Listing recommendation in a network-based commerce system

• US 7,831,476 B2
• Filed: 10/20/2003
• Issued: 11/09/2010
• Est. Priority Date: 10/21/2002
• Status: Active Grant

• Current Assignee: eBay Inc.
• Original Assignee: eBay Inc.
• Inventors: Stewart, Lori Kathleen, Foster, Benjamin David, Speiser, Leonard Robert, Sandler, Andrew Leigh, Raimondi, Anne Chang, Kalko, Charles Zoran, Quick, Sterling Ryan
• Primary Examiner(s): Smith; Jeffrey A.
• Assistant Examiner(s): LEVINE, ADAM L
• Application Number:
  US10/689,970
• Publication Number:
  US 20040260621A1
• Time in Patent Office: 2,577 Days
• Field of Search: 705/26, 705/27
• US Class Current: 705/26.8
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0625 Directed, with specific intent or strategy
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: G06Q 30/0633 Lists, e.g. purchase orders, compilation or processing
• CPC Class Codes: G06Q 30/08 Auctions

Abstract

According to one aspect of the invention, there is provided a method to facilitate generating listing recommendations to a user of a network-based commerce system. In one embodiment, the method includes identifying a term associated with a user interaction in a network-based commerce system. The method further includes generating a recommendation query including the identified term. In addition, the method includes running the recommendation query against a plurality of listings hosted by the network-based commerce system to identify a recommendation. Moreover, the method includes presenting the recommendation to a user of the network-based commerce system.

Claims

1. A method of generating listing recommendations to a user of a network-based commerce system, the method including:

identifying a term associated with a user interaction in the network-based commerce system, the identified term occurring within a search query;

automatically generating a recommendation query including the identified term;

running the recommendation query against a plurality of listings of the network-based commerce system to identify at least one recommended listing; and

presenting the at least one recommended listing to a user of the network-based commerce system.

2. The method of claim 1, wherein the user interaction with the network-based commerce system includes searching a plurality of listings of the network-based commerce system utilizing the search query.

3. The method of claim 1, wherein the user interaction with the network-based commerce system includes viewing the plurality of listings hosted by the network-based commerce system, and the identified term is associated with the listings viewed.

4. The method of claim 1, wherein the user interaction with the network-based commerce system includes transacting via the network-based commerce system, and the identified term occurs within a listing to which the transacting relates.

5. The method of claim 4, wherein the transacting includes purchasing a product associated with one of the listings.

6. The method of claim 1, wherein the identified term is selected based on its existence in a predetermined minimum number of user-generated search queries submitted to the network-based commerce system.

7. The method of claim 6, wherein the search queries are category-specific.

8. The method of claim 6, wherein the predetermined minimum number of search queries comprise search queries submitted by a plurality of users of the network-based commerce system.

9. The method of claim 1, wherein the identified term comprises a plurality of words.

10. The method of claim 1, wherein the identifying the term includes:

retrieving data related to a previous user interaction;

determining category data related to a listing associated with the previous user interaction;

retrieving at least one popular search term associated with the category data; and

generating the recommended listing based on the popular search term.

11. The method of claim 10, which includes:

determining if any one of a plurality of popular search terms match any portion of a title of a listing;

ranking the matches based on popularity of the popular search terms when a plurality of popular search terms match the title; and

selecting the popular search term ranked based on its ranking.

12. The method of claim 1, wherein running the recommendation query against the plurality of listings of the network-based commerce system to identify the recommended listing includes:

identifying listings hosted by the network-based commerce system, the identifying of the listings being based on an upper popularity boundary and a lower popularity boundary, wherein the upper popularity boundary and the lower popularity boundary are associated with the identified term;

determining if the listings meet at least one predetermined criterion;

ranking the listings meeting the predetermined criterion; and

selecting a predetermined number of highest ranked listings for recommendation to the user.

13. The method of claim 12, wherein the listings that include the identified term include listings that have a title that contains the identified term.

14. The method of claim 12, wherein the recommendation query includes the identified term, the lower popularity boundary, and the upper popularity boundary.

15. The method of claim 14, wherein the lower popularity boundary comprises a corresponding parent level category of the identified term.

16. The method of claim 12, wherein the determining if the listings meet the at least one predetermined criterion includes determining if the listings are designated by the network-based commerce system as being for mature audiences.

17. The method of claim 12, wherein the determining if the listings meet the at least one predetermined criterion includes determining if the listings are banned by the network-based commerce system.

18. The method of claim 12, wherein the determining if the listings meet the at least one predetermined criterion includes determining if the listings would be returned in a search relying on the identified term as search criteria.

19. The method of claim 12, wherein the determining if the listings meet the at least one predetermined criterion includes determining if remaining times of the listings are greater than a predetermined minimum time.

20. The method of claim 12, wherein the determining if the listings meet the at least one predetermined criterion includes determining if the listings are available to the user based on a site through which the user is registered to communicate with the network-based commerce system.

29. The method of claim 4, wherein the transacting includes bidding on a product associated with one of the listings.

30. The method of claim 10, wherein the previous user interaction with the network-based commerce system includes bidding on a product associated with the listing.

21. A system to generate listing recommendations to a user of a network-based computer system, the system including:

a communication engine to receive interaction data relating to a user interaction with a client machine;

a database engine to identify a term associated with the user interaction in the network-based computer system, the identified term occurring within a search query, and automatically to generate a recommendation query including the identified term; and

a search engine to run the recommendation query against a plurality of listings of the network-based computer system to identify at least one recommended listing, wherein the at least one recommended listing is communicated to the client machine of the network-based computer system.

22. The system of claim 21, wherein at least one of the communication engine, database engine and the search engine are provided by at least one server.

23. The system of claim 21, wherein the identified term occurs within a predetermined minimum number of search queries submitted to the network-based computer system.

24. The system of claim 21, wherein the predetermined minimum number of search queries comprise search queries submitted by a plurality of users of the network-based computer system.

25. A machine-readable non-transitory medium including a set of instructions that, when executed by a machine, cause the machine to:

identify a term associated with a user interaction in the network-based computer system, the identified term occurring within a search query;

automatically generate a recommendation query including the identified term;

run the recommendation query against a plurality of listings of the network-based computer system to identify at least one recommended listing; and

communicate a data signal including the at least one recommended listing to a user of the network-based computer system.

26. The machine-readable non-transitory medium of claim 25, wherein the user interaction with the network-based computer system includes searching a plurality of listings of the network-based computer system utilizing a search query and the identified term occurs within a search query.

27. The machine-readable non-transitory medium of claim 25, wherein a listings signal including the plurality of listings hosted by the network-based computer system is communicated to the client machine for viewing, and the identified term is associated with the listings viewed.

28. A system to generate listing recommendations to a user of a network-based computer system, the system including:

means for identifying a term associated with a user interaction in the network-based computer system, the identified term occurring within a search query;

means for automatically generating a recommendation query including the identified term;

means for running the recommendation query against a plurality of listings of the network-based computer system to identify at least one recommended listing; and

means for communicating a data signal including the at least one recommended listing to a user of the network-based computer system.