Related-item tag suggestions

• US 8,170,916 B1
• Filed: 09/06/2007
• Issued: 05/01/2012
• Est. Priority Date: 09/06/2007
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Dicker, Russell A., Ahmed, Waqas, Wilson, Aaron D., Mongrain, Scott Allen, Rosca, Val Dan Dar Ion I., Manolache, Florin V., Munteanu, Valentin Radu, Rudeanu, Corneliu Gabriel Alexandru
• Primary Examiner(s): Airapetian, Mila
• Application Number:
  US11/851,320
• Time in Patent Office: 1,699 Days
• Field of Search: 705/26.1, 705/27.1
• US Class Current: 705/26.1
• CPC Class Codes: G06Q 30/0601 Electronic shopping [e-shopping]

Abstract

Tag suggestions enable a hosting entity such as a website to determine one or more tags to suggest to a user for association with a particular item within an electronic catalog. After this determination, the hosting entity may suggest the determined tags to the user. To determine these tags, the hosting entity may employ techniques to determine items related to the particular item. The hosting entity then suggests some or all of the tags associated with the related items. Additionally or alternatively, the hosting entity may determine certain metadata associated with the particular item. The entity then may suggest this metadata, or some related phrase or tag, to the user for association with the particular item. However the tag suggestions are determined, the hosting entity may rank the tag suggestions to determine which tags to present to the user or to determine an order in which to present the tags.

Claims

1. A method of implementing an item catalog hosted by a merchant website, comprising:

under control of one or more computer systems configured with specific executable instructions,

determining one or more items within the item catalog that are related to a particular item within the item catalog;

determining tags that users of the merchant website have previously associated with the one or more related items; and

suggesting that the tags that are associated with the one or more related items be associated as tags with the particular item, wherein the suggesting includes;

assigning weights to the tags that are associated with the one or more related items based at least in part on a source of each of the tags and whether each of the tags was already associated with the particular item;

ranking the tags that are associated with the one or more related items based at least in part on the assigned weights; and

presenting at least a portion of the tags that are associated with the one or more related items to a user of the merchant website based, at least in part, on the ranking to enable the user of the merchant website to associate one or more of the tags with the particular item.

2. A method comprising:

under control of one or more computer systems configured with specific executable instructions,

determining one or more items that are related to a particular item within an electronic catalog;

determining tags that are associated with the one or more related items;

assigning weights to the tags that are associated with the one or more related items based at least in part on whether each of the tags was already associated with the particular item;

ranking the tags that are associated with the one or more related items based at least in part on the assigned weights; and

suggesting that one or more of the tags associated with the one or more related items be associated with the particular item based at least in part on the rankings of the tags.

3. A method as recited in claim 2, wherein the one or more related items and the particular item comprise items for sale on a merchant website.

4. A method as recited in claim 2, wherein the tags that are associated with the one or more related items have been associated by users of a merchant web site.

5. A method as recited in claim 2, wherein the determining of the one or more related items comprises determining, for users that purchased the particular item, which other items within the electronic catalog the users also purchased.

6. A method as recited in claim 2, wherein the determining of the one or more related items comprises determining, for users that viewed the particular item within the electronic catalog during a particular session, which other items within the electronic catalog the users also viewed during the particular session.

7. A method as recited in claim 2, wherein the determining of the one or more related items comprises:

determining metadata about the particular item; and

searching the electronic catalog for other items that contain the determined metadata.

8. A method as recited in claim 2, wherein the determining of the one or more related items comprises:

determining a particular tag that has been associated with the particular item; and

searching the electronic catalog for other items that have also been associated with the particular tag.

9. A method as recited in claim 2, wherein the determining of the one or more related items comprises determining items within a same category of the electronic catalog as the particular item.

10. A method as recited in claim 2, wherein the determining of the one or more related items comprises examining customer-created lists that include the particular item to determine other items that the customer-created lists also include.

11. A method as recited in claim 2, wherein the determining of the one or more related items comprises:

examining a corpus of text associated with the particular item to determine a statistically improbable phrase within the corpus; and

examining corpuses of texts associated with other items in the electronic catalog to determine other corpuses that also include the statistically improbable phrase.

12. A method as recited in claim 2, wherein the determining of the one or more related items comprises:

examining a corpus of text associated with the particular item to determine a statistically improbable phrase within the corpus;

determining one or more tags related to the statistically improbable phrase; and

examining corpuses of texts associated with other items in the electronic catalog to determine other corpuses that also include the statistically improbable phrase or a tag related to the statistically improbable phrase.

13. A method as recited in claim 2, wherein the determining of the one or more related items comprises:

examining a corpus of text associated with the particular item to determine a capitalized phrase that appears, within the corpus, more than a threshold number of times; and

examining corpuses of texts associated with other items in the electronic catalog to determine other corpuses that also include the capitalized phrase more than the threshold number of times.

14. A method as recited in claim 2, wherein the determining of the one or more related items comprises:

examining a corpus of text associated with the particular item to determine a capitalized phrase that appears, within the corpus, more than a threshold number of times;

determining one or more tags related to the capitalized phrase; and

examining corpuses of texts associated with other items in the electronic catalog to determine other corpuses that also include the capitalized phrase, or one of the one or more tags related to the capitalized phrase, more than the threshold number of times.

15. A method as recited in claim 2, wherein the determining of the one or more related items comprises examining user-created relationships that relate the particular item with other items in the electronic catalog.

16. A method as recited in claim 2, wherein the determining of the one or more related items comprises examining a customer or critic review of the particular item to determine one or more other items in the electronic catalog identified in the customer or critic review.

17. A method as recited in claim 2, wherein the suggesting comprises presenting the tags that are associated with the one or more related items to a user of a merchant website, and further comprising:

receiving a selection of the one or more tags from the user; and

associating the one or more selected tags with the particular item responsive to the receiving of the selection.

18. A method as recited in claim 2, further comprising:

determining an order of the tags based at least in part on the ranking; and

presenting the tags that are associated with the one or more related items to a user in the determined order.

19. A system comprising:

one or more processors;

memory, accessible by the one or more processors;

a related item engine stored in the memory and executable on the one or more processors to determine items that are related to a particular item;

determine, based on multiple sources, tags that have been associated with the related items to enable suggesting that the tags be associated with the particular item; and

a ranking engine stored in the memory and executable on the one or more processors to weight each of the tags based at least in part a respective source of the tag and to rank the tags based at least in part on the weighting.

20. A system as recited in claim 19, wherein the ranking engine is further configured to sum a number of times that the one or more tags have been associated with the related items;

and further comprising a presentation engine to present, as tag suggestions for the particular item, the one or more tags that have been associated with the related items a highest number of times.

21. A system as recited in claim 19, wherein the ranking engine is further configured to determine a strength of a relationship between the particular item and each of the related items.

22. A system as recited in claim 19, wherein at least one of the weights is determined, at least in part, upon a category in an electronic catalog of the particular item.

23. A system as recited in claim 19, wherein the ranking engine is configured to rank the one or more tags by determining, for each of the tags:

(1) a number of items in an electronic catalog that have been associated with the tag, or (2) a number of users that have used the tag.

24. A system as recited in claim 19, further comprising a presentation engine to present:

(1) a set number of the one or more tags based on the ranking of the one or more tags, or (2) an ordered list of at least some of the one or more tags based on the ranking of the one or more tags.