Granted Patent B2

US 12,393,956 · App. 17/938,252 · Granted Aug 19, 2025

Inventors: Fabian L. Gallusser (Palo Alto, CA); Lian Jian (San Jose, CA)

Assignee: Disney Enterprises, Inc.

G06Q30/0201

Abstract

Claims (83)

1. A method comprising:

parsing, by a recommendation computing system, a media file for a plurality of scoring elements using a factor of interest for a first user, wherein the recommendation computing system receives the media file from a content server communicatively coupled to the recommendation computing system through a network;

determining, by the recommendation computing system, a media distribution of one or more dimensions of the factor of interest for the first user for the media file based on a presence of the one or more dimensions of the factor of interest for the first user in the plurality of scoring elements;

generating, by the recommendation computing system, a reference distribution of the one or more dimensions of the factor of interest for the first user based on a presence of the one or more dimensions of the of the factor of interest for the first user in a reference dataset;

determining, by the recommendation computing system, a factor score for the factor of interest for the first user in the media file based on the media distribution and the reference distribution;

generating, by the recommendation computing system, a scored action for the media file using the factor score; and

performing, by the recommendation computing system, the scored action by at least filtering a media repository based on the scored action and the factor score by:

accessing the media repository comprising the media file, wherein the media repository is accessible by the first user through a user system that is communicatively coupled to the recommendation computing system through the network; and

filtering, by the recommendation computing system according to the scored action, the media repository to change an order of the media file in the media repository, wherein the media repository provides filtered media to the first user through the recommendation computing system, wherein the filtered media is displayed on a display of the user system upon access by the first user.

2. The method of claim 1 , wherein parsing, by the recommendation computing system, the media file further comprises:

determining, by the recommendation computing system, a scoring element structure for the media file based on the factor of interest for the first user and a media type of the media file;

generating, by the recommendation computing system, at least one parsing instance in the scoring element structure from the media file; and

applying, by the recommendation computing system, one or more tracking tags to the at least one parsing instance, wherein the one or more tracking tags track the presence of the one or more dimensions in the scoring element structure.

3. The method of claim 2 , wherein determining, by the recommendation computing system, the media distribution for the media file further comprises:

aggregating, by the recommendation computing system, the one or more tracking tags for the at least one parsing instance; and

generating, by the recommendation computing system, the media distribution using the aggregated one or more tracking tags demonstrating the presence of the one or more dimensions in the media file.

4. The method of claim 3 , wherein generating, by the recommendation computing system, the reference distribution for the factor of interest for the first user further comprises:

receiving, at the recommendation computing system, the reference dataset, wherein the reference dataset comprises data representing factors of interest and the one or more dimensions; and

parsing, by the recommendation computing system, the reference dataset to tabulate the presence of the one or more dimensions in the reference dataset; and

generating, by the recommendation computing system, the reference distribution using the presence of the one or more dimensions in the reference dataset.

5. The method of claim 4 , wherein determining, by the recommendation computing system, the factor score comprises:

calculating, by the recommendation computing system, a distance across from the media distribution to the reference distribution for each of the one or more dimensions;

scoring, by the recommendation computing system, the distance for each of the one or more dimensions; and

aggregating, by the recommendation computing system, the scores to generate the factor score for the media file.

6. The method of claim 1 , wherein generating, by the recommendation computing system, the scored action further comprises:

accessing, by the recommendation computing system, an action index for one or more action candidates; and

determining, by the recommendation computing system, from the factor of interest for the first user, the scored action from the action candidates.

7. A system, comprising:

a processor; and

a memory comprising instructions which, when executed on the processor, performs an operation, the operation comprising:

parsing, by a recommendation computing system, a media file for a plurality of scoring elements using a factor of interest for a first user, wherein the recommendation computing system receives the media file from a content server communicatively coupled to the recommendation computing system through a network;

determining, by the recommendation computing system, a media distribution of one or more dimensions of the factor of interest for the first user for the media file based on a presence of the one or more dimensions of the factor of interest for the first user in the plurality of scoring elements;

generating, by the recommendation computing system, a reference distribution of the one or more dimensions of the factor of interest for the first user based on a presence of the one or more dimensions of the of the factor of interest for the first user in a reference dataset;

determining, by the recommendation computing system, a factor score for the factor of interest for the first user in the media file based on the media distribution and the reference distribution;

generating, by the recommendation computing system, a scored action for the media file using the factor score; and

performing, by the recommendation computing system, the scored action by at least filtering a media repository based on the scored action and the factor score by:

accessing the media repository comprising the media file, wherein the media repository is accessible by the first user through a user system that is communicatively coupled to the recommendation computing system through the network; and

filtering, by the recommendation computing system according to the scored action, the media repository to change an order of the media file in the media repository, wherein the media repository provides filtered media to the first user through the recommendation computing system, wherein the filtered media is displayed on a display of the user system upon access by the first user.

8. The system of claim 7 , wherein parsing, by the recommendation computing system, the media file further comprises:

determining, by the recommendation computing system, a scoring element structure for the media file based on the factor of interest for the first user and a media type of the media file;

generating, by the recommendation computing system, at least one parsing instance in the scoring element structure from the media file; and

applying, by the recommendation computing system, one or more tracking tags to the at least one parsing instance, wherein the one or more tracking tags track the presence of the one or more dimensions in the scoring element structure.

