APARATUS AND METHOD FOR GENERATING A HIGHLIGHT VIDEO USING CHAT DATA AND AUDIO DATA

摘要

In the highlight image generation apparatus using chat data and audio data generated during the provision of an image, the data extracted from the image is divided into a first time period and a second time period longer than the first time period, and the first segment data and the first Separator for generating two-segmented data, extracting unit for extracting a first feature vector from the first segmented data of the separator, extracting unit for extracting a second feature vector from the second segmented data for the separator, a first feature vector and a second for the extractor A learning unit learning a feature vector through a recurrent neural network (RNN) and generating a first result vector and a second result vector using the learned result, the first result vector and the second result vector of the learning unit A highlight image generating apparatus using chat data and audio data, including a prediction unit generating a score vector for a probability that can be predicted as a highlight from and a determination unit generating a final highlight using the score vector generated by the prediction unit Is disclosed.