KR-20260062766-A - ELECTRONIC DEVICE, METHOD, AND RECORDING MEDIUM FOR SUPPORTING CONTENTS CREATION BASED ON PREVIEW IMAGE

KR20260062766AKR 20260062766 AKR20260062766 AKR 20260062766AKR-20260062766-A

Abstract

Embodiments of the present disclosure provide an electronic device, a method, and a recording medium that support the creation (or production) of content based on a preview image. The electronic device may execute an application that operates a camera and acquire a preview image transmitted from the camera. The electronic device may display the preview image in a first defined display area of the display. The electronic device may receive inputs related to editing the preview image. The inputs may include one or more sequential inputs that generate information regarding content to be created based on the preview image. In response to the inputs, the electronic device may generate a prompt containing information of the preview image and the inputs to create content for the preview image. The electronic device may provide the prompts to a generative artificial intelligence (AI) on the device and/or on a server. The electronic device may acquire content in relation to the prompts and, while displaying the preview image, display one or more contents acquired in response to the one or more sequential inputs in a second defined display area of the display. Various embodiments are possible.

Inventors

유정곤
김문수
배창섭
유형진
이성민
정주영
하대성

Assignees

삼성전자주식회사

Dates

Publication Date: 20260507
Application Date: 20241213
Priority Date: 20241029

Claims (20)

