Content personalization based on actions performed during browsing sessions

• US 20050102202A1
• Filed: 12/10/2004
• Published: 05/12/2005
• Est. Priority Date: 09/18/1998
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Brent R. Smith, Gregory D. Linden, Nida K. Zada
• Inventors: Smith, Brent R., Linden, Gregory D., Zada, Nida K.
• Granted Patent: US 7,970,664 B2
• Time in Patent Office: Days
• US Class Current: 705/27
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0253 During e-commerce, i.e. online transactions
• CPC Class Codes: G06Q 30/0254 based on statistics
• CPC Class Codes: G06Q 30/0255 based on user history
• CPC Class Codes: G06Q 30/0256 User search
• CPC Class Codes: G06Q 30/0271 Personalized advertisement
• CPC Class Codes: G06Q 30/0277 Online advertisement
• CPC Class Codes: G06Q 30/0282 Rating or review of business operators or products
• CPC Class Codes: G06Q 30/0601 Electronic shopping [e-shopping]
• CPC Class Codes: G06Q 30/0603 Catalogue ordering
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: G06Q 30/0633 Lists, e.g. purchase orders, compilation or processing
• CPC Class Codes: G06Q 30/0641 Shopping interfaces
• CPC Class Codes: H04L 51/02 using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
• CPC Class Codes: Y10S 707/99943 Generating database or data structure, e.g. via user interface

Abstract

Various methods are disclosed for monitoring user browsing activities, and for using such information to provide item recommendations to users. In one embodiment, a monitoring component of a merchant'"'"'s Web site maintains a record of products viewed by each user during a current browsing session—preferably based on visits to product detail pages. A recommendations component uses the resulting history of viewed products to identify additional products to recommend, preferably using a pre-existing table that maps products to related products. In one embodiment, this table is generated by periodically analyzing user browsing histories to identify correlations between purchases, viewing events, and/or other actions performed with respect to particular products. The recommended items may be displayed together with an option to individually deselect the recently viewed items on which the recommendations are based. Embodiments are also disclosed that use recent browse node visits, and recent searches, to generate the recommendations.

Claims

1. A computer-implemented method of assisting users in locating items of interest during browsing of an electronic catalog, the method comprising:

maintaining, in computer storage during a browsing session of a user, a record of a plurality of catalog items selected by the user for viewing during the browsing session (“

accessed items”

); and

programmatically selecting during the browsing session at least one additional item to present to the user, taking into consideration item viewing activities of prior users who have selected an accessed item for viewing during browsing of the electronic catalog.

2. The method of claim 1, wherein selecting the additional item comprises taking into consideration how many times a prior user who selected an accessed item for viewing also selected the additional item for viewing.

3. The method of claim 1, wherein selecting the additional item comprises taking into consideration, for each respective accessed item, how many times the accessed item and the additional item have been selected for viewing within a common browsing session.

4. The method of claim 1, wherein selecting the additional item comprising taking into consideration a quantity of browsing sessions that have occurred in which both an accessed item and the additional item were selected for viewing.

5. The method of claim 1, wherein each of the plurality of accessed items is taken into consideration in selecting an additional item to present to the user.

6. The method of claim 1, wherein selecting the additional item comprises accessing a pre-generated data structure that associates catalog items with related catalog items, said data structure reflecting a result of a programmatic analysis of item viewing activities of a plurality of users.

7. The method of claim 1, further comprising generating, and outputting to the user, a web page that lists the plurality of accessed items and the at least one additional item, and which provides functionality for the user to deselect one or more of the accessed items to cause a recommendation of the at least one additional item to be refined.

8. The method of claim 1, wherein maintaining the record comprises recording accesses by the user to item detail pages of the electronic catalog.

9. The method of claim 1, further comprising recording a search string submitted by the user during the browsing session, and taking the search string into consideration in selecting the at least one additional item to present to the user.

10. The method of claim 1, further comprising recording an access by the user to a browse node during the browsing session, and taking the browse node into consideration in selecting the at least one additional item to present to the user.

11. The method of claim 1, further comprising generating, and outputting to the user, a session-specific browse history that includes links to item detail pages of each of the plurality of accessed items.

12. The method of claim 1, wherein the items are products represented in the electronic catalog.

13. The method of claim 1, wherein the method is performed in its entirety while the user is unrecognized.

14. A computer program which embodies the method of claim 1, represented in computer storage.

15. A computer-implemented method of assisting users in locating items of interest during browsing of an electronic catalog, the method comprising:

maintaining, in computer storage during a browsing session of a user, a record of a plurality of catalog items selected by the user for viewing during the browsing session (“

accessed items”

); and

programmatically selecting during the browsing session at least one additional item to present to the user, taking into consideration statistical data reflective of a likelihood that a user who selects an accessed item for viewing will also select the additional item for viewing.

16. The method of claim 15, wherein the statistical data reflects how frequently an accessed item and the additional item are selected during a common browsing session.