9. The system of claim 8 , wherein determining, by the recommendation computing system, the media distribution for the media file further comprises:

aggregating, by the recommendation computing system, the one or more tracking tags for the at least one parsing instance; and

generating, by the recommendation computing system, the media distribution using the aggregated one or more tracking tags demonstrating the presence of the one or more dimensions in the media file.

10. The system of claim 9 , wherein generating, by the recommendation computing system, the reference distribution for the factor of interest for the first user further comprises:

receiving, at the recommendation computing system, the reference dataset, wherein the reference dataset comprises data representing factors of interest and the one or more dimensions; and

parsing, by the recommendation computing system, the reference dataset to tabulate the presence of the one or more dimensions in the reference dataset; and

generating, by the recommendation computing system, the reference distribution using the presence of the one or more dimensions in the reference dataset.

11. The system of claim 9 , wherein determining, by the recommendation computing system, the factor score comprises:

calculating, by the recommendation computing system, a distance across from the media distribution to the reference distribution for each of the one or more dimensions;

scoring, by the recommendation computing system, the distance for each of the one or more dimensions; and

aggregating, by the recommendation computing system, the scores to generate the factor score for the media file.

12. The system of claim 7 , wherein generating, by the recommendation computing system, the scored action further comprises:

accessing, by the recommendation computing system, an action index for one or more action candidates; and

determining, by the recommendation computing system, from the factor of interest for the first user, the scored action from the action candidates.

13. A non-transitory computer-readable storage medium comprising computer-readable program code embodied therewith, the computer-readable program code is configured to perform, when executed by a processor, an operation, the operation comprising:

parsing, by a recommendation computing system, a media file for a plurality of scoring elements using a factor of interest for a first user, wherein the recommendation computing system receives the media file from a content server communicatively coupled to the recommendation computing system through a network;

determining, by the recommendation computing system, a media distribution of one or more dimensions of the factor of interest for the first user for the media file based on a presence of the one or more dimensions of the factor of interest for the first user in the plurality of scoring elements;

generating, by the recommendation computing system, a reference distribution of the one or more dimensions of the factor of interest for the first user based on a presence of the one or more dimensions of the of the factor of interest for the first user in a reference dataset;

determining, by the recommendation computing system, a factor score for the factor of interest for the first user in the media file based on the media distribution and the reference distribution;

generating, by the recommendation computing system, a scored action for the media file using the factor score; and

performing, by the recommendation computing system, the scored action by at least filtering a media repository based on the scored action and the factor score by:

accessing the media repository comprising the media file, wherein the media repository is accessible by the first user through a user system that is communicatively coupled to the recommendation computing system through the network; and

filtering, by the recommendation computing system according to the scored action, the media repository to change an order of the media file in the media repository, wherein the media repository provides filtered media to the first user through the recommendation computing system, wherein the filtered media is displayed on a display of the user system upon access by the first user.

14. The computer-readable storage medium of claim 13 , wherein parsing, by the recommendation computing system, the media file further comprises:

determining, by the recommendation computing system, a scoring element structure for the media file based on the factor of interest for the first user and a media type of the media file;

generating, by the recommendation computing system, at least one parsing instance in the scoring element structure from the media file; and

applying, by the recommendation computing system, one or more tracking tags to the at least one parsing instance, wherein the one or more tracking tags track the presence of the one or more dimensions in the scoring element structure.

15. The computer-readable storage medium of claim 14 , wherein determining, by the recommendation computing system, the media distribution for the media file further comprises:

aggregating, by the recommendation computing system, the one or more tracking tags for the at least one parsing instance; and

generating, by the recommendation computing system, the media distribution using the aggregated one or more tracking tags demonstrating the presence of the one or more dimensions in the media file.

16. The computer-readable storage medium of claim 15 , wherein generating, by the recommendation computing system, the reference distribution for the factor of interest for the first user further comprises:

receiving, at the recommendation computing system, the reference dataset, wherein the reference dataset comprises data representing factors of interest and the one or more dimensions; and

parsing, by the recommendation computing system, the reference dataset to tabulate the presence of the one or more dimensions in the reference dataset; and

generating, by the recommendation computing system, the reference distribution using the presence of the one or more dimensions in the reference dataset.

17. The computer-readable storage medium of claim 16 , wherein determining, by the recommendation computing system, the factor score comprises:

calculating, by the recommendation computing system, a distance across from the media distribution to the reference distribution for each of the one or more dimensions;

scoring, by the recommendation computing system, the distance for each of the one or more dimensions; and

aggregating, by the recommendation computing system, the scores to generate the factor score for the media file.

18. The computer-readable storage medium of claim 13 , wherein generating, by the recommendation computing system, the scored action further comprises:

accessing, by the recommendation computing system, an action index for one or more action candidates; and

determining, by the recommendation computing system, from the factor of interest for the first user, the scored action from the action candidates.

Assignments (1)

Continuity (1)

References Cited (23)