SELECTING AND ORDERING GROUPS OF TITLES

• US 20150356087A1
• Filed: 06/06/2014
• Published: 12/10/2015
• Est. Priority Date: 06/06/2014
• Status: Active Grant

• Current Assignee: Netflix, Inc.
• Original Assignee: Netflix, Inc.
• Inventors: Alvino, Christopher, Gomez-Uribe, Carlos, Hammond, Che, Stipins, Janis III
• Granted Patent: US 9,477,713 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0631 Item recommendations

Abstract

Techniques for selecting and ordering groups of titles to present as recommendations. In one embodiment, for example, a method performed by one or more computing devices of an online services comprises selecting, for each of a plurality of row positions, a group of titles to fill the row position based at least in part on a relevance score computed for the group of titles. The relevance score is based at least in part on a personalized ranking for a particular user of titles in the groups in titles selected to fill the row positions. The groups of titles selected to fill to the row positions are presented as recommendations to the particular user as a sequence of rows in which each row in the sequence corresponds to one of the selected groups of titles.

Claims

1. A method comprising:

selecting, from among a plurality of groups of titles, a group of titles to fill a row position of a plurality of row positions based at least in part on a relevance score computed for the group of titles, the relevance score based at least in part on a personalized ranking of titles in the plurality of groups of titles; and

causing the selected group of titles to be visibly presented in the row position as a recommendation;

wherein the method is performed by one or more computing devices.

2. The method of claim 1, further comprising:

selecting, from among the plurality of groups of titles, the group of titles to fill the row position of the plurality of row positions based at least in part on the relevance score computed for the group of titles, the relevance score based at least in part on the personalized ranking and an un-personalized ranking of titles in the plurality of groups of titles.

3. The method of claim 1, further comprising:

selecting, from among the plurality of groups of titles, the group of titles to fill the row position of the plurality of row positions based at least in part on the relevance score computed for the group of titles and a diversity score computed for the group of titles, the diversity score based at least in part on similarity between titles in the group of titles and titles in one or more groups of titles that have already been selected to fill one or more row positions of the plurality of row positions.

4. The method of claim 1, further comprising:

selecting, from among the plurality of groups of titles, the group of titles to fill the row position of the plurality of row positions based at least in part on the relevance score computed for the group of titles and a coverage score computed for the group of titles, the coverage score based at least in part on similarity between titles in the group of titles and titles in the plurality of groups of titles associated with a positive user interaction.

5. The method of claim 1, further comprising:

selecting, from among the plurality of groups of titles, the group of titles to fill the row position of the plurality of row positions based at least in part on the relevance score computed for the group of titles and a coverage score computed for the group of titles, the coverage score based at least in part on similarity between titles in the group of titles and titles in the plurality of groups of titles recently consumed.

6. The method of claim 1, further comprising:

selecting, from among the plurality of groups of titles, the group of titles to fill the row position of the plurality of row positions based at least in part on the relevance score computed for the group of titles and a coverage score computed for the group of titles, the coverage score based at least in part on similarity between titles in the group of titles and titles in the plurality of groups of titles associated with a positive user recommendation, rating, or like.

7. The method of claim 1, further comprising:

selecting, from among the plurality of groups of titles, the group of titles to fill the row position of the plurality of row positions based at least in part on the relevance score computed for the group of titles, a diversity score computed for the group of titles, and a coverage score computed for the group of titles, the diversity score based at least in part on similarity between titles in the group of titles and titles in one or more groups of titles that have already been selected to fill one or more of the plurality of row positions, the coverage score based at least in part on similarity between titles in the group of titles and titles in the plurality of groups of titles associated with a positive user interaction.

8. The method of claim 1, further comprising:

wherein the row position corresponds to a position on a web page; and

wherein causing the selected group of titles to be visibly presented in the row position comprises causing the selected group of titles to be visibly presented at the web page position.

9. The method of claim 1, wherein the personalized ranking comprises a ranking of titles in the plurality of groups of titles from 1 to C, where C is a number of titles ranked in the personalized ranking.