In the electronic device (101, 201, 400), Display(160, 440); Camera(180, 450); At least one processor (120, 230, 410) including processing circuitry; and It includes memory (130, 240, 420) for storing instructions, When the above instructions are executed individually and/or collectively by the at least one processor, the electronic device, Run the application that operates the above camera, and Acquire a preview image transmitted from the above camera, and The above preview image is displayed in a first predetermined display area of the above display, and Receives input related to editing the above preview image, and the input includes one or more sequential inputs that generate information regarding content to be generated based on the above preview image. In response to the above input, a prompt including information of the preview image and the input is generated to generate content for the above preview image, and Provide the above prompt to on-device and/or server generative AI, and In relation to the above prompt, obtain content, and An electronic device that displays one or more contents obtained in response to one or more sequential inputs in a second defined display area of the display while displaying the above preview image.
In paragraph 1, when the instructions are executed individually and/or collectively by the at least one processor, the electronic device, While displaying the above preview image, in response to a first input related to editing the above preview image, a first content corresponding to the first input is generated based on the above preview image and displayed in the second defined area. An electronic device that, while displaying the above preview image, in response to a first input related to editing the above preview image, generates a second content corresponding to the second input based on the above preview image and displays it in the second designated area.
In paragraph 1, The above input is an electronic device that generates text input, drawing input, voice input, and/or image input while displaying the above preview image.
In paragraph 1, The above input is an electronic device that includes the function of a command to instruct the creation of the content based on the information of the above preview image and the above input.
In paragraph 1, when the instructions are executed individually and/or collectively by the at least one processor, the electronic device, The display area of the above display is divided into a first display area that displays a preview of the above preview image and a second display area that displays the above content, and A preview image is placed and displayed in the first display area above, and An electronic device that displays content by placing it in the second display area.
In paragraph 1, when the instructions are executed individually and/or collectively by the at least one processor, the electronic device, While displaying the above preview image, detect changes in the above preview image, and Based on the change in the above preview image, the content information of the previously generated first content is identified, and Acquire a second content generated based on a prompt that takes the above content information and preview image as input, and An electronic device that updates and displays the first content of a second display area with the second content.
In paragraph 6, when the instructions are executed individually and/or collectively by the at least one processor, the electronic device, Acquire regenerated content corresponding to each of multiple previously generated contents, and An electronic device that updates and displays the regenerated content in the second display area.
In paragraph 1, when the instructions are executed individually and/or collectively by the at least one processor, the electronic device, An electronic device that stores content information of the above content.
In paragraph 1, when the instructions are executed individually and/or collectively by the at least one processor, the electronic device, While displaying the above preview image, a first input regarding an image search request is received, and In response to the first input above, an image is searched and displayed in the third display area of the display, and Receiving a second input for selecting the above image, In response to the above second input, content generated based on a prompt to generate content for a preview image based on an image is obtained, and An electronic device that displays the above content in a second display area of a display.
In paragraph 9, when the instructions are executed individually and/or collectively by the at least one processor, the electronic device, The display area of the above display is divided into a first display area for displaying a preview of the above preview image, a second display area (702) for displaying the above content, and a third display area for displaying the searched image. A preview image is placed and displayed in the first display area above, and Content is placed and displayed in the second display area above, and An electronic device that displays an image list of images searched in the third display area.
In a method of operating an electronic device (101, 201, 400), The operation of executing an application that operates the camera (180, 450) of the electronic device; The operation of acquiring a preview image transmitted from the above camera; The operation of displaying the above preview image in a first predetermined display area of the display (160, 440) of the electronic device; An operation of receiving input related to editing the above-mentioned preview image, wherein the input includes one or more sequential inputs that generate information regarding content to be generated based on the above-mentioned preview image; An operation to generate a prompt containing information of the preview image and the input in response to the above input to generate content for the above preview image; The operation of providing the above prompt to generative AI on-device and/or a server; An action of acquiring content in relation to the above prompt; and A method comprising the operation of displaying one or more contents obtained in response to one or more sequential inputs in a second defined display area of the display while displaying the above preview image.
In Clause 11, the operation of acquiring the above content is, While displaying the above preview image, in response to a first input related to editing the above preview image, an operation of generating first content corresponding to the first input based on the above preview image and displaying it in the second defined area, A method comprising, while displaying the preview image, generating second content corresponding to the second input based on the preview image and displaying it in the second defined area in response to a first input related to editing the preview image.
In Paragraph 11, The above input is generated based on text input, drawing input, voice input, and/or image input while displaying the above preview image, and A method in which the above input includes the function of a command that instructs to generate the content based on the information of the above preview image and the above input.
In paragraph 11, the operation of displaying the above content is, The operation of dividing the display area of the above display into a first display area that displays a preview of the above preview image and a second display area that displays the above content, The operation of placing and displaying a preview image in the first display area, A method comprising the operation of placing and displaying content in the second display area.
In Paragraph 11, An operation to detect changes in the preview image while displaying the preview image, An operation to identify content information of a previously generated first content based on changes in the above-mentioned preview image, The operation of obtaining a second content generated based on a prompt that takes the above content information and preview image as input, A method comprising the operation of updating and displaying the first content of the second display area with the second content.
In paragraph 15, The operation of acquiring regenerated content corresponding to each of multiple previously generated contents, A method including the operation of updating and displaying the regenerated content in the second display area.
In Paragraph 11, A method comprising the operation of storing content information of the above content.
In Paragraph 11, The operation of receiving a first input regarding an image search request while displaying the above preview image, The operation of searching for an image in response to the first input and displaying it in the third display area of the display, The operation of receiving a second input selecting the above image, The operation of obtaining content generated based on a prompt that generates content for a preview image based on an image in response to the above second input, A method comprising the operation of displaying the above content in a second display area of a display.
In Paragraph 18, The operation of dividing the display area of the above display into a first display area for displaying a preview of the above preview image, a second display area (702) for displaying the above content, and a third display area for displaying the searched image, The operation of placing and displaying a preview image in the first display area, The operation of placing and displaying content in the second display area above, A method comprising the operation of displaying an image list of images searched in the third display area.
In a non-transitory computer-readable medium that stores instructions that cause the processor to perform operations when executed by the processor of an electronic device, When the above instructions are executed by the processor, the electronic device, The operation of executing an application that operates the camera of the above electronic device; The operation of acquiring a preview image transmitted from the above camera; The operation of displaying the above preview image in a first predetermined display area of the display (160, 440) of the electronic device; An operation of receiving input related to editing the above-mentioned preview image, wherein the input includes one or more sequential inputs that generate information regarding content to be generated based on the above-mentioned preview image; An operation to generate a prompt containing information of the preview image and the input in response to the above input to generate content for the above preview image; The operation of providing the above prompt to generative AI on-device and/or a server; An action of acquiring content in relation to the above prompt; and A recording medium that performs the operation of displaying one or more contents obtained in response to one or more sequential inputs in a second predetermined display area of the display while displaying the above preview image.

