Apparatus and method of program classification using observed cues in the transcript information
First Claim
Patent Images
1. A method for classification of a program comprising the steps of:
- receiving an audio/video signal corresponding to the program;
determining transcript information associated with the program using the audio/video signal;
identifying at least one cue in the transcript information and an associated time of occurrence, each of the cues being associated with a type of program;
correlating the at least one cue identified in the transcript information to the type of program;
comparing the time of occurrence of two cues selected from the at least one identified cue and determining a proximity of occurrence of the two selected cues,wherein if the proximity of occurrence is greater than a predetermined amount, the two selected cues are ignored in connection with determining the program classification; and
wherein if the proximity of occurrence is not greater than the predetermined amount, the two selected cues are utilized in connection with determining the program classification; and
classifying the program based on the proximity of occurrence of the two selected cues.
2 Assignments
0 Petitions
Accused Products
Abstract
A method for classification of a program includes receiving transcript information associated with the program, identifying at least one cue of a plurality of cues in the transcript information wherein each of the plurality of cues has associated therewith a type of program, correlating the at least one cue of the plurality of cues identified in the transcript information to the type of program, and classifying the program based on the correlation of the at least one cue of the plurality of cues identified in the transcript information.
78 Citations
7 Claims
-
1. A method for classification of a program comprising the steps of:
-
receiving an audio/video signal corresponding to the program; determining transcript information associated with the program using the audio/video signal; identifying at least one cue in the transcript information and an associated time of occurrence, each of the cues being associated with a type of program; correlating the at least one cue identified in the transcript information to the type of program; comparing the time of occurrence of two cues selected from the at least one identified cue and determining a proximity of occurrence of the two selected cues, wherein if the proximity of occurrence is greater than a predetermined amount, the two selected cues are ignored in connection with determining the program classification; and wherein if the proximity of occurrence is not greater than the predetermined amount, the two selected cues are utilized in connection with determining the program classification; and classifying the program based on the proximity of occurrence of the two selected cues. - View Dependent Claims (2, 3, 4)
-
-
5. Apparatus for classification of a program, comprising:
-
a receiver to receive an audio/data/video signal corresponding to the program; a transcript information extractor for extracting transcript information associated with the program from the audio/data/video input signal; a cue extractor for identifying at least one cue in the transcript information and an associated time of occurrence, each of the cues having associated therewith a type of program; a knowledge database for correlating the at least one cue identified in the transcript information to the type of program; a temporal database for comparing the time of occurrence of two selected cues, of the at least one cue to determine a proximity of occurrence of the two selected cues wherein if the proximity of occurrence is greater than a predetermined amount, the two selected cues are ignored in connection with determining the program classification; and wherein if the proximity of occurrence is not greater than the predetermined amount, the two selected cues are utilized in connection with determining the program classification; and a classifier for classifying the program based on the proximity of occurrence. - View Dependent Claims (6, 7)
-
Specification