Recommendation of network object information to user

• US 8,898,283 B2
• Filed: 04/09/2010
• Issued: 11/25/2014
• Est. Priority Date: 04/13/2009
• Status: Active Grant

• Current Assignee: Alibaba Group Holding Ltd.
• Original Assignee: Alibaba Group Holding Ltd.
• Inventors: Zhang, Jinyin, Yang, Zhixiong, Peng, Xinyu
• Primary Examiner(s): Zele, Krista
• Assistant Examiner(s): FORMAN, JAMES Q
• Application Number:
  US12/798,711
• Publication Number:
  US 20100262692A1
• Time in Patent Office: 1,691 Days
• Field of Search: 709/224, 707/14.54
• US Class Current: 709/224
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0255 based on user history
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46

Abstract

Recommending network object information to a user includes, for each of a plurality of network objects, a respective plurality of behavior frequencies by the user is determined; a network object among the plurality of network objects that is of interest to the user is identified, the identification being based at least in part on the respective plurality of behavior frequencies that corresponds to each of the plurality of network objects; and additional information relating to the identified network object is provided to the user.

Claims

1. A method for recommending network object information to a user, comprising:

determining, using a processor, for each of a plurality of network objects, a respective plurality of behavior frequencies by the user, each of the plurality of behavior frequencies corresponds to a number of times the user conducted a respective one of a plurality of behaviors on said each network object within a period of time, wherein the plurality of network objects is associated with a plurality of product categories;

identifying one or more network objects among the plurality of network objects that are of interest to the user, the identification being based at least in part on the respective plurality of behavior frequencies that corresponds to each of the plurality of network objects, wherein identifying the one or more network objects includes;

determining a degree of user preference for each of at least a subset of the plurality of network objects;

selecting a first network object of the plurality of network objects based at least in part on a first ranking associated with a degree of user preference associated with the first network object, wherein the first network object comprises a first keyword associated with a category of the plurality of categories;

selecting a second network object of the plurality of network objects based at least in part on a second ranking associated with a degree of user preference associated with the second network object, wherein the second network object comprises a second keyword associated with the category; and

combining the first network object, the second network object, and the category into a combined network object, wherein the combined network object comprises a concatenation of the first keyword, the second keyword, and the category; and

providing to the user recommended product information relating to the combined network object.

2. The method of claim 1, wherein the plurality of behaviors includes releasing information on one of the plurality of network objects.

3. The method of claim 1, wherein the plurality of behaviors includes receiving an e-mail containing information on one of the plurality of network objects.

4. The method of claim 1, wherein the plurality of behaviors includes releasing opinion information on one of the plurality of network objects.

5. The method of claim 1, wherein the plurality of behaviors includes retrieving information on one of the plurality of network objects.

6. The method of claim 1, wherein the plurality of behaviors includes searching for information on one of the plurality of network objects.

7. The method of claim 1, wherein determining the degree of user preference for each of the at least subset of the plurality of network objects comprises:

deriving, for each of the at least subset of the plurality of network objects, a respective sum of the respective plurality of behavior frequencies by the user, wherein the respective sum comprises adding together each of the respective plurality of behavior frequencies.

8. The method of claim 1, wherein determining the degree of user preference for each of the at least subset of the plurality of network objects comprises:

assigning each of the respective plurality of behavior frequencies a respective weight; and

deriving, for each of the at least subset of the plurality of network objects, a respective sum of the respective weighted plurality of behavior frequencies by the user, wherein the respective sum comprises adding together each of the respective weighted plurality of behavior frequencies.

9. The method of claim 8, wherein the respective weight comprises a value between 0 and 1.

10. The method of claim 8, wherein deriving, for each of the at least subset of the plurality of network objects, a respective sum of the respective weighted plurality of behavior frequencies by the user is derived by equation:

11. The method of claim 1, wherein the first ranking associated with the degree of user preference associated with the first network object and the second ranking associated with the degree of user preference associated with the second network object comprises the two highest rankings associated with respective degrees of user preferences associated with the at least subset of the plurality of network objects.

12. A system for recommending network object information to a user, comprising:

one or more processors configured to;

determine, for each of a plurality of network objects, a respective plurality of behavior frequencies by the user, each of the plurality of behavior frequencies corresponds to a number of times the user conducted a respective one of a plurality of behaviors on said each network object within a period of time, wherein the plurality of network objects is associated with a plurality of product categories;

identify one or more network objects among the plurality of network objects that are of interest to the user, the identification being based at least in part on the respective plurality of behavior frequencies that corresponds to each of the plurality of network objects, wherein identifying the one or more network objects includes;

determining a degree of user preference for each of at least a subset of the plurality of network objects;

selecting a first network object of the plurality of network objects based at least in part on a first ranking associated with a degree of user preference associated with the first network object, wherein the first network object comprises a first keyword associated with a category of the plurality of categories;

selecting a second network object of the plurality of network objects based at least in part on a second ranking associated with a degree of user preference associated with the second network object, wherein the second network object comprises a second keyword associated with the category; and

combining the first network object, the second network object, and the category into a combined network object, wherein the combined network object comprises a concatenation of the first keyword, the second keyword, and the category; and

provide to the user recommended product information relating to the combined network object; and

one or more memories coupled to the one or more processors, configured to provide the one or more processors with instructions.

13. The system of claim 12, wherein the plurality of behaviors includes releasing information on one of the plurality of network objects.

14. The system of claim 12, wherein the plurality of behaviors includes receiving an e-mail containing information on one of the plurality of network objects.

15. The system of claim 12, wherein the plurality of behaviors includes releasing opinion information on one of the plurality of network objects.

16. The system of claim 12, wherein the plurality of behaviors includes retrieving information on one of the plurality of network objects.

17. The system of claim 12, wherein the plurality of behaviors includes searching for information on one of the plurality of network objects.

18. The system of claim 12, wherein determining the degree of user preference for each of the at least subset of the plurality of network objects comprises:

deriving, for each of the at least subset of the plurality of network objects, a respective sum of the respective plurality of behavior frequencies by the user, wherein the respective sum comprises adding together each of the respective plurality of behavior frequencies.

19. The system of claim 12, wherein determining the degree of user preference for each of the at least subset of the plurality of network objects comprises:

assigning each of the respective plurality of behavior frequencies a respective weight; and

deriving, for each of the at least subset of the plurality of network objects, a respective sum of the respective weighted plurality of behavior frequencies by the user, wherein the respective sum comprises adding together each of the respective weighted plurality of behavior frequencies.

20. The system of claim 12, wherein the first ranking associated with the degree of user preference associated with the first network object and the second ranking associated with the degree of user preference associated with the second network object comprises the two highest rankings associated with respective degrees of user preferences associated with the at least subset of the plurality of network objects.