Description

ELECTRONIC DEVICE, METHOD, AND RECORDING MEDIUM FOR SUPPORTING CONTENTS CREATION BASED ON PREVIEW IMAGE Embodiments of the present disclosure provide an electronic device, a method, and a recording medium that support the creation (or production) of content based on a preview image. With the development of digital technology, various types of electronic devices such as smartphones, tablet PCs (personal computers), digital cameras, laptop computers, and/or wearable devices are widely used. To support and enhance the functionality of these electronic devices, the hardware and/or software parts of the devices are continuously being developed. For example, portable electronic devices, such as smartphones (hereinafter referred to as “electronic devices”), have become capable of incorporating various functions. Electronic devices include a touchscreen-based display to allow users easy access to various functions and can provide screens of various applications through the display. Electronic devices include a camera to support video recording and can capture video acquired through the camera and provide it to the user. Electronic devices can display the video acquired from the camera through the display. Recently, with the rapid advancement of big data and deep learning technologies, artificial intelligence (AI) has been implemented in electronic devices and is also being applied to intelligent personalized services that analyze specific data and integrate and utilize information from various fields tailored to the user. For example, users can control electronic devices through voice conversation and perform searches, queries, and responses regarding specific information using a knowledge base powered by deep learning. Furthermore, with the evolution of AI technology, generative AI is being implemented. Generative AI refers to AI technology that creates new, similar content using existing content such as text, audio, and/or images. For instance, generative AI can represent AI technology capable of generating content (e.g., text, audio, images, and/or videos) corresponding to a given input. Meanwhile, to generate content in generative AI, a prompt (or instruction) is required to direct the AI to create content, and this prompt can be generated based on input provided by the user. For example, to obtain the content desired by the user through generative AI, it is necessary to configure an optimal prompt. 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. In one embodiment of the present disclosure, an electronic device that supports content creation (or production) using a preview image acquired through a camera, a method of operation thereof, and a recording medium are provided. In one embodiment of the present disclosure, an electronic device that supports the creation of content based on generative artificial intelligence (generative AI) based on a real-time preview image, a method of operation thereof, and a recording medium are provided. In one embodiment of the present disclosure, an electronic device, a method of operation, and a recording medium are provided, which generates new content (e.g., a new preview image or an AI preview image) by generating various virtual objects on a preview image acquired from a camera of an electronic device using generative artificial intelligence, and provides the preview image and the new content generated based on the preview image to a display. In one embodiment of the present disclosure, an electronic device, a method of operation, and a recording medium are provided, which generates a generative artificial intelligence-based object corresponding to user input in a real-time preview image, combines the generated object with the preview image to provide at least one new preview image simultaneously with the real-time preview image in real time. In one embodiment of the present disclosure, an electronic device, a method of operation, and a recording medium are provided that change (or update or reflect) a generative artificial intelligence-based preview image in real time in response to a change in a preview image acquired from a camera. The technical problems intended to be solved in this document are not limited to those mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art to which this disclosure pertains from the description below. According to an embodiment of the present disclosure, an electronic device (e.g., a smartphone, a foldable electronic device, and/or a digital camera) that supports the generation of content based on generative artificial intelligence (e.g., an AI preview image) is provided. The electronic device may include a display, a camera, a memory that stores one or more computer prog