Action prediction and identification of user behavior

• US 8,843,429 B2
• Filed: 04/01/2013
• Issued: 09/23/2014
• Est. Priority Date: 11/17/2010
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Wang, Gang, Chen, Weizhu, Chen, Zheng, Fan, Zhikai
• Primary Examiner(s): Holmes, Michael B
• Application Number:
  US13/854,737
• Publication Number:
  US 20130218824A1
• Time in Patent Office: 540 Days
• Field of Search: 706/46
• US Class Current: 706/46
• CPC Class Codes: G06F 16/3349 Reuse of stored results of previous queries
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 5/043 Distributed expert systems; Blackboards
• CPC Class Codes: G06Q 30/00 Commerce
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities

Abstract

User behavior modeling can include determining actions performed by various users. From the mined user actions, future actions can be predicted. Certain implementations include providing information and/or services based on the predicted future actions. Some implementations, include providing relevant information, services, and/or goods regarding the predicted future action.

Claims

1. A method performed by one or more computing systems comprising:

determining a population of users performing online actions;

selecting from the population of users, a group of users that have performed particular time-based user actions that relate to a user behavior; and

predicting a subsequent user action based at least in part upon the user behavior.

2. The method of claim 1, wherein the determining further includes determining offline actions based on at least one of:

one or more online searches, or

one or more website visits.

3. The method of claim 1, wherein the particular time-based user actions comprise one or more website visits.

4. The method of claim 1, further comprising removing, from the group of users, a user that has performed the subsequent action.

5. The method of claim 1, further comprising providing an identification of the group of users to a party that provides at least one of information, services, or goods associated with the subsequent action.

6. The method of claim 5, further comprising receiving, from the party, a bid to provide the at least one of information, services, or goods.

7. The method of claim 1, wherein the selecting from the population is based at least in part on an ensemble of models that include models for the particular user behavior actions.

8. The method of claim 7, wherein the removing from the group of users is based at least in part on another ensemble of models.

9. A computing device comprising:

one or more processors; and

a memory coupled to the one or more processors, the memory comprising instructions which, when executed by the one or more processors, cause the one or more processors to perform operations that include;

selecting, from a population of users, a group of users that have performed particular time-based user actions that relate to a user behavior, wherein the selecting is based, at least in part, on an ensemble of models that include models for particular user behavior actions; and

determining a subsequent user action based at least in part upon the user behavior.

10. The computing device of claim 9, the operations further comprising:

determining which users of the group of users have performed the subsequent action; and

removing, from the group, the users that have performed the subsequent action.

11. The computing device of claim 10, wherein the determining which users have performed the subsequent action is based at least in part on another ensemble of models.

12. The computing device of claim 9, wherein the selecting the group of users further comprises selecting the group of users from a user log that comprises the population of users.

13. The computing device of claim 9, the operations further comprising collecting user actions based in part on data provided by users through a browser toolbar.

14. The computing device of claim 13, wherein:

the browser toolbar provides a user log; and

the selecting the group of users further comprises selecting the group of users from the user log, the user log comprising the population of users.

15. The computing device of claim 9, the operations further comprising selectively providing information regarding the group of users to one or more parties providing at least one of information, goods or services associated with the subsequent user action.

16. The computing device of claim 9, wherein the selecting is based at least in part on online actions performed by the users.

17. A method comprising:

determining, by one or more processors, a population of users performing online actions, wherein the determining is based, at least in part, on selecting a set of users to include in the population based on a seed pattern;

selecting, from the population of users, a group of users that have performed particular time-based user actions that relate to a user behavior; and

predicting a subsequent user action based at least in part upon the user behavior.

18. The method of claim 17, wherein the particular time-based user behavior actions are associated with a behavior model of an ensemble of behavior models.

19. The method of claim 17, wherein the determining the population of users further comprises identifying a new user and predicting if the new user will perform the subsequent action.

20. The method of claim 17, further comprising removing, from the group of users, one or more users that perform the subsequent action.