| 摘要 |
A system for detecting streaming of advertisements that occur while streaming a media program is provided. The system includes a broadcast content receiving module, a feature extracting module, an advertisement detecting module, a weight computing module, and a neighborhood context identifying module. The broadcast content receiving module receives a broadcast content from a content source. The feature extracting module extracts video features, audio features, and metadata features associated with broadcast chunks of the broadcast content for time segments. The advertisement detecting module analyzes the video features, the audio features, and the metadata features for the time segments. The weight computing module computes final weight for validating start and end of first advertisement slot based on the weight. The neighborhood context identifying module validates a start time of a first advertisement slot based on a content type of a first broadcast chunk and a second broadcast chunk. |
| 主权项 |
1. A system for detecting streaming of advertisements that occur while streaming a media program, said system comprising:
a memory unit that stores a database and a set of modules; and a processor that executes said set of modules, wherein said set of modules comprise: (a) a broadcast content receiving module, executed by said processor, configured to receive a broadcast content from a content source, wherein said broadcast content comprises a media program that is stitched with advertisements at a plurality of predefined advertisement slots; (b) a feature extracting module, executed by said processor, that extracts video features, audio features, and metadata features associated with a plurality of broadcast chunks of said broadcast content for a plurality of time segments; (c) an advertisement detecting module, executed by said processor, that
(i) analyzes said video features, said audio features, and said metadata features for said plurality of time segments;(ii) identifies a start of a first advertisement slot corresponds to a first time segment at which a first transition occurs from said media program to said first advertisement slot by analyzing (a) a change in a video feature of said video features, (b) a change in an audio feature of said audio features, or (c) presence of a metadata feature of said metadata features; and(iii) identifies an end of said first advertisement slot corresponds to a second time segment at which a second transition occurs back from said first advertisement slot to said media program by analyzing (a) a change in said video feature, (b) a change in an audio feature, or (c) said metadata feature, and (d) a weight computing module, executed by said processor, that
(i) assigns a weight for at least one of said video feature, said audio feature, and said metadata feature based on predefined rules; and(ii) computes a final weight for validating said start and said end of said first advertisement slot based on said weight, and (e) a neighborhood context identifying module, executed by said processor, that
(i) obtains a first broadcast chunk that precedes said first time segment, and a second broadcast chunk that follows said first time segment;(ii) performs an analysis on features selected from a group comprising of video features, audio features, and metadata features of said first broadcast chunk and said second broadcast chunk;(iii) identifies content type of said first broadcast chunk and said second broadcast chunk based on said analysis; and(iv) validates said start time of said first advertisement slot based on said content type of said first broadcast chunk and said second broadcast chunk. |
