Personalized selection and display of user-supplied content to enhance browsing of electronic catalogs

• US 20050038717A1
• Filed: 08/13/2003
• Published: 02/17/2005
• Est. Priority Date: 08/13/2003
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon.com, Inc.
• Inventors: McQueen, Clyde D. III, Hyman, Michael Irvin, Brinkerhoff, Richard Scott
• Granted Patent: US 7,310,612 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 30/0245 Surveys
• CPC Class Codes: G06Q 30/0254 based on statistics
• CPC Class Codes: G06Q 30/0255 based on user history
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: G06Q 30/0601 Electronic shopping [e-shopping]
• CPC Class Codes: G06Q 30/0623 Item investigation
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: G06Q 30/0641 Shopping interfaces
• CPC Class Codes: G06Q 50/10 Services

Abstract

An electronic catalog system provides an interface for users to author and post pieces of content, referred to as “blurbs,” for viewing by other users. The blurbs submitted by a particular author are made available for viewing in an author-specific blog (web log) format. Blurbs may also be obtained from external sources, such as from blogs hosted by various web sites. A personalized blurb selection component selects blurbs to present to users based on histories of catalog items selected by such users, and/or based on various other criteria. The blurbs selected for a particular user are presented within a personal log or “plog,” which may be updated daily and will typically contain entries from many different authors. User feedback provided on specific blurbs is taken into consideration by the personalized blurb selection algorithms.

Claims

1. An electronic catalog system, comprising:

a browsable electronic catalog of items;

a tracking component that maintains user-specific item selection histories of items selected from the electronic catalog by users;

a blurb submission component that provides functionality for users of the electronic catalog to author and post blurbs for viewing by other users;

a personalized blurb selection component that selects blurbs to present to specific users based at least in part on the item selection histories of such users; and

a personalized blurb display component that displays the blurbs selected by the personalized blurb selection component to corresponding users in association with the electronic catalog.

2. The system of claim 1, further comprising a voting component that provides an option for users to explicitly rate the blurbs they review by casting votes, wherein the personalized blurb selection component takes such votes into consideration in selecting blurbs to present to users.

3. The system of claim 2, wherein the personalized blurb selection component evaluates whether a candidate blurb should be selected based at least in part on the votes cast by users in association with other blurbs submitted by the author of the candidate blurb.

4. The system of claim 2, wherein the personalized blurb selection component evaluates whether a candidate blurb should be presented to a target user based at least in part on a degree to which those who voted favorably on the candidate blurb have item selection histories that are similar to the item selection history of the target user.

5. The system of claim 1, wherein the personalized blurb display component presents the blurbs selected by the personalized blurb selection component in a personal log format in which selected blurbs are generally displayed in a reverse chronological order.

6. The system of claim 1, wherein the blurb submission component provides a tool for blurb authors to insert references within the blurbs to specific catalog items.

7. The system of claim 6, wherein the personalized blurb selection component evaluates whether a given blurb should be presented to a target user based at least in part on whether the blurb references a catalog item that appears in the item selection history of the target user.

8. The system of claim 1, wherein the personalized blurb selection component evaluates whether a candidate blurb should be presented to a target user based at least in part on a degree of similarity between the item selection history of the target user and the item selection history of the candidate blurb'"'"'s author.

9. The system of claim 1, further comprising a blog display component that displays the blurbs submitted by a given author in an author-specific blog.

10. The system of claim 1, wherein the item selection histories are or include histories of specific catalog items selected by users for viewing.

11. The system of claim 1, wherein the item selection histories are or include histories of specific catalog items selected by users for purchasing.

12. The system of claim 1, wherein the item selection histories are or include histories of specific catalog items selected by users for submissions of reviews.

13. The system of claim 1, wherein the blurbs selected by the personalized blurb selection component additionally include blurbs obtained from at least one external source.

14. The system of claim 1, wherein the personalized blurb selection component uses a plurality of competing blurb selection algorithms to select blurbs to present to users.

15. In a system that provides online access to an electronic catalog of items, a method of enhancing browsing of the electronic catalog, comprising:

maintaining user-specific item selection histories indicative of specific items selected from the electronic catalog by specific users;

receiving a plurality of blurbs, including blurbs generated by each of multiple different users;

selecting specific blurbs of said plurality of blurbs to present to a target user based at least in part on an item selection history of the target user, to thereby identify a personalized set of selected blurbs; and

presenting the personalized set of selected blurbs to the target user when the target user browses the electronic catalog.

16. The method of claim 15, wherein receiving a plurality of blurbs comprises receiving blurbs generates using a blurb authoring pipeline provided in association with the electronic catalog.

17. The method of claim 15, wherein receiving a plurality of blurbs comprises receiving blurbs from external sources via a plurality of RSS feeds.

18. The method of claim 15, wherein selecting specific blurbs to present to the target user comprises taking into consideration whether a candidate blurb references an item in the target user'"'"'s item selection history.

19. The method of claim 18, wherein selecting specific blurbs to present to the target user further comprises taking into consideration whether the candidate blurb references an item that is similar to an item in the target user'"'"'s item selection history.

20. The method of claim 15, wherein selecting specific blurbs to present to the target user comprises evaluating a blurb as a selection candidate at least in part by calculating a degree of similarity between the item selection history of the target user and an item selection history of an author of the blurb.

21. The method of claim 15, wherein selecting specific blurbs to present to the target user comprises evaluating a blurb as a selection candidate at least in part by evaluating an extent to which users having item selection histories similar to the item selection history of the target user have responded favorably to the blurb.

22. The method of claim 15, further comprising:

providing an option for the target user to rate each of the selected blurbs;

receiving from the target user a vote that indicates the target user'"'"'s rating of a selected blurb; and

taking said vote into consideration in evaluating whether the blurb should be selected for display to other users.

23. The method of claim 22, further comprising taking said vote into consideration in evaluating whether other blurbs authored by the author of the selected blurb should be selected to present to users.

24. The method of claim 15, wherein the personalized set of selected blurbs comprises blurbs that do not correspond to any items in the electronic catalog.

25. The method of claim 15, wherein the selected blurbs are presented to the target user as entries within in a personalized log.

26. The method of claim 15, further comprising providing a blog display interface through which users can view author-specific logs of blurbs submitted by specific authors.

27. In an electronic catalog system that maintains user-specific item selection histories reflective of items selected from an electronic catalog, a computer-implemented method of evaluating whether a content item should be presented to a user, the method comprising:

presenting the content item to users together with an option to at least respond favorably to the content item;

monitoring and recording the user responses to the content item; and

determining whether to present the content item to a target user based at least in part on a degree to which an item selection history of the target user is similar to the item selection histories of users who responded favorably to the content item.

28. The method of claim 27, wherein the content item is presented to the users with an option to explicitly vote on the content item.

29. The method of claim 27, wherein the content item is presented to the users with an option to respond favorably to the content item and an option to respond unfavorably to the content item.

30. The method of claim 29, wherein monitoring and recording the user responses comprises

if a first user responds favorably to the content item, updating a mapping to increase scores associated with items contained in the item selection history of the first user;

and

if a second user responds unfavorably to the content item, updating the mapping to decrease scores associated with items included in the item selection history of the second user.

31. The method of claim 27, wherein determining whether to present the content item to the target user further comprises taking into consideration a degree to which the target user'"'"'s item selection history is dissimilar to item selection histories of users who responded unfavorably to the content item.

32. The method of claim 27, wherein the content item is a blurb.

33. The method of claim 27, wherein the content item is a unit of content other than a blurb.