10. The method of claim 1, wherein titles in the plurality of groups of titles are movies.

11. One or more non-transitory computer-readable media storing instructions which, when executed by one or more computing devices, causes the one or more computing devices to perform the steps of:

selecting, from among a plurality of groups of titles, a group of titles to fill a row position of a plurality of row positions based at least in part on a relevance score computed for the group of titles, the relevance score based at least in part on a personalized ranking of titles in the plurality of groups of titles; and

causing the selected group of titles to be visibly presented in the row position as a recommendation.

12. The one or more non-transitory computer-readable media of claim 11, wherein the instructions, when executed by the one or more computing devices, further cause the one or more computing devices to perform the steps of:

selecting, from among the plurality of groups of titles, the group of titles to fill the row position of the plurality of row positions based at least in part on the relevance score computed for the group of titles, the relevance score based at least in part on the personalized ranking and an un-personalized ranking of titles in the plurality of groups of titles.

13. The one or more non-transitory computer-readable media of claim 11, wherein the instructions, when executed by the one or more computing devices, further cause the one or more computing devices to perform the steps of:

selecting, from among the plurality of groups of titles, the group of titles to fill the row position of the plurality of row positions based at least in part on the relevance score computed for the group of titles and a diversity score computed for the group of titles, the diversity score based at least in part on similarity between titles in the group of titles and titles in one or more groups of titles that have already been selected to fill one or more row positions of the plurality of row positions.

14. The one or more non-transitory computer-readable media of claim 11, wherein the instructions, when executed by the one or more computing devices, further cause the one or more computing devices to perform the steps of:

selecting, from among the plurality of groups of titles, the group of titles to fill the row position of the plurality of row positions based at least in part on the relevance score computed for the group of titles and a coverage score computed for the group of titles, the coverage score based at least in part on similarity between titles in the group of titles and titles in the plurality of groups of titles associated with a positive user interaction.

15. The one or more non-transitory computer-readable media of claim 11, wherein the instructions, when executed by the one or more computing devices, further cause the one or more computing devices to perform the steps of:

selecting, from among the plurality of groups of titles, the group of titles to fill the row position of the plurality of row positions based at least in part on the relevance score computed for the group of titles and a coverage score computed for the group of titles, the coverage score based at least in part on similarity between titles in the group of titles and titles in the plurality of groups of titles recently consumed.

16. The one or more non-transitory computer-readable media of claim 11, wherein the instructions, when executed by the one or more computing devices, further cause the one or more computing devices to perform the steps of:

selecting, from among the plurality of groups of titles, the group of titles to fill the row position of the plurality of row positions based at least in part on the relevance score computed for the group of titles and a coverage score computed for the group of titles, the coverage score based at least in part on similarity between titles in the group of titles and titles in the plurality of groups of titles associated with a positive user recommendation, rating, or like.

17. The one or more non-transitory computer-readable media of claim 11, wherein the instructions, when executed by the one or more computing devices, further cause the one or more computing devices to perform the steps of:

selecting, from among the plurality of groups of titles, the group of titles to fill the row position of the plurality of row positions based at least in part on the relevance score computed for the group of titles, a diversity score computed for the group of titles, and a coverage score computed for the group of titles, the diversity score based at least in part on similarity between titles in the group of titles and titles in one or more groups of titles that have already been selected to fill one or more of the plurality of row positions, the coverage score based at least in part on similarity between titles in the group of titles and titles in the plurality of groups of titles associated with a positive user interaction.

18. The one or more non-transitory computer-readable media of claim 11, wherein the row position corresponds to a position on a web page;

and wherein causing the selected group of titles to be visibly presented in the row position comprises causing the selected group of titles to be visibly presented at the web page position.

19. The one or more non-transitory computer-readable media of claim 11, wherein the personalized ranking comprises a ranking of titles in the plurality of groups of titles from 1 to C, where C is a number of titles ranked in the personalized ranking.

20. The one or more non-transitory computer-readable media of claim 11, wherein titles in the plurality of groups of titles are movies.

21. A system comprising:

one or more databases storing a plurality of groups of titles;

one or more computing devices of a row score cluster configured to select, from among the plurality of groups of titles, a group of titles to fill a row position of a plurality of row positions based at least in part on a relevance score computed for the group of titles, the relevance score based at least in part on a personalized ranking of titles in the plurality of groups of titles; and

one or more computing devices of a web cluster configured to cause the selected group of titles to be visibly presented in the row position as a recommendation.