Electronic device and video generation method using same

Abstract

According to various embodiments, an electronic device may comprise: a display; a processor including a processing circuit; and a memory for storing instructions. When the instructions are individually or collectively executed by the processor, the electronic device can: identify, in response to a user input, a user intention corresponding to a user input; extract at least one keyword on the basis of the identified user intention; identify a processing order for video generation on the basis of the extracted at least one keyword and environment information of the electronic device; determine one or more prompts corresponding to the identified processing order; generate a plurality of images corresponding to the determined one or more prompts; and display, on the display, the plurality of generated images as a video. Other various embodiments are possible.

Description

Electronic device and image generation method using the same

[0001] An embodiment of the present disclosure relates to an electronic device and a method for generating an image using the same.

[0002] With the recent development of digital technology, various types of electronic devices (user devices) capable of communication and personal information processing (e.g., mobile communication terminals, PDAs (Personal Digital Assistants), electronic notebooks, smartphones, tablets, wearable electronic devices, and / or PCs (Personal Computers)) are being released. As the functions provided by electronic devices become more diverse and they are widely utilized in daily life, the time spent using electronic devices is gradually increasing.

[0003] An electronic device may store user manuals (e.g., manuals, product manuals) that explain the usage, key functions, precautions for use, and / or troubleshooting methods in relation to various types of products. The electronic device may search for information requested by the user within the stored user manuals and provide the search results to the user. For example, if the electronic device fails to search within the user manuals, it may not be able to provide information to the user.

[0004] The information described above may be provided as related art for the purpose of aiding understanding of the present disclosure. No claim or determination is made as to whether any of the foregoing may be applied as prior art related to the present disclosure.

[0005] The electronic device can be implemented in various form factors and can be operated based on various versions of software programs tailored to each form factor. The electronic device can implement said user interface based on a software program that implements the user interface, in accordance with the usage environment (e.g., specification information and / or version information for the electronic device). For example, if the versions of the software program are different, the form of the user interface may be implemented differently.

[0006] The electronic device can provide information tailored to the user interface (e.g., video manual) to the user based on the user interface. The electronic device can analyze the content of the user's inquiry and determine result information regarding the content of the user's inquiry. In providing result information to the user, the electronic device can process the result information according to the user's usage environment (e.g., specification information and / or version information of the electronic device) and provide the user with a video (e.g., video manual) corresponding to the processed result information.

[0007] According to one embodiment, the electronic device may determine one or more prompts based on the content of a user's inquiry, generate a plurality of images corresponding to each of the one or more prompts, and generate a video (e.g., a video manual) based on the plurality of images in response to the user's inquiry. For example, the video may include video information tailored to the user's usage environment (e.g., specification information and / or version information of the electronic device). According to one embodiment, the electronic device may provide the user with a video regarding the inquiry, tailored to the user's usage environment (e.g., specification information and / or version information of the electronic device), in response to the user's inquiry.

[0008] The technical tasks intended to be accomplished in this document are not limited to those mentioned above, and other technical tasks not mentioned will be clearly understood by those skilled in the art to which this document belongs from the description below.

[0009] According to one embodiment, the electronic device may include a display, a processor including a processing circuit, and a memory for storing instructions. When the instructions are executed individually or collectively by the processor, the electronic device may respond to user input to identify a user's intention corresponding to the user input, extract at least one keyword based on the identified user's intention, identify a processing order for image generation based on the extracted at least one keyword and environmental information of the electronic device, determine one or more prompts corresponding to the identified processing order, generate a plurality of images corresponding to the determined one or more prompts, and display the generated plurality of images as the image through the display.

[0010] According to one embodiment, a method for displaying an image in an electronic device may include: an operation of confirming a user's intention corresponding to the user input in response to a user input; an operation of extracting at least one keyword based on the confirmed user's intention; an operation of confirming a processing order for image generation based on the extracted at least one keyword and environment information of the electronic device; an operation of determining one or more prompts corresponding to the confirmed processing order; an operation of generating a plurality of images corresponding to the determined one or more prompts; and an operation of displaying the generated plurality of images as an image through a display of the electronic device.

[0011] According to one embodiment, a server connected to an electronic device may include a processor comprising a communication circuit and a processing circuit, and a memory for storing instructions. When the instructions are executed individually or collectively by the processor, the server may acquire environmental information of the electronic device and input information related to image generation from the electronic device, identify a user's intention based on the acquired input information, extract at least one keyword based on the identified user's intention, identify a processing order for image generation based on the extracted at least one keyword and the environmental information of the electronic device, determine one or more prompts corresponding to the identified processing order, generate a plurality of images corresponding to the determined one or more prompts, and transmit the generated plurality of images to the electronic device through the display.

[0012] According to one embodiment, a non-transient computer-readable storage medium (or computer program product) storing one or more programs for performing a method of displaying an image on an electronic device may be described. According to one embodiment, the one or more programs may include instructions that, when executed by a processor of an electronic device, perform, in response to user input, an operation of confirming a user's intention corresponding to said user input; an operation of extracting at least one keyword based on said confirmed user intention; an operation of confirming a processing order for image generation based on said extracted at least one keyword and environment information of said electronic device; an operation of determining one or more prompts corresponding to said confirmed processing order; an operation of generating a plurality of images corresponding to said determined one or more prompts; and an operation of displaying said generated plurality of images as an image through a display of said electronic device.

[0013] According to one embodiment, an electronic device can generate a video (e.g., a video manual) tailored to the usage environment of the electronic device (e.g., specification information and / or version information of the electronic device) based on an inquiry made by a user, and can provide said video (e.g., a video manual) to the user. For example, the electronic device can generate a video (e.g., video information, image information, a video manual, a guide video) according to the inquiry based on the user interface of the electronic device. By visually checking the video generated based on the user interface of the electronic device, the user can easily understand the questions regarding the inquiry. By checking the video information (e.g., a video manual) tailored to the usage environment of the electronic device, the user can accurately understand the answer to the inquiry. User convenience can be improved when utilizing the electronic device.

[0014] The effects obtainable from the present disclosure are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art to which the present disclosure belongs from the description below.

[0015] In relation to the description of the drawings, the same or similar reference numerals may be used for identical or similar components. The aforementioned features and advantages will be clearly understood based on the attached drawings and the description thereof.

[0016] FIG. 1 is a block diagram of an electronic device in a network environment according to one embodiment of the present disclosure.

[0017] FIG. 2 is a drawing illustrating an embodiment in which a manual generated based on a user's inquiry according to one embodiment of the present disclosure is displayed on an electronic device.

[0018] FIG. 3a is a block diagram of an electronic device according to one embodiment of the present disclosure.

[0019] FIG. 3b is a diagram of the relationship of state transition information according to one embodiment of the present disclosure.

[0020] FIG. 4 is a flowchart illustrating a method for generating a manual in an electronic device according to one embodiment of the present disclosure.

[0021] FIG. 5 is a diagram illustrating a manual generation process according to one embodiment of the present disclosure, divided into four steps.

[0022] FIG. 6 is a flowchart illustrating a user environment analysis method according to one embodiment of the present disclosure.

[0023] FIG. 7 is a flowchart illustrating a method for verifying text based on user input according to one embodiment of the present disclosure.

[0024] FIG. 8 is a flowchart illustrating a user context analysis method according to one embodiment of the present disclosure.

[0025] FIG. 9 is a flowchart illustrating a manual generation method according to one embodiment of the present disclosure.

[0026] FIG. 10a is an exemplary illustration showing a first image corresponding to a first prompt according to one embodiment of the present disclosure.

[0027] FIG. 10b is an exemplary illustration showing a second image corresponding to a second prompt according to one embodiment of the present disclosure.

[0028] FIG. 10c is an exemplary illustration showing a third image corresponding to a third prompt according to one embodiment of the present disclosure.

[0029] FIG. 10d is an exemplary illustration showing a fourth image corresponding to a fourth prompt according to one embodiment of the present disclosure.

[0030] FIG. 10e is an exemplary illustration showing a fifth image corresponding to a fifth prompt according to one embodiment of the present disclosure.

[0031] FIG. 10f is an exemplary illustration showing a sixth image corresponding to a sixth prompt according to one embodiment of the present disclosure.

[0032] FIG. 10g is an exemplary illustration showing a seventh image corresponding to a seventh prompt according to one embodiment of the present disclosure.

[0033] FIG. 11 is an example diagram showing a video manual displayed in a multi-window mode according to one embodiment of the present disclosure.

[0034] FIG. 12 is a flowchart illustrating a method for generating a video manual based on a server connected to an electronic device according to one embodiment of the present disclosure.

[0035] Hereinafter, embodiments of the present disclosure are described in detail with reference to the drawings so that those skilled in the art can easily practice them. However, the present disclosure may be embodied in various different forms and is not limited to the embodiments described herein. In relation to the description of the drawings, the same or similar reference numerals may be used for identical or similar components. Furthermore, in the drawings and related descriptions, descriptions of well-known functions and configurations may be omitted for clarity and brevity.

[0036] FIG. 1 is a block diagram of an electronic device (101) in a network environment (100) according to various embodiments. Referring to FIG. 1, in the network environment (100), the electronic device (101) may communicate with an electronic device (102) through a first network (198) (e.g., a short-range wireless communication network) or may communicate with at least one of an electronic device (104) or a server (108) through a second network (199) (e.g., a long-range wireless communication network). According to one embodiment, the electronic device (101) may communicate with the electronic device (104) through a server (108). According to one embodiment, the electronic device (101) may include a processor (120), memory (130), input module (150), sound output module (155), display module (160), audio module (170), sensor module (176), interface (177), connection terminal (178), haptic module (179), camera module (180), power management module (188), battery (189), communication module (190), subscriber identification module (196), or antenna module (197). In some embodiments, at least one of these components (e.g., connection terminal (178)) may be omitted from the electronic device (101), or one or more other components may be added. In some embodiments, some of these components (e.g., sensor module (176), camera module (180), or antenna module (197)) may be integrated into a single component (e.g., display module (160)).

[0037] The processor (120) can control at least one other component (e.g., a hardware or software component) of the electronic device (101) connected to the processor (120) by executing software (e.g., a program (140)), and can perform various data processing or operations. According to one embodiment, as at least part of the data processing or operations, the processor (120) can store commands or data received from other components (e.g., a sensor module (176) or a communication module (190)) in volatile memory (132), process the commands or data stored in volatile memory (132), and store the resulting data in 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) that can operate independently or together with it (e.g., a graphics processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor). For example, if the electronic device (101) includes a main processor (121) and an auxiliary processor (123), the auxiliary processor (123) may be configured to use lower power than the main processor (121) or to be specialized for a designated function. The auxiliary processor (123) may be implemented separately from the main processor (121) or as part thereof.

[0038] The auxiliary processor (123) may control at least some of the functions or states associated with at least one component of the electronic device (101) (e.g., display module (160), sensor module (176), or communication module (190)) 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. According to one embodiment, the auxiliary processor (123) (e.g., image signal processor or communication processor) may be implemented as part of another functionally related component (e.g., camera module (180) or communication module (190)). According to one embodiment, the auxiliary processor (123) (e.g., neural network processing unit) may include a hardware structure specialized for processing an artificial intelligence model. The artificial intelligence model may be generated through machine learning. Such learning may be performed, for example, on the electronic device (101) itself where the artificial intelligence is performed, or through a separate server (e.g., server (108)). The learning algorithm may 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 may include a plurality of artificial neural network layers.An artificial neural network may be a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), 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 the hardware structure, the artificial intelligence model may include a software structure, either additionally or substantially.

