Recommending candidates for consumption

• US 9,471,572 B1
• Filed: 12/31/2013
• Issued: 10/18/2016
• Est. Priority Date: 12/31/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Anderson, Ashton, Vassilvitskii, Sergei, Tomkins, Andrew, Ravikumar, Shanmugasundaram
• Primary Examiner(s): Choi, Yuk Ting
• Application Number:
  US14/145,383
• Time in Patent Office: 1,022 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 16/435 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06F 16/48 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually

Abstract

Methods and apparatus are described herein for recommending candidates for consumption. A first set of one or more candidates for first time consumption by a user and associated utility scores may be identified. A second set of one or more candidates for reconsumption by the user may be determined. Utility scores of the second set of one or more candidates for reconsumption may be determined based on consumption history of the user and aggregate consumption history of a population of users of which the user is associated. A candidate to be recommended to the user for consumption may be selected from the first or second set. The candidate may be selected based at least in part on the utility scores of the first and second sets.

Claims

1. A computer-implemented method, comprising:

identifying, by a computing system, a consumption category to be recommended to a user for consumption;

identifying, by the computing system, a first set of one or more candidates for first time consumption by a user and associated utility scores, wherein the one or more candidates for first time consumption share the consumption category;

determining, by the computing system, a second set of one or more candidates for reconsumption by the user, wherein the one or more candidates for reconsumption share the consumption category;

determining, by the computing system, utility scores of the second set of one or more candidates for reconsumption based on localities of the one or more candidates for reconsumption and aggregate consumption history of a population of users of which the user is associated; and

selecting, by the computing system, a candidate to be recommended to the user for consumption from the first or second set, the candidate selected based at least in part on the utility scores of the first and second sets;

wherein the locality of each of the one or more candidates for reconsumption is based on a number of consumption iterations in a sequence of consumption iterations by the user of items sharing the consumption category since the candidate was last consumed by the user, and wherein each consumption iteration in the sequence is weighted based on its position within the sequence.

2. The computer-implemented method of claim 1, further comprising determining, by the computing system, weights to assign to the past consumption iterations based at least in part on the consumption category.

3. The computer-implemented method of claim 2,

further comprising determining, by the computing system, the weights to assign to the past consumption iterations based at least in part on aggregate consumption history of the population of users of items having the consumption category.

4. The computer-implemented method of claim 2, further comprising determining, by the computing system, the weights to assign to the past consumption iterations based at least in part on consumption history of the user of items sharing the consumption category.

5. The computer-implemented method of claim 1, further comprising calculating, by the computing system, the utility scores associated with the one or more candidates for reconsumption based at least in part on reconsumability of the candidates for reconsumption.

6. The computer-implemented method of claim 5, further comprising determining, by the computing system, reconsumability of a candidate of the second set for reconsumption based on a popularity of the candidate among the population of users.

7. The computer-implemented method of claim 6, wherein reconsumability of the candidate of the second set for reconsumption is further based on a reconsumption rate of the candidate in relation to the popularity of the candidate.

8. A system comprising:

memory; and

one or more processors operably coupled to the memory and configured to execute instructions stored in the memory to perform the following operations;

identify a consumption category to be recommended to a user for consumption;

identify a first set of one or more candidates for first time consumption by a user and associated utility scores, wherein the one or more candidates for first time consumption share the consumption category;

determine a second set of one or more candidates for reconsumption by the user, wherein the one or more candidates for reconsumption share the consumption category;

determine utility scores of the second set of one or more candidates for reconsumption based on localities of the one or more candidates for reconsumption and aggregate consumption history of a population of users of which the user is associated; and

select a candidate to be recommended to the user for consumption from the first or second set, the candidate selected based at least in part on the utility scores of the first and second sets;

wherein the locality of each of the one or more candidates for reconsumption is based on a number of consumption iterations in a sequence of consumption iterations by the user of items sharing the consumption category since the candidate was last consumed by the user, and wherein each consumption iteration in the sequence is weighted based on its position within the sequence.

9. The system of claim 8, wherein the memory further stores instructions to determine weights to assign to the past consumption iterations based at least in part on the consumption category.

10. The system of claim 9, wherein the memory further stores instructions to determine the weights to assign to the past consumption iterations based at least in part on aggregate consumption history of the population of users of items having the consumption category.

11. The system of claim 9, wherein the memory further stores instructions to determine the weights to assign to the past consumption iterations based at least in part on consumption history of the user of items sharing the consumption category.

12. The system of claim 8, wherein the memory further stores instructions to calculate the utility scores associated with the one or more candidates for reconsumption based at least in part on reconsumability of the candidates for reconsumption.

13. A non-transitory computer readable storage medium storing computer instructions executable by a processor to perform a method comprising:

identifying a consumption category to be recommended to a user for consumption

identifying a first set of one or more candidates for first time consumption by a user and associated utility scores, wherein the one or more candidates for first time consumption share the consumption category;

determining a second set of one or more candidates for reconsumption by the user, wherein the one or more candidates for reconsumption share the consumption category;

determining utility scores of the second set of one or more candidates for reconsumption based on localities of the one or more candidates for reconsumption and aggregate consumption history of a population of users of which the user is associated; and

selecting a candidate to be recommended to the user for consumption from the first or second set, the candidate selected based at least in part on the utility scores of the first and second sets;

wherein the locality of each of the one or more candidates for reconsumption is based on a number of consumption iterations in a sequence of consumption iterations by the user of items sharing the consumption category since the candidate was last consumed by the user, and wherein each consumption iteration in the sequence is weighted based on its position within the sequence.