Signature matching with meter data aggregation for media identification
Example apparatus disclosed herein to implement signature matching with meter data aggregation for use in media identification applications include a match job aggregator to aggregate batches of meter data from a meter to form aggregated meter data associated with the meter, and a hash matcher to identify a valid hash key match between meter hash keys generated from meter signatures in the aggregated meter data and reference hash keys corresponding to a collection of media assets. Disclosed example apparatus also include a signature matcher to align, based on the valid hash key match, a sequence of reference signatures corresponding to a first media asset associated with the valid hash key match and a corresponding sequence of the meter signatures, and compare the sequence of reference signatures and the corresponding sequence of meter signatures to identify media represented by at least a portion of the sequence of the meter signatures.
1. A media identification apparatus, the apparatus comprising:
at least one memory;
computer readable instructions; and
at least one processor to execute the computer readable instructions to at least:
aggregate batches of meter data from a meter to form aggregated meter data associated with the meter, the batches of meter data corresponding to respective reporting intervals having a first duration, the aggregated meter data corresponding to a monitoring interval having a second duration larger than the first duration;
identify a valid hash key match between meter hash keys generated from meter signatures in the aggregated meter data and reference hash keys corresponding to a collection of media assets;
align, based on the valid hash key match, (i) a sequence of reference signatures corresponding to a duration of a first media asset associated with the valid hash key match with (ii) a corresponding sequence of the meter signatures in the aggregated meter data; and
compare the sequence of reference signatures and the corresponding sequence of the meter signatures to identify media represented by at least a portion of the sequence of the meter signatures.
2. The apparatus of claim 1 , wherein the at least one processor is to output (i) an identifier of the media represented by the at least the portion of the sequence of the meter signatures, and (ii) a third duration corresponding to a duration represented by the at least the portion of the sequence of the meter signatures, the at least one processor to output the identifier and the third duration to an application that is to perform an operation based on the identifier and the third duration.
3. The apparatus of claim 1 , wherein the second duration corresponds to a twenty-four period, and the first duration corresponds to a fraction of the twenty-four period.
4. The apparatus of claim 3 , wherein the sequence of reference signatures corresponds to an entirety of the first media asset.
5. The apparatus of claim 1 , wherein the at least one processor is to generate the meter hash keys from the meter signatures in the aggregated meter data.
6. The apparatus of claim 1 , wherein the at least one processor is to:
identify, for a first one of the meter hash keys, a set of reference hash keys that match the first one of the meter hash keys;
store ones of the set of reference hash keys in respective data structures corresponding to media assets represented by the ones of the set of reference hash keys, the media assets including the first media asset, a first one of the data structures corresponding to the first media asset, the first one of the data structures to include a sequence of reference hash keys that match a corresponding sequence of the meter hash keys; and
determine that the first one of the sequence of reference hash keys included in the first one of the data structures corresponds to the valid hash key match when the sequence of reference hash keys and the corresponding sequence of the meter hash keys satisfy one or more validation criteria.
7. The apparatus of claim 6 , wherein to align the sequence of reference signatures with the corresponding sequence of the meter signatures, the at least one processor is to:
identify a first number of signatures from (i) an initial reference signature of the sequence of reference signatures corresponding to the duration of the first media asset to (ii) a reference signature in the sequence of reference signatures that corresponds to an initial reference hash key in the sequence of reference hash keys corresponding to the valid hash key match;
identify an initial meter signature of the sequence of the meter signatures to be a first meter signature in the aggregated meter data that precedes, by the first number of signatures, a second meter signature in the aggregated meter data that corresponds to an initial meter hash key in the sequence of the meter hash keys corresponding to the valid hash key match; and
determine the sequence of the meter hash keys to begin with the initial meter signature and include a same second number of signatures as the sequence of reference signatures.
8. A non-transitory computer readable medium comprising computer readable instructions that, when executed, cause a processor to at least:
aggregate batches of meter data from a meter to form aggregated meter data associated with the meter, the batches of meter data corresponding to respective reporting intervals having a first duration, the aggregated meter data corresponding to a monitoring interval having a second duration larger than the first duration;
identify a valid hash key match between meter hash keys generated from meter signatures in the aggregated meter data and reference hash keys corresponding to a collection of media assets;
align, based on the valid hash key match, (i) a sequence of reference signatures corresponding to a duration of a first media asset associated with the valid hash key match with (ii) a corresponding sequence of the meter signatures in the aggregated meter data; and
compare the sequence of reference signatures and the corresponding sequence of the meter signatures to identify media represented by at least a portion of the sequence of the meter signatures.
9. The non-transitory computer readable medium of claim 8 , wherein the computer readable instructions, when executed, cause the processor to output (i) an identifier of the media represented by the at least the portion of the sequence of the meter signatures, and (ii) a third duration corresponding to a duration represented by the at least the portion of the sequence of the meter signatures, the instructions to cause the processor to output the identifier and the third duration to an application that is to perform an operation based on the identifier and the third duration.
