APPLICATION RECOMMENDATION SYSTEM

• US 20130185292A1
• Filed: 01/04/2013
• Published: 07/18/2013
• Est. Priority Date: 01/04/2012
• Status: Active Grant

• Current Assignee: Baidu Online Network Technology (Beijing) Co., Ltd (Baidu Incorporated)
• Original Assignee: TrustGo Mobile, Inc. (Baidu Incorporated)
• Inventors: Li, Xuyang, Bao, Chenfu, Li, Shiyong
• Granted Patent: US 9,213,729 B2
• Time in Patent Office: Days
• US Class Current: 707/723
• CPC Class Codes: G06F 16/22 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/2457 with adaptation to user needs
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 21/562 Static detection
• CPC Class Codes: G06F 21/577 Assessing vulnerabilities and evaluating computer system security
• CPC Class Codes: G06Q 30/0282 Rating or review of business operators or products

Abstract

Systems and method for receiving mobile device usage data from mobile electronic devices using security applications with enhanced access privileges. The mobile device usage data includes user-specific and application usage data. Application classification databases are searched for application characteristics of applications available for download from multiple marketplaces. Using the application characteristics, a weighted application relationship graph that includes relationship scores for application pairs that describe the degree to which applications in each of the application pairs are related to, is generated. Based on the mobile device usage and the relationship scores, a list of recommended applications can be generated for a particular user. The list of recommended applications includes the applications determined to be associated with at least one of the applications installed on the user'"'"'s mobile device with a relationship score greater than a threshold. The method then sends the list of recommended applications to the user'"'"'s mobile device.

Claims

1. A method comprising:

receiving, by a computer system, mobile device usage data from a plurality of mobile electronic devices, wherein the mobile device usage data is gathered by security applications with enhanced access privileges executed on the mobile devices and comprises user-specific information for users associated with the plurality of mobile electronic devices and application usage data associated with a plurality of installed applications installed on the plurality of mobile electronic devices;

searching, by the computer system, an application classification database for a plurality of application characteristics associated with a plurality of applications, wherein the plurality of applications comprises the plurality of installed applications, and wherein each of the plurality of applications is available for download from at least one of a plurality of application marketplaces;

determining, by the computer system, a weighted application relationship graph, wherein the weighted application relationship graph comprises a plurality of relationship scores for a plurality of application pairs in the plurality of applications that describe the degree to which applications in each of the plurality of application pairs are related based on the plurality of application characteristics associated with the plurality of applications;

determining, by the computer system, a list of recommended applications for a user in the plurality of users based on a first mobile device usage data from a first mobile device associated with the user and the plurality of relationship scores, wherein the list of recommended applications comprises a portion of the plurality of applications determined to be paired with at least one of a plurality of installed applications installed on the first mobile device and associated with a relationship score greater than a threshold score; and

sending, by the computer system, the list of recommended applications to the first mobile device.

2. The method of claim 1, wherein the plurality of application characteristics comprise a plurality of category identifiers that categorize the plurality of applications by type, and wherein a portion of the plurality of relationships scores are higher for application pairs in the plurality of application pairs that include applications determined to have matching category identifiers.

3. The method of claim 1, wherein the plurality of application characteristics comprise a plurality of user generated tags, and wherein the plurality of user generated tags comprise user generated keywords or descriptions for each of the plurality of applications, wherein a portion of the plurality of relationships scores are higher for application pairs in the plurality of application pairs that include applications determined to have matching user generated tags.

4. The method of claim 1, wherein determining the list of recommended applications comprises:

determining, by the computer system, a plurality of frequently used applications based on a first application usage data from the first mobile device associated with the user; and

searching, by the computer system, the weighted application relationship graph for a plurality of applications determined to be paired with the plurality of frequently used applications.

5. The method of claim 4, wherein searching the weighted application relationship graph comprises comparing, by the computer system, a first plurality of relationship scores associated with the plurality of frequently used applications in the weighted application relationship graph with a threshold score value.

