System, methods and computer products for determining affinity to a content creator

• US 9,798,823 B2
• Filed: 11/17/2015
• Issued: 10/24/2017
• Est. Priority Date: 11/17/2015
• Status: Active Grant

• Current Assignee: Spotify AB (Spotify Technology SA)
• Original Assignee: Spotify AB (Spotify Technology SA)
• Inventors: Cody, Noel, Mishra, Kinshuk, Shirley, Steve
• Primary Examiner(s): Bullock, Joshua
• Application Number:
  US14/943,995
• Publication Number:
  US 20170140060A1
• Time in Patent Office: 707 Days
• Field of Search: 707758
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/955 using information identifiers, e.g. uniform resource locators [URL]

Abstract

Affinity scores are computed for a plurality of user accounts, each affinity score quantifies an affinity of a user account to a content creator of one or more digital objects hosted in a content hosting platform. Each affinity score is computed by collecting interaction data for the user account corresponding to the content creator, normalizing the collected interaction data using a total activity data of the user account on the content hosting platform and attribute data associated with the content creator, and generating the affinity score using the normalized interaction data.

Claims

1. A computer-implemented method, comprising the steps of:

computing, by a processing device, affinity scores for a plurality of user accounts, each affinity score quantifying affinity of a user account to one of a plurality of content creators of one or more digital objects hosted in a content hosting platform, wherein computing an affinity score corresponding to the user account includes;

collecting, from a client device communicatively coupled to the content hosting platform, interaction data identifying activity of a user associated with the user account corresponding at least to a content creator of one or more digital objects hosted in the content hosting platform,

collecting, from a plurality of data sources, attribute data associated with the content creator including at least cultural data,

associating activities of the user account on the content hosting platform with weights based on a type of the respective activity, wherein a weight of a first type of activity is different from a weight of a second type of activity;

normalizing the interaction data based on the activity of the user account on the content hosting platform, the attribute data associated with the content creator, and the weights associated by the associating, and

generating the affinity score using the normalized interaction data;

storing, in a database, the affinity scores; and

sending, to a device associated with one of the plurality of user accounts, targeted data based on the affinity score of the respective user account with one of the plurality of content creators.

2. The method according to claim 1, wherein the step of normalizing the collected interaction data further includes normalizing the collected interaction data using activity data of one or more other user accounts.

3. The method according to claim 1 further including a step of generating a ranking of the stored affinity score against affinity scores of one or more other user accounts corresponding to the content creator.

4. The method according to claim 3 further including a step of categorizing the user account into one or more groups using the affinity score or the ranking generated for the affinity score.

5. The method according to claim 4, wherein one of the one or more groups includes only user accounts having affinity scores that increased at least a threshold amount over a time period.

6. The method according to claim 1 further including a step of periodically updating the affinity score using a most recent activity data of the user account corresponding to the content creator.

7. The method according to claim 1, wherein at least a portion of the total activity data for the user account is collected from at least one data source external to the content hosting platform.

8. A device configured to determining affinity of a user account to a content creator, the device comprising:

a computing unit, including a processor, configured to compute affinity scores for a plurality of user accounts, each affinity score quantifying affinity of a user account to one of a plurality of content creators of one or more digital objects hosted in a content hosting platform, wherein the computing unit further includes;

a collection unit configured to collect;

from a client device communicatively coupled to the content hosting platform, interaction data identifying activity of a user associated with the user account corresponding at least to a content creator of one or more digital objects hosted in the content hosting platform; and

from a plurality of data sources, attribute data associated with the content creator including at least cultural data,

a normalization unit configured to (1) associate activities of the user account on the content hosting platform with weights based on a type of the respective activity, wherein a weight of a first type of activity is different from a weight of a second type of activity, and (2) normalize the collected interaction data using a total activity data of the user account on the content hosting platform attribute data associated with the content creator, and the associated weights, and

a score generation unit configured to generate the affinity score using the normalized interaction data, wherein

the computing unit is further configured to store the affinity scores in a database, and to send, to a device associated with one of the plurality of user accounts, targeted data based on the affinity score of the respective user account with one of the plurality of content creators.

9. The device according to claim 8, wherein the normalization unit is further configured to normalize the collected interaction data using activity data of one or more other user accounts.

10. The device according to claim 8 further including a ranking unit configured to rank the affinity score against affinity scores of one or more other user accounts corresponding to the content creator.

11. The device according to claim 10 further including a categorization unit configured to categorize the user account into one or more groups using the ranking of the affinity score produced by the ranking unit.

12. The device according to claim 11, wherein one of the one or more groups includes only user accounts having affinity scores that increased at least a threshold amount over a time period.

13. The device according to claim 8, wherein the computing unit is further configured to update the affinity score periodically using a most recent activity data of the user account corresponding to the content creator.

14. The device according to claim 8, wherein the collection unit is configured to collect at least a portion of the total activity data for the user account from at least one data source external to the content hosting platform.

15. A non-transitory computer-readable medium having instructions stored therein that in response to execution by a device cause the device to perform operations comprising:

computing affinity scores for a plurality of user accounts, each affinity score quantifying affinity of a user account to one of a plurality of content creators of one or more digital objects hosted in a content hosting platform, wherein computing an affinity score corresponding to the user account includes;

collecting, from a client device communicatively coupled to the content hosting platform, interaction data identifying activity of a user associated with the user account corresponding to a content creator of one or more digital objects hosted in the content hosting platform,

collecting, from a plurality of data sources, attribute data associated with the content creator including at least cultural data,

associating activities of the user account on the content hosting platform with weights based on a type of the respective activity, wherein a weight of a first type of activity is different from a weight of a second type of activity;

normalizing the interaction data based on the activity of the user account on the content hosting platform, the attribute data associated with the content creator, and the weights associated by the associating, and

generating the affinity score using the normalized interaction data;

storing, in a database, the affinity scores; and

sending, to a device associated with one of the plurality of user accounts, targeted data based on the affinity score of the respective user account with one of the plurality of content creators.

16. The non-transitory computer-readable medium of claim 15, wherein the operation step of normalizing the collected interaction data further includes normalizing the collected interaction data using activity data of one or more other user accounts.

17. The non-transitory computer-readable medium of claim 15, wherein the operations further include a step of ranking the affinity score against affinity scores of one or more other user accounts corresponding to the content creator.

18. The non-transitory computer-readable medium of claim 17, wherein the operations further include a step of categorizing the user account into one or more groups using the step of ranking the affinity score among affinity scores of one or more other user accounts corresponding to the content creator.

19. The non-transitory computer-readable medium of claim 18, wherein one of the one or more groups includes only user accounts having affinity scores that increased at least a threshold amount over a time period.

20. The non-transitory computer-readable medium of claim 15, wherein the operations further include a step of periodically updating the affinity score using a most recent activity data of the user account corresponding to the content creator.

21. The non-transitory computer-readable medium of claim 15, wherein at least a portion of the total activity data for the user account is collected from at least one data source external to the content hosting platform.