Listing recommendation using generation of a user-specific query in a network-based commerce system

• US 8,712,868 B2
• Filed: 08/27/2010
• Issued: 04/29/2014
• Est. Priority Date: 10/21/2002
• Status: Active Grant

• Current Assignee: eBay Inc.
• Original Assignee: eBay Inc.
• Inventors: Foster, Benjamin David, Speiser, Leonard Robert, Sandler, Andrew Leigh, Kalko, Charles Zoran, Quick, Sterling Ryan, Raimondi, Anne Chang, Stewart, Lori Kathleen
• Primary Examiner(s): LEVINE, ADAM L
• Application Number:
  US12/870,031
• Publication Number:
  US 20110055040A1
• Time in Patent Office: 1,341 Days
• Field of Search: 705 26- 272, 707/722, 707/767
• US Class Current: 705/26.7
• 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 comprising:

selecting a user to receive one or more recommended listings hosted by a network-based commerce system;

determining a term-category pair that pairs a term with a category of listings in which the term matches at least a predetermined number of listings and with which the selected user has interacted in an interaction;

generating a user-specific query that corresponds to the selected user and that includes the term from the term-category pair, the generating of the user-specific query being performed by a processor of a machine;

identifying a recommended listing from among a plurality of listings hosted by the network-based commerce system, the identifying of the recommended listing being based on the generated user-specific query and including

identifying a set of listings within the plurality of listings, the set of listings being identified between an upper popularity boundary of the term-category pair and a lower popularity boundary of the term-category pair; and

providing the recommended listing to a client machine of the selected user.

2. The method of claim 1, wherein:

the interaction includes a purchase by the user of an item that corresponds to a further listing within the plurality of listings; and

the selecting of the user is based on at least one of the purchase or the further listing.

3. The method of claim 1, wherein:

the interaction includes a bid by the user on an item that corresponds to a further listing within the plurality of listings, the bid being indicative of an attempted purchase of the item by the user; and

the selecting of the user is based on at least one of the bid or the further listing.

4. The method of claim 1, wherein:

the interaction includes a presentation to the user of a further listing within the plurality of listings in response to a request to view the further listing; and

the selecting of the user is based on at least one of the request, or the further listing.

5. The method of claim 1, wherein:

the selecting of the user includes determining that the user has not opted out of receiving recommended listings from the network-based commerce system.

6. The method of claim 1, wherein:

the determining of the term-category pair includes identifying the term, wherein the identifying of the term includes determining that the term is present in a minimum number of listings within the category of listings, the minimum number of listings being a subset of the category of listings.

7. The method of claim 1 further comprising:

determining a rank of the term-category pair; and

wherein

the generating of the user-specific query is based on the rank of the term-category pair.

8. The method of claim 7, wherein:

the rank of the term-category pair is based on a number that represents a quantity of listings within the category of listings, the quantity of listings having titles that include the term from the term-category pair.

9. The method of claim 1, wherein:

the generating of the user-specific query includes updating a previously generated user-specific query that corresponds to the user; and

the interaction includes an activity performed by the user since generation of the previously generated user-specific query.

10. The method of claim 1, wherein:

the term from the term-category pair includes a plurality of words.

11. The method of claim 1, wherein:

the identifying of the recommended listing includes;

determining that the set of listings each satisfy a criterion;

ranking each listing of the set of listings; and

selecting the recommended listing from the set of ranked listings.

12. The method of claim 11, wherein:

the determining that the set of listings each satisfy the criterion includes determining that each listing of the set of listings is not designated as for mature audiences.

13. The method of claim 11, wherein:

the determining that the set of listings each satisfy the criterion includes determining that each listing of the set of listings is not designated as banned by the network-based commerce system.

14. The method of claim 11, wherein:

the determining that the set of listings each satisfy the criterion includes determining that each listing of the set of listings does not have an expired listing time.

15. The method of claim 11, wherein:

the determining that the set of listings each satisfy the criterion includes determining that each listing of the set of listings has a remaining time period greater than a minimum time period.

16. The method of claim 11, wherein:

the network-based commerce system includes a plurality of registration sites;

the user is registered with the network-based commerce system as corresponding to a registration site among the plurality of registration sites; and

the determining that the set of listings each satisfy the criterion includes determining that each listing of the set of listings is available to the user based on the registration site that corresponds to the user.

17. A system comprising:

a database engine implemented using a processor of a machine within a network-based commerce system, the database engine being configured to;

select a user to receive one or more recommended listings hosted by a network-based commerce system;

determine a term-category pair that pairs a term with a category of listings in which the term matches have used a predetermined number of listings and with which the selected user has interacted; and

generate a user-specific query that corresponds to the selected user and that includes the term from the term-category pair; and

a search engine configured to;

identify a recommended listing from among a plurality of listings hosted by the network-based commerce system, the identifying of the recommended listing being based on the generated user-specific query and including

identifying a set of listings within the plurality of listings, the set of listings being identified between an upper popularity boundary of the term-category pair and a lower popularity boundary of the term-category pair; and

provide the recommended listing to a client machine of the selected user.

18. The system of claim 17, wherein:

the database engine is configured to;

determine a rank of the term-category pair; and

generate the user-specific query based on the rank of the term from the term-category pair.

19. A non-transitory machine-readable storage medium comprising instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:

selecting a user to receive one or more recommended listings hosted by a network-based commerce system;

determining a term-category pair that pairs a term with a category of listings in which the term matches at least a predetermined number of listings and with which the selected user has interacted;

generating a user-specific query that corresponds to the selected user and that includes the term from the term-category pair;

identifying a recommended listing from among a plurality of listings hosted by the network-based commerce system, the identifying of the recommended listing being based on the generated user-specific query and including

identifying a set of listings within the plurality of listings, the set of listings being identified between an upper popularity boundary of the term-category pair and a lower popularity boundary of the term-category pair; and

providing the recommended listing to a client machine of the selected user.