[0039] The memory (130) can store various data used by at least one component of the electronic device (101) (e.g., processor (120) or sensor module (176)). The data may include, for example, input data or output data for software (e.g., program (140)) and related commands. The memory (130) may include volatile memory (132) or non-volatile memory (134).

[0040] The program (140) may be stored as software in memory (130) and may include, for example, an operating system (142), middleware (144), or an application (146).

[0041] The input module (150) can receive commands or data to be used for a component of the electronic device (101) (e.g., processor (120)) from outside the electronic device (101) (e.g., user). The input module (150) may include, for example, a microphone, a mouse, a keyboard, a key (e.g., a button), or a digital pen (e.g., a stylus pen).

[0042] The sound output module (155) can output a sound signal to the outside of the electronic device (101). The sound output module (155) may include, for example, a speaker or a receiver. The speaker may be used for general purposes, such as multimedia playback or recording playback. The receiver may be used to receive incoming calls. According to one embodiment, the receiver may be implemented separately from the speaker or as part thereof.

[0043] The display module (160) can visually provide information to an external (e.g., 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 said 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 the force generated by said touch.

[0044] The audio module (170) can convert sound into an electrical signal or, conversely, convert an electrical signal into sound. According to one embodiment, the audio module (170) can acquire sound through the input module (150) or output sound through the sound output module (155) or an external electronic device (e.g., electronic device (102)) (e.g., speaker or headphones) connected directly or wirelessly to the electronic device (101).

[0045] The sensor module (176) can detect the operating state of the electronic device (101) (e.g., power or temperature) or the external environmental state (e.g., user state) and generate an electrical signal or data value corresponding to the detected state. According to one embodiment, the sensor module (176) may include, for example, a gesture sensor, a gyroscope sensor, a barometric pressure sensor, a magnetic sensor, an accelerometer sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biosensor, a temperature sensor, a humidity sensor, or an illuminance sensor.

[0046] The interface (177) may support one or more specified protocols that can be used for the electronic device (101) to be connected directly or wirelessly to an external electronic device (e.g., electronic device (102)). According to 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.

[0047] The connection terminal (178) may include a connector through which the electronic device (101) can 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).

[0048] The haptic module (179) can convert an electrical signal into a mechanical stimulus (e.g., vibration or movement) or an electrical stimulus that can be perceived by the user through tactile or kinesthetic senses. According to one embodiment, the haptic module (179) may include, for example, a motor, a piezoelectric element, or an electric stimulation device.

[0049] The camera module (180) can capture still images and video. According to one embodiment, the camera module (180) may include one or more lenses, image sensors, image signal processors, or flashes.

[0050] The power management module (188) can manage power supplied to the electronic device (101). According to one embodiment, the power management module (188) can be implemented, for example, as at least part of a power management integrated circuit (PMIC).

[0051] The battery (189) can supply power to at least one component of the electronic device (101). According to one embodiment, the battery (189) may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0052] The communication module (190) can support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between an 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 include one or more communication processors that operate independently of the processor (120) (e.g., application processor) and 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., cellular communication module, short-range wireless communication module, or GNSS (global navigation satellite system) communication module) or a wired communication module (194) (e.g., LAN (local area network) communication module, or power line communication module). The corresponding communication module among these communication modules can communicate with an external electronic device (104) through a first network (198) (e.g., a short-range communication network such as Bluetooth, WiFi (wireless fidelity) direct, or IrDA (infrared data association)) or a second network (199) (e.g., 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 may 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 identify or authenticate the electronic device (101) within a communication network such as the first network (198) or the second network (199) using subscriber information (e.g., International Mobile Subscriber Identifier (IMSI)) stored in the subscriber identification module (196).

[0053] The wireless communication module (192) can support 5G networks and next-generation communication technologies following 4G networks, for example, new radio access technology. NR access technology can support high-speed transmission of high-capacity data (enhanced mobile broadband (eMBB)), minimization of terminal power and connection of multiple terminals (massive machine type communications (mMTC)), or high reliability and low latency (ultra-reliable and low-latency communications (URLLC)). The wireless communication module (192) can support a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate, for example. The wireless communication module (192) can support various technologies for securing performance in the high-frequency band, such as beamforming, massive MIMO (multiple-input and multiple-output), 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), external electronic device (e.g., electronic device (104)), or network system (e.g., second network (199)). According to one embodiment, the wireless communication module (192) may support a Peak data rate (e.g., 20 Gbps or more) for eMBB realization, loss coverage (e.g., 164 dB or less) for mMTC realization, or U-plane latency (e.g., downlink (DL) and uplink (UL) each 0.5 ms or less, or round trip 1 ms or less) for URLLC realization.

[0054] An antenna module (197) can transmit a signal or power to or from an external source (e.g., an external electronic device). According to one embodiment, the antenna module (197) may include an antenna comprising a radiator made of a conductor or a conductive pattern formed on a substrate (e.g., a PCB). According to 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 a first network (198) or a second network (199), may be selected from the plurality of antennas, for example, by a communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device through the selected at least one antenna. According to some embodiments, in addition to the radiator, other components (e.g., a radio frequency integrated circuit (RFIC)) may be additionally formed as part of the antenna module (197).

[0055] According to one embodiment, the antenna module (197) may form a mmWave antenna module. According to one embodiment, the mmWave antenna module may include a printed circuit board, an RFIC disposed on or adjacent to a first surface (e.g., bottom surface) of the printed circuit board and capable of supporting a specified high frequency band (e.g., mmWave band), and a plurality of antennas (e.g., array antennas) disposed on or adjacent to a second surface (e.g., top surface or side surface) of the printed circuit board and capable of transmitting or receiving a signal of the specified high frequency band.

[0056] At least some of the above components can be connected to each other via a communication method between peripheral devices (e.g., bus, GPIO (general purpose input and output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface)) and exchange signals (e.g., commands or data) with each other.

[0057] According to one embodiment, commands or data may be transmitted or received between an electronic device (101) and an external electronic device (104) through 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 performed on the electronic device (101) may be performed on one or more of the external electronic devices (102, 104, or 108). For example, if the electronic device (101) needs to perform a function or service automatically or in response to a request from a user or another device, the electronic device (101) may request one or more external electronic devices to perform at least part of the function or service instead of performing the function or service itself or additionally. One or more external electronic devices that receive the above request may execute at least part of the requested function or service, or 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 provide the result as is or additionally processed as at least part of the response to the request. For this purpose, for example, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used. The electronic device (101) may provide ultra-low latency services using, for example, distributed computing or mobile edge computing. In another embodiment, the external electronic device (104) may include an Internet of Things (IoT) device. The server (108) may be an intelligent server using machine learning and / or neural networks. According to one embodiment, the external electronic device (104) or the server (108) may be included within a 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.

[0058] FIG. 2 is a drawing illustrating an embodiment in which a manual generated based on a user's inquiry according to one embodiment of the present disclosure is displayed on an electronic device.

[0059] The electronic device (101) of FIG. 2 may be at least partially similar to the electronic device (101) of FIG. 1, or may further include other embodiments of the electronic device (101). According to one embodiment, the electronic device (101) may include components at least partially similar to the electronic device (101) of FIG. 1. The electronic device (101) of FIG. 2 is illustrated as a portable terminal that can be carried by a user, but is not limited thereto. The electronic device (101) may include various forms of electronic devices.

[0060] Referring to FIG. 2, the electronic device (101) may be in a state where a manual generation program (e.g., an application that generates video manuals based on an artificial intelligence model) for generating manuals (e.g., video information, image information) is running. For example, the processor of the electronic device (101) (e.g., the processor (120) of FIG. 1) can determine the processing order according to the processing of the content based on the content inquired by the user, and can determine multiple prompts based on the processing order. For example, the processing order can be subdivided into multiple prompts. For example, the user (201) may be curious about “how to input text into a photo” and can use the electronic device (101) to ask, “Tell me how to input text into a photo.” The user (201) may input the content of the inquiry as an audio signal using a microphone (e.g., input module (150) of FIG. 1) of the electronic device (101), or input the content of the inquiry as text using a keyboard (e.g., user interface) displayed through a display (e.g., display module (160) of FIG. 1). If the content of the inquiry is input as an audio signal, the processor (120) may convert the audio signal into text.

[0061] According to one embodiment, the processor (120) of the electronic device (101) can determine an answer (e.g., a manual (210) that sequentially shows the process of text being entered into a photo) in response to a user's (201) inquiry, and can verify the processing order corresponding to the answer. According to one embodiment, an artificial intelligence model (e.g., an AI model, an AI algorithm) for determining a plurality of prompts can be stored in the memory of the electronic device (101) (e.g., the memory (130) of FIG. 1). For example, the processor (120) can activate at least a part of the artificial intelligence model in response to the execution of a manual generation program. The processor (120) can analyze the user's (201) inquiry based on the activated artificial intelligence model and determine an answer according to the inquiry. For example, the artificial intelligence model can subdivide the processing order corresponding to the determined answer and determine the subdivided processing order as a plurality of prompts.

[0062] According to one embodiment, the processor (120) may determine a first prompt based on a processing order and an artificial intelligence model (e.g., an AI algorithm), and may determine a second prompt that is at least partially linked to the first prompt based on the first prompt. The processor (120) may determine a third prompt that is at least partially linked to the second prompt based on the determined second prompt. The processor (120) may determine a plurality of prompts that are at least partially linked based on the processing order. The processor (120) may determine the plurality of prompts based on an artificial intelligence model (e.g., an AI algorithm).

[0063] According to one embodiment, the processor (120) may generate a plurality of images based on a plurality of prompts. For example, the processor (120) may generate a first image corresponding to a first prompt, a second image corresponding to a second prompt, and / or a third image corresponding to a third prompt. In generating the images, the processor (120) may generate guide information (211) for each image and may generate the images in a form in which the guide information (211) is included in the images. The processor (120) may generate a manual (210) by concatenating a plurality of images (e.g., a first image, a second image, and / or a third image) sequentially or discontinuously. For example, the manual (210) may include image information in which a plurality of images are displayed in a processing order.

[0064] According to one embodiment, the electronic device (101) can analyze the content of a user's (201) inquiry and determine an answer to the inquiry. In providing an answer to the user (201), the electronic device (101) can determine a processing order corresponding to the answer and can determine a plurality of prompts corresponding to the processing order. The electronic device (101) can generate a plurality of images corresponding to the plurality of prompts and, based on the plurality of images, generate a manual (210) corresponding to the answer. The electronic device (101) can display the generated manual (210) through a display (160).

[0065] According to one embodiment, the user (201) can easily understand the questions regarding the inquiry by visually checking the manual (210) tailored to the usage environment information of the electronic device (101). The user (201) can accurately understand the answer to the inquiry by receiving the manual tailored to the usage environment of the electronic device (101) as visual information. The user's convenience can be improved when utilizing the electronic device (101).

[0066] FIG. 3a is a block diagram of an electronic device according to one embodiment of the present disclosure. FIG. 3b is a diagram of the relationship of state transition information according to one embodiment of the present disclosure.

