KR-20260063246-A - METHOD FOR EDITING VIDEO CONTENTS, DEVICE FOR EDITING VIDEO CONTENTS USING TEXT PROMPT AND PROGRAM STORED IN A RECORDING MEDIUM

KR20260063246AKR 20260063246 AKR20260063246 AKR 20260063246AKR-20260063246-A

Abstract

According to one embodiment of the present invention, a video content editing method, a video content editing device, and a program may be provided. A video content editing method may include: a prompt receiving step for receiving a text prompt from a user related to editing video content; a video splitting step for dividing video content to be edited into a plurality of sub-videos; a video extraction step for extracting one or more sub-videos that match the user's text prompt among the plurality of sub-videos; and a video editing step for generating edited video data from the extracted one or more sub-videos.

Inventors

황재민
권정식

Assignees

주식회사 스쿼드엑스

Dates

Publication Date: 20260507
Application Date: 20241030

Claims (10)

A video content editing method performed by a video content editing device comprising: one or more processors; and one or more memories storing instructions that cause the one or more processors to perform operations when executed by the one or more processors, wherein A prompt receiving step for receiving a user's text prompt related to editing video content; A video splitting step for dividing video content to be edited into multiple sub-videos; Image extraction step for extracting one or more sub-images that match a user's text prompt among a plurality of sub-images; and Video editing step that generates edited video data from one or more extracted sub-videos A method for editing video content including
In paragraph 1, The above image extraction step is, A score calculation step for calculating a matching score representing the degree of matching between a user's text prompt and a sub-video for a plurality of sub-videos based on video content to be edited and a user's text prompt; and A video selection step that calculates an editing priority order for multiple sub-videos of video content to be edited based on a matching score calculated for multiple sub-videos, and selects one or more sub-videos to generate edited video data based on the calculated editing priority. A method for editing video content including
In paragraph 2, The above score calculation step is a video content editing method comprising extracting text data from video content to be edited and calculating a matching score for a plurality of sub-videos based on the extracted text data and a user's text prompt.
In paragraph 1, The above image segmentation step includes detecting one or more scene change points of the image content and segmenting the image based on the detected scene change points. A video content editing method in which the point of scene change is detected based on changes in video data and audio data.
In paragraph 1, Editing tool provision step that provides an editing tool enabling the user to perform additional editing on the edited video data. A method for editing video content that further includes
In paragraph 5, The above editing tool is a method for editing video content that includes a ratio changing tool for changing the video ratio to a ratio selected by the user.
In paragraph 5, The above editing tool is a method for editing video content that includes a blank addition tool for adding video blanks between the start, end, or scenes of the edited video data.
In paragraph 5, A method for editing video content, comprising a data addition tool that adds audio data, subtitle data, and text data for TTS to the edited video data.
A video content editing device comprising: one or more processors; and one or more memories storing instructions that cause the one or more processors to perform operations when executed by the one or more processors, One or more of the above processors, A prompt receiving step for receiving a user's text prompt related to editing video content; A video splitting step for dividing video content to be edited into multiple sub-videos; Image extraction step for extracting one or more sub-images that match a user's text prompt among a plurality of sub-images; and Video editing step that generates edited video data using one or more extracted sub-videos A video content editing device configured to perform steps including
A computer program stored on a computer-readable recording medium capable of being executed on a computer comprising: one or more processors; and one or more memories in which instructions are stored that cause the one or more processors to perform operations when executed by the one or more processors, wherein One or more of the above processors, A prompt receiving step for receiving a user's text prompt related to editing video content; A video splitting step for dividing video content to be edited into multiple sub-videos; Image extraction step for extracting one or more sub-images that match a user's text prompt among a plurality of sub-images; and Video editing step that generates edited video data using one or more extracted sub-videos A computer program stored on a computer-readable recording medium configured to perform steps including...

Description

Method for editing video content using a text prompt, device for editing video content, and program stored in a recording medium The present invention relates to video content editing technology, and more specifically, to a method for editing video content using a text prompt, a video content editing device, and a program stored on a recording medium. In the modern digital content market, a large amount of video content is provided through various platforms, and the demand for short, concise short-form content is surging, particularly in mobile environments. Accordingly, there is a demand for technology that effectively summarizes long-form content to provide key information within a short period of time. Conventional techniques for summarizing long-form content have primarily utilized text summarization techniques or manual editing methods. These conventional techniques are as follows. Existing sentence summarization systems generate summaries by extracting key keywords or sentences from long text content using Natural Language Processing (NLP) technology, making them suitable for text-based content. However, video content has complex characteristics that require consideration of visual elements of scenes and audio data, so simply applying a text summarization system has limitations. Conventional video editing software supports the task of manually selecting and summarizing important parts of a video by allowing users to directly select and edit specific scenes. However, this manual editing method is time-consuming and labor-intensive, and involves the inefficiency of requiring users to review the video individually to select key scenes. Furthermore, there is a risk that important information may be omitted or content edited inappropriately based on the editor's subjective judgment. Recently, services have been provided that allow users to easily create short video content using designated templates. In these services, users can produce short-form content by inserting images into the template or adding simple text. However, this method does not provide features to analyze existing content or automatically extract key scenes, and it has limitations as it relies on templates of a fixed format. Consequently, it is difficult to obtain suitable editing results depending on the characteristics of individual content, and the creation of user-customized content is limited. FIG. 1 is a diagram showing the connection relationship between a video content editing device and other components according to one embodiment of the present invention. FIG. 2 is a block diagram illustrating an example of a computer device according to one embodiment of the present invention. FIG. 3 is a block diagram showing the configuration of a video content editing device according to one embodiment of the present invention. FIG. 4 is a flowchart illustrating an image extraction method performed in an image extraction unit according to an embodiment of the present invention. FIG. 5 is a conceptual diagram illustrating a method for determining the editing priority of sub-images divided according to an embodiment of the present invention. FIG. 6 is a diagram illustrating the UI of a service screen performed by a video content editing device according to an embodiment of the present invention. FIG. 7 is a drawing showing an example of a UI screen of an editing tool provided by a video content editing device according to an embodiment of the present invention. FIG. 8 is a drawing showing another example of a UI screen of an editing tool provided by a video content editing device according to one embodiment of the present invention. FIG. 9 is a drawing showing another example of a UI screen of an editing tool provided by a video content editing device according to one embodiment of the present invention. FIG. 10 is a drawing showing another example of a UI screen of an editing tool provided by a video content editing device according to one embodiment of the present invention. FIG. 11 is a flowchart of a video content editing method performed by a video content editing device according to an embodiment of the present invention. Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the attached drawings. The embodiments of the present invention are provided to more fully explain the invention to those skilled in the art, and the following embodiments may be modified in various different forms, and the scope of the invention is not limited to the following embodiments. Rather, these embodiments are provided to make the disclosure more faithful and complete and to fully convey the spirit of the invention to those skilled in the art. The various embodiments described herein may be implemented, for example, in a recording medium readable by a computer or similar device using software, hardware, or a combination thereof. According to hardware implementation, the embodiments described herein may be i