Adaptive music and video recommendations

• US 9,619,470 B2
• Filed: 02/04/2014
• Issued: 04/11/2017
• Est. Priority Date: 02/04/2014
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Ross, David Alexander, Althoff, Christopher Tim, Ning, Huazhong, Tarifi, Mohamad, Eck, Douglas
• Primary Examiner(s): Beausoliel, Jr., Robert
• Assistant Examiner(s): Santos, Pedro J
• Application Number:
  US14/172,770
• Publication Number:
  US 20150220525A1
• Time in Patent Office: 1,162 Days
• Field of Search: 707E17009, 707722, 707751, 707737, 707736, 707740
• CPC Class Codes: G06F 16/00 Information retrieval; Database structures therefor; File system structures therefor
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/435 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06F 16/4387 by the use of playlists
• CPC Class Codes: G06F 16/48 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually

Abstract

A user feedback module, executable by a processing device from memory is disclosed. The user feedback module receives from a user device a selection of a seed media item. The seed media item includes a seed label. The user feedback module further generates a list, the list includes the seed label and a set of related labels based on the seed label. The seed label and each related label include a separate label weight. The user feedback module also identifies multiple media items associated with an associate label. The associate label includes at least one of the seed label or a related label of the first set of related labels. The user feedback module also transmits to the user device a first media item from the multiple media items. The user feedback module adjusts the label weight of the associate label based on a user feedback on the first media item.

Claims

1. A method comprising:

receiving, from a user device, a selection of a seed media item that is associated with a seed label;

generating a list comprising the seed label and a first set of related labels based on the seed label, the seed label and the first set of related labels comprising a separate label weight, wherein the first set of related labels are categories related to the seed label;

identifying a first plurality of media items associated with a related label of the first set of related labels;

transmitting to the user device a first media item of the first plurality of media items associated with the related label;

adjusting the label weight of the related label associated with the first media item based on a user feedback on the first media item;

identifying an additional label based on the adjusted label weight of the related label, wherein the additional label is a category related to the related label; and

updating the list to contain the additional label, wherein a second media item of a second plurality of media items associated with the additional label is selected for transmission to the user device based on the updated list.

2. The method of claim 1, further comprising:

identifying the additional label in response to the adjusted label weight of the related label exceeding a first threshold value.

3. The method of claim 1, further comprising:

calculating a cumulative weight of the separate label weights of the list;

comparing the cumulative weight of the separate label weights of the list to a second threshold value; and

replacing one or more related labels of the first set of related labels of the list with a second set of related labels when the cumulative weight is under the second threshold value, the second set of related labels based on the seed label.

4. The method of claim 1, further comprising:

assigning a media weight to each of the first plurality of media items associated with the related label.

5. The method of claim 4, wherein transmitting the first media item to the user device is based on the media weight of each of the first plurality of media items.

6. The method of claim 4, further comprising:

calculating a full-rank weight for each of the first plurality of media items associated with the related label, the full-rank weight comprising a combination of the label weight of the related label and the media weight of a media item of the first plurality of media items.

7. The method of claim 1, wherein the user feedback comprises an explicit user feedback, the explicit user feedback comprising at least one of a like action, a dislike action, a comment, removal action, or a sharing action.

8. The method of claim 1, wherein the user feedback comprises an implicit user feedback, the implicit user feedback comprising at least one of a long watch action or a skip action.

9. The method of claim 1, wherein the label weight of the related label is adjusted based on a temporal relation to the user feedback.

10. The method of claim 1, wherein the seed label and each related label of the first set of related labels comprise an artist identifier and each of the first plurality of media items associated with the related label comprise a video identifier.

11. A non-transitory machine-readable storage medium storing instructions that, when executed by a processing device, cause the processing device to perform operations comprising:

receiving, from a user device, a selection of a seed media item that is associated with a seed label;

generating, by the processing device, a list comprising the seed label and a first set of related labels based on the seed label, the seed label and the first set of related labels comprising a separate label weight, wherein the first set of related labels are categories related to the seed label;

identifying a first plurality of media items associated with a related label of the first set of related labels;

transmitting to the user device a first media item of the first plurality of media items associated with the related label;

adjusting the label weight of the related label associated with the first media item based on a user feedback on the first media item;

identifying an additional label based on the adjusted label weight of the related label, wherein the additional label is a category related to the related label; and

updating the list to contain the additional label, wherein a second media item of a second plurality of media items associated with the additional label is selected for transmission to the user device based on the updated list.