[0067] The electronic device (101) of FIGS. 3a and 3b may be at least partially similar to the electronic device (101) of FIGS. 1 and 2, or may further include other embodiments of the electronic device (101). According to one embodiment, the electronic device (101) may include at least partially similar components to the electronic device (101) of FIG. 1.

[0068] Referring to FIG. 3a, the electronic device (101) may include a processor (120) (e.g., the processor (120) of FIG. 1), a memory (130) (e.g., the memory (130) of FIG. 1), a display (e.g., the display module (160) of FIG. 1), a microphone (310) (e.g., the input module (150) of FIG. 1), and / or a communication circuit (190) (e.g., the communication module (190) of FIG. 1). The memory (130) of the electronic device (101) may store environmental information (331) for the electronic device (101) (e.g., information related to hardware constituting the electronic device (101), information related to software installed on the electronic device (101), state transition information (332), and / or information related to an artificial intelligence model (333) (e.g., AI-related model information, AI algorithm information). The processor (120) of the electronic device (101) can at least partially activate an artificial intelligence model (e.g., an AI-related model, an AI algorithm) and can analyze the content of a user's inquiry based on the activated artificial intelligence model.

[0069] According to one embodiment, the processor (120) of the electronic device (101) can execute a program (e.g., program (140) of FIG. 1) stored in memory (130) to control at least one other component (e.g., hardware or software component) and perform various data processing or operations. For example, the processor (120) can at least partially activate the AI-related model (e.g., an AI algorithm for determining multiple prompts based on state transition information (332)) for generating a manual while said AI-related model is stored in memory (130). The processor (120) can analyze the content of a user's inquiry based on the AI-related model and generate a manual that indicates an answer according to said inquiry. According to one embodiment, the processor (120) can be operatively, functionally, and / or electrically connected to memory (130), a display (160), a microphone (310), and / or a communication circuit (190). According to one embodiment, the processor (120) may include at least one processor including a processing circuit.

[0070] According to one embodiment, the memory (130) of the electronic device (101) may store environmental information (331), state transition information (332), and / or artificial intelligence model-related information (333) for analyzing the content of an inquiry regarding the electronic device (101).

[0071] For example, the environment information (331) may include hardware information (e.g., specification information) related to the components constituting the electronic device (101) and / or software information (e.g., version information, patch information) related to the program installed on the electronic device (101). According to one embodiment, the processor (120) may generate a manual based on the environment information (331) that matches the specifications of the electronic device (101) and / or the version of the user interface (UI). The processor (120) may generate at least one image for generating the manual based on the environment information (331), and may generate a manual (e.g., video content) by integrating the generated at least one image.

[0072] For example, the state transition information (332) may include information related to menu entry or information related to selectable functions. Referring to FIG. 3b, an operational relationship diagram for the state transition information (332) is illustrated. The state transition information (332) may include a user interface that changes or transitions its state according to a user's selection. For example, the processor (120) may display at least one selectable second object in response to the selection of a first object included in the user interface, after the selection of the first object. The processor (120) may display at least one selectable third object in response to the selection of the at least one second object. The state transition information (332) may include an operational relationship diagram regarding the processing order. The state transition information (332) may indicate the state change process of the user interface according to the relationship diagram of FIG. 3b.

[0073] Referring to FIG. 3b, for example, the processor (120) may launch a gallery app (351) to view photos. In response to the launch of the gallery app (351), the processor (120) may display a gallery app launch screen. For example, the gallery app launch screen may include a “Photo” option (352), an “Album” option (353), and / or a “Story” option (354), and one may be selected by the user. Here, when the “Photo” option (352) is selected, photos classified by shooting date may be listed and displayed (e.g., Photo Display (355)), and when one photo (e.g., First Photo) is selected, at least one editing function for the selected photo (e.g., Photo Edit (357), AI Edit (358), Share (359), Delete Photo (360), Add to Favorites (361)) may be displayed. For another example, when the “Album” option (353) is selected, multiple photos included in the “Album” may be displayed. For another example, when the “Story” option (354) is selected, a story may be played (e.g., Story Playback (356)), and an “Add to Favorites (361)” option may be provided to classify the played story as a “Favorites.” According to one embodiment, state transition information (332) may include information about at least one function (e.g., at least one option, at least one object, selectable option) associated with a specific step. For example, the state transition information (332) may include an action (355) of displaying photos classified according to the shooting date when the aforementioned “Photo” option (352) is selected, and an action of displaying editing functions (357, 358, 359, 360, 361) for the first photo when the first photo is selected. The state transition information (332) may include a function or a second action (e.g., a second option) that can be additionally performed in conjunction with the first action when the first action (e.g., a first option) is performed.According to one embodiment, the electronic device (101) can extract at least one keyword based on user input and can determine a processing order suitable for the extracted at least one keyword (e.g., processing process, relationship diagram for the state transition information (332) of FIG. 3b) based on state transition information (332) stored in memory (130).

[0074] According to one embodiment, the electronic device (101) can update the state transition information (332) at least partially based on user feedback information related to the state transition information (332). For example, the electronic device (101) can obtain user feedback information in relation to the provision of a manual and can update the state transition information (332) based on said feedback information.

[0075] Referring to FIG. 3a, the artificial intelligence model related information (333) refers to an artificial intelligent model and may include a program or system trained to perform a specific task. The processor (120) of the electronic device (101) can analyze input data based on the artificial intelligence model related information (333) and can perform prediction, classification, generation, and / or optimization tasks on the result data of the input data.

[0076] For example, information related to an artificial intelligence model (333) (e.g., artificial intelligent model, AI algorithm, machine learning model, deep learning model) can determine one or more prompts (e.g., multiple prompts) when performing an action according to a processing order determined based on user input (e.g., processing order for generating an image (e.g., manual)). For example, the processor (120) can determine a processing order for image generation based on the information related to the artificial intelligence model (333) and determine one or more prompts (e.g., multiple prompts) corresponding to the determined processing order. For example, when performing a specific action according to the processing order, one or more prompts may include information that sequentially subdivides the process leading up to the execution of the specific action. Referring to FIGS. 10a to 10g, the “action of inputting text into a photo” (e.g., user input) is illustrated by sequentially distinguishing it. FIGS. 10a to 10g, each of which may be an example drawing in which a respective prompt is illustrated. According to one embodiment, the processor (120) may determine one or more prompts corresponding to a processing order based on artificial intelligence model related information (333).

[0077] According to one embodiment, the electronic device (101) may utilize a first artificial intelligence model to verify the user's intent regarding user input, utilize a second artificial intelligence model to determine the processing order for image generation, and utilize a third artificial intelligence model to determine one or more prompts corresponding to the processing order. For example, the first artificial intelligence model to the third artificial intelligence model may each be different from one another, or at least partially different from the other. The artificial intelligence model-related information (333) of FIG. 3a may include the first artificial intelligence model, the second artificial intelligence model, and / or the third artificial intelligence model.

[0078] According to one embodiment, the electronic device (101) can update the artificial intelligence model-related information (333) at least partially based on user feedback information related to the artificial intelligence model-related information (333). For example, after watching a video (e.g., a video manual), the user can input feedback information about the video into the electronic device (101). The electronic device (101) can obtain user feedback information regarding the provision of the video and can update the artificial intelligence model-related information (333) based on the feedback information.

[0079] According to one embodiment, the electronic device (101) can determine one or more prompts based on artificial intelligence model-related information (333) and can generate a plurality of images corresponding to each prompt based on the one or more prompts. The electronic device (101) can integrate the generated plurality of images to generate a video (e.g., video content, video manual, guide video). The electronic device (101) can play the generated video through a display (160). For example, regarding the content inquired about in relation to the operation of the electronic device (101), the user may be provided with a video (e.g., video content, video manual, guide video) that takes into account the environmental information (331) of the electronic device (101). The user may have improved convenience in operating the electronic device (101).

[0080] According to one embodiment, an electronic device (101) can visually provide an image (e.g., a video manual) through a display (160). Information regarding the specifications and settings of the display (160) can be stored as environment information (331) in a memory (130). In generating an image corresponding to a prompt, the processor (120) can generate an image suitable for the electronic device (101) based on the environment information (331) for the electronic device (101) (e.g., an image optimized to match the specifications and settings (e.g., version information) of the electronic device (101). The processor (120) can generate a video manual (e.g., video content) by integrating multiple images and can play the video manual through the display (160).

[0081] According to one embodiment, an electronic device (101) may be operatively or functionally connected to an external electronic device (e.g., a server) (e.g., a server (108) in FIG. 1) through a communication circuit (190) (e.g., a communication module (190) in FIG. 1). The electronic device (101) may transmit data to the external electronic device (e.g., a server (108)) or receive data from the external electronic device through the communication circuit (190).

[0082] According to one embodiment, an electronic device (101) can acquire a user's voice signal (e.g., user input, audio signal containing user voice information) by using a microphone (310) (e.g., input module (150) of FIG. 1). For example, regarding an inquiry, the user may input text through a display (160) or input a voice signal through the microphone (310). When a voice signal is input through the microphone (310), the processor (120) can convert the voice signal into text. When converting to text, the processor (120) can perform a correction operation on the text. According to one embodiment, the processor (120) can extract at least one keyword based on the text according to the user input.

[0083] According to one embodiment, the electronic device (101) can generate an image (e.g., a video manual) tailored to the user interface of the electronic device (101) and provide said image to the user. The electronic device (101) can analyze content inquired by the user (e.g., user input) based on an artificial intelligence model (e.g., an AI algorithm) and determine result information regarding the content inquired by the user (e.g., multiple prompts determined according to the processing order). The electronic device (101) can process one or more prompts and generate an image corresponding to one or more prompts according to the user's usage environment (e.g., specification information for the electronic device, version information, version information for the user interface, and / or environment information (331)). For example, when one or more prompts are processed or generated, version information for the user interface (e.g., version information of the user interface according to the user environment) may be added to said one or more prompts. For example, the electronic device (101) can generate a first prompt that reflects version information for a user interface and can generate a first image corresponding to the first prompt. The electronic device (101) can generate a video manual (e.g., video content) based on the generated image and the content of the user's inquiry. The electronic device (101) can provide the generated video manual to the user as visual information through a display (160).

[0084] According to one embodiment, the user can easily understand the answer to the inquiry (e.g., result information) by visually checking a video manual generated based on the user interface of the electronic device (101) (e.g., version information for the user interface). The user can visually check a video manual (e.g., video content) tailored to the usage environment of the electronic device (101) (e.g., environment information (331)) and accurately understand the answer to the inquiry (e.g., result information). The user's convenience can be improved when utilizing the electronic device (101).

[0085] According to one embodiment, the electronic device (101) may include a display (160), a processor (120) including a processing circuit, and a memory (130) for storing instructions. When the instructions are executed individually or collectively by the processor (120), the electronic device (101) may respond to user input, identify the user's intention corresponding to the user input, extract at least one keyword based on the identified user's intention, determine a processing order for image generation based on the extracted at least one keyword and environment information of the electronic device (101), determine one or more prompts corresponding to the identified processing order, generate a plurality of images corresponding to the determined one or more prompts, and display the generated plurality of images as the image through the display (160).

[0086] According to one embodiment, when the instructions are executed individually or collectively by the processor (120), the electronic device (101) can determine the processing order according to the at least one keyword based on the state transition information (332) and the artificial intelligence model stored in the memory (130), and determine the one or more prompts corresponding to the determined processing order. The state transition information (332) may include an operation relationship diagram for the processing order.

