Recommendations based on item tagging activities of users

• US 8,122,020 B1
• Filed: 01/25/2010
• Issued: 02/21/2012
• Est. Priority Date: 11/17/2005
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Donsbach, Aaron, Gregov, Andrej, Few, Jeffrey D., Lehman, Jeffrey D., Brownell, Jeffrey T.
• Primary Examiner(s): Cottingham, John R.
• Assistant Examiner(s): Richardson, James E
• Application Number:
  US12/693,210
• Time in Patent Office: 757 Days
• Field of Search: 707/738, 707765-767, 707/948, 707732-734, 705/26.7, 705/27.1
• US Class Current: 707/732
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: G06Q 30/0641 Shopping interfaces
• CPC Class Codes: Y10S 707/948 Product or catalog

Abstract

A system provides a user interface through which users can flexibly tag individual items represented in an electronic catalog with user-defined tags, such as text strings, and obtain recommendations that are specific to particular tags. The tags and tag-item assignments created by each user are stored persistently in association with the user, and may be kept private to the user or exposed to others. Once a user has assigned a tag to a number of items, the user (or another user in some embodiments) can request and obtain recommendations that are specific to this tag. These recommendations may be generated in real time by a recommendation service that identifies items that are collectively similar or related to the items associated with the tag.

Claims

1. A system for enabling a user to obtain focused item recommendations for a user-specified category of items, the system comprising:

one or more computer systems comprising computer hardware, the one or more computer systems programmed to implement;

a tagging system that provides functionality for a user to;

create tags via entry of text strings into tag fields of item detail pages, the item detail pages each comprising information descriptive of a catalog item in an interactive catalog of items, and

associate the tags with selected catalog items of the interactive catalog such that each of the tags classifies one or more of the catalog items, wherein the tagging system is configured to store user-specific tag data in a data repository, the user-specific tag data reflecting an association created by the user between the tags and the selected catalog items,

wherein the tagging system outputs for display to the user one or more of the tags created by the user; and

a recommendation system configured to generate tag-specific recommendations by at least;

receiving a user selection of a displayed tag of the one or more tags output for display to the user;

programmatically accessing the user-specific tag data in response to receiving the user selection of the displayed tag, to thereby identify at least one of the selected catalog items previously tagged with the displayed tag by the user,

without requiring further user interaction, programmatically accessing item relationship data to identify a set of additional items that are related to the at least one of the selected catalog items previously tagged by the user, and

selecting the tag-specific recommendations from the set of additional items for output to the user.

2. The system of claim 1, wherein the item relationship data comprises item-to-item similarity mappings.

3. The system of claim 2, wherein the item-to-item similarity mappings are based, at least in part, on tag-based item similarities detected by analyzing aggregated tag data of a population of users.

4. The system of claim 1, wherein the tagging system and the recommendation system are implemented by one or more machines.

5. The system of claim 1, wherein said user selection of one of the tags previously created by the user comprises a user selection of a link comprising text corresponding to the tag previously created by the user.

6. The system of claim 1, wherein the recommendation system is further configured to identify a plurality of catalog items previously tagged with the displayed tag by the user and generate recommendations based on the plurality of catalog items.

7. A method of enabling a user to obtain focused item recommendations for a user-specified category of items, the method comprising:

by one or more computer systems comprising computer hardware;

providing a tagging interface that provides functionality for a user to create tags for classifying items represented in an interactive catalog via entry of text strings into tag fields of item detail pages of the catalog, the item detail pages each comprising information descriptive of a catalog item in an interactive catalog of items;

persistently storing tag data of the user in a data repository, the tag data specifying tags and tag-item associations created by the user via the tagging interface;

outputting for display to the user one or more of the tags created by the user; and

generating tag-specific item recommendations, said generating comprising;

receiving a user selection of a displayed tag of the one or more tags output for display to the user;

programmatically accessing the tag data in response to receiving the user selection of the displayed tag, to thereby identify at least one of the catalog items previously tagged with the displayed tag by the user,

without requiring further user interaction, programmatically accessing item relationship data to identify a set of additional items that are related to the catalog items previously tagged by the user with the displayed tag, and

selecting at least a portion of the additional items to recommend to the user as the tag-specific item recommendations.

8. The method of claim 7, wherein identifying the set of additional items comprises identifying the additional items from item relationship data, the item relationship data comprising item-to-item similarity mappings.

9. The method of claim 8, further comprising generating the item-to-item similarity mappings, at least in part, by analyzing aggregated tag-item association data of a plurality of users to detect tag-based item similarities.

10. The method of claim 7, wherein the method is configured to be performed by an interactive system comprising one or more machines.

11. The method of claim 7, wherein the tagging interface further enables the user to limit the tag-specific item recommendations to selected items within a category of the interactive catalog.

12. A system, comprising:

a server system that provides user access to an interactive catalog of items, said interactive catalog including item detail pages that correspond to particular catalog items, the item detail pages providing functionality for users to tag individual catalog items via entry of textual strings into tag fields provided on the item detail pages, the item detail pages thereby enabling each user to create one or more tags, and to associate each tag with one or more catalog items;

a data repository that persistently stores user-specific tag data specifying the tags and tag-item associations created by the users via the item detail pages; and

a recommendation system, said recommendation system comprising a recommendation interface accessible to users via the server system, said recommendation interface providing functionality for a user to view a list of the tags created by the user, and to generate a tag-specific request for recommendations corresponding to a tag selected from said list by the user, the recommendation system capable of responding to the tag-specific request for recommendations by at least;

(a) programmatically using the user-specific tag data to identify a plurality of catalog items that have been tagged by the user with the selected tag,

(b) without requiring further user interaction, programmatically accessing item relationship data to identify a set of additional related items that are related to the catalog items tagged by the user; and

(c) selecting tag-specific recommendations from the set of additional items for output to the user;

wherein the server system and the recommendation system are implemented by one or more computing devices comprising computer hardware.

13. The system of claim 12, wherein the item detail pages are configured to display a list of the tags created by the user and to provide functionality for the user to select from the list of tags.

14. The system of claim 12, wherein the set of additional related items are related to the catalog items based at least partly on item-to-item similarity mappings.

15. The system of claim 14, wherein the item-to-item similarity mappings are based, at least in part, on tag-based item similarities detected by analyzing aggregated tag data of a population of users.

16. The system of claim 12, wherein the server system and the recommendation system are implemented by one or more machines.

17. The system of claim 12, wherein the recommendation system is further configured to receive a category selection from the user and to limit the tag-specific item recommendations to selected items within the category.