12. A non-transitory machine-readable storage medium of claim 11, the operations further comprising:

identifying the additional label in response to the adjusted label weight of the related label exceeding a first threshold value.

13. A non-transitory machine-readable storage medium of claim 11, the operations further comprising:

calculating a cumulative weight of the separate label weights of the list;

comparing the cumulative weight of the separate label weights of the list to a second threshold value; and

replacing one or more related labels of the first set of related labels of the list with a second set of related labels when the cumulative weight is under the second threshold value, the second set of related labels based on the seed label.

14. A non-transitory machine-readable storage medium of claim 11, the operations further comprising:

assigning a media weight to each of the first plurality of media items associated with the related label.

15. A non-transitory machine-readable storage medium of claim 14, wherein transmitting the first media item to the user device is based on the media weight of each of the first plurality of media items.

16. A non-transitory machine-readable storage medium of claim 14, the operations further comprising:

calculating a full-rank weight for each of the first plurality of media items associated with the related label, the full-rank weight comprising a combination of the label weight of the related label and the media weight of a media item of the first plurality of media items.

17. A non-transitory machine-readable storage medium of claim 11, wherein the user feedback comprises an explicit user feedback, the explicit user feedback comprising at least one of a like action, a dislike action, a comment, removal action, or a sharing action.

18. A non-transitory machine-readable storage medium of claim 11, wherein the user feedback comprises an implicit user feedback, the implicit user feedback comprising at least one of a long watch action or a skip action.

19. A non-transitory machine-readable storage medium of claim 11, wherein the label weight of the related label is adjusted based on a temporal relation to the user feedback.

20. A non-transitory machine-readable storage medium of claim 11, wherein the seed label and each related label of the first set of related labels comprise an artist identifier and each of the first plurality of media items associated with the related label comprise a video identifier.

21. A server computer system comprising:

a memory; and

a processing device, operatively coupled to the memory, to;

receive, from a user device, a selection of a seed media item that is associated with a seed label;

generate a list comprising the seed label and a first set of related labels based on the seed label, the seed label and the first set of related labels comprising a separate label weight, wherein the first set of related labels are categories related to the seed label;

identify a first plurality of media items associated with a related label of the first set of related labels;

transmit to the user device a first media item of the first plurality of media items associated with the related label;

adjust the label weight of the related label associated with the first media item based on a user feedback on the first media item;

identify an additional label based on the adjusted label weight of the related label, wherein the additional label is a category related to the related label; and

update the list to contain the additional label, wherein a second media item of a second plurality of media items associated with the additional label is selected for transmission to the user device based on the updated list.

22. The server computer system of claim 21, the processing device further to:

identify the additional label in response to the adjusted label weight of the associate label exceeding a first threshold value.

23. The server computer system of claim 21, the processing device further to:

calculate a cumulative weight of the separate label weights of the list;

compare the cumulative weight of the separate label weights of the list to a second threshold value; and

replace one or more related labels of the first set of related labels of the list with a second set of related labels when the cumulative weight is under the second threshold value, the second set of related labels based on the seed label.

24. The server computer system of claim 21, the processing device further to:

assign a media weight to each of the first plurality of media items associated with the related label.

25. The server computer system of claim 24, wherein to transmit the first media item to the user device is based on the media weight of each of the first plurality of media items.

26. The server computer system of claim 24, the processing device further to:

calculate a full-rank weight for each of the first plurality of media items associated with the related label, the full-rank weight comprising a combination of the label weight of the related label and the media weight of a media item of the first plurality of media items.

27. The server computer system of claim 21, wherein the user feedback comprises an explicit user feedback, the explicit user feedback comprising at least one of a like action, a dislike action, a comment, removal action, or a sharing action.

28. The server computer system of claim 21, wherein the user feedback comprises an implicit user feedback, the implicit user feedback comprising at least one of a long watch action or a skip action.

29. The server computer system of claim 21, the processing device further to:

adjust the label weight of the related label based on a temporal relation to the user feedback.

30. The server computer system of claim 21, wherein the seed label and each related label of the first set of related labels comprise an artist identifier and each of the first plurality of media items associated with related label comprise a video identifier.