[0087] According to one embodiment, the artificial intelligence model is characterized by being stored in the memory (130) as a program that analyzes input data and generates result data.

[0088] According to one embodiment, when the instructions are executed individually or collectively by the processor (120), the electronic device (101) performs a correction operation on the text when the user input is text input, and can confirm the user's intention based on the text on which the correction operation is performed.

[0089] According to one embodiment, when the instructions are executed individually or collectively by the processor (120), the electronic device (101) can convert the audio input into text based on the voice information when the user input is an audio input containing the user's voice information, and can confirm the user's intention based on the converted text.

[0090] According to one embodiment, environmental information for the electronic device (101) may include hardware-related information of the electronic device and software-related information of the electronic device.

[0091] According to one embodiment, the hardware-related information includes specification information for a component of the electronic device, and the software-related information may include at least one of version information, form information, frame information, text information, and / or font information related to a user interface.

[0092] According to one embodiment, when the instructions are executed individually or collectively by the processor (120), the electronic device (101) can display the image based on environmental information for the electronic device and the generated plurality of images.

[0093] According to one embodiment, when the instructions are executed individually or collectively by the processor (120), the electronic device (101) may determine a first prompt according to the processing order based on an artificial intelligence model stored in the memory (130), generate a first image corresponding to the first prompt based on the artificial intelligence model, determine a second prompt based on the artificial intelligence model, the processing order, and the first prompt, generate a second image corresponding to the second prompt based on the artificial intelligence model, and display the image based on the first image and the second image.

[0094] According to one embodiment, when the instructions are executed individually or collectively by the processor (120), the electronic device (101) can obtain feedback information regarding an image displayed through the display (160) and update information related to an artificial intelligence model and state transition information stored in the memory (130) based on the obtained feedback information.

[0095] FIG. 4 is a flowchart illustrating a method for generating a manual in an electronic device according to one embodiment of the present disclosure.

[0096] 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.

[0097] According to one embodiment, operations 401 to 413 may be understood to be performed by a processor (e.g., processor (120) of FIG. 3a, processing circuit, at least one processor) of an electronic device (e.g., electronic device (101) of FIG. 3a). The electronic device of FIG. 4 may be at least partially similar to the electronic device (101) of FIG. 2 and FIG. 3a, or may further include other embodiments of the electronic device (101).

[0098] According to one embodiment, the processor (120) of the electronic device (101) can execute a manual creation program (e.g., an application that creates a video manual based on an artificial intelligence model (e.g., an AI algorithm)) for creating a video manual (e.g., video content, image information) while the manual creation program is installed in memory (e.g., memory (130) of FIG. 3a). For example, while the manual creation program is running, the processor (120) can detect events related to manual creation (e.g., user interaction input). According to one embodiment, the electronic device (101) can activate at least a part of an artificial intelligence model (e.g., an AI model, an AI algorithm) in response to the execution of the manual creation program.

[0099] In operation 401, the processor (120) may check environment information (e.g., environment information (331) of FIG. 3A) for the electronic device (101) in response to a manual generation event. For example, the environment information (331) may include hardware information (e.g., specification information, specification information) related to components constituting the electronic device (101) and / or software information (e.g., version information, patch information, version information related to the user interface, form information, frame information, text information, and / or font information) related to programs installed on the electronic device (101). The environment information (331) may be stored in memory (e.g., memory (130) of FIG. 3A). For example, the environment information (331) may be managed in a state stored in memory (130) at the time of the first execution of the electronic device (101). Operation 401 may be an operation of checking environment information (331) that is already recognized by the electronic device (101). For example, a manual generation event may include input of a set icon (e.g., item) or input of an input module (e.g., input module (150) of FIG. 1) to verify user input (e.g., input of inquiry content). Referring to FIG. 4, the operation of verifying environment information (311) is illustrated as operation 401, but is not limited thereto. Operation 401 may be performed during the process of generating an image after a plurality of prompts are determined in operation 409. Operation 401 may be performed prior to operation 407, in which environment information (331) is utilized.

[0100] In operation 403, the processor (120) can identify the user's intent corresponding to the user input. For example, the processor (120) can activate a display (e.g., the display (160) in FIG. 3a) or activate a microphone (e.g., the microphone (310) in FIG. 3a) in response to a manual generation event to obtain user input. The processor (120) can identify user input (e.g., text input) through the display (160) and identify the user's intent corresponding to the text. As another example, the processor (120) can obtain user input (e.g., voice signal input, audio signal containing the user's voice information) through the microphone (310) and convert the obtained voice signal into text. The processor (120) can identify the user's intent corresponding to the converted text. For example, the user input may include the content of the user's inquiry (e.g., a word or a sentence).

[0101] In operation 405, the processor (120) can extract keywords based on the user's intent. For example, if the user input is a sentence such as “I want to write text on a photo” (e.g., text input), the processor (120) can extract at least one keyword such as “photo, text, input” based on the aforementioned sentence. For example, the processor (120) can extract at least one keyword according to the user's intent.

[0102] In operation 407, the processor (120) can determine the processing order for video manual generation based on environment information (331) and keywords. For example, the processor (120) can determine the processing order for video manual generation based on state transition information (332) and artificial intelligence model related information (333) stored in memory (130). If the user input is the sentence “I want to input text into a photo,” the processor (120) can determine the user’s intent (e.g., need for a guide video for inputting text into a photo) and, in accordance with the user’s intent, determine the processing order for video generation (e.g., a video in which the process of inputting text into a photo appears sequentially). The processing order can be determined in multiple steps. For example, the state transition information (332) is in a state stored in memory (130), and the artificial intelligence model related information (333) (e.g., artificial intelligence model, AI algorithm) may be in a state that is at least partially activated in response to the execution of the manual generation program. The processor (120) can determine the processing order for image generation based on state transition information (332).

[0103] In operation 409, the processor (120) may determine one or more prompts corresponding to the processing order. For example, the processor (120) may subdivide the processing order into one or more prompts based on artificial intelligence model-related information (333) (e.g., AI algorithm). For example, the processor (120) may determine a first prompt corresponding to the first operation and, at least partially linked to the first prompt, determine a second prompt corresponding to the second operation. After determining the second prompt, the processor (120) may determine a third prompt corresponding to the third operation, at least partially linked to the second prompt. For example, the first prompt, the second prompt, and the third prompt may be operations performed sequentially according to the processing order. According to one embodiment, the processor (120) may determine a second prompt, which is the second operation, based on the first prompt, which is the first operation, and may determine a third prompt, which is the third operation, based on the second prompt.

[0104] In operation 411, the processor (120) may generate multiple images corresponding to one or more prompts. For example, the processor (120) may generate a first image corresponding to a first prompt, a second image corresponding to a second prompt, and / or a third image corresponding to a third prompt based on environment information (331). The first image, the second image, and / or the third image may be generated in accordance with the environment information (331) of the electronic device (101) (e.g., setting information and / or version information for the user interface of the electronic device (101).

[0105] In operation 413, the processor (120) can display multiple images as a video (e.g., video content, video manual). For example, the processor (120) can combine multiple images to display them as a single video content. The processor (120) can provide a video (e.g., video manual) to the user by displaying multiple images at set time intervals.

[0106] According to one embodiment, the electronic device (101) can determine an answer (e.g., creation of a video manual) by analyzing the content of a user's inquiry (e.g., user's intent) and can determine a processing order corresponding to the answer. The electronic device (101) can subdivide the processing order into one or more prompts based on artificial intelligence model-related information (333) (e.g., AI model, AI algorithm) and can generate multiple images corresponding to the one or more prompts. The electronic device (101) can generate a video (e.g., video content, video manual) based on the multiple images and provide it to the user.

[0107] According to one embodiment, the user can intuitively understand the answer to the inquiry (e.g., result information) by visually checking a video (e.g., video content, video manual, guide video) tailored to the usage environment (e.g., environment information (331)) of the electronic device (101). With respect to the inquiry, user convenience can be improved.

[0108] FIG. 5 is a diagram illustrating a manual generation process according to one embodiment of the present disclosure, divided into four steps.

[0109] According to one embodiment, steps 1 (510) through 4 (540) may be understood to be performed by a processor (e.g., processor (120) of FIG. 3a, processing circuit, at least one processor) of an electronic device (e.g., electronic device (101) of FIG. 3a). The electronic device of FIG. 5 may be at least partially similar to the electronic device (101) of FIG. 2 and FIG. 3a, or may further include other embodiments of the electronic device (101).

[0110] According to one embodiment, the processor (120) of the electronic device (101) can execute a manual generation program (e.g., an application that generates a manual based on an artificial intelligence model (e.g., an AI algorithm)) for generating a manual (e.g., video content, image information) while the manual generation program is installed in memory (e.g., memory (130) of FIG. 3a). For example, while the manual generation program is running, the processor (120) can detect events related to manual generation (e.g., user interaction input).

[0111] According to one embodiment, in the first step (510), the processor (120) may check for user input (501) (e.g., user interaction input). For example, user input (501) may include a situation where text is entered through the display of the electronic device (101) (e.g., the display (160) in FIG. 3a), or a situation where a user's voice signal is entered through the microphone of the electronic device (101) (e.g., the microphone (310) in FIG. 3a). User input (501) may include content in which the user inquires about a specific device and a specific function. According to one embodiment, user input (501) is not limited to user input by a specific input means.

[0112] According to one embodiment, in the second step (520), the processor (120) may perform user environment analysis (502), user input language interpretation (503), and / or user context analysis (504). For example, user environment analysis (502) may be an operation of analyzing hardware information (e.g., specification information, specification information) related to components constituting the electronic device (101) and / or software information (e.g., version information, patch information) related to programs installed on the electronic device (101). The processor (120) may perform user environment analysis (502) based on environment information (331) stored in the memory (130) of FIG. 3A. For example, user input language interpretation (503) may include an operation of extracting at least one keyword based on text and voice signals according to user input (501) and determining a processing order corresponding to the extracted at least one keyword. For example, the processor (120) can extract at least one keyword for user input (501) based on existing data such as manuals, web pages, chatbots, and / or emails (e.g., information related to previously extracted keywords). The processor (120) can perform user input language interpretation (503) based on state transition information (332) stored in the memory (130) of FIG. 3A. The processor (120) can convert user input (501) into text form, extract a word that matches the state transition information (332) from among a plurality of words included in the text, and determine said extracted word as at least one keyword. The processor (120) can determine a processing order corresponding to said at least one keyword based on the state transition information (332). For example, user context analysis (504) may include an operation of determining a plurality of prompts based on information confirmed in user environment analysis (502) and information confirmed in user input language interpretation (503).

