Ranking videos based on experimental data

• US 9,405,775 B1
• Filed: 03/15/2013
• Issued: 08/02/2016
• Est. Priority Date: 03/15/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Sarukkai, Ramesh Rangarajan, Lee, Juhyun
• Primary Examiner(s): Ly, Anh
• Application Number:
  US13/833,133
• Time in Patent Office: 1,236 Days
• Field of Search: 707/723, 707/728, 707/709, 707/741, 707/E17.064, 707/742, 707/767, 707/759, 707/765, 707/766, 707/768, 707/769, 707/736, 707/705, 707/E17.071, 707/E17.044, 707/E17.005, 707/E17.121, 707/748, 707/722, 707/732, 707/749, 707/735, 707/798, 707/673, 707/706, 707/E17.108, 707/7.071, 705/5, 705/10, 705/14.43, 705/14, 705/25, 705/14.41, 705/14.49, 705/14.42, 705/14.4, 705/14.73, 705/14.54, 705/7.11, 705/7.14, 705/7.29, 705/35, 705/319, 384/135, 384/208.6, 384/411, 384/705, 384/E07.085, 384/E07.003, 384/14.08, 384/E07.083, 384/E07.83, 715/723, 715/719, 715/720, 715/750, 715/738, 715/736, 715/230, 715/704, 715/716, 715/781, 715/236, 715/854, 725/9, 725/32, 725/34, 725/35, 725/113, 725/112, 725/62, 725/134, 725/46, 725/45, 725/47, 725/36, 725/39, 725/40, 725/43, 725/44, 725/48, 725/4, 725/41, 725/146, 725/145, 725/416, 725/110, 725/109, 725/24, 725/19, 725/715, 725/42, 725/49, 386/283, 386/289, 386/262, 386/287, 386/285, 386/286, 386/239, 386/241, 386/240, 386/343, 386/278, 382/156, 382/159, 382/190, 382/229, 382/305, 382/233, 382/100, 382/224, 382/155
• US Class Current: 1/1
• CPC Class Codes: G06F 16/78 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually

Abstract

A system and method for ranking additional videos based on experiment data. The system includes an additional video request retrieval unit to receive a request for a plurality of additional videos, and a number of the plurality of additional videos based on a video being served; an additional video database to retrieve the plurality of additional videos based on the video, and to retrieve a relevance ranking for each of the plurality of additional videos, a monetization ranking for each of the plurality of additional videos, and a likelihood ranking for each of the plurality of additional videos, the likelihood ranking being sourced from the experimental data; a weighting/ranking unit to assign a score for each of the plurality of videos based on the retrieved rankings from the additional video database; and an additional video selection unit to select the number of the plurality of videos based the score.

Claims

1. A system, comprising:

a data store comprising a computer readable medium storing a program of instructions for performing ranking of videos based on experimental data;

a processor that executes the program of instructions;

an additional video request retrieval unit that receives a request for a plurality of additional videos;

an additional video database that;

retrieves the plurality of additional videos; and

retrieves respective relevance rankings for the plurality of additional videos, respective monetization rankings for the plurality of additional videos, and respective likelihood rankings for the plurality of additional videos, the likelihood ranking being sourced from the experimental data;

a weighting/ranking unit that assigns respective scores for the plurality of additional videos based on the retrieved respective relevance rankings, the retrieved respective monetization rankings and the retrieved respective likelihood rankings from the additional video database; and

an additional video selection unit that selects a number of the plurality of additional videos based on one or more of the respective scores.

2. The system of claim 1, wherein the program of instructions further comprises an instruction to transmit the selected plurality of additional videos to a video sharing web site.

3. The system of claim 2, wherein the experimental data is based on whether the video is presently being served from the video sharing web site.

4. The system of claim 2, wherein the experimental data is based on users associated with the video sharing web site.

5. The system of claim 2, wherein the number of the plurality of additional videos is also based on available space to display the plurality of additional videos on the video sharing web site.

