Recommendations based on item tagging activities of users

• US 7,668,821 B1
• Filed: 11/17/2005
• Issued: 02/23/2010
• Est. Priority Date: 11/17/2005
• Status: Expired due to Fees

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Donsbach, Aaron, Lehman, Jeffrey D., Few, Jeffrey D., Gregov, Andrej, Brownell, Jeffrey T.
• Primary Examiner(s): Cottingham; John R.
• Assistant Examiner(s): Richardson; James E
• Application Number:
  US11/281,886
• Time in Patent Office: 1,559 Days
• Field of Search: 707 1- 5, 707100-102, 707/104.1, 705/26, 705/27, 715/700, 715/733, 715/744, 715/745
• US Class Current: 707/765
• 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 computing system, comprising:

an interactive system that comprises one or more machines that are remotely accessible to user computing devices via a network, said one or more machines programmed to provide;

an interactive catalog of items, the interactive catalog comprising a plurality of item detail pages, each of the item detail pages comprising information descriptive of a particular item in the interactive catalog;

a tagging interface that provides functionality for a user of the interactive catalog to create tags for classifying items represented in the interactive catalog of items, and to associate particular tags with particular items in the interactive catalog, the tagging interface comprising tag entry fields provided on at least some of the item detail pages of the interactive catalog, the tagging interface enabling the user to create tags via entry of text strings into the tag entry fields;

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

a search engine system comprising a tag keyword index, the search engine system operative to provide functionality for the user to conduct keyword searches of said tag data to locate items in the interactive catalog based at least in part on the information stored in the tag keyword index, the search engine system operative to return a list comprising items tagged by the user in response to a keyword search conducted by the user;

a recommendation system that provides customized item recommendations to the user based on information known about the user; and

a user interface that displays to the user a list of tags created by the user, and is responsive to the user selecting one or more selected tags from said list by invoking the recommendation system to generate, and provide to the user, item recommendations comprising additional items that are related to items the user has associated with the one or more selected tags.

2. The computing system of claim 1, wherein the system provides an option for a first user to obtain tag-specific recommendations that are specific to a tag created by a second user.

3. The computing system of claim 1, wherein the recommendations system generates tag-specific item recommendations for the one or more selected tags, at least in part, by using item-to-item similarity mappings to identify a set of additional items that are related to said plurality of items.

4. The computing system of claim 3, 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.

5. The computing system of claim 1, wherein the one or more selected tags are maintained private to the user.

6. The computing system of claim 1, wherein the search engine system provides an option for a user to conduct a tag-based search that is substantially limited in scope to the user'"'"'s tag data, wherein the system is responsive to the tag-based search by returning a list of catalog items that the user has associated with a tag that corresponds to a search string submitted by the user.

13. The computing system of claim 1, wherein the recommendation system is further configured to identify a corresponding set of related items for at least some of the plurality of items associated with the one or more selected tags.

14. The computing system of claim 13, wherein the recommendation system is further configured to provide tag-specific item recommendations by selecting at least a portion of the set of related items to recommend to the target user in association with the one or more selected tags.

15. The computing system of claim 1, further comprising an interface for displaying item groupings by tags.

17. The computing system of claim 1, wherein the information descriptive of a particular item comprises one or more of a description of the particular item, a picture of the particular item, a price of the particular item, customer reviews of the particular item, lists of related items, and information about the particular item'"'"'s availability from one or more sellers.

18. The computing system of claim 1, wherein the one or more selected tags comprise multiple tags.

19. The computing system of claim 1, wherein the user interface further enables the user to limit the item recommendations to items within a category of the interactive catalog.

21. The computing system of claim 1, further comprising a web server machine that provides web-based user access to the item detail pages, the tagging interface, the search engine system, the recommendations system, and the user interface.

7. A computer-implemented method of providing item recommendations to users, comprising:

providing a tagging interface that provides functionality for a user of an interactive catalog to create tags for classifying items represented in the interactive catalog via entry of text strings into tag fields of corresponding item detail pages, the tagging interface thereby enabling the user to create tags that describe items represented on particular item details page of the interactive catalog;

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;

providing functionality for the user to conduct keyword searches of said tag data to locate items in the interactive catalog based at least in part on information stored in a tag keyword index of a search engine;

returning a list from the search engine in response to a keyword search conducted by the user;

providing a user interface that displays to a user a list of tags created by the user;

in response to the user selecting a tag from said list, programmatically invoking a recommendations system comprising computer hardware to identify a plurality of items associated with the tag;

for each of the plurality of items associated with the tag, identifying a corresponding set of related items at least in part by accessing item-to-item similarity mappings represented in a computer memory;

combining the sets of related items to generate a combined set of related items; and

selecting at least a portion of the combined set of related items to recommend to the user in association with said tag, such that the related items comprise personalized, tag-specific item recommendations.

8. The method of claim 7, further comprising persistently recording tag-item associations created by the user during browsing of said repository of items, said tag-item associations including associations between said tag and said plurality of items.

9. The method of claim 7, 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 tag is private to the user.

11. The method of claim 7, further comprising receiving a search string specified by the user, identifying one or more tags of the user that match the search string, and returning a list of a plurality of items that are associated with the one or more tags.

12. The method of claim 7 and further comprising:

presenting a set of one or more proposed descriptors to a user; and

accepting a user selection of one descriptor from among the proposed set;

and wherein, in identifying the plurality of items associated with said user-defined tag, said tag comprises the selected descriptor.

16. The method of claim 7, further comprising displaying item groupings by tags.

20. The method of claim 7, further comprising receiving a category selection from the user and limiting the tag-specific item recommendations to items within the category.

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