[0113] For example, user context analysis (504) may include an operation to determine multiple prompts based on a processing order determined based on environment information (331) for an electronic device (101) identified in user environment analysis (502) and at least one keyword and / or state transition information (332) identified in user input language interpretation (503). For example, the operation to determine multiple prompts may include an operation to divide the user input (501) into multiple prompts. For example, the processor (120) may analyze the aforementioned information (e.g., environment information (331), at least one keyword, and / or state transition information (332)) based on artificial intelligence model-related information (333) stored in the memory (130) of FIG. 3A, and may determine multiple prompts that subdivide the processing order according to the user input (501) into multiple steps. The processor (120) may determine a first prompt corresponding to the first action in relation to the processing order, and may determine a second prompt corresponding to the second action that is at least partially linked to the first prompt. After determining the second prompt, the processor (120) may determine a third prompt corresponding to the third action that is at least partially linked to the second prompt. For example, the first prompt, the second prompt, and the third prompt may be actions performed sequentially according to the processing order. According to one embodiment, the electronic device (101) may determine a plurality of prompts that are at least partially linked based on artificial intelligence model related information (333).

[0114] According to one embodiment, in the third step (530), the processor (120) may generate a plurality of images corresponding to a plurality of prompts and may generate a video manual (505) based on the plurality of images. For example, the processor (120) may generate a first image corresponding to a first prompt, a second image corresponding to a second prompt, and / or a third image corresponding to a third prompt based on environment information (331). The electronic device (101) may generate a plurality of images that match the specifications of the electronic device (101). The plurality of images may be at least partially corrected to match the user interface of the electronic device (101). The processor (120) may integrate the generated plurality of images to generate a video manual (e.g., video content).

[0115] According to one embodiment, the operation (505) of generating a video manual in the third step (530) can be performed independently in the electronic device (101) based on an artificial intelligence model installed in the electronic device (101). For example, the processor (120) of the electronic device (101) can input each prompt into the artificial intelligence model to generate each image corresponding to each prompt, and can generate a video manual based on each generated image.

[0116] According to another embodiment, the operation (505) of generating a video manual in step 3 (530) may be performed independently by an external electronic device based on an artificial intelligence model installed in an external electronic device (e.g., a server). For example, an electronic device (101) may provide information related to each prompt to an external electronic device and input each prompt into an artificial intelligence model of the external electronic device. The external electronic device may generate each image corresponding to each prompt and generate a video manual based on each generated image. The external electronic device may provide the generated video manual to the electronic device (101). The electronic device (101) may output the video manual generated by the external electronic device.

[0117] According to one embodiment, in step 4 (540), the processor (120) can output the generated video manual (506). For example, the processor (120) can output the video manual through a display (e.g., the display (160) of FIG. 3a).

[0118] Referring to FIG. 5, user input (501) may include an operation in which a user's inquiry is entered, and user output (506) may include an operation in which an answer to the inquiry (e.g., creation of a video manual) is output. Referring to FIG. 5, in the second step (520), the processor (120) may analyze the user input (501) and verify a processing order corresponding to the answer determined according to the analysis result. In the user context analysis (504) operation of the second step (520), the processor (120) may determine a plurality of prompts based on the processing order and may generate a plurality of images corresponding to the plurality of prompts. Referring to FIG. 5, in the third step (530), the processor (120) may generate a video manual (e.g., video content) based on the plurality of images.

[0119] According to one embodiment, the electronic device (101) can generate a video manual (e.g., video content) as an answer to a user's inquiry (e.g., user input (501)) and can display the video manual through a display (160). By visually checking the manual (e.g., video content) tailored to the user's environment (e.g., environment information (331)) of the electronic device (101), the user can intuitively understand the answer to the inquiry (e.g., result information).

[0120] According to one embodiment, at least one of the first step (510) to the fourth step (540) may be performed by an electronic device (101) and an external electronic device (e.g., a server, the server (108) of FIG. 1) that is connected to the electronic device (101) through communication. For example, the first step (510) and the fourth step (540) may be performed based on the electronic device (101), and the second step (520) and the third step (530) may be performed based on an external electronic device (e.g., the server (108)). In this case, in the first step (510), the electronic device (101) transmits the user's inquiry to the server (108), and in the fourth step (540), the video manual received from the server (108) may be output through the display (160). According to one embodiment, the second step (520) and the third step (530) may be performed on a server (108) that is connected to the electronic device (101) via communication. For example, the server (108) may perform the second step (520) and the third step (530) based on an artificial intelligence model.

[0121] FIG. 6 is a flowchart illustrating a user environment analysis method according to one embodiment of the present disclosure. The user environment analysis method of FIG. 6 may include a detailed description in relation to the user environment analysis (502) operation of FIG. 5.

[0122] According to one embodiment, operations 601 to 605 may be understood to be performed by a processor (e.g., processor (120) of FIG. 3a, processing circuit, at least one processor) of an electronic device (e.g., electronic device (101) of FIG. 3a). The electronic device of FIG. 6 may be at least partially similar to the electronic device (101) of FIG. 2 and FIG. 3a, or may further include other embodiments of the electronic device (101).

[0123] In operation 601, the processor (120) of the electronic device (101) can check the model information of the electronic device (101) (e.g., model name (hardware model name), hardware information about the electronic device (101) (e.g., specification information, specification information)). For example, the electronic device (101) may have coded model information (e.g., information related to hardware) stored in memory (e.g., memory (130) of FIG. 3a). The processor (120) can check the model information stored in memory (130).

[0124] In operation 603, the processor (120) can check version information related to the user interface (e.g., information related to a program installed on the electronic device (101), patch information, software information, version information related to the user interface, form information, frame information, text information, and / or font information). For example, the electronic device (101) may have programs (e.g., operating system programs, OS) installed to operate the components constituting the electronic device (101), and using said programs, a user interface tailored to the specifications of the electronic device (101) (e.g., hardware information, software information) may be implemented. The user interface may be updated periodically or non-periodically, and version information may be assigned. For example, if the version information for the user interface is different, the form of the user interface may be at least partially different.

[0125] In operation 605, the processor (120) may add model information and version information for each prompt. The model information and version information may be included in the environment information (331) of FIG. 3A. For example, when determining the prompt, the processor (120) may determine a prompt to which the model information and the version information have been added. The processor (120) may add model information and version information for each prompt and may generate each prompt step by step. For example, the processor (120) may reflect information (e.g., environment information) corresponding to a user interface that matches the specifications (e.g., spec) of the electronic device (101) in the prompt.

[0126] According to one embodiment, the processor (120) can input a prompt to an artificial intelligence model to which environmental information (e.g., model information and version information) has been added, and can generate an image corresponding to the prompt.

[0127] According to one embodiment, the processor (120) may generate an image (e.g., user interface) corresponding to a prompt, and may generate a user interface that reflects the model information and the version information. A user of the electronic device (101) may be familiar with the usage environment (e.g., user interface) of a specific version (e.g., a version tailored to the electronic device (101) currently in use). According to one embodiment, the electronic device (101) may generate an image (e.g., an image corresponding to each prompt) based on information related to the user interface familiar to the user (e.g., model information and / or version information). The electronic device (101) may generate a manual based on the generated image.

[0128] According to one embodiment, the user checks a manual tailored to their usage environment, so they can intuitively understand the answer to the user input. The user can intuitively understand the image generated based on information related to the user interface of the electronic device (101) (e.g., model information and / or version information), and user convenience can be improved.

[0129] FIG. 7 is a flowchart illustrating a method for verifying text based on user input according to one embodiment of the present disclosure. The text verification method of FIG. 7 may include a description related to a part of the user input language interpretation (503) operation of FIG. 5.

[0130] According to one embodiment, operations 701 to 705 may be understood to be performed by a processor (e.g., processor (120) of FIG. 3a, processing circuit, at least one processor) of an electronic device (e.g., electronic device (101) of FIG. 3a). The electronic device of FIG. 7 may be at least partially similar to the electronic device (101) of FIG. 2 and FIG. 3a, or may further include other embodiments of the electronic device (101).

[0131] In operation 701, the processor (120) of the electronic device (101) can determine whether the user input (e.g., user input (501) of FIG. 5, content of inquiry) is text input. For example, user input through the display of the electronic device (101) (e.g., display (160) of FIG. 3a) is text input, and user input through the microphone of the electronic device (101) (e.g., microphone (310) of FIG. 3a) may be voice input (e.g., input of an audio signal containing the user's voice information).

[0132] In operation 701, if the user input is text input, in operation 703, the processor (120) can correct the input sentence based on the input text. For example, the processor (120) can check at least one of typos, spacing, grammar, and / or spelling based on the input text, and if there is a misspelled part, it can correct the misspelled part. Based on the input sentence (e.g., text) for which the correction operation is completed, the processor (120) can extract a set keyword.

[0133] In operation 705, the processor (120) can extract at least one keyword based on the input text (e.g., text after the correction operation is completed). For example, the processor (120) can compare a word included in the input text with state transition information (e.g., state transition information (332) of FIG. 3a) stored in memory (e.g., memory (130) of FIG. 3a), and determine the matching word as a keyword. The processor (120) can extract at least one keyword included in the text.

[0134] In operation 701, if the user input is not text input, in operation 707, the processor (120) can convert the input voice signal into text. For example, the electronic device (101) may include a text conversion module that converts the voice signal into text.

[0135] When a voice signal is converted into text in operation 707, in operation 703, the processor (120) can perform a correction operation (e.g., correction of input sentence) based on the converted text, and in operation 705, can extract at least one keyword based on the text on which the correction operation was performed. According to one embodiment, the electronic device (101) can extract at least one keyword based on user input (501) (e.g., text and / or voice signal), and can determine a processing order corresponding to the extracted at least one keyword based on state transition information (332).

[0136] FIG. 8 is a flowchart illustrating a user context analysis method according to one embodiment of the present disclosure. The user context analysis method of FIG. 8 may include a detailed description in relation to the user context analysis (504) operation of FIG. 5.

[0137] According to one embodiment, operations 801 to 807 may be understood to be performed by a processor (e.g., processor (120) of FIG. 3a, processing circuit, at least one processor) of an electronic device (e.g., electronic device (101) of FIG. 3a). The electronic device of FIG. 8 may be at least partially similar to the electronic device (101) of FIG. 2 and FIG. 3a, or may further include other embodiments of the electronic device (101).

[0138] In operation 801, the processor (120) of the electronic device (101) can analyze keywords extracted based on input text. For example, the input text may include text corresponding to the user input (501) of FIG. 5. For example, the processor (120) can identify the user's intent based on the input text and can extract keywords based on the identified user's intent. The processor (120) can determine a processing order corresponding to the extracted keywords based on state transition information (e.g., state transition information (332) of FIG. 3a)) stored in memory (e.g., memory (130) of FIG. 3a).

[0139] In operation 803, the processor (120) can determine a processing process (e.g., processing order, processing procedure) corresponding to the text based on keywords and state transition information (332). For example, if the input text is “Tell me how to input text into a photo,” the keywords may include at least one of “photo,” “text,” “input,” and / or “method.” The processing process may include a plurality of steps (e.g., procedure) in which the “process of inputting text into a photo” is listed in sequence. According to one embodiment, the processor (120) may reflect the keywords and state transition information (332) in the artificial intelligence model related information (333) of FIG. 3a, and the processing process may be determined based on the artificial intelligence model related information (333).

[0140] In operation 805, the processor (120) may generate one or more prompts corresponding to a processing process. The processor (120) may subdivide the processing process based on an artificial intelligence model (e.g., an artificial intelligence model, an AI algorithm) included in the artificial intelligence model-related information (333), and may determine one or more prompts corresponding to the subdivided processing process. In relation to the processing process, the processor (120) may determine a first prompt corresponding to a first action, and may determine a second prompt corresponding to a second action, at least partially linked to the first prompt. After determining the second prompt, the processor (120) may determine a third prompt corresponding to a third action, at least partially linked to the second prompt. For example, the first prompt, the second prompt, and the third prompt may be actions performed sequentially according to the processing order.