6. The system of claim 2, wherein the experimental data comprises information indicative of a record of users associated with the video sharing web site that indicate a likelihood of a specific additional video of the plurality of additional videos being viewed in entirety when augmented with shared content.

7. The system of claim 2, wherein the experimental data comprises information indicative of a record of users associated with the video sharing web site that indicate a time that shared content when presented with a specific additional video of the plurality of additional videos has a defined likelihood of being skipped.

8. The system of claim 1, wherein one or more of the respective scores is also based on a defined weighting applied to the respective relevance ranking, the monetization ranking and the likelihood ranking, respectively.

9. A method, comprising:

receiving, using a device comprising a processor that ranks videos based on experimental data, a request for a plurality of additional videos;

retrieving the plurality of additional videos;

retrieving respective relevance rankings for the plurality of additional videos, respective monetization rankings for the plurality of additional videos, and respective likelihood rankings for the plurality of additional videos, one or more of the respective likelihood rankings being sourced from the experimental data;

assigning respective scores for the plurality of additional videos based on the retrieved respective rankings; and

selecting a number of the plurality of additional videos based on one or more of the respective scores.

10. The method of claim 9, wherein the selected plurality of additional videos is transmitted to a video sharing web site.

11. The method of claim 10, wherein the experimental data is based on whether the video is presently being served from the video sharing web site.

12. The method of claim 10, wherein the experimental data is based on all users associated with video sharing web site.

13. The method of claim 10, wherein the number is based on available space to display additional videos on the video sharing web site.

14. The method of claim 10, wherein the experimental data comprises information indicative of a record of users associated with the video sharing web site that indicate a likelihood of a specific additional video of the plurality of additional videos being viewed in entirety when augmented with shared content.

15. The method of claim 10, wherein the experimental data comprises information indicative of a record of users associated with the video sharing web site that indicate a time that shared content when presented with a specific additional video of the plurality of additional videos has a defined likelihood of being skipped.

16. The method of claim 9, wherein the score is calculated based on a predefined weighting applied to the relevance ranking, the monetization ranking and the likelihood ranking, respectively.

17. A non-transitory computer-readable medium having stored thereon computer-executable instructions that, in response to execution, cause a system to perform operations, including:

retrieving a plurality of additional videos and a request for the plurality of additional videos, wherein the plurality of additional videos are ranked based on experimental information;

assigning respective scores for the plurality of additional videos based on retrieved respective monetization rankings of the plurality of additional videos; and

selecting a number of the plurality of additional videos based on one or more of the respective scores.

18. The non-transitory computer-readable medium of claim 17, wherein the respective rankings comprise respective likelihood rankings for the plurality of additional videos.

19. The non-transitory computer-readable medium of claim 17, wherein the experimental information comprises information indicative of a record of users associated with the video sharing web site that indicate a time that shared content when presented with a specific additional video of the plurality of additional videos has a defined likelihood of being skipped.

20. A method, comprising:

receiving a request for additional videos via a client device;

retrieving a plurality of additional videos;

determining likelihood rankings for the plurality of additional videos, the likelihood ranking for each of the plurality of additional videos based on experimental data for the additional video and the likelihood ranking indicative of a likelihood that the additional video is watched in its entirety on the client device if the additional video is displayed on the client device;

assigning, by a device comprising a processor, a plurality of scores to the plurality of additional videos based on the likelihood rankings; and

selecting a number of the plurality of additional videos to display on the client device for selection by the user based on the plurality of scores.

21. The method of claim 20, wherein the experimental data includes a total amount of time a plurality of users viewed the additional video.

22. The method of claim 21, further comprising:

retrieving monetization rankings for the plurality of additional videos, the monetization ranking for each additional video based on a number of total views the additional video received; and

wherein the plurality of scores for the plurality of additional videos is further based on the monetization rankings.