at least one processor, may cause the electronic device to determine a generation request pattern when a deletion command for content included in a location corresponding to a selection area exceeds a threshold number of times.

[0200] According to one embodiment, a method of operating an electronic device may include an operation of analyzing an input pattern of a user who generates content. The method of operating the electronic device may include an operation of determining whether the input pattern is a generation request pattern for target content corresponding to a portion of the content. If the input pattern is the generation request pattern, the method of operating the electronic device may include an operation of determining a selection area for generating the target content and a reference area for reference when generating the target content. The method of operating the electronic device may include an operation of displaying the target content generated based on the selection area and the reference area.

[0201] According to one embodiment, the operation of determining the reference area may determine the reference area based on a location and / or size of the selection area.

[0202] According to one embodiment, the method of operating an electronic device may further include an operation of determining status information of the user. The method of operating an electronic device may further include an operation of determining whether to determine the selection area and the reference area based on the status information.

[0203] In one embodiment, the operation of displaying the target content may include an operation of generating a prompt that commands a generative artificial intelligence model to generate the target content to be included in the selection area based on the reference content included in the reference area. The operation of displaying the target content may include an operation of transmitting the prompt to a server including the generative artificial intelligence model.

[0204] According to one embodiment, the selection area and the reference area may be controllable based on a control command of the user.

[0205] According to one embodiment, the target content may reflect the style of the reference content included in the reference area.

[0206] According to one embodiment, the operation of determining whether the above-mentioned generation request pattern is the above-mentioned generation request pattern may be determined if the input time of the user generating the content exceeds a threshold time.

[0207] According to one embodiment of the present disclosure, target content suitable for the user's intention can be generated without separate operation by the user based on content previously generated by the user.

[0208] According to one embodiment of the present disclosure, target content with a user's style applied can be generated by referencing content previously generated by the user, thereby maintaining consistency with the previously generated content.

[0209] According to one embodiment of the present disclosure, modification of previously generated content and generation of new target content based on previously generated content may be provided.

[0210]

[0211] The embodiments of the present invention disclosed in this specification and drawings are merely specific examples presented to easily explain the technical contents according to the embodiments of the present invention and to help understand the embodiments of the present invention, and are not intended to limit the scope of the embodiments of the present invention. Therefore, the scope of the various embodiments of the present invention should be interpreted as including all changes or modified forms derived based on the technical ideas of the various embodiments of the present invention in addition to the embodiments disclosed herein.

Claims

1. In electronic devices (101, 701, 1101), At least one memory (130) storing one or more commands; and At least one processor (120) for executing one or more of the above instructions Including, The one or more instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101, 701, 1101) to: An input pattern of a user (720) who creates content (311; 711) is analyzed, and whether the input pattern is a generation request pattern for target content (311; 711) corresponding to a part of the content (311; 711) is determined, and if the input pattern is the generation request pattern, a selection area (313; 413; 513; 613; 713; 813; 913; 1013) for generating the target content (311; 711) and a reference area (315; 415; 515; 715; 815; 915; 1015) for reference when generating the target content (311; 711) are determined, and the selection area (313; 413; 513; 613; 713; 813; 913; 1013) and display the target content (311; 711) generated based on the reference areas (315; 415; 515; 715; 815; 915; 1015). Electronic devices (101, 701, 1101).

2. In paragraph 1, The one or more instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101, 701, 1101) to: Determine the reference area (315; 415; 515; 715; 815; 915; 1015) based on the location and / or size of the above selection area (313; 413; 513; 613; 713; 813; 913; 1013). Electronic devices (101, 701, 1101).

3. In either of paragraphs 1 and 2, The one or more instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101, 701, 1101) to: To determine the status information of the user (720) and further determine whether to determine the selection area (313; 413; 513; 613; 713; 813; 913; 1013) and the reference area (315; 415; 515; 715; 815; 915; 1015) based on the status information. Electronic devices (101, 701, 1101).

