Character based media analytics
View Patent ↗Techniques for analyzing media content are described. One technique generally comprises performing a regression analysis for characters in a plurality of media content based on user demographics, content outcome measure, and character models. The technique determines an attribute of significance. In some embodiments, the technique selects media content for display that depicts a character having at least a threshold value of the attribute of significance. In some embodiments, the technique displays media analytics for the attribute of significance determined based on a value of the attribute of significance exceeding a threshold significance value.
1. A computer-implemented method for analyzing media content, the method comprising:
accessing demographics information of a plurality of users to identify a subset of the plurality of users;
accessing outcome measure information of the subset of the plurality of users, the outcome measure information relating to a plurality of media content, the plurality of media content comprising a first media content and a second media content;
calculating a first outcome measure for the first media content, the first outcome measure based on the outcome measure information;
calculating a second outcome measure for the second media content, the second outcome measure based on the outcome measure information;
accessing respective character models of one or more characters depicted in the first media content;
accessing respective character models of one or more characters depicted in the second media content;
determining, for the first media content:
a first attribute value of a first attribute of the one or more characters depicted in the first media content, the determination based on the respective character models and in accordance with a first capture function; and
a second attribute value of a second attribute of the one or more characters depicted in the first media content, the determination based on the respective character models and in accordance with a second capture function;
determining, for the second media content:
a third attribute value of the first attribute of the one or more characters depicted in the second media content, the determination based on the respective character models and in accordance with the first capture function; and
a fourth attribute value of the second attribute of the one or more characters depicted in the second media content, the determination based on the respective character models and in accordance with the second capture function; and
performing a regression using the first attribute value, the second attribute value, the third attribute value, the fourth attribute value, the first outcome measure, and the second outcome measure to determine at least one attribute of significance.
2. The computer-implemented method of claim 1 , wherein the at least one attribute of significance is determined based on a value of the at least one attribute of significance exceeding a threshold significance value.
3. The computer-implemented method of claim 1 , wherein the outcome measure information comprises video playback completion data for the first media content and the second media content and wherein the first attribute is different from the second attribute.
4. The computer-implemented method of claim 1 , wherein the outcome measure information comprises minimum duration of video playback data for the first media content and the second media content.
5. The computer-implemented method of claim 1 , wherein the determined attribute of significance is one of the first attribute and the second attribute.
6. The computer-implemented method of claim 1 , wherein the plurality of media content further comprises a third media content, and the method further comprising:
calculating a third outcome measure for the third media content, the third outcome measure based on the outcome measure information;
accessing respective character models of one or more characters depicted in the third media content;
determining, for the third media content:
a fifth attribute value of the first attribute of the one or more characters depicted in the third media content, the determination based on the respective character models and in accordance with the first capture function;
a sixth attribute value of the second attribute of the one or more characters depicted in the third media content, the determination based on the respective character models and in accordance with the second capture function; and
wherein performing the regression to determine the at least one attribute of significance further comprises using the fifth attribute value and the sixth attribute value.
7. The computer-implemented method of claim 1 , the method further comprising:
selecting media content for display, the media selected based on depicting a character having at least a threshold value of the at least one attribute of significance.
8. The computer-implemented method of claim 1 , the method further comprising:
displaying media analytics for the at least one attribute of significance, wherein the at least one attribute of significance is determined based on a value of the at least one attribute of significance exceeding a threshold significance value.
9. A non-transitory computer-readable storage medium comprising computer-executable instructions for analyzing media content, the computer-executable instructions comprising instructions for:
accessing demographics information of a plurality of users to identify a subset of the plurality of users;
accessing outcome measure information of the subset of the plurality of users, the outcome measure information relating to a plurality of media content, the plurality of media content comprising a first media content and a second media content;
calculating a first outcome measure for the first media content, the first outcome measure based on the outcome measure information;
calculating a second outcome measure for the second media content, the second outcome measure based on the outcome measure information;
accessing respective character models of one or more characters depicted in the first media content;
accessing respective character models of one or more characters depicted in the second media content;
determining, for the first media content:
a first attribute value of a first attribute of the one or more characters depicted in the first media content, the determination based on the respective character models and in accordance with a first capture function; and
a second attribute value of a second attribute of the one or more characters depicted in the first media content, the determination based on the respective character models and in accordance with a second capture function;
determining, for the second media content:
a third attribute value of the first attribute of the one or more characters depicted in the second media content, the determination based on the respective character models and in accordance with the first capture function; and
a fourth attribute value of the second attribute of the one or more characters depicted in the second media content, the determination based on the respective character models and in accordance with the second capture function; and
performing a regression using the first attribute value, the second attribute value, the third attribute value, the fourth attribute value, the first outcome measure, and the second outcome measure to determine at least one attribute of significance.