6. The method of claim 1, wherein determining the list of recommended applications comprises:

determining, by the computer system, a user search behavior data based on a first application usage data from the first mobile device usage data, wherein the user search behavior data comprises;

a plurality of search keywords used by the user in a in plurality of previously conducted searches; and

a plurality of associated search frequencies associated with the plurality of search keywords;

comparing, by the computer system, the plurality of associated search frequencies to a threshold value;

determining, by the computer system, a portion of the plurality of search keywords associated with associated search frequencies greater than the threshold value; and

searching, by the computer system, the application classification database for applications associated with application characteristics determined to match the portion of the plurality of search keywords.

7. The method of claim 1,

wherein the mobile device usage data further comprises a plurality of user application ratings from a social network, and

wherein determining the list of recommended applications comprises:

determining, by the computer system, a first portion of the plurality of user application ratings associated with the user from the first mobile device usage data; and

searching, by the computer system, the weighted application relationship graph for applications based on the first portion of the plurality of user application ratings associated with the user.

8. The method of claim 1,

wherein the mobile device usage data further comprises a plurality of user connections from a social network, and

wherein determining the list of the recommended applications for the user comprises:

determining, by the computer system, a first portion of the plurality of user connections from the social network associated with the user from the first mobile device usage data;

determining, by the computer system, a plurality of application lists associated with the first portion of the plurality of user connections, wherein the first portion of the plurality of user connections describe relationships between the user and a plurality of other users in the social network; and

searching, by the computer system, the weighted application relationship graph for applications based the plurality of application lists.

9. A non-transitory computer-readable storage medium containing instructions, that when executed, control a computer system to be configured for:

receiving mobile device usage data from a plurality of mobile electronic devices, wherein the mobile device usage data is gathered by security applications with enhanced access privileges executed on the mobile devices and comprises user-specific information for users associated with the plurality of mobile electronic devices and application usage data associated with a plurality of installed applications installed on the plurality of mobile electronic devices;

searching an application classification database for a plurality of application characteristics associated with a plurality of applications, wherein the plurality of applications comprises the plurality of installed applications, and wherein each of the plurality of applications is available for download from at least one of a plurality of application marketplaces;

determining a weighted application relationship graph, wherein the weighted application relationship graph comprises a plurality of relationship scores for a plurality of application pairs in the plurality of applications that describe the degree to which applications in each of the plurality of application pairs are related based on the plurality of application characteristics associated with the plurality of applications;

determining a list of recommended applications for a user in the plurality of users based on a first mobile device usage data from a first mobile device associated with the user and the plurality of relationship scores, wherein the list of recommended applications comprises a portion of the plurality of applications determined to be paired with at least one of a plurality of installed applications installed on the first mobile device and associated with a relationship score greater than a threshold score; and

sending the list of recommended applications to the first mobile device.

10. The non-transitory computer-readable storage medium of claim 9, wherein the plurality of application characteristics comprise a plurality of category identifiers that categorize the plurality of applications by type, and wherein a portion of the plurality of relationships scores are higher for application pairs in the plurality of application pairs that include applications determined to have matching category identifiers.

11. The non-transitory computer-readable storage medium of claim 9, wherein the plurality of application characteristics comprise a plurality of user generated tags, and wherein the plurality of user generated tags comprise user generated keywords or descriptions for each of the plurality of applications, wherein a portion of the plurality of relationships scores are higher for application pairs in the plurality of application pairs that include applications determined to have matching user generated tags.

12. The method of claim 9, wherein determining the list of recommended applications comprises:

determining a plurality of frequently used applications based on a first application usage data from the first mobile device associated with the user; and

searching the weighted application relationship graph for a plurality of applications determined to be paired with the plurality of frequently used applications.

13. The non-transitory computer-readable storage medium of claim 12, wherein searching the weighted application relationship graph comprises comparing a first plurality of relationship scores associated with the plurality of frequently used applications in the weighted application relationship graph with a threshold score value.

