| 摘要 |
Potential content item slots (e.g., ad slots) in a media (e.g., video, audio, or both) are identified, and each content item slot is associated with a weight that indicates a degree of potential disruption to a flow of the media when a content item (e.g., ad) is inserted in the content item slot. |
| 主权项 |
1. A computer-implemented method comprising:
identifying, by one or more video processing servers, a plurality of video shot boundaries in a first media, said video shot boundaries representing a plurality of content item slots; determining, for each of the plurality of content item slots, by the one or more video processing servers, a degree of potential disruption of flow of the first media that would be created by the insertion of a content item in each of the plurality of content item slots, the potential disruption of flow of the first media is based on one or more of:
A similarity of preceding or succeeding portions of the first media surrounding each of the plurality of content item slots;Cut activity in the first media preceding or succeeding each of the plurality of content item slots;Cut to black activity in the first media preceding or succeeding each of the plurality of content items, audio silence in the first media before or after each of the plurality of content items slots;Or audio continuity across each of the plurality of content item slots in the first media; assigning, by the one or more video processing servers, weights based on said determined degree of potential disruption to each of the plurality of content item slots; determining, by the one or more video processing servers, a classification type for each of a plurality of content items as being a text content item, an image content item, or a video content item; assigning, by the one or more video processing servers, a confidence score to each of the plurality of content items, the confidence score is based on an amount of disruption to the video flow caused by the classification type; selecting, by the one or more video processing servers, at least one content item of the plurality of content items and at least one content item slot of the plurality of content item slots in the media based on an evaluation of the weights assigned to each of the plurality of content items slots, the classification type of each of the plurality of content items and the confidence score assigned to each of plurality of content item; and Generating, by the one or more video processing servers, a second media by inserting the selected at least one content item into the selected at least one content item slot of the first media. |
