Personalized content recommendations based on consumption periodicity
Aspects described herein describe providing content recommendations such as, for example, recommendations for video content. A content recommendation may be based on when content was previously consumed.
1. A method comprising:
determining, by a computing device, a plurality of first past time periods relative to an output time associated with content for recommendation, wherein each of the plurality of first past time periods is a first time period multiple of a first time period;
determining a plurality of second past time periods relative to the output time associated with the content for recommendation, wherein each of the plurality of second past time periods is a second time period multiple of a second time period;
determining, based on an output history and based on the plurality of first past time periods and the plurality of second past time periods, one or more previously outputted content items;
generating, based on the one or more previously outputted content items, a recommendation that indicates content that is recommended for output; and
causing output of the recommendation.
2. The method of claim 1 , wherein the generating the recommendation is further based on a proximity of an output time of at least one of the previously outputted content items to a time corresponding to one of the plurality of first past time periods or corresponding to one of the plurality of second past time periods.
3. The method of claim 1 , wherein the generating the recommendation is further based on an amount of time between an output time of at least one of the previously outputted content items and the output time associated with the content for recommendation.
4. The method of claim 1 , wherein the second time period is a time period multiple of the first time period.
5. The method of claim 1 , wherein the first time period is 24 hours.
6. The method of claim 1 , wherein the second time period is 168 hours.
7. The method of claim 1 , wherein the first time period is 24 hours and the second time period is 168 hours.
8. The method of claim 1 , wherein the output time associated with the content for recommendation is associated with an output time of the content that is recommended for output.
9. The method of claim 8 , wherein the output time associated with the content for recommendation is associated with at least one of a scheduled broadcast time or a time at which output of the content item is requested.
10. The method of claim 1 , wherein the generating the recommendation is further based on at least one of a request for content or a request for a recommended content item.
11. The method of claim 1 , wherein the content item that is recommended for output is at least one of recorded content, on-demand content, or content that is scheduled for broadcast.
12. The method of claim 1 , wherein the generating the recommendation is further based on at least one of:
similarity between the content item and at least one of the one or more previously outputted content items;
popularity of the content item; or
a genre of the content item and a genre of at least one of the one or more previously outputted content items.
13. The method of claim 1 , wherein the first time period multiple of the first time period is a number of days prior to the recommended content output time.
14. The method of claim 1 , wherein the second time period multiple of the second time period is a number of weeks prior to the recommended content output time.
15. The method of claim 1 , wherein the one or more previously outputted content items comprise one or more previously outputted content items that were output at an output time within a threshold distance of a time associated with at least one of the plurality of first past time periods or with at least one of the plurality of second past time periods.
16. A method comprising:
determining, by a computing device and based on an output history, one or more previously outputted content items;
determining, based on the output history, proximity information that indicates, for each previously outputted content item of the one or more previously outputted content items, proximity of an output time of the previously outputted content item to:
a first past time, relative to an output time associated with content for recommendation, corresponding to a first time period multiple of a first time period; and
a second past time, relative to the output time associated with the content for recommendation, corresponding to a second time period multiple of a second time period;
generating, based on the proximity information, a recommendation that indicates content that is recommended for output; and
causing output of the recommendation.
17. The method of claim 16 , wherein the second time period is a time period multiple of the first time period.
18. The method of claim 16 , wherein the first time period is 24 hours and the second time period is 168 hours.
19. The method of claim 16 , wherein the first time period multiple of the first time period is a number of days prior to the output time associated with the content for recommendation and the second time period multiple of the second time period is a number of weeks prior to the output time associated with the content for recommendation.
20. The method of claim 16 , wherein the generating the recommendation is further based on at least one of a request for content or a request for a recommended content item.
21. The method of claim 16 , wherein the content that is recommended for output is at least one of recorded content, on-demand content, or content that is scheduled for broadcast.
22. The method of claim 16 , wherein the generating the recommendation is further based on at least one of:
similarity between the content item and at least one of the one or more previously outputted content items;
popularity of the content item; or
a genre of the content item and a genre of at least one of the one or more previously outputted content items.
23. The method of claim 16 , wherein the one or more previously outputted content items comprise one or more previously outputted content items that were output at an output time within a threshold distance of a time associated with at least one of the first past time or the second past time.
