Methods and apparatus to increase a match rate for media identification
Methods and apparatus are disclosed herein that increase a match rate for over-the-top media. An example apparatus includes a signature generator to generate a first signature of a first portion of a first media element and an audience measurement interface to receive a second signature of media monitored by a panelist meter. The example apparatus further includes a media element analyzer to compare the first signature and the second signature, determine a number of hits associated with the first media element based on the comparison, and, when the number of hits meets a threshold, generate a third signature of the first media element, the third signature generated for a second portion of the first media element, the second portion greater than the first portion.
1. An apparatus comprising:
a signature generator to generate a first signature of a first portion of a first media element, wherein the first signature is a preliminary signature;
an audience measurement interface to receive a second signature of media monitored by a panelist meter; and
a media element analyzer to:
compare the first signature and the second signature;
determine a number of hits associated with the first media element based on the comparison; and
when the number of hits meets a threshold, generate a third signature for a second portion of the first media element, the second portion having a greater duration than the first portion of the first media element, wherein the third signature is an expanded version of the first signature.
2. The apparatus of claim 1 , wherein the first media element is associated with over-the-top media.
3. The apparatus of claim 1 , wherein the first portion of the first media element is the first thirty seconds of the first media element.
4. The apparatus of claim 1 , further including a media identifier to identify, prior to generating the first signature, the first media element based on a number of impressions associated with the first media element on a website hosting the first media element.
5. The apparatus of claim 4 , wherein the first media element is identified by a web crawler.
6. The apparatus of claim 1 , wherein the media element analyzer determines a hit associated with the first media element by detecting when the second signature matches the first signature.
7. The apparatus of claim 1 , further including a reference database to store the third signature, the third signature used to determine a number of impressions associated with monitored media elements.
8. A tangible, non-transitory computer readable storage medium comprising instructions that, when executed, cause a machine to at least:
generate, at a central facility, a first signature of a first portion of a first media element, wherein the first signature is a preliminary signature;
receive, at the central facility, a second signature from monitored media elements;
compare the second signature with the first signature;
determine a number of hits associated with the first media element based on the comparison; and
when the number of hits meets a threshold, generate, at the central facility, a third signature for a second portion of the first media element, the second portion having a greater duration than the first portion of the first media element, wherein the third signature is an expanded version of the first signature.
9. The tangible, non-transitory computer readable storage medium of claim 8 , wherein the first media element is associated with over-the-top media.
10. The tangible, non-transitory computer readable storage medium of claim 8 , wherein the first portion of the first media element is the first thirty seconds of the first media element.
11. The tangible, non-transitory computer readable storage medium of claim 8 , wherein the instructions further cause the machine to identify the first media element prior to generating the first signature based on a number of impressions associated with the first media element on a website hosting the first media element.
12. The tangible, non-transitory computer readable storage medium of claim 11 , wherein the first media element is identified by a web crawler.
13. The tangible, non-transitory computer readable storage medium of claim 8 , wherein the instructions further causes the machine to store the third signature in a reference database as a reference signature, the third signature is used to determine a number of impressions associated with monitored media elements.
14. A method comprising:
generating, at a central facility, a first signature of a first portion of a first media element, wherein the first signature is a preliminary signature;
receiving, at the central facility, a second signature from monitored media elements;
comparing the second signature with the first signature;
determining a number of hits associated with the first media element based on the comparison; and
when the number of hits meets a threshold, generating, at the central facility, a third signature for a second portion of the first media element, the second portion having a greater duration than the first portion of the first media element, wherein the third signature is an expanded version of the first signature.
15. The method of claim 14 , wherein the first media element is associated with over-the-top media.
16. The method of claim 14 , wherein the first portion of the first media element is the first thirty seconds of the first media element.
17. The method of claim 14 , further including identifying the first media element prior to generating the first signature based on a number of impressions associated with the first media element on a website hosting the first media element.
18. The method of claim 17 , wherein the first media element is identified by a web crawler.
19. The method of claim 14 , further including storing the third signature in a reference database as a reference signature, the third signature is used to determine a number of impressions associated with monitored media elements.