• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.6
• /
• pp.15-20
• /
• 2023

This paper is a study on the development of an artificial intelligence (AI) system algorithm that recommends indirect advertising products suitable for character web dramas. The goal of this study is to increase viewers' content immersion and help them understand the story of the drama more deeply by recommending indirect advertising products that are suitable for writing lines for web dramas. In this study, we analyze dialogue and plot using the natural language processing model GPT, and develop two types of indirect advertising product recommendation systems, including prop type and background type, based on the analysis results. Through this, products that fit the story of the web drama are appropriately placed, allowing indirect advertisements to be exposed naturally, thereby increasing viewer immersion and enhancing the effectiveness of product promotion. There are limitations of artificial intelligence models, such as the difficulty in fully understanding hidden meanings or cultural nuances, and the difficulty in securing sufficient data for learning. However, this study will provide new insights into how AI can contribute to the production of creative works, and will be an important stepping stone to expand the possibilities of using natural language processing models in the creative industry.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.4
• /
• pp.17-22
• /
• 2023

This study analyzed the genres of popular character web dramas and studied the development of story recommendations through the language model GPT. As a result of the study, it was confirmed that similar cliches are repeated in web dramas. In this study, a common story structure (cliché) was analyzed and a typical story structure was standardized and presented so that even unskilled video producers can easily produce character web dramas. For analysis, clichés of web dramas in the school romance genre, which is the most popular genre among teenagers, were listed in order of success. In addition, this study studied the story recommendation mechanism for users by learning the clichés that were analyzed and cataloged in GPT. Through this study, it is expected to accelerate the production of various contents as well as popular popularity through the acceptance of various databases from the standpoint of database consumption theory of web contents.

• The Journal of the Korea Contents Association
• /
• v.18 no.6
• /
• pp.399-413
• /
• 2018

The purpose of this study is to find out the significance and functions of the voice-over narration in the storytelling of the web-drama OH Ku-sil. As a result, the first person narration has enhanced the intimacy with a viewer via subjective statements and produced the two time zone effect that the image and the voice-over stood on different tenses. On the other hand, the third person narration has expanded its functions beyond those of the cinema and TV drama. First, the third person narration in OH Ku-sil has performed the essential role presenting significant information for the viewer's understanding story. Second, the objective/authoritative statements of the third person narration have changed to the subjective/suggestive statements. Third, the third person narrator has expanded his/her role from a narrator to a virtual character by means of the comic statements. It seems to be the existing narration's effective response to the web-drama's medium characteristics seeking efficient storytelling under the tight time restriction. Delivering speedily the story information and amusement, this evolutionary voice-over narration is changing its status from the staying off subject to the condition of the new medium called web-drama.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.5
• /
• pp.591-596
• /
• 2023

This study developed a program that can produce videos easily and conveniently, focusing on teenage media producers. Through user research, we identified the needs and problems of teenage producers, and implemented a character customization function desired by users and an emotion and action recommendation system using GPT. In the rendering process, the final image was created by combining audio and video using OpenCV and FFmpeg. Teenage users who do not have expertise in video production can customize web drama characters through a simple interface and receive recommendations for emotions and actions with the help of GPT. The program of this study is expected to be a tool that can help teenage users who do not have expertise in editing and directing to produce high-quality videos, lower the entry barrier to video production, and contribute to the development of the one-person media industry. do. In the future, we plan to provide a video production environment considering mobile or vertical resolution versions.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.3
• /
• pp.107-114
• /
• 2008

In this paper, a management system of characters and roles for storytelling that is used for drama is proposed with ontology which is a key factor of semantic web. While there are few tools domestically, usage for storytelling with authoring tools is increasing outside. Especially, a study for the management system of characters. roles and casting is not performed. This study proposes a system to control a series of works related with them. It contributes to poor domestic environment of writing, which makes it systematically. Also, it applies semantic web technology by defining ontology.