Application recommendations based on application and lifestyle fingerprinting

• US 9,262,470 B1
• Filed: 06/25/2013
• Issued: 02/16/2016
• Est. Priority Date: 06/25/2013
• Status: Expired due to Fees

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Evans, Ethan Zane, Adkins, James Newton III, Markley, David Allen
• Primary Examiner(s): NGUYEN, CAM LINH T
• Application Number:
  US13/926,574
• Time in Patent Office: 966 Days
• Field of Search: 707/736, 707/749, 707/767
• US Class Current: 1/1
• CPC Class Codes: G06F 16/24 Querying
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/288 Entity relationship models
• CPC Class Codes: G06F 16/738 Presentation of query results
• CPC Class Codes: G06F 16/90324 using system suggestions
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 30/0255 based on user history
• CPC Class Codes: G06Q 30/0272 Period of advertisement exposure

Abstract

Disclosed are various embodiments that employ application fingerprinting and lifestyle fingerprinting. Application fingerprints are received, where each application fingerprints is associated with a corresponding application and is generated based at least in part on a static analysis, a dynamic analysis, and a behavioral analysis of the corresponding application. A selection of an application is received. Applications that are similar to the selected application are determined by comparing a particular application fingerprint that is associated with the selected application with other application fingerprints. Users are determined based at least in part on lifestyle fingerprints. In one embodiment, such users may be invited to test the selected application.

Claims

1. A method comprising:

receiving, via at least one computing device, a plurality of application fingerprints, individual ones of the plurality of application fingerprints being associated with a corresponding one of a plurality of applications, the individual ones of the plurality of application fingerprints being generated based at least in part on a static analysis, a dynamic analysis, and a behavioral analysis of the corresponding one of the applications;

receiving, via the at least one computing device, a selection of a particular one of the plurality of applications;

identifying, via the at least one computing device, a subset of the plurality of applications that are similar to the particular one of the plurality of applications based at least in part on the plurality of application fingerprints;

receiving, via the at least one computing device, an identification of a particular user;

determining, via the at least one computing device, a plurality of users who are similar to the particular user based at least in part on lifestyle fingerprint data for the plurality of users and the particular user; and

generating, via the at least one computing device, a recommendation of the particular one of the plurality of applications for the particular user based at least in part on usage data associated with usage of the subset of the plurality of applications by the plurality of users.

2. The method of claim 1, further comprising implementing, via the at least one computing device, the recommendation by sending a notification that promotes the particular one of the plurality of applications to the particular user.

3. A system, comprising:

at least one computing device; and

at least one service executable in the at least one computing device, the at least one service configured to at least;

determine an application fingerprint for individual ones of a plurality of applications, a respective application fingerprint being generated based at least in part on a static analysis, a dynamic analysis, and a behavioral analysis, and being indicative of one or more features of an application;

determine a lifestyle fingerprint for individual ones of a plurality of users, a respective lifestyle fingerprint being indicative of one or more preferences of a user; and

correlate the lifestyle fingerprint of the user with the application based at least in part on the application fingerprint.

4. The system of claim 3, wherein the lifestyle fingerprint is based at least in part on application usage data, application download data, purchase data, and a device profile.

5. The system of claim 3, wherein the application fingerprint indicates a set of code fragments employed by the application and a set of device resources employed by the application.

6. The system of claim 3, wherein the correlation is determined based at least in part on the application indicating one or more code fragments indicative of code that matches the one or more preferences of the user.

7. The system of claim 3, wherein the at least one service is further configured to at least recommend the application to the user.

8. The system of claim 3, wherein the at least one service is further configured to at least generate a pricing model recommendation for the application based at least in part on the lifestyle fingerprint and the application fingerprint.

9. The system of claim 3, wherein the at least one service is further configured to at least send data to a client computing device associated with the user, the data configured to include one or more of, an upgrade to the application, an advertisement, or an in-application item.

10. The system of claim 3, wherein the at least one service is further configured to at least send data to a developer, the data configured to include a recommended change to the application.

11. The system of claim 3, wherein the lifestyle fingerprint indicates a willingness of the user to initiate a purchase transaction during application use.

12. The system of claim 3, wherein the lifestyle fingerprint indicates whether the user has a preference for free application trials.

13. The system of claim 3, wherein the lifestyle fingerprint indicates whether the user is likely to purchase the application irrespective of price.

14. A method, comprising:

receiving, by at least one computing device, a plurality of application fingerprints, individual ones of the plurality of application fingerprints being associated with corresponding ones of a plurality of applications, the individual ones of the plurality of application fingerprints being generated based at least in part on a static analysis, a dynamic analysis, and a behavioral analysis of the corresponding ones of the plurality of applications;

receiving, by the at least one computing device, a selection of one of the plurality of applications;

determining, by the at least one computing device, a subset of the plurality of applications that are similar to the one of the plurality of applications by comparing a particular one of the plurality of application fingerprints that is associated with the selected one of the plurality of applications with others of the plurality of application fingerprints;

identifying, by the at least one computing device, a subset of a plurality of users based at least in part on lifestyle fingerprints of the subset of the plurality of users that indicate a preference for at least one application from the subset of the plurality of applications; and

sending, by the at least one computing device, an invitation to test the selected one of the plurality of applications to individual ones of the subset of the plurality of users.

15. The method of claim 14, wherein the lifestyle fingerprints indicate prior usage of the at least one application from the subset of the plurality of applications by the subset of the plurality of users.

16. The method of claim 14, wherein the subset of the plurality of users are identified based at least in part on data indicating prior purchases of the at least one application from the subset of the plurality of applications by the subset of the plurality of users.

17. The method of claim 14, wherein the subset of the plurality of users are identified based at least in part on user demographic data.

18. The method of claim 14, wherein the subset of the plurality of users are identified based at least in part on a characteristic associated with a developer of the selected one of the plurality of applications.

19. The method of claim 14, wherein the dynamic analysis of an application of the plurality of applications comprises an analysis of resource consumption of a client computing device during execution of an instance of the application and a delivery of a report on the resource consumption by the instance of the application.

20. The method of claim 19, wherein the behavioral analysis of an application of the plurality of applications comprises an analysis of usage of an instance of the application, wherein the analysis considers at least one of a location of the client computing device during execution of the instance of the application, a duration of use for the instance of the application, and a time of day that the instance of the application is executed.