17. The method of claim 15, wherein the statistical data reflects, for each accessed item, a frequency with which the respective accessed item and the additional item have been viewed within a common browsing session.

18. The method of claim 15, further comprising generating the statistical data in-part by determining how many browsing sessions have occurred in which both an accessed item and the additional item were selected for viewing.

19. The method of claim 15, wherein the statistical data reflects how frequently users who access an item detail page of an accessed item also access an item detail page of the additional item.

20. The method of claim 15, wherein the statistical data reflects how frequently an item detail page of an accessed item and an item detail page of the additional item are accessed during a common browsing session.

21. The method of claim 15, wherein each of the plurality of accessed items is taken into consideration in selecting the additional item to present to the user.

22. The method of claim 15, wherein the items are products represented in the electronic catalog.

23. The method of claim 15, wherein the method is performed in its entirety while the user is unrecognized.

24. A computer program which embodies the method of claim 15, represented in computer storage.

25. A computer-implemented method of assisting users in locating items of interest during browsing of an electronic catalog, the method comprising:

recording, in a session record of a browsing session of a user, identifiers of a plurality of catalog items selected by the user for viewing in the electronic catalog (“

accessed items”

);

programmatically selecting a plurality of additional items to recommend to the user based, at least in part, on the plurality of accessed items recorded in said session record; and

during the browsing session;

(a) outputting to the user a list of the accessed items and a list of the additional items, (b) detecting de-selection by the user of one or more of the accessed items, and (c) generating, and outputting to the user, a refined list of additional items which reflects said de-selection.

26. The method of claim 25, wherein the method comprises generating, and outputting to the user, a web page that provides functionality for the user to individually deselect one or more of the accessed items.

27. The method of claim 25, wherein recording the identifiers in the session record comprises recording accesses by the user to item detail pages of the electronic catalog.

28. The method of claim 25, wherein programmatically selecting a plurality of additional items comprises taking into consideration frequencies with which the additional items have been selected for viewing by prior users that have selected an accessed item for viewing.

29. The method of claim 25, wherein programmatically selecting a plurality of additional items comprises taking into consideration item viewing histories of a plurality of prior users who have selected an accessed item for viewing.

30. The method of claim 25, wherein programmatically selecting a plurality of additional items comprises taking into consideration a frequency with which a candidate additional item is selected for viewing in a browsing session in which an accessed item is selected for viewing.

31. The method of claim 25, wherein programmatically selecting a plurality of additional items to recommend comprises accessing a pre-generated data structure that associates items with related items, said data structure being reflective of item co-occurrences within item viewing histories of users.

32. The method of claim 25, wherein the session record additionally includes a search string submitted by the user during the browsing session, and the search string is taken into consideration in programmatically selecting the plurality of additional items to recommend.

33. The method of claim 25, wherein the session record additionally includes an identifier of a browse node selected by the user during the browsing session, and the browse node is taken into consideration in programmatically selecting the plurality of additional items to recommend.

34. The method of claim 25, wherein the method is performed in its entirety while the user is unrecognized.

35. A computer program that embodies the method of claim 25 represented in computer storage.

36. A computer-implemented method of assisting users in locating items represented in an electronic catalog, the method comprising:

recording a plurality of search queries submitted by a user during a browsing session of the electronic catalog;

programmatically selecting a set of items to recommend to the user, such that a decision whether to include a candidate item in said set of items to recommend takes into consideration whether the candidate item is responsive to more than one of said plurality of search queries; and

outputting a representation of said set of items to the user during said browsing session.

37. The method of claim 36, further comprising providing to the user an option to individually deselect one or more of the plurality of search queries and to thereafter view a refined set of items that reflects such de-selection.

38. The method of claim 37, wherein the option to individually deselect one or more of the plurality of search queries is provided on a web page that includes a listing of the items.

39. The method of claim 36, wherein the items are products represented in the electronic catalog.

40. A method of assisting users in locating items that are arranged within a hierarchy of item categories, the method comprising:

maintaining a record of a plurality of item categories accessed by a user during a browsing session, including a first item category and a second item category that do not stand in an ancestor-descendant relationship with one another in said hierarchy;

selecting a set of items to recommend to the user based, at least in part, on said record, such that a decision whether to include a candidate item in said set of items to recommend takes into consideration whether the candidate item falls within both the first item category and the second item category; and

outputting a representation of the set of items to the user during the browsing session.

41. The method of claim 40, further comprising providing to the user an option to individually deselect one or more of the plurality of item categories and to thereafter view a refined set of items that reflects such de-selection.

42. The method of claim 41, wherein the option to individually deselect one or more of the plurality of item categories is provided on a web page that includes a listing of the set of items.

43. The method of claim 40, wherein the items are products represented in an electronic catalog.

44. The method of claim 40, wherein the first and second item categories are at a common level of the hierarchy.