Personalized recommendations based on related users

• US 8,468,164 B1
• Filed: 03/09/2011
• Issued: 06/18/2013
• Est. Priority Date: 03/09/2011
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Paleja, Ameesh, Okereke, Mekka C., Jones, Matthew A.
• Primary Examiner(s): Corrielus, Jean M
• Assistant Examiner(s): Ly, Anh
• Application Number:
  US13/044,235
• Time in Patent Office: 832 Days
• Field of Search: 707/767, 707/723, 707/735, 707/748, 707/732, 707/E17.109, 707/E17.046, 707/805, 705/26.7, 705/26.5, 705/26, 705/61, 705/26.63, 705/347, 705/14, 705/67, 705/27.2, 705/29, 705/27
• US Class Current: 707/767
• CPC Class Codes: G06F 16/24 Querying
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 30/0635 Processing of requisition or of purchase orders
• CPC Class Codes: H04L 67/1097 for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]

Abstract

This disclosure describes systems and associated processes for generating recommendations for users based on usage, among other things. These systems and processes are described in the context of an interactive computing system that enables users to download applications for mobile devices (such as phones) or for other computing devices. Users'"'"' interactions with applications once they are downloaded can be observed and tracked, with such usage data being collected and provided to the interactive computing system. The interactive computing system can include a recommendation system or service that processes the usage data from a plurality of users to detect usage patterns. Using these usage patterns, among possibly other data, such as data about related users'"'"' applications, the recommendation system can recommend applications to users for download.

Claims

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

selecting a target user of an application distribution system for which to generate recommendations;

identifying one or more related users of the target user;

identifying first applications accessed by installed on first devices of the one or more related users;

identifying usage characteristics of the first applications, the one or more usage characteristics reflecting usage of the first applications subsequent to installation of the first applications on the first devices by the one or more related users, wherein the usage characteristics comprise the following;

a frequency of usage associated with the first applications, a time of usage associated with the first applications, and a location of usage associated with the first applications; and

selecting one or more second applications as recommendations for the target user based at least partly on the usage characteristics, said selecting comprising selecting one or more related applications that have usage associations with the first applications, and wherein said selecting the one or more second applications comprises selecting a most highly-ranked subset of the first applications based at least in part on the usage characteristics;

wherein at least said selecting is implemented by one or more processors.

2. The method of claim 1, wherein said selecting the one or more second applications further comprises selecting one or more related applications that have item-to-item associations with the first applications.

3. The method of claim 1, wherein said identifying the first applications accessed by the one or more related users comprises identifying which applications the one or more related users downloaded from the application distribution system.

4. The method of claim 1, wherein the one or more second applications comprise at least some of the first applications.

5. The method of claim 1, wherein said identifying the one or more related users comprises identifying a list of social networking friends or acquaintances of the target user.

6. The method of claim 1, wherein the method is configured to be implemented by the one or more processors.

7. A Non-transitory physical computer storage comprising computer-executable instructions configured to implement a method of recommending computer applications, the method comprising:

selecting a target user of an application distribution system for which to generate recommendations;

identifying one or more related users of the target user;

identifying first applications accessed by installed on first devices of the one or more related users;

identifying usage characteristics of the first applications, the one or more usage characteristics reflecting usage of the first applications subsequent to installation of the first applications on the first devices by the one or more related users, wherein the usage characteristics comprise the following;

a frequency of usage associated with the first applications, a time of usage associated with the first applications, and a location of usage associated with the first applications; and

selecting one or more second applications as recommendations for the target user based at least partly on the identified first applications, said selecting comprising selecting one or more related applications that have usage associations with the first applications, and wherein said selecting the one or more second applications comprises selecting a most highly-ranked subset of the first applications based at least in part on the usage characteristics.

8. The non-transitory physical computer storage of claim 7, wherein said selecting the one or more second applications comprises selecting one or more of the first applications as the recommendations.

9. The non-transitory physical computer storage of claim 8, wherein said selecting comprises selecting an intersection of most popular ones of the first applications among the related users.

10. The non-transitory physical computer storage of claim 7, wherein the method further comprises identifying an achievement associated with the first applications.

11. The non-transitory physical computer storage of claim 10, wherein the achievement comprises a game score achievement.

12. The non-transitory physical computer storage of claim 11, wherein said selecting comprises selecting one of more of the first applications associated with the achievement.

13. A system for recommending computer applications, the system comprising:

an application distribution service configured to provide applications for download by a plurality of user computing systems; and

a recommendation service comprising computer hardware configured to implement a social recommender, the social recommender configured to;

select a target user of an application distribution system for which to generate recommendations;

identify one or more related users of the target user;

identify first applications accessed by installed on first devices of the one or more related users;

identify usage characteristics of the first applications, the usage characteristics reflecting usage of the first applications subsequent to installation of the first applications on the first devices by the one or more related users; and

select one or more second applications as recommendations for the target user based at least partly on usage characteristics, by at least selecting one or more related applications that have usage associations with the first applications, wherein the social recommender is further configured to select the one or more second applications by at least selecting a most highly-ranked subset of the first applications based at least in part on the usage characteristics.

14. The system of claim 13, wherein the one or more second applications comprise a subset of the first applications.