A Proposed Recommendation System to Exhibit Product Advertising at Proper Time Stamps of Video

الملخص

An advertisement is a notice or announcement in a public medium promoting a product. Advertising plays significant role in the introduction of a new product in the market. It stimulates the people to purchase the product and provides an opportunity for e-commerce companies to recommend their products in videos. In this research, we propose a video advertising system to exhibit appropriate video product ads to particular users at proper time stamps. This takes into account video content (semantics or relation between video and products), and viewing behavior (user and video). In the proposed framework, the first stage will be analyzed video structure into its primary components. Next stage will be associations between users and videos and videos and products. Finally, the recommendation system is proposed to integrate key frame-product association and the important shot of original video to recommend appropriate video of product advertisement(ads) to user. The results of determining the video category by employing the Yolo deep learning model (Yolov5s) in precision. Thus, the proposed method is more accurate in getting the video content. The results of the recommendation and video advertising algorithm demonstrate that all the recommended videos are accurately classified and suggested to the actual type of viewing videos in the GWO algorithm.
Corresponding