10. The non-transitory computer readable medium of claim 8 , wherein the second duration corresponds to a twenty-four period, and the first duration corresponds to a fraction of the twenty-four period.
11. The non-transitory computer readable medium of claim 10 , wherein the sequence of reference signatures corresponds to an entirety of the first media asset.
12. The non-transitory computer readable medium of claim 8 , wherein the computer readable instructions, when executed, cause the processor to generate the meter hash keys from the meter signatures in the aggregated meter data.
13. The non-transitory computer readable medium of claim 8 , wherein the computer readable instructions, when executed, cause the processor to:
identify, for a first one of the meter hash keys, a set of reference hash keys that match the first one of the meter hash keys;
store ones of the set of reference hash keys in respective data structures corresponding to media assets represented by the ones of the set of reference hash keys, the media assets including the first media asset, a first one of the data structures corresponding to the first media asset, the first one of the data structures to include a sequence of reference hash keys that match a corresponding sequence of the meter hash keys; and
determine that the first one of the sequence of reference hash keys included in the first one of the data structures corresponds to the valid hash key match when the sequence of reference hash keys and the corresponding sequence of the meter hash keys satisfy one or more validation criteria.
14. The non-transitory computer readable medium of claim 13 , wherein to align the sequence of reference signatures with the corresponding sequence of the meter signatures, the instructions, when executed, cause the processor to:
identify a first number of signatures from (i) an initial reference signature of the sequence of reference signatures corresponding to the duration of the first media asset to (ii) a reference signature in the sequence of reference signatures that corresponds to an initial reference hash key in the sequence of reference hash keys corresponding to the valid hash key match;
identify an initial meter signature of the sequence of the meter signatures to be a first meter signature in the aggregated meter data that precedes, by the first number of signatures, a second meter signature in the aggregated meter data that corresponds to an initial meter hash key in the sequence of the meter hash keys corresponding to the valid hash key match; and
determine the sequence of the meter hash keys to begin with the initial meter signature and include a same second number of signatures as the sequence of reference signatures.
15. A media identification method comprising:
aggregating batches of meter data from a meter to form aggregated meter data associated with the meter, the batches of meter data corresponding to respective reporting intervals having a first duration, the aggregated meter data corresponding to a monitoring interval having a second duration larger than the first duration;
identifying, by executing an instruction with a processor, a valid hash key match between meter hash keys generated from meter signatures in the aggregated meter data and reference hash keys corresponding to a collection of media assets;
aligning, based on the valid hash key match, (i) a sequence of reference signatures corresponding to a duration of a first media asset associated with the valid hash key match with (ii) a corresponding sequence of the meter signatures in the aggregated meter data; and
comparing, by executing an instruction with the processor, the sequence of reference signatures and the corresponding sequence of the meter signatures to identify media represented by at least a portion of the sequence of the meter signatures.
16. The method of claim 15 , further including outputting (i) an identifier of the media represented by the at least the portion of the sequence of the meter signatures, and (ii) a third duration corresponding to a duration represented by the at least the portion of the sequence of the meter signatures, the identifier and the third duration to be output to an application that is to perform an operation based on the identifier and the third duration.
17. The method of claim 15 , wherein the second duration corresponds to a twenty-four period, the first duration corresponds to a fraction of the twenty-four period, and the sequence of reference signatures corresponds to an entirety of the first media asset.
18. The method of claim 15 , further including generating the meter hash keys from the meter signatures in the aggregated meter data.
19. The method of claim 15 , further including:
identifying, for a first one of the meter hash keys, a set of reference hash keys that match the first one of the meter hash keys;
storing ones of the set of reference hash keys in respective data structures corresponding to media assets represented by the ones of the set of reference hash keys, the media assets including the first media asset, a first one of the data structures corresponding to the first media asset, the first one of the data structures to include a sequence of reference hash keys that match a corresponding sequence of the meter hash keys; and
determining that the first one of the sequence of reference hash keys included in the first one of the data structures corresponds to the valid hash key match when the sequence of reference hash keys and the corresponding sequence of the meter hash keys satisfy one or more validation criteria.
20. The method of claim 19 , wherein the aligning of the sequence of reference signatures with the corresponding sequence of the meter signatures includes:
identifying a first number of signatures from (i) an initial reference signature of the sequence of reference signatures corresponding to the duration of the first media asset to (ii) a reference signature in the sequence of reference signatures that corresponds to an initial reference hash key in the sequence of reference hash keys corresponding to the valid hash key match;
identifying an initial meter signature of the sequence of the meter signatures to be a first meter signature in the aggregated meter data that precedes, by the first number of signatures, a second meter signature in the aggregated meter data that corresponds to an initial meter hash key in the sequence of the meter hash keys corresponding to the valid hash key match; and
determining the sequence of the meter hash keys to begin with the initial meter signature and include a same second number of signatures as the sequence of reference signatures.