10. The non-transitory computer-readable storage medium of claim 9 , wherein the at least one attribute of significance is determined based on a value of the at least one attribute of significance exceeding a threshold significance value.
11. The non-transitory computer-readable storage medium of claim 9 , wherein the outcome measure information comprises video playback completion data for the first media content and the second media content and wherein the first attribute is different from the second attribute.
12. The non-transitory computer-readable storage medium of claim 9 , wherein the outcome measure information comprises minimum duration of video playback data for the first media content and the second media content.
13. The non-transitory computer-readable storage medium of claim 9 , wherein the determined attribute of significance is one of the first attribute and the second attribute.
14. The non-transitory computer-readable storage medium of claim 9 , wherein the plurality of media content further comprises a third media content, and further comprising computer-executable instructions for:
calculating a third outcome measure for the third media content, the third outcome measure based on the outcome measure information;
accessing respective character models of one or more characters depicted in the third media content;
determining, for the third media content:
a fifth attribute value of the first attribute of the one or more characters depicted in the third media content, the determination based on the respective character models and in accordance with the first capture function;
a sixth attribute value of the second attribute of the one or more characters depicted in the third media content, the determination based on the respective character models and in accordance with the second capture function; and
wherein performing the regression to determine the at least one attribute of significance further comprises using the fifth attribute value and the sixth attribute value.
15. The non-transitory computer-readable storage medium of claim 9 , further comprising computer-executable instructions for:
selecting media content for display, the media selected based on depicting a character having at least a threshold value of the at least one attribute of significance.
16. The non-transitory computer-readable storage medium of claim 9 , further comprising computer-executable instructions for:
displaying media analytics for the at least one attribute of significance, wherein the at least one attribute of significance is determined based on a value of the at least one attribute of significance exceeding a threshold significance value.
17. An apparatus for analyzing media content, the apparatus comprising:
memory; and
one or more computer processors configured to:
access demographics information of a plurality of users to identify a subset of the plurality of users;
access outcome measure information of the subset of the plurality of users, outcome measure information relating to a plurality of media content, the plurality of media content comprising a first media content and a second media content;
calculate a first outcome measure for the first media content, the first outcome measure based on the outcome measure information;
calculate a second outcome measure for the second media content, the second outcome measure based on the outcome measure information;
access respective character models of one or more characters depicted in the first media content;
access respective character models of one or more characters depicted in the second media content;
determine, for the first media content:
a first attribute value of a first attribute of the one or more characters depicted in the first media content, the determination based on the respective character models and in accordance with a first capture function; and
a second attribute value of a second attribute of the one or more characters depicted in the first media content, the determination based on the respective character models and in accordance with a second capture function;
determine, for the second media content:
a third attribute value of the first attribute of the one or more characters depicted in the second media content, the determination based on the respective character models and in accordance with the first capture function; and
a fourth attribute value of the second attribute of the one or more characters depicted in the second media content, the determination based on the respective character models and in accordance with the second capture function; and
perform a regression using the first attribute value, the second attribute value, the third attribute value, the fourth attribute value, the first outcome measure, and the second outcome measure to determine at least one attribute of significance.
18. The apparatus of claim 17 , wherein the at least one attribute of significance is determined based on a value of the at least one attribute of significance exceeding a threshold significance value.
19. The apparatus of claim 17 , wherein the outcome measure information comprises video playback completion data for the first media content and the second media content and wherein the first attribute is different from the second attribute.
20. The apparatus of claim 17 , wherein the outcome measure information comprises minimum duration of video playback data for the first media content and the second media content.
21. The apparatus of claim 17 , wherein the plurality of media content further comprises a third media content, and the one or more computer processors further configured to:
calculate a third outcome measure for the third media content, the third outcome measure based on the outcome measure information;
access respective character models of one or more characters depicted in the third media content;
determine, for the third media content:
a fifth attribute value of the first attribute of the one or more characters depicted in the third media content, the determination based on the respective character models and in accordance with the first capture function;
a sixth attribute value of the second attribute of the one or more characters depicted in the third media content, the determination based on the respective character models and in accordance with the second capture function; and
wherein performing the regression to determine the at least one attribute of significance further comprises using the fifth attribute value and the sixth attribute value.
22. The apparatus of claim 17 , the one or more computer processors further configured to:
select media content for display, the media selected based on depicting a character having at least a threshold value of the at least one attribute of significance.
23. The apparatus of claim 17 , the one or more computer processors further configured to:
display media analytics for the at least one attribute of significance, wherein the at least one attribute of significance is determined based on a value of the at least one attribute of significance exceeding a threshold significance value.