14. The non-transitory computer-readable storage medium of claim 9, wherein determining the list of recommended applications comprises:

determining a user search behavior data based on a first application usage data from the first mobile device usage data, wherein the user search behavior data comprises;

a plurality of search keywords used by the user in a in plurality of previously conducted searches; and

a plurality of associated search frequencies associated with the plurality of search keywords;

comparing the plurality of associated search frequencies to a threshold value;

determining a portion of the plurality of search keywords associated with associated search frequencies greater than the threshold value; and

searching the application classification database for applications associated with application characteristics determined to match the portion of the plurality of search keywords.

15. The non-transitory computer-readable storage medium of claim 9,

wherein the mobile device usage data further comprises a plurality of user application ratings from a social network, and

wherein determining the list of recommended applications comprises:

determining a first portion of the plurality of user application ratings associated with the user from the first mobile device usage data; and

searching the weighted application relationship graph for applications based on the first portion of the plurality of user application ratings associated with the user.

16. The non-transitory computer-readable storage medium of claim 9,

wherein the mobile device usage data further comprises a plurality of user connections from a social network, and

wherein determining the list of the recommended applications for the user comprises:

determining a first portion of the plurality of user connections from the social network associated with the user from the first mobile device usage data; and

determining a plurality of application lists associated with the first portion of the plurality of user connections, wherein the first portion of the plurality of user connections describe relationships between the user and a plurality of other users in the social network; and

searching the weighted application relationship graph for applications based the plurality of application lists.

17. A system comprising:

a computer processor; and

anon-transitory computer-readable storage medium containing instructions, that when executed, control the computer processor to be configured for;

receiving mobile device usage data from a plurality of mobile electronic devices, wherein the mobile device usage data is gathered by security applications with enhanced access privileges executed on the mobile devices and comprises user-specific information for users associated with the plurality of mobile electronic devices and application usage data associated with a plurality of installed applications installed on the plurality of mobile electronic devices;

searching an application classification database for a plurality of application characteristics associated with a plurality of applications, wherein the plurality of applications comprises the plurality of installed applications, and wherein each of the plurality of applications is available for download from at least one of a plurality of application marketplaces;

determining a weighted application relationship graph, wherein the weighted application relationship graph comprises a plurality of relationship scores for a plurality of application pairs in the plurality of applications that describe the degree to which applications in each of the plurality of application pairs are related based on the plurality of application characteristics associated with the plurality of applications;

determining a list of recommended applications for a user in the plurality of users based on a first mobile device usage data from a first mobile device associated with the user and the plurality of relationship scores, wherein the list of recommended applications comprises a portion of the plurality of applications determined to be paired with at least one of a plurality of installed applications installed on the first mobile device and associated with a relationship score greater than a threshold score; and

sending the list of recommended applications to the first mobile device.

18. The system of claim 17, wherein determining the list of recommended applications comprises:

determining a plurality of frequently used applications based on a first application usage data from the first mobile device associated with the user; and

searching the weighted application relationship graph for a plurality of applications determined to be paired with the plurality of frequently used applications.

19. The system of claim 17, wherein determining the list of recommended applications comprises:

determining a user search behavior data based on a first application usage data from the first mobile device usage data, wherein the user search behavior data comprises;

a plurality of search keywords used by the user in a in plurality of previously conducted searches; and

a plurality of associated search frequencies associated with the plurality of search keywords;

comparing the plurality of associated search frequencies to a threshold value;

determining a portion of the plurality of search keywords associated with associated search frequencies greater than the threshold value; and

searching the application classification database for applications associated with application characteristics determined to match the portion of the plurality of search keywords.

20. The system of claim 17,

wherein the mobile device usage data further comprises a plurality of user connections from a social network, and

wherein determining the list of the recommended applications for the user comprises:

determining a first portion of the plurality of user connections from the social network associated with the user from the first mobile device usage data;

determining a plurality of application lists associated with the first portion of the plurality of user connections, wherein the first portion of the plurality of user connections describe relationships between the user and a plurality of other users in the social network; and

searching the weighted application relationship graph for applications based the plurality of application lists.