Back to results
US 11,386,056 B2Granted
Duplicate multimedia entity identification and processing
AssigneeInternational Business Machines Corporation
InventorsKeith G. Frost, Stephen A. Boxwell, Kyle M. Brake, Stanley J. Vernier
Life of this patent
Estimating the term…
Abstract
Embodiments relate to a computer platform and corresponding process and program code to assess multimedia files with respect to similarity and duplicate media content. Data streams are converted into sequences of events, and object representation within the streams is identified and subject to processing with respect to the event sequences. A similarity assessment is conducted between two or more of the data streams, and a corresponding distance measurement to quantify similarity is produced. Duplicate data is selectively identified in response to the similarity assessment and the produced distance measurement.
Claims15
A computer system comprising:
- a processing unit operatively coupled to memory;
- a knowledge engine in communication with the processing unit, the knowledge engine to identify duplicate media content, the knowledge engine comprising:
- a data stream manager configured to convert a first data stream into a first sequence of events and to convert a second data stream into a second sequence of events, the first sequence of events comprising a first event represented by at least a first tuple, the first tuple comprising one or more first object representations and one or more first dialogue representations, the one or more first object representations representing one or more visual entities of the first event, the one or more first dialogue representations representing one or more dialogue words of the first event, the one or more first object representations and the one or more first dialogue representations being associated with a first timestamp, the second sequence of events comprising a second event represented by at least a second tuple, the second tuple comprising one or more second object representations and one or more second dialogue representations, the one or more second object representations representing one or more visual entities of the second event, the one or more second dialogue representations representing one or more dialogue words of the second event, the one or more second object representations and the one or more second dialogue representations being associated with a second timestamp;
- and
- an assessment manager configured to conduct a similarity assessment between at least the one or more first object representations and the one or more first dialogue representations of the first tuple of the first data stream and the one or more second object representations and the one or more second dialogue representations of the second tuple of the second data stream, respectively, the similarity assessment to produce a distance measurement, the distance measurement representing a quantity of edits necessary to make the one or more first object representations and the one or more first dialogue representations of the first tuple equivalent to the one or more second object representations and the one or more second dialogue representations of the second tuple;
- and
- the processing unit to selectively identify duplicate data in the first and second sequence of events responsive to the distance measurement.
4 more elements
A computer program product for similarity assessment, the computer program product comprising:
- a computer readable storage medium having program code embodied therewith, the program code executable by a processor to:
- convert a first data stream into a first sequence of events and convert a second data stream into a second sequence of events, the first sequence of events comprising a first event represented by at least a first tuple, the first tuple comprising one or more first object representations and one or more first dialogue representations, the one or more first object representations representing one or more visual entities of the first event, the one or more first dialogue representations representing one or more dialogue words of the first event, the one or more first object representations and the one or more first dialogue representations being associated with a first timestamp, the second sequence of events comprising a second event represented by at least a second tuple, the second tuple comprising one or more second object representations and one or more second dialogue representations, the one or more second object representations representing one or more visual entities of the second event, the one or more second dialogue representations representing one or more dialogue words of the second event, the one or more second object representations and the one or more second dialogue representations being associated with a second timestamp;
- conduct a similarity assessment between at least the one or more first object representations and the one or more first dialogue representations of the first tuple of the first data stream and the one or more second visual object representations and the one or more second object representations and the one or more second dialogue representations of the second tuple of the second data stream, respectively, the similarity assessment to produce a distance measurement representing a quantity of edits necessary to make the one or more first object representations and the one or more first dialogue representations of the first tuple equivalent to the one or more second object representations and the one or more second dialogue representations of the second tuple;
- and
- selectively identify duplicate data in the first and second sequence of events responsive to the distance measurement.
2 more elements
A method comprising:
- converting a first data stream into a first sequence of events and a second data stream into a second sequence of events, the first sequence of events comprising a first event represented by at least a first tuple, the first tuple comprising one or more first object representations and one or more first dialogue representations, the one or more first object representations representing one or more visual entities of the first event, the one or more first dialogue representations representing one or more dialogue words of the first event, the one or more first object representations and the one or more first dialogue representations being associated with a first timestamp, the second sequence of events comprising a second event represented by at least a second tuple, the second tuple comprising one or more second object representations and one or more second dialogue representations, the one or more second object representations representing one or more visual entities of the second event, the one or more second dialogue representations representing one or more dialogue words of the second event, the one or more second object representations and the one or more second dialogue representations being associated with a second timestamp;
- conducting a similarity assessment between at least the one or more first object representations and the one or more first dialogue representations of the first tuple of the first data stream and the one or more second object representations and the one or more second dialogue representations of the second tuple of the second data stream, respectively, the similarity assessment producing a distance measurement, the distance measurement representing a quantity of edits necessary to make the one or more first object representations and the one or more first dialogue representations of the first tuple equivalent to the one or more second object representations and the one or more second dialogue representations of the second tuple;
- and
- selectively identifying duplicate data in the first and second sequence of events responsive to the distance measurement.
1 more element
Dependencies are inferred from the claim text.