4. In any one of paragraphs 1 to 3, The one or more instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101, 701, 1101) to: Generating a prompt (420; 820; 1020) that commands a generative artificial intelligence model to generate the target content (311; 711) to be included in the selection area (313; 413; 513; 613; 713; 813; 913; 1013) based on the reference content (421) included in the reference area (315; 415; 515; 715; 815; 915; 1015), and transmitting the prompt (420; 820; 1020) to a server including the generative artificial intelligence model. Electronic devices (101, 701, 1101).

5. In any one of paragraphs 1 to 4, The above selection area (313; 413; 513; 613; 713; 813; 913; 1013) and the above reference area (315; 415; 515; 715; 815; 915; 1015) are Controllable based on the control command of the above user (720), Electronic devices (101, 701, 1101).

6. In any one of paragraphs 1 to 5, The above target content (311; 711) is The style for the reference content (421) included in the above reference areas (315; 415; 515; 715; 815; 915; 1015) is reflected, Electronic devices (101, 701, 1101).

7. In any one of paragraphs 1 to 6, The one or more instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101, 701, 1101) to: If the input time of the user (720) who creates the above content (311; 711) exceeds the threshold time, it is determined by the above creation request pattern. Electronic devices (101, 701, 1101).

8. In any one of paragraphs 1 to 7, The one or more instructions, when executed by the at least one processor (120), cause the electronic device (101, 701, 1101) to: If the number of deletion commands for the content (311; 711) included in the location corresponding to the above selection area (313; 413; 513; 613; 713; 813; 913; 1013) exceeds the threshold number, it is determined as the above generation request pattern. Electronic devices (101, 701, 1101).

9. In the operating method of an electronic device (101, 701, 1101), An action to analyze the input pattern of a user (720) who creates content (311; 711); An operation for determining whether the above input pattern is a generation request pattern for target content (311; 711) corresponding to a part of the above content (311; 711); When the input pattern is the generation request pattern, an operation of determining a selection area (313; 413; 513; 613; 713; 813; 913; 1013) for generating the target content (311; 711) and a reference area (315; 415; 515; 715; 815; 915; 1015) for reference when generating the target content (311; 711); and An operation of displaying the target content (311; 711) generated based on the above selection area (313; 413; 513; 613; 713; 813; 913; 1013) and the above reference area (315; 415; 515; 715; 815; 915; 1015) including, How it works.

10. In paragraph 9, The operation of determining the above reference areas (315; 415; 515; 715; 815; 915; 1015) is as follows: Determining the reference area (315; 415; 515; 715; 815; 915; 1015) based on the location and / or size of the above selection area (313; 413; 513; 613; 713; 813; 913; 1013). How it works.

11. In any one of paragraphs 9 and 10, An operation for determining the status information of the above user (720); and An operation for determining whether to determine the selection area (313; 413; 513; 613; 713; 813; 913; 1013) and the reference area (315; 415; 515; 715; 815; 915; 1015) based on the above status information. including more, How it works.

12. In any one of paragraphs 9 to 11, The action of displaying the above target content (311; 711) is: An action of generating a prompt (420; 820; 1020) for commanding a generative artificial intelligence model to generate the target content (311; 711) to be included in the selection area (313; 413; 513; 613; 713; 813; 913; 1013) based on the reference content (421) included in the reference area (315; 415; 515; 715; 815; 915; 1015); and An action of transmitting the above prompt (420; 820; 1020) to a server including the generative artificial intelligence model. including, How it works.

13. In any one of paragraphs 9 to 12, The above selection area (313; 413; 513; 613; 713; 813; 913; 1013) and the above reference area (315; 415; 515; 715; 815; 915; 1015) are Controllable based on the control command of the above user (720), How it works.

14. In any one of paragraphs 9 to 13, The above target content (311; 711) is The style for the reference content (421) included in the above reference areas (315; 415; 515; 715; 815; 915; 1015) is reflected, How it works.

15. In any one of paragraphs 9 to 14, The action to determine whether the above creation request pattern is: If the input time of the user (720) who creates the above content (311; 711) exceeds the threshold time, it is determined by the above creation request pattern. How it works.

Images