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

摘要

In the apparatus for generating a highlight image using chat data and audio data generated during video provision, the data extracted from the image is divided into a first time section and a second time section longer than the first time section, A separating unit for generating two-segmented data, an extracting unit for extracting a first feature vector from the first segmented data of the separating unit and for extracting a second feature vector from the second segmental data of the separating unit, A learning unit that learns a feature vector through a recurrent neural network (RNN) and generates 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 An apparatus for generating a highlight image using chat data and audio data including a prediction unit that generates a score vector for a probability that can be predicted as a highlight from and a decision unit that generates a final highlight using the score vector generated by the prediction unit. Is initiating.