[0141] In operation 807, the processor (120) may add environment information (e.g., model information, version information, environment information (331) of FIG. 3a) to one or more prompts (e.g., a first prompt, a second prompt, and / or a third prompt). For example, the processor (120) may reflect the added environment information when generating an image corresponding to each prompt.

[0142] In operation 809, the processor (120) may generate multiple images corresponding to one or more prompts based on environment information (e.g., model information, version information, and / or environment information (331) of FIG. 3A). For example, in generating images corresponding to prompts, the processor (120) may generate images to which environment information (331) for the electronic device (101) is applied. The generated images may be generated according to the specifications (e.g., specifications, version, hardware information, software information) of the electronic device (101). The generated images may be at least partially corrected according to the user interface (e.g., usage environment) of the electronic device (101). The processor (120) may generate a first image corresponding to a first prompt, a second image corresponding to a second prompt, and / or a third image corresponding to a third prompt based on environment information (331). For example, the processor (120) may input a first prompt to the artificial intelligence model to which the environment information (331) is applied. The artificial intelligence model may analyze the requirements of the first prompt and generate a first image corresponding to the first prompt. The processor (120) may generate a first image corresponding to the first prompt based on the artificial intelligence model. According to one embodiment, the processor (120) may generate one or more prompts and an image corresponding to each prompt based on the artificial intelligence model.

[0143] According to one embodiment, the electronic device (101) can verify an answer (e.g., processing order, processing process) to a user's inquiry (e.g., user input (501)) based on extracted keywords. The electronic device (101) can determine one or more prompts corresponding to the processing process based on an artificial intelligence model (e.g., an AI model, an AI algorithm) and can generate multiple images based on the one or more prompts. The electronic device (101) can generate the multiple images based on environmental information (331) for the electronic device (101). For example, the multiple images may be images generated according to the specifications (e.g., specs) of the electronic device (101).

[0144] FIG. 9 is a flowchart illustrating a manual generation method according to one embodiment of the present disclosure. The manual generation method of FIG. 9 may include a detailed description in relation to the image manual generation (505) operation of FIG. 5.

[0145] According to one embodiment, operations 901 to 905 may be understood to be performed by a processor (e.g., processor (120) of FIG. 3a, processing circuit, at least one processor) of an electronic device (e.g., electronic device (101) of FIG. 3a). The electronic device of FIG. 9 may be at least partially similar to the electronic device (101) of FIG. 2 and FIG. 3a, or may further include other embodiments of the electronic device (101).

[0146] In operation 901, the processor (120) of the electronic device (101) may generate multiple images corresponding to one or more prompts. For example, the processor (120) may receive one or more prompts as input values ​​based on an artificial intelligence model (e.g., an AI model, an AI algorithm), and multiple images may be output as output values ​​based on said artificial intelligence model. When generating images, the artificial intelligence model may generate comments for each prompt. Comments for prompts may include descriptions related to actions to be performed by the user at the corresponding prompt. When generating images based on environmental information (331) for the electronic device (101), the processor (120) may generate comments related to said images and may add said comments to said images.

[0147] In operation 903, the processor (120) can generate a video manual (e.g., video content, video manual generation (505) of FIG. 5) based on a plurality of generated images. For example, the processor (120) can generate a video manual by integrating a plurality of images. Since the generated video manual is generated based on environmental information (331) for the electronic device (101), it can provide a user experience (e.g., user interface) familiar to the user of the electronic device (101).

[0148] In operation 905, the processor (120) can display the generated video manual. For example, the processor (120) can display (e.g., output) the generated video manual through a display (e.g., the display (160) of FIG. 3A). The video manual includes video content and can be played under the control of a video-related program. For example, the video manual may include a video or animation in which a plurality of images are displayed sequentially according to a set time interval.

[0149] According to one embodiment, the electronic device (101) can generate a plurality of images, each having one or more prompts and a related description (e.g., comment) for each prompt, and can generate a video manual (e.g., video content) based on the plurality of images. For example, since the video manual is generated based on environment information (331) for the electronic device (101), it can provide a user experience (e.g., user interface) familiar to the user of the electronic device (101). According to one embodiment, by watching a video manual tailored to the usage environment of the electronic device (e.g., environment information (331)), the user can intuitively understand the answer to the inquiry. The user's convenience can be improved when utilizing the electronic device (101).

[0150] FIG. 10a is an exemplary illustration showing a first image corresponding to a first prompt according to an embodiment of the present disclosure. FIG. 10b is an exemplary illustration showing a second image corresponding to a second prompt according to an embodiment of the present disclosure. FIG. 10c is an exemplary illustration showing a third image corresponding to a third prompt according to an embodiment of the present disclosure. FIG. 10d is an exemplary illustration showing a fourth image corresponding to a fourth prompt according to an embodiment of the present disclosure. FIG. 10e is an exemplary illustration showing a fifth image corresponding to a fifth prompt according to an embodiment of the present disclosure. FIG. 10f is an exemplary illustration showing a sixth image corresponding to a sixth prompt according to an embodiment of the present disclosure. FIG. 10g is an exemplary illustration showing a seventh image corresponding to a seventh prompt according to an embodiment of the present disclosure.

[0151] FIGS. 10a through 10g may be drawings sequentially illustrating a situation in which a plurality of images corresponding to a plurality of prompts are generated. An embodiment illustrated in FIGS. 10a through 10g may be understood to be performed by a processor (e.g., processor (120) of FIG. 3a, processing circuit, at least one processor) of an electronic device (e.g., electronic device (101) of FIG. 3a). The electronic device of FIGS. 10a through 10g may be at least partially similar to the electronic device (101) of FIG. 2 and FIG. 3a, or may further include other embodiments of the electronic device (101).

[0152] According to one embodiment, the processor (120) of the electronic device (101) can execute a manual generation program (e.g., an application that generates a manual based on an artificial intelligence model (e.g., an AI algorithm)) for generating a manual (e.g., video content, video manual, image information) while the manual generation program is installed in memory (e.g., memory (130) of FIG. 3a). The electronic device (101) can generate a video manual tailored to the environment information (e.g., hardware information, software information) of the electronic device (101) based on the manual generation program, and can provide the video manual to the user. The electronic device (101) can analyze the content of the user's inquiry (e.g., user input, user intent) based on an artificial intelligence model (e.g., an AI algorithm) and determine result information regarding the content of the user's inquiry (e.g., one or more prompts determined according to the processing order). The electronic device (101) can process each prompt according to the user's usage environment (e.g., specification information, version information, and / or environment information (331) for the electronic device) and can generate multiple images corresponding to each prompt. The electronic device (101) can generate a manual (e.g., video content) according to the user's inquiry based on the generated multiple images. The electronic device (101) can provide the generated manual to the user as visual information through a display (160).

[0153] Referring to FIGS. 10a through 10g, in response to a user input stating, “Tell me how to input text into a photo,” the electronic device (101) can analyze the user input and extract a keyword corresponding to at least one of “photo,” “text,” “input,” and / or “method.” Based on the extracted keyword, the electronic device (101) can generate a plurality of prompts in which the “process of inputting text into a photo” is sequentially listed. For example, the first prompt may include a situation where “Draw a picture of selecting a gallery application on the electronic device (101).” The second prompt may include a situation where “Draw a picture of selecting one photo while multiple photos are being displayed after the gallery application has been launched.” The third prompt may include a situation where “Draw a picture of selecting an edit icon to enter an edit mode for the selected photo.” The fourth prompt may include a situation where “Draw a picture of selecting an icon to enter a text-related edit menu in photo editing mode.” The fifth prompt may include a situation where “draw a text icon to input text into a selected photo.” The sixth prompt may include a situation where “draw a user inputting “text” into a photo and determining its position in text editing mode.” The seventh prompt may include a situation where “draw a user adjusting the size of the “text” input into the photo.” The electronic device (101) may generate multiple images (e.g., first to seventh images) corresponding to multiple prompts (e.g., first to seventh prompts).

[0154] FIGS. 10a to 10g illustrate a plurality of images corresponding to a plurality of prompts generated by an electronic device (101). FIG. 10a may include a first image corresponding to a first prompt, and FIG. 10b may include a second image corresponding to a second prompt. For example, FIGS. 10a to 10g may include a first image corresponding to a first prompt to a seventh image corresponding to a seventh prompt. A processor (120) of the electronic device (101) may integrate the first image of FIG. 10a to the seventh image of FIG. 10g to generate a manual (e.g., video content). For example, when the manual is played, the first image of FIG. 10a to the seventh image of FIG. 10g may be displayed sequentially through a display (e.g., the display (160) of FIG. 3a).

[0155] FIG. 10a illustrates a first image (1001) included in a manual. For example, the first image (1001) may be generated based on a first prompt (e.g., “Draw me selecting a gallery application on the electronic device (101)” situation). The first image (1001) illustrates a situation where a gallery application (1021) (e.g., a photo-related application) is selected on the home screen of the electronic device (101). The first image (1001) may include a first description (1011) (e.g., “Select gallery”) corresponding to the first prompt. The first image (1001) may be included as the first image of a manual (e.g., video content).

[0156] FIG. 10b illustrates a second image (1002) included in the manual. For example, the second image (1002) may be generated based on a second prompt (e.g., “Draw a picture of selecting one photo while multiple photos are displayed after the gallery application is launched”). The second image (1002) illustrates a situation in which one photo (1022) is selected from multiple photos on the execution screen of the gallery application (1021). The second image (1002) may include a second description (1012) (e.g., “Select photo”) corresponding to the second prompt. The second image (1002) may be included as a second image in the manual (e.g., video content).

[0157] FIG. 10c illustrates a third image (1003) included in the manual. For example, the third image (1003) may be generated based on a third prompt (e.g., the situation “Draw me selecting the edit icon to enter edit mode for the selected photo”). The third image (1003) may include multiple option icons related to the selected photo and illustrates a situation in which the edit icon (1023) is selected among the multiple option icons. The third image (1003) may include a third description (1013) corresponding to the third prompt (e.g., “Select edit icon”). The third image (1003) may be included as the third image of the manual (e.g., video content).

[0158] FIG. 10d illustrates a fourth image (1004) included in the manual. For example, the fourth image (1004) may be generated based on a fourth prompt (e.g., "Draw me selecting an icon to enter a text-related editing menu in photo editing mode"). The fourth image (1004) illustrates a situation where a "text-related editing icon (1024)" is selected in "editing mode" for a selected photo. The fourth image (1004) may include a fourth description (1014) (e.g., "Entering editing mode") corresponding to the fourth prompt. The fourth image (1004) may be included as the fourth image in the manual (e.g., video content). The electronic device (101) may display a text-related editing menu in response to user input regarding the "text-related editing icon (1024)."

[0159] FIG. 10e illustrates a fifth image (1005) included in the manual. For example, the fifth image (1005) may be generated based on a fifth prompt (e.g., the situation “Draw me selecting a text icon to input text into the selected photo”). The fifth image (1005) illustrates a situation where a text-related editing menu may be displayed in “text editing mode” for the selected photo, and the user selects a “text icon (1025)” to input text. The fifth image (1005) may include a fifth description (1015) corresponding to the fifth prompt (e.g., “Selection of the text icon”). The fifth image (1005) may be included as the fifth image in the manual (e.g., video content).