24. A device comprising:
one or more processors; and
memory storing instructions that, when executed by the one or more processors, cause the device to:
determine a plurality of first past time periods relative to an output time associated with content for recommendation, wherein each of the plurality of first past time periods is a first time period multiple of a first time period;
determine a plurality of second past time periods relative to the output time associated with the content for recommendation, wherein each of the plurality of second past time periods is a second time period multiple of a second time period;
determine, based on an output history and based on the plurality of first past time periods and the plurality of second past time periods, one or more previously outputted content items;
generate, based on the one or more previously outputted content items, a recommendation that indicates content that is recommended for output; and
cause output of the recommendation.
25. The device of claim 24 , wherein the instructions, when executed by the one or more processors, further cause the device to generate the recommendation further based on a proximity of an output time of at least one of the previously outputted content items to a time corresponding to one of the plurality of first past time periods or corresponding to one of the plurality of second past time periods.
26. The device of claim 24 , wherein the instructions, when executed by the one or more processors, further cause the device to generate the recommendation further based on an amount of time between an output time of at least one of the previously outputted content items and the output time associated with the content for recommendation.
27. The device of claim 24 , wherein the second time period is a time period multiple of the first time period.
28. The device of claim 24 , wherein the first time period is 24 hours.
29. The device of claim 24 , wherein the second time period is 168 hours.
30. The device of claim 24 , wherein the first time period is 24 hours and the second time period is 168 hours.
31. The device of claim 24 , wherein the output time associated with the content for recommendation is associated with an output time of the content that is recommended for output.
32. The device of claim 31 , wherein the output time associated with the content for recommendation is associated with at least one of a scheduled broadcast time or a time at which output of the content item is requested.
33. The device of claim 24 , wherein the instructions, when executed by the one or more processors, cause the device to generate the recommendation further based on at least one of a request for content or a request for a recommended content item.
34. The device of claim 24 , wherein the content that is recommended for output is at least one of recorded content, on-demand content, content that is scheduled for broadcast.
35. The device of claim 24 , wherein the instructions, when executed by the one or more processors, cause the device to generate the recommendation further based on at least one of:
similarity between the content item and at least one of the one or more previously outputted content items;
popularity of the content item; or
a genre of the content item and a genre of at least one of the one or more previously outputted content items.
36. The device of claim 24 , wherein the first time period multiple of the first time period is a number of days prior to the recommended content output time.
37. The device of claim 24 , wherein the second time period multiple of the second time period is a number of weeks prior to the recommended content output time.
38. The device of claim 24 , wherein the one or more previously outputted content items comprise one or more previously outputted content items that were output at an output time within a threshold distance of a time associated with at least one of the plurality of first past time periods or with at least one of the plurality of second past time periods.
39. A device comprising:
one or more processors; and
memory storing instructions that, when executed, cause the device to:
determine based on an output history, one or more previously outputted content items;
determine, based on the output history, proximity information that indicates, for each previously outputted content item of the one or more previously outputted content items, proximity of an output time of the previously outputted content item to:
a first past time, a first past time, relative to an output time associated with content for recommendation, wherein the first past time corresponds to a first time period multiple of a first time period; and
a second past time, relative to the output time associated with the content for recommendation, wherein the second past time corresponds to a second time period multiple of a second time period;
generate, based on the proximity information, a recommendation that indicates content that is recommended for output; and
cause output of the recommendation.
40. The device of claim 39 , wherein the second time period is a time period multiple of the first time period.
41. The device of claim 39 , wherein the first time period is 24 hours and the second time period is 168 hours.
42. The device of claim 39 , wherein the first time period multiple of the first time period is a number of days prior to the output time associated with the content for recommendation and the second time period multiple of the second time period is a number of weeks prior to the output time associated with the content for recommendation.
43. The device of claim 39 , wherein the instructions, when executed, cause the device to generate the recommendation further based on at least one of a request for content or a request for a recommended content item.
44. The device of claim 39 , wherein the content that is recommended for output is at least one of recorded content, on-demand content, content that is scheduled for broadcast.
45. The device of claim 39 , wherein the instructions, when executed, cause the device to generate the recommendation further based on at least one of:
similarity between the content item and at least one of the one or more previously outputted content items;
popularity of the content item; or
a genre of the content item and a genre of at least one of the one or more previously outputted content items.
46. The device of claim 39 , wherein the one or more previously outputted content items comprise one or more previously outputted content items that were output at an output time within a threshold distance of a time associated with at least one of the first past time or the second past time.