Content personalization based on actions performed during a current browsing session

• US 20020198882A1
• Filed: 01/15/2002
• Published: 12/26/2002
• Est. Priority Date: 03/29/2001
• Status: Abandoned Application

• Current Assignee: Alexa Internet Inc (Amazon.com, Inc.)
• Original Assignee: Alexa Internet Inc (Amazon.com, Inc.)
• Inventors: Mack, Geoffrey B., Smith, Brent R., Linden, Gregory D., Zada, Nida K., Aizen, Jonathan O.
• Application Number:
  US10/050,579
• Publication Number:
  US 20020198882A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/904 Browsing; Visualisation therefor for navigating the web G06F16/954; browsing optimisation for the web G06F16/957
• 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

Abstract

A system provides session-specific web page or web site recommendations to a user based upon an identification of web pages previously viewed by the user during a browsing session. During a sequence of proximately visited locations, users tend to view web pages with similar content. To collect data, a client program executes in conjunction with a web browser on each of multiple users'"'"' computers. Each client program identifies pages viewed by the user and transmits the sequence of identifications to a server application executing on a recommendation system. The recommendation system creates tables of similar web pages based upon the sequences of locations visited by users. To create session-specific web page recommendations, the system uses the client program to identify a set of locations visited by the user during the session. The system then identifies similar web pages based upon the created tables and combines, sorts, and filters the results.

Claims

1. A system for assisting users in locating items related to their current browsing sessions, comprising:

a server component which communicates with a plurality of user computers and provides personalized recommendations of items to users thereof; and

a client component which runs on each of the plurality of user computers in association with a web browser and displays the personalized recommendations of items, wherein the client component notifies the server component of web addresses accessed by associated users; and

wherein the server component uses the information reported by an instance of the client component to generate the personalized recommendations for a user by at least (1) identifying a plurality of items accessed by the user during a current browsing session and (2) during said browsing session, selecting an item to recommend to the user based at least in part on a degree of relatedness to each of the plurality of items accessed by the user.

2. The system of claim 1, wherein the server component accesses a table which indicates said degrees of relatedness between items.

3. The system of claim 2, wherein the degrees of relatedness indicated by the table are reflective of an automated analysis of usage trail data of a plurality of users of the client component.

4. The system of claim 1, further comprising an analysis component which collectively analyzes usage trail data of a plurality of users of the client component in an off-line mode to generate data reflective of the degrees of relatedness between items, wherein the server component uses the data to provide the personalized recommendations.

5. The method of claim 1, wherein degrees of relatedness are based upon scores that take into account browsing history data for a plurality of users.

6. The system of claim 1, wherein degrees of relatedness are based upon a commonality index that takes into account a number of co-occurrences of accesses of a pair of items within a set of web browsing sessions.

7. The system of claim 1, wherein degrees of relatedness are based upon a minimum sensitivity determination.

8. The system as in claim 1, wherein the client component is a browser plug-in.

9. The system of claim 1, wherein the item to recommend to the user is a web page, a web site or a web address.

10. The system of claim 1, wherein the plurality of items are web pages, web sites or web addresses.

11. A system for assisting users in locating web content, comprising:

a server component which provides personalized recommendations of web pages to users; and

a client component which communicates with the server component over a computer network and displays the personalized recommendations of web pages to a user, wherein the client component notifies the server component of web pages accessed by the user; and

wherein the server component uses the information reported by the client component to generate the personalized recommendations for the user by at least (1) identifying a plurality of web pages accessed by the user and (2) selecting at least one additional web page to recommend to the user based at least in part on a degree of relatedness to each of the plurality of web pages accessed by the user.

13. The system of claim 12, wherein the plurality of web addresses are browsed during a single browsing session.

14. The system of claim 12, wherein the item is a web page, a web site or a web address.

15. The system of claim 12, wherein the item is selected based additionally upon at least a degree of relatedness between the item and each of the plurality of web addresses.

16. The system of claim 15, wherein the degree of relatedness is based upon a score that takes into account browsing history data for a plurality of users.

17. The system of claim 15, wherein the degree of relatedness is based upon a commonality index that takes into account a number of co-occurrences of accesses of a pair of items within each of a plurality of web browsing sessions.

