Search

KR-102961479-B1 - ARTIFICIAL INTELLIGENCE RECOMMENDATION BASED WEBTOON CONTROL DEVICE AND METHOD

KR102961479B1KR 102961479 B1KR102961479 B1KR 102961479B1KR-102961479-B1

Abstract

The present invention relates to an artificial intelligence recommendation-based webtoon control device and method, wherein the device comprises: an image recommendation unit that receives a story text for webtoon generation from a user terminal and recommends candidate webtoon images in which each object is implemented as an independent layer for each scene of the story text; an image generation unit that recommends at least one candidate object image corresponding to the object when a specific layer of the candidate webtoon image is selected on the user terminal and completes the object image according to the user selection to update the specific layer; and a webtoon generation unit that receives a user input controlling the layers of the objects from the user terminal and controls the relativity between the objects according to the user input to generate a final webtoon image corresponding to a specific scene of the story text.

Inventors

  • 박준석
  • 오하령

Assignees

  • 국민대학교산학협력단

Dates

Publication Date
20260507
Application Date
20230425

Claims (12)

  1. An image recommendation unit that receives story text for webtoon generation from a user terminal, compresses the story text into story sentences, generates an overall story image corresponding to the story sentences through a webtoon model, divides the story text into scenes based on changes in the background or characters of the overall story image during the story progression of the story text, and recommends candidate webtoon images in which each object is implemented as an independent layer for each scene; An image generation unit that, when a specific layer of the candidate webtoon image is selected on the user terminal, recommends at least one candidate object image corresponding to the object and completes the object image according to the user selection to update the specific layer; and A webtoon generation unit that receives user input controlling layers of the objects from the user terminal and controls the relativity between the objects according to the user input to generate a final webtoon image corresponding to a specific scene of the story text, and receives text input regarding the objects through a tool interface for webtoon generation and controls the relativity between the objects using a relativity control model constructed to control the relative composition of each layer constituting the scene according to the text input; The above webtoon model An AI recommendation-based webtoon control device characterized by being constructed with a first webtoon model that generates an image of a scene corresponding to a conversation between characters by learning correlation information between images and text included in training data, which is represented as a set of images and text extracted from each of multiple scenes included in a webtoon, and a second webtoon model that generates a conversation between characters suitable for the scene represented as an image.
  2. In paragraph 1, the image recommendation unit An AI recommendation-based webtoon control device characterized by receiving a scenario including scenes, characters, and dialogue from the above-mentioned user terminal as the story text.
  3. In paragraph 2, the image recommendation unit An AI recommendation-based webtoon control device characterized by converting the story text into the scenario when the story text is not the scenario.
  4. In paragraph 1, the image recommendation unit An AI recommendation-based webtoon control device characterized by generating the entire story image including at least one of a background, a character, and a message based on the above story sentence.
  5. In paragraph 4, the image recommendation unit An AI recommendation-based webtoon control device characterized by dividing the scene of the story text based on the point of occurrence of the change when a change in either the background or the character of the entire story image exceeds a preset standard.
  6. In claim 1, the image generating unit An AI recommendation-based webtoon control device characterized by recommending images whose similarity exceeds a preset standard based on the image of the object as candidate object images.
  7. In claim 1, the image generating unit An AI recommendation-based webtoon control device characterized by processing direct modification of the corresponding object according to user input on the specific layer through the tool interface for generating the webtoon.
  8. delete
  9. In paragraph 1, the webtoon generating unit An AI recommendation-based webtoon control device characterized by generating a scene story image of a specific scene by inputting a story text regarding the specific scene into a pre-established webtoon model when the result of relativity control between the above objects exceeds a preset threshold.
  10. In a webtoon control method performed in a webtoon control device, A step of receiving a story text for webtoon generation from a user terminal through an image recommendation unit, compressing the story text into a story sentence, generating an overall story image corresponding to the story sentence through a webtoon model, dividing the story text by scene based on a change point of the background or character of the overall story image during the story progression of the story text, and recommending candidate webtoon images in which each object is implemented as an independent layer for each scene; A step of, through an image generation unit, recommending at least one candidate object image corresponding to the object when a specific layer of the candidate webtoon image is selected on the user terminal, and completing the object image according to the user selection to update the specific layer; and The method includes the step of receiving user input controlling the layers of the objects from the user terminal through the webtoon generation unit, and controlling the relativity between the objects according to the user input to generate a final webtoon image corresponding to a specific scene of the story text. The above webtoon model It is constructed with a first webtoon model that generates images of scenes corresponding to dialogue between characters by learning correlation information between images and text included in training data, which is represented as a set of images and text extracted from each of multiple scenes included in the webtoon, and a second webtoon model that generates dialogue between characters suitable for scenes represented as images. The step of generating the final webtoon image above A method for controlling an AI recommendation-based webtoon, characterized by including the step of receiving text input regarding the objects through a tool interface for generating the webtoon and controlling the relativity between the objects using a relativity control model constructed to control the relative composition of each layer constituting the scene according to the text input.
  11. In item 10, the step of updating the specific layer above An AI recommendation-based webtoon control method characterized by including a step of processing direct modification of the corresponding object according to user input on the specific layer through the tool interface for generating the webtoon.
  12. delete