[0160] FIG. 10f illustrates a sixth image (1006) included in the manual. For example, the sixth image (1006) may be generated based on a sixth prompt (e.g., “Draw me the user entering “text” into the photo and determining its location in text editing mode”). The sixth image (1006) illustrates a situation in which a “text” object (1026) (e.g., characters, letters, numbers) is entered based on a selected photo. For example, the user may enter the content (e.g., characters, letters, numbers) of the “text” object (1026) and, based on the user’s touch input (e.g., drag input) on the “text” object (1026), it may be entered in a form that is added to a specific location on the photo. The sixth image (1006) may include a sixth description (1016) (e.g., “determining text location”) corresponding to the sixth prompt. The 6th image (1006) may be included as the sixth image of the manual (e.g., video content).

[0161] FIG. 10g illustrates a seventh image (1007) included in the manual. For example, the seventh image (1007) may be generated based on a seventh prompt (e.g., “Draw me the resizing of the “text” entered in the photo) situation). The seventh image (1007) illustrates a situation in which the size of a “text” object (e.g., a character, letter, number) is resized. For example, a guideline (1027) for resizing the “text” object may be displayed. The “text” object may be resized as the area (e.g., region) of the guideline (1027) changes. For example, if the area of ​​the guideline (1027) is expanded, the size of the “text” object may increase, and if the area of ​​the guideline (1027) is reduced, the size of the “text” object may decrease. The seventh image (1007) may include a seventh description (1017) (e.g., “Text size adjustment”) corresponding to the seventh prompt. The seventh image (1007) may be included as the seventh image of a manual (e.g., video content).

[0162] According to one embodiment, the electronic device (101) can generate a plurality of images corresponding to a plurality of prompts and can generate a manual (e.g., video content) based on the generated plurality of images. For example, the manual may include video content in which a plurality of images are displayed sequentially at set time intervals.

[0163] According to one embodiment, the electronic device (101) can obtain user feedback information related to the manual and, based on the feedback information, can at least partially update state transition information (332) and artificial intelligence model related information (333) stored in memory (130). For example, the electronic device (101) can obtain user feedback information regarding images that are missing or incorrectly added in the manual and, based on the feedback information, can update information related to the manual generation program.

[0164] According to one embodiment, the user can visually check a manual generated based on the usage environment of the electronic device (101) (e.g., specification information, version information, user interface, and / or environment information (environment information (331) in FIG. 3a) for the electronic device) and can easily understand the answer (e.g., result information) to the inquiry content (e.g., user input). According to one embodiment, user convenience can be improved when utilizing the electronic device (101).

[0165] FIG. 11 is an example diagram showing a video manual displayed in a multi-window mode according to one embodiment of the present disclosure.

[0166] The electronic device of FIG. 11 (e.g., the electronic device (101) of FIG. 3a) may be at least partially similar to the electronic device (101) of FIG. 1 and FIG. 2, or may further include other embodiments of the electronic device (101). According to one embodiment, the electronic device (101) may include at least partially similar components to the electronic device (101) of FIG. 1. FIG. 11 may be understood as being performed by a processor of the electronic device (101) (e.g., the processor (120) of FIG. 3a, a processing circuit, at least one processor).

[0167] According to one embodiment, the electronic device (101) can determine an answer (e.g., creation of a video manual) by analyzing the content of a user's inquiry (e.g., user's intent) and can determine a processing order corresponding to the answer. The electronic device (101) can subdivide the processing order into one or more prompts based on artificial intelligence model-related information (333) (e.g., AI model, AI algorithm) and can generate multiple images corresponding to the one or more prompts. The electronic device (101) can generate a video (e.g., video content, video manual) based on the multiple images and can display the generated video through a display (e.g., display (160) of FIG. 3a).

[0168] Referring to FIG. 11, the electronic device (101) can operate in a multi-window mode. For example, the processor (120) of the electronic device (101) can divide a single display (160) into multiple display areas (1110, 1120) and display different images based on the multiple display areas. For example, the processor (120) can display a video (1111) (e.g., a video manual) based on the first display area (1110) and display a user interface related to the video (1111) based on the second display area (1120), which is different from the first display area (1110).

[0169] Referring to FIG. 11, the processor (120) can display a video (1111) (e.g., a video manual) in a first display area (1110) based on a video playback program (e.g., a user interface for video playback (1112)). In response to the situation where the video (1111) is displayed in the first display area (1110), the processor (120) can display a home screen related to the video (1111) in a second display area (1120). For example, the processor (120) can display an icon included in the video (1111) (e.g., a gallery icon (1121)) in the second display area (1120). In response to user input regarding the gallery icon (1121), the processor (120) can apply a visual effect (1122) in which the gallery icon (1121) is selected.

[0170] According to one embodiment, while viewing the video (1111) being displayed through the first display area (1110), the user can intuitively perform actions according to the video (1111) in the second display area (1120). For example, the user can select a gallery icon (1121) displayed in the second display area (1120) in accordance with a comment on the video (1111) (e.g., “Select Gallery”). While viewing the video (1111) (e.g., video manual), the user can intuitively follow and perform actions guided by the video.

[0171] According to one embodiment, an electronic device (101) can display a video manual (1111) based on a user's inquiry content based on a first display area (1110), and can display a home screen corresponding to the video manual (1111) based on a second display area (1120) that is distinct from the first display area (1110). A processor (120) of the electronic device (101) can execute a gallery application corresponding to the gallery icon (1121) in response to user input regarding the gallery icon (1121) displayed in the second display area (1120). While displaying the video manual (1111) through the first display area (1110), the electronic device (101) can display a user interface corresponding to the video manual (1111) through the second display area (1120) so that the user can directly perform an action according to the video manual (1111).

[0172] FIG. 12 is a flowchart illustrating a method for generating a video manual based on a server connected to an electronic device according to one embodiment of the present disclosure.

[0173] 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.

[0174] The electronic device (1221) of FIG. 12 (e.g., the electronic device (101) of FIG. 3a) may be at least partially similar to the electronic device (101) of FIG. 1 and FIG. 2, or may further include other embodiments of the electronic device (101). According to one embodiment, the electronic device (101) may include at least partially similar components to the electronic device (101) of FIG. 1. The server (1222) of FIG. 12 may be at least partially similar to the server (108) of FIG. 1, or may further include other embodiments of the server (108). According to one embodiment, the server (108) may include at least partially similar components to the electronic device (101) of FIG. 1.

[0175] Referring to FIG. 12, operations 1201, 1202, 1203, and 1211 may be understood to be performed by a processor of an electronic device (1221) (e.g., processor (120) of FIG. 3a, processing circuit, at least one processor). Operations 1204 through 1210 may be understood to be performed by a processor of a server (1222) (e.g., processing circuit, at least one processor).

[0176] According to one embodiment, the processor (120) of the electronic device (1221) can execute a manual creation program (e.g., an application that creates a video manual based on an artificial intelligence model (e.g., an AI algorithm)) for creating a video manual (e.g., video content, image information) while the manual creation program is installed in memory (e.g., memory (130) of FIG. 3a). For example, while the manual creation program is running, the processor (120) can detect events related to manual creation (e.g., user interaction input, user input). According to one embodiment, the electronic device (101) can activate at least a part of an artificial intelligence model (e.g., an AI model, an AI algorithm) in response to the execution of the manual creation program.

[0177] In operation 1201, the processor (120) can check environmental information (e.g., environmental information (331) of FIG. 3A) for an electronic device (1221). For example, the environmental information (331) may include hardware information (e.g., specification information, specification information) related to components constituting the electronic device (1221) and / or software information (e.g., version information, patch information, version information related to the user interface, form information, frame information, text information, and / or font information) related to a program installed on the electronic device (101). The environmental information (331) may be stored in memory (e.g., memory (130) of FIG. 3A). In operation 1201, the processor (120) can check the environmental information (331) stored in memory (130).

[0178] In operation 1202, the processor (120) can obtain user input (e.g., input of inquiry content). For example, the user can inquire about a function (e.g., operation) related to the electronic device (101) based on a manual generation program. User input may include text input or audio input.

[0179] In operation 1203, the processor (120) can transmit environment information (331) and user input to the server (1222). For example, the electronic device (1221) may be in a state of communication connection with the server (1222) and may transmit data to the server (1222) or receive data from the server (1222).

[0180] In operation 1204, the server (1222) can confirm the user's intention corresponding to the user input by responding to confirmation of the environment information (331) and user input transmitted from the electronic device (1221). For example, the server (1222) can analyze the user input based on an artificial intelligence model and infer (predict) the user's intention corresponding to the user input. For example, if the user input is a sentence such as “I want to write text on a photo” (e.g., text input), the server (1222) can confirm the user's intention that “the user wants to write text on a specific photo” based on the aforementioned sentence.

[0181] In operation 1205, the server (1222) can extract keywords based on the user's intent. Based on the aforementioned sentence, the server (1222) can extract at least one keyword, such as “photo, text, input”.

[0182] In operation 1206, the server (1222) can determine the processing order for creating a video manual based on environmental information (331) provided from the electronic device (1221) and extracted keywords (e.g., photo, text, input). For example, the server (1222) can input the environmental information (331) and the extracted keywords based on an artificial intelligence model, and the processing order for creating the video manual (e.g., a video in which text is entered into a specific photo and the process of editing the text appears sequentially) can be determined as an output result based on the artificial intelligence model. According to one embodiment, the artificial intelligence model that analyzes user input in operation 1204 and the artificial intelligence model that determines the processing order in operation 1206 may be different from each other, or at least partially different from each other.

[0183] In operation 1207, the server (1222) may determine one or more prompts corresponding to the processing order. For example, the server (1222) may subdivide the processing order into one or more prompts. For example, the server (1222) may determine a first prompt corresponding to the first operation and, at least partially linked to the first prompt, determine a second prompt corresponding to the second operation. After determining the second prompt, the server (1222) may determine a third prompt corresponding to the third operation, at least partially linked to the second prompt. For example, the first prompt, the second prompt, and the third prompt may be operations performed sequentially according to the processing order.

[0184] In operation 1208, the server (1222) may generate multiple images corresponding to one or more prompts. For example, the server (1222) may generate a first image corresponding to a first prompt, a second image corresponding to a second prompt, and / or a third image corresponding to a third prompt based on environment information (331) of the electronic device (1221). The first image, the second image, and / or the third image may be images generated in accordance with the environment information (331) of the electronic device (1221) (e.g., configuration information and / or version information for the user interface of the electronic device (1221).

[0185] In operation 1209, the server (1222) can generate a video manual (e.g., video content, guide video) based on multiple images. For example, the server (1222) can combine multiple images to generate a single video content.

[0186] In operation 1210, the server (1222) can transmit the generated video manual to the electronic device (1221).

[0187] In operation 1211, the processor (120) of the electronic device (1221) can obtain a video manual transmitted from the server (1222) and can display the video manual through a display (e.g., the display (160) of FIG. 3A). The electronic device (1221) can provide a video manual (e.g., video content, video, guide video) generated based on a plurality of images to the user.

[0188] Referring to the four steps of the manual generation process illustrated in FIG. 5, the first step (510) and the fourth step (540) can be performed by an electronic device (1221), and the second step (520) and the third step (530) can be performed by a server (1222).

