Generating trend-based item recommendations

• US 10,068,006 B1
• Filed: 12/09/2011
• Issued: 09/04/2018
• Est. Priority Date: 12/09/2011
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Indukuri, Kiran Kumar
• Primary Examiner(s): Reyes, Mariela
• Assistant Examiner(s): Harmon, Courtney
• Application Number:
  US13/315,971
• Time in Patent Office: 2,461 Days
• Field of Search: 707767
• CPC Class Codes: G06F 16/3322 using system suggestions G06F16/3325 takes precedence
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06Q 30/00 Commerce

Abstract

Disclosed are various embodiments for generating recommendations for one or more items related to a topic of interest. In one embodiment, one or more items are identified that are related to one or more topics of ephemeral interest. A subset of the identified items may be selected to recommend to a plurality of users. One or more users may then be sent a notification comprising the recommendations for one or more of the items in the subset.

Claims

1. A non-transitory computer-readable medium embodying a program executable in a computing device, the program comprising:

code that identifies a topic of interest from activity on a social network site, wherein the topic of interest is associated with a geographic area;

code that selects a plurality of items related to the topic of interest based at least in part on a correlation of keywords extracted from the activity on the social network site and the geographic area with a catalog of items;

code that generates at least one recommendation to purchase at least one of the plurality of items; and

code that provides the at least one recommendation to purchase the at least one of the plurality of items to a user.

2. The non-transitory computer-readable medium of claim 1, wherein the code that selects the plurality of items is further based at least in part on a purchase history associated with a user.

3. The non-transitory computer-readable medium of claim 1, wherein the program further comprises:

code that identifies the geographic area based at least in part on keywords associated with the topic of interest.

4. A system, comprising:

at least one computing device; and

an application executable in the at least one computing device, the application comprising;

logic that identifies a topic of interest from user activity on a network site;

logic that identifies a plurality of search terms based at least in part on the topic of interest;

logic that determines a plurality of correlations between the plurality of search terms and metadata associated with a plurality of items;

logic that selects at least one of a subset of the plurality of items to recommend for purchase, wherein the subset of the plurality of items is based at least in part on the plurality of correlations; and

logic that generates at least one recommendation to purchase the at least one of the subset of the plurality of items.

5. The system of claim 4, wherein the plurality of items are offered for sale through an electronic commerce system.

6. The system of claim 4, wherein the topic of interest is identified from a plurality of popular trends.

7. The system of claim 4, wherein the topics of interest are identified from content on the network site submitted by users of the network site.

8. The system of claim 4, wherein the logic that selects the at least one of the subset of the plurality of items to recommend for purchase is further based at least upon data associated with users of an electronic commerce system.

9. The system of claim 4, wherein the logic that selects the at least one of the subset of the plurality of items to recommend for purchase is further based at least upon data associated with individual ones of the subset of the plurality of the items.

10. The system of claim 4, further comprising logic that generates and selects a notification to at least one of the users, the notification including the at least one recommendation to purchase the at least one of the subset of the plurality of the items.

11. The system of claim 10, wherein the notification further comprises at least one of a text message, an email, a voicemail message, or an automated phone message.

12. The system of claim 10, wherein the notification further comprises a post of the at least one recommendation on one of a plurality of social networking sites.

13. The system of claim 4, wherein the application further comprises:

logic that determines a plurality of secondary items having an affinity with the at least one of the subset of the plurality of items related to the plurality of the search terms associated with the topic of interest; and

logic that recommends the plurality of secondary items to at least one user.

14. The system of claim 4, wherein the topic of interest is related to a geographic area associated with user activity on the network site.

15. A method comprising:

generating, in a computing device, a first value associated with a topic of interest, wherein the first value represents a level of interest expressed by a plurality of users on a social network site and the first value is based at least in part on a first number of posts related to the topic of interest by the plurality of users to the social network site;

generating, in the computing device, a second value associated with the topic of interest, the second value representing the level of interest expressed by the users on the social network site after a predetermined period of time after the generation of the first value and the second value is based at least in part on a second number of posts related to the topic of interest by the plurality of users to the social network site;

determining, in the computing device, whether the level of interest associated with the topic of interest is decreasing based at least upon a comparison of the first value with the second value;

identifying, in the computing device, a promotion associated with a plurality of items in response to a determination that the level of interest associated with the topic of interest is decreasing;

determining, in the computing device, at least one recommendation to purchase the at least one of the plurality of items based at least upon the promotion; and

providing, in the computing device, a network page including the at least one recommendation to a user.

16. The method of claim 15, wherein the topic of interest is obtained by at least one user of the social network site selecting a target geography on a map, the topic of interest being associated with the target geography.

17. The method of claim 15, wherein the second value is below a threshold.

18. The method of claim 15, wherein the promotion comprises a decrease in price associated with the at least one item.

19. The method of claim 15, wherein the promotion comprises shipping the at least one item to the at least one of the users on the social network site for free.

20. The method of claim 15, wherein the topic of interest is identified from content on the social network site submitted by at least one of the plurality of users of the social network site.