18. The system of claim 15, wherein the degree of relatedness is based upon a minimum sensitivity determination.

19. The system of claim 12, wherein the item is a product.

20. The system of claim 19, wherein the item is selected based additionally upon a degree of relatedness between the item and each of a plurality of products represented upon web pages at the plurality of web addresses.

12. A system for recommending items to users, the system comprising:

a client component configured to execute on each of a plurality of user computers in conjunction with a web browser to identify web addresses browsed through the web browser; and

a server component configured to select an item to recommend to a user based at least upon identifications of a plurality of web addresses browsed by the user, wherein the identifications of the web addresses are transmitted from an instance of the client component to the server component through a computer network.

21. A method for providing recommendations of items to a user, the method comprising:

using a client component which runs on the user'"'"'s computer in conjunction with a web browser to identify a plurality of items accessed by the user through a plurality of web sites during a web browsing session;

selecting an additional item based at least upon a degree of relatedness between the additional item and each of the plurality of items; and

recommending the additional item to the user.

22. The method of claim 21, wherein the additional item is a web page, a web site or a web address.

23. The method of claim 21, wherein the plurality of items are web pages, web sites or web addresses.

24. The method of claim 21, wherein the additional item is recommended to the user through the client component.

25. The method of claim 21, wherein the degree of relatedness is based upon a score that takes into account browsing history data for a plurality of users.

26. The method of claim 21, wherein the degree of relatedness is based upon a commonality index that takes into account a number of co-occurrences of accesses of a pair of items within each of a plurality of web browsing sessions.

27. The method of claim 21, wherein the degree of relatedness is based upon a minimum sensitivity determination.

28. The method of claim 21, wherein the additional item is selected by a server component that receives an identification of the plurality of items from the client component.

29. The method of claim 21, wherein the additional item is a product.

30. The method of claim 21, wherein using the client component to identify a plurality of items comprises:

receiving from the client component identifications of a plurality of web addresses browsed by the user during the web browsing session; and

using an association of web addresses with items to identify the plurality of items based upon the plurality of web addresses.

31. The method of claim 30, wherein the association of web addresses with items is based at least upon content-based analysis of web pages.

32. The method of claim 30, wherein the association of web addresses with items is based at least upon structure-based analysis of web pages.

33. The method of claim 30, wherein the association of web addresses with items is based at least upon user identification of items on web pages.

35. The method of claim 34, wherein the plurality of items is identified by at least retrieving and analyzing the plurality of web pages.

36. The method of claim 35, wherein analyzing the plurality of web pages comprises performing content-based analyses of web pages.

37. The method of claim 35, wherein analyzing the plurality of web pages comprises performing structure-based analyses of web pages.

38. The method of claim 34, wherein the plurality of items is identified by at least receiving information from users browsing web pages regarding representations of items on the web pages.

39. The method of claim 34, wherein the additional item is a product.

40. The method of claim 34, wherein each of the plurality of web pages is identified through its web address.

34. A method of recommending items, the method comprising:

using a client component which runs on a user'"'"'s computer in conjunction with a web browser to identify a plurality of web pages accessed by the user at a plurality of web sites during a web browsing session;

using the identification of the plurality of web pages to identify a plurality of items;

selecting an additional item based at least upon a degree of relatedness between the additional item and each of the plurality of items; and

recommending the additional item to the user.

41. A method of determining the relatedness of items, the method comprising:

for each of a plurality of web browsing sessions, capturing a browsing history of web pages;

for each browsing history, identifying a history of items represented on the web pages in the browsing history by at least retrieving the web pages in the browsing history and analyzing the retrieved web pages; and

determining degrees of relatedness between items based at least in part upon the histories of items.

42. The method of claim 41, further comprising providing a client component configured to execute on each of a plurality of user computers in conjunction with a web browser to identify web addresses browsed through the web browser, wherein each browsing history is captured using an instance of the client component.

43. The method of claim 41, wherein the items are products.

44. The method of claim 41, wherein the degrees of relatedness are determined using a commonality index.

45. The method of claim 41, wherein the degrees of relatedness are determined using a minimum sensitivity calculation.

46. The method of claim 41, wherein the analysis of the retrieved web pages comprises at least a content-based analysis of the web pages.

47. The method of claim 41, wherein the analysis of the retrieved web pages comprises at least a structure-based analysis of the web pages.

48. The method of claim 41, wherein the histories of items are identified by at least additionally accessing a database that associates web pages with items, wherein the database is populated at least in part by input from users browsing the web pages.