[0189] A method for displaying an image in an electronic device (101) according to one embodiment may include: an operation of confirming a user's intention corresponding to the user input in response to a user input; an operation of extracting at least one keyword based on the confirmed user's intention; an operation of confirming a processing order for image generation based on the extracted at least one keyword and environment information of the electronic device (101); an operation of determining one or more prompts corresponding to the confirmed processing order; an operation of generating a plurality of images corresponding to the one or more determined prompts; and an operation of displaying the generated plurality of images as an image through a display (160) of the electronic device (101).

[0190] According to one embodiment, the operation of determining the one or more prompts may include the operation of verifying the processing order according to the at least one keyword based on state transition information (332) and an artificial intelligence model stored in the memory of the electronic device (101), and the operation of determining the one or more prompts corresponding to the verified processing order. The state transition information (332) may include an operation relationship diagram for the processing order.

[0191] According to one embodiment, the artificial intelligence model is characterized by being stored in the memory (130) as a program that analyzes input data and generates result data.

[0192] According to one embodiment, the operation of confirming the user's intention may include, when the user input is text input, an operation of performing a correction operation on the text and an operation of confirming the user's intention based on the text on which the correction operation was performed.

[0193] According to one embodiment, the operation of confirming the user's intention may include, when the user input is an audio input containing the user's voice information, an operation of converting the audio input into text based on the voice information and an operation of confirming the user's intention based on the converted text.

[0194] According to one embodiment, environmental information for an electronic device (101) may include hardware-related information of the electronic device and software-related information of the electronic device. Hardware-related information may include specification information for the components of the electronic device. Software-related information may include at least one of version information, form information, frame information, text information, and font information related to a user interface.

[0195] According to one embodiment, the operation of displaying the image may include the operation of displaying the image based on environmental information for the electronic device and the plurality of generated images.

[0196] A method according to one embodiment may further include: determining a first prompt according to the processing order based on the artificial intelligence model; generating a first image corresponding to the first prompt based on the artificial intelligence model; determining a second prompt based on the artificial intelligence model, the processing order, and the first prompt; generating a second image corresponding to the second prompt based on the artificial intelligence model; and displaying the image based on the first image and the second image.

[0197] A method according to one embodiment may further include the operation of obtaining feedback information for the displayed image and the operation of updating information related to the artificial intelligence model and the state transition information based on the obtained feedback information.

[0198] According to one embodiment, a server (108) connected to an electronic device (101) may include a communication circuit, a processor including a processing circuit, and a memory for storing instructions. When the instructions are executed individually or collectively by the processor (120), the server (108) may obtain environment information of the electronic device (101) and input information related to image generation from the electronic device (101), verify the user's intention based on the obtained input information, extract at least one keyword based on the verified user's intention, verify the processing order for image generation based on the extracted at least one keyword and the environment information of the electronic device (101), determine one or more prompts corresponding to the verified processing order, generate a plurality of images corresponding to the determined one or more prompts, and transmit the generated plurality of images to the electronic device (101).

[0199] According to one embodiment, a non-transient computer-readable storage medium (or computer program product) storing one or more programs for performing a method of displaying an image in an electronic device (101) may be described. According to one embodiment, the one or more programs may include instructions that, when executed by a processor (120) of the electronic device (101), perform, in response to user input, an operation of confirming a user's intention corresponding to said user input, an operation of extracting at least one keyword based on said confirmed user intention, an operation of confirming a processing order for image generation based on said extracted at least one keyword and environment information of said electronic device, an operation of determining one or more prompts corresponding to said confirmed processing order, an operation of generating a plurality of images corresponding to said determined one or more prompts, and an operation of displaying said generated plurality of images as an image through a display of said electronic device.

[0200] The electronic device according to the various embodiments disclosed in this document may be of various forms. The electronic device may include, for example, a portable communication device (e.g., a smartphone), a computer device, a portable multimedia device, a portable medical device, a camera, a wearable device, or a consumer electronics device. The electronic device according to the embodiments of this document is not limited to the devices described above.

[0201] The various embodiments of this document and the terms used therein are not intended to limit the technical features described in this document to specific embodiments, and should be understood to include various modifications, equivalents, or substitutions of said 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 said items unless the relevant context clearly indicates otherwise. In this document, phrases such as "A or B," "at least one of A and B," "at least one of A or B," "A, B or C," "at least one of A, B and C," and "at least one of A, B, or C" may each include any one of the items listed together in the corresponding phrase, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used simply to distinguish said components from other said components and do not limit said components in any other aspect (e.g., importance or order). Where any (e.g., 1st) component is referred to as “coupled” or “connected” to another (e.g., 2nd) component, with or without the terms “functionally” or “communicationly,” it means that said any component may be connected to said other component directly (e.g., via a wire), wirelessly, or through a third component.

[0202] The term “module” as used in the 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, for example. A module may be a component formed integrally, or a minimum unit of said component or a part thereof 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).

[0203] Various embodiments of the present document may be implemented as software (e.g., program (140)) comprising one or more instructions stored in a storage medium (e.g., internal memory (136) or external memory (138)) readable by a machine (e.g., electronic device (101)). For example, a processor (e.g., processor (120)) of the machine (e.g., electronic device (101)) may call at least one of the one or more instructions stored in the storage medium and execute it. This enables the machine to be operated 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 that can be executed by an interpreter. The storage medium readable by the machine may be provided in the form of a non-transitory storage medium. Here, 'non-temporary' simply means that the storage medium is a tangible device and does not contain a signal (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently and cases where it is stored temporarily.

[0204] According to one embodiment, the method according to the various embodiments disclosed herein may be provided as included in a computer program product. The computer program product may be traded between a seller and a buyer 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 distributed online (e.g., download or upload) through an application store (e.g., Play Store™) or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily created on a device-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0205] According to various embodiments, each component (e.g., module or program) of the components described above may include a singular or multiple entities, and some of the multiple entities may be separated and placed in other components. According to various embodiments, one or more of the components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Generally or additionally, multiple components (e.g., module or program) may be integrated into a single component. In this case, the integrated component may perform one or more functions of each of the multiple components in the same or similar manner as those performed by the corresponding component among the multiple components prior to integration. According to various embodiments, operations performed by the module, program, or other components may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

Claims

1. In an electronic device (101), Display (160); A processor (120) including a processing circuit; and Includes memory (130) for storing instructions, When the above instructions are executed individually or collectively by the processor (120), the electronic device (101) is made to, In response to user input, the user's intention corresponding to the user input is confirmed, and Based on the above-mentioned confirmed user intent, at least one keyword is extracted, and Based on at least one extracted keyword and the environment information of the electronic device (101), the processing order for image generation is determined, and Determine one or more prompts corresponding to the above-identified processing order, and Generate multiple images corresponding to one or more of the above-determined prompts, and An electronic device that displays the generated plurality of images as images through the display (160).

2. In Paragraph 1, When the above instructions are executed individually or collectively by the processor (120), the electronic device (101) is made to, Based on the state transition information (332) and artificial intelligence model stored in the memory (130), the processing order according to the at least one keyword is determined, and Determining one or more prompts corresponding to the above-identified processing order, and The above state transition information (332) is an electronic device including an operation relationship diagram for the processing sequence.

3. In Paragraph 2, The above artificial intelligence model is an electronic device characterized by being stored in the memory (130) as a program that analyzes input data and generates result data.

4. In Paragraph 1, When the above instructions are executed individually or collectively by the processor (120), the electronic device (101) is made to, If the above user input is text input, a correction operation is performed on the above text, and An electronic device that verifies the user's intention based on the text on which the above correction operation is performed.

5. In Paragraph 1, When the above instructions are executed individually or collectively by the processor (120), the electronic device (101) is made to, If the above user input is an audio input containing the user's voice information, the audio input is converted into text based on the voice information, and An electronic device that verifies the user's intent based on the converted text.

6. In Paragraph 1, An electronic device characterized in that environmental information for the electronic device (101) includes hardware-related information and software-related information of the electronic device, and is stored in the memory (130).

7. In Paragraph 6, The above hardware-related information includes specification information for the components of the electronic device, and the above software-related information includes at least one of version information, form information, frame information, text information, and font information related to the user interface.

8. In Paragraph 6, When the above instructions are executed individually or collectively by the processor (120), the electronic device (101) is made to, An electronic device that displays the image based on environmental information about the electronic device (101) stored in the memory (130) and the generated plurality of images.

9. In Paragraph 1, When the above instructions are executed individually or collectively by the processor (120), the electronic device (101) is made to, A first prompt according to the processing order is determined based on the artificial intelligence model stored in the memory (130), and Based on the above artificial intelligence model, a first image corresponding to the above first prompt is generated, and Determining a second prompt based on the above artificial intelligence model, the above processing order, and the above first prompt, and Based on the above artificial intelligence model, a second image corresponding to the above second prompt is generated, and An electronic device that displays the image based on the first image and the second image.

10. In Paragraph 2, When the above instructions are executed individually or collectively by the processor (120), the electronic device (101) is made to, Obtain feedback information regarding the image displayed through the above display (160), and An electronic device that updates information related to an artificial intelligence model stored in the memory (130) and state transition information based on the acquired feedback information.

11. A method for displaying an image in an electronic device (101), An operation to confirm the user's intention corresponding to the user input in response to the user input; An operation to extract at least one keyword based on the user's intent confirmed above; An operation to determine the processing order for image generation based on at least one extracted keyword and environmental information of the electronic device (101); An operation to determine one or more prompts corresponding to the above-determined processing order; The operation of generating a plurality of images corresponding to one or more of the above-determined prompts; and A method comprising the operation of displaying the generated plurality of images as an image through the display (160) of the electronic device (101).

12. In Paragraph 11, The operation of determining one or more of the above prompts is, An operation to determine the processing order according to the at least one keyword based on the state transition information (332) and the artificial intelligence model stored in the memory of the electronic device (101); and It includes an operation to determine one or more prompts corresponding to the above-identified processing order, and The above state transition information (332) includes an operation relationship diagram for the processing sequence, and A method characterized in that the above artificial intelligence model is a program that analyzes input data and generates result data, and is stored in memory (130).

13. In Paragraph 11, The action of confirming the user's intent is, If the above user input is text input, an action of performing a correction action on the text; and A method comprising: an action of confirming the user's intent based on the text on which the above correction action is performed.

14. In Paragraph 11, The action of confirming the user's intent is, If the above user input is an audio input containing the user's voice information, an operation to convert the audio input into text based on the voice information; and A method comprising: an action of confirming the user's intent based on the converted text.

15. In a server (108) that is connected to an electronic device (101) through communication, Communication circuit; A processor including a processing circuit; and Memory for storing instructions; including, When the above instructions are executed individually or collectively by the processor, the server (108) is made to, Input information related to environmental information and image generation of the electronic device (101) is obtained from the electronic device (101), and Based on the above-mentioned acquired input information, the user's intent is verified, and Based on the above-mentioned confirmed user intent, at least one keyword is extracted, and Based on at least one extracted keyword and the environment information of the electronic device (101), the processing order for image generation is determined, and Determine one or more prompts corresponding to the above-identified processing order, and Generate multiple images corresponding to one or more of the above-determined prompts, and A server that transmits the generated multiple images to the electronic device (101).

Images