Description

Artificial Intelligence Recommendation-Based Webtoon Control Device and Method The present invention relates to a webtoon generation technology, and more specifically, to an AI recommendation-based webtoon control device and method that recommends webtoon images composed of independent layers for each object based on a user's scenario through artificial intelligence, and controls the relativity between objects by adjusting the layers through user control. Webtoon is a compound word of "web" and "cartoon" (comic), and it can be used as a general term for web comic platforms. Webtoons developed based on the internet, and their format began to take shape in the early 21st century; currently, they are serialized on the web through various platforms. The webtoon production process can be broadly divided into story work and artwork work. Specifically, the story work can proceed in the order of synopsis, scenario, and storyboard. The synopsis process involves briefly summarizing the overall structure and plan of the story to generate multiple scenes; the scenario process involves adding dialogue and stage directions for each scene; and the storyboard process involves creating a storyboard based on the scenario to serve as the foundation for the webtoon. Furthermore, the drawing process can proceed in the order of sketching, inking, and coloring. The sketching process may correspond to creating sketches based on the storyboard; the inking process may correspond to refining the sketch more precisely through pen strokes; and the coloring process may correspond to completing a three-dimensional drawing by adding rich colors and shading to the finished underdrawing. Much of the webtoon creation process can be carried out manually, and various webtoon development tools are being developed to facilitate efficient work. However, despite these various tools, creating a webtoon can still require a significant amount of time and effort. FIG. 1 is a diagram illustrating a webtoon generation system according to the present invention. Figure 2 is a diagram illustrating the system configuration of the webtoon control device of Figure 1. Figure 3 is a diagram illustrating the functional configuration of the webtoon control device of Figure 1. FIG. 4 is a flowchart illustrating an artificial intelligence recommendation-based webtoon control method according to the present invention. FIGS. 5 and 6 are drawings illustrating embodiments of the model building process according to the present invention. FIG. 7 is a diagram illustrating the service flow of a webtoon control device according to the present invention. FIG. 8 is a drawing illustrating an embodiment of a service model regarding a webtoon control device according to the present invention. FIG. 9 is a drawing illustrating a scene-by-scene webtoon image composed of independent layers for each object according to the present invention. The description of the present invention is merely an example for structural or functional explanation, and therefore the scope of the present invention should not be interpreted as being limited by the examples described in the text. That is, since the examples are subject to various modifications and may take various forms, the scope of the present invention should be understood to include equivalents capable of realizing the technical concept. Furthermore, the objectives or effects presented in the present invention do not imply that a specific example must include all of them or only such effects; therefore, the scope of the present invention should not be understood as being limited by them. Meanwhile, the meaning of the terms described in this application should be understood as follows. Terms such as "first," "second," etc., are intended to distinguish one component from another, and the scope of rights shall not be limited by these terms. For example, the first component may be named the second component, and similarly, the second component may be named the first component. When it is stated that one component is "connected" to another component, it should be understood that it may be directly connected to that other component, or that there may be other components in between. Conversely, when it is stated that one component is "directly connected" to another component, it should be understood that there are no other components in between. Meanwhile, other expressions describing the relationships between components, such as "between" and "exactly between," or "adjacent to" and "directly adjacent to," should be interpreted in the same way. A singular expression should be understood to include a plural expression unless the context clearly indicates otherwise, and terms such as "include" or "have" are intended to specify the existence of the implemented features, numbers, steps, actions, components, parts, or combinations thereof, and should be understood not to preclude the existence or addition of one or more other features, numbers, step