Systems and methods to identify a filter set in a query comprised of keywords

• US 10,210,262 B2
• Filed: 08/15/2014
• Issued: 02/19/2019
• Est. Priority Date: 06/09/2014
• Status: Active Grant

• Current Assignee: eBay Inc.
• Original Assignee: eBay Inc.
• Inventors: Konik, Tolga, Mukherjee, Rajyashree
• Primary Examiner(s): Mofiz, Apu M
• Assistant Examiner(s): Agharahimi, Farhad
• Application Number:
  US14/460,728
• Publication Number:
  US 20150356187A1
• Time in Patent Office: 1,649 Days
• Field of Search: None
• CPC Class Codes: G06F 16/9038 Presentation of query results
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 30/0625 Directed, with specific intent or strategy

Abstract

Systems and methods to identify a filter set in a keyword query are described. The system receives a query from a client machine. The system identifies filter sets based on the query and a based on rules. The filter sets include a first filter set that includes a first filter. The rules are utilized to associate at the least one keyword from the query to the first filter. The system further scores the filter sets based on probabilities to generate scores. The probabilities describe occurrences of attribute-value pairs in listings that respectively describe items that were previously transacted on a network-based marketplace. The system further identifies the first filter set from the filter sets based on the scores, generates a user interface including search results that are identified based on the identified first filter set, and communicates the user interface, over the network, to the client machine.

Claims

1. A system comprising:

one or more processors; and

a machine-readable hardware storage device coupled with the one or more processors, the machine-readable hardware storage device storing instructions that, when executed by the one or more processors, cause the system to perform operations comprising;

receiving a query, over a network, from a client machine, the query including at least one keyword;

applying, to the received query, classification rules that are each associated with one or more defined domains to identify a plurality of filter sets that are each applicable to the received query, each applicable filter set in the identified plurality of applicable filter sets including at least one attribute-value pair determined to correspond to at least a portion of the received query;

generating a score for each applicable filter set in the identified plurality of applicable filter sets based on a determined number of times that the applicable filter set corresponds to titles of previously-transacted item listings of a network-based marketplace;

selecting a first filter set from the identified plurality of filter sets based on a determination that the first filter set is associated with a highest generated score of the scores generated for each of the identified plurality of applicable filter sets; and

employing the selected first filter set to generate search results for item listings offered on the network-based marketplace, the search results being generated for communication, over the network, to the client machine as a response to the received query.

2. The system of claim 1, wherein each of the applied classification rules includes corresponding condition information that is comparable to one or more portions of the received query, and corresponding supplemental information that includes one or more filter sets.

3. The system of claim 1, wherein each filter set of the included one or more filter sets comprises at least a first corresponding attribute-value pair.

4. The system of claim 3, wherein each filter set further comprises a second corresponding attribute-value pair, and the score for each applicable filter set in the identified plurality of applicable filter sets is generated based further in part on a determined probability that the first corresponding attribute-value pair co-occurs with the second corresponding attribute-value pair.

5. The system of claim 1, wherein the generated score corresponds to a probability that the applicable filter set in the identified plurality of applicable filter sets corresponds to one of the plurality of item listings offered on the network-based marketplace.

6. The system of claim 1, wherein the score for each applicable filter set in the identified plurality of applicable filter sets is generated based further in part on a number of filters in the applicable filter set.

15. The system of claim 1, wherein the search results are generated based on a set of offered item listings determined to correspond to the selected first filter set.

7. A method performed by at least one processor, comprising:

receiving a query, over a network, from a client machine, the query including a set of keywords;

applying, to the received query, classification rules that are each associated with one or more defined domains to identify a plurality of applicable filter sets, each filter set of the identified plurality of applicable filter sets comprising at least one attribute-value pair determined to correspond to at least one keyword in a set of keywords included the received query;

generating a score for each applicable filter set in the identified plurality of applicable filter sets based on a determined probability that the at least one attribute-value pair of the applicable filter set corresponds to titles of previously-transacted item listings of a network-based marketplace;

generating search results from a plurality of item listings offered on the network-based marketplace by employing one of the identified plurality of applicable filter sets determined to have a highest generated score, wherein the search results are generated for communication, over the network, to the client machine as a response to the received query.

8. The method of claim 7, wherein each of the applied classification rules includes corresponding condition information that is comparable to one or more portions of the received query, and corresponding supplemental information that includes one or more filter sets.

9. The method of claim 7, wherein each filter set of the included one or more filter sets comprises at least a first corresponding attribute-value pair.

10. The method of claim 9, wherein each filter set further comprises a second corresponding attribute-value pair, and the score for each applicable filter set in the identified plurality of applicable filter sets is generated based further in part on a determined probability that the first corresponding attribute-value pair co-occurs with the second corresponding attribute-value pair.

11. The method of claim 7, wherein the score for each applicable filter set in the identified plurality of applicable filter sets is generated based further in part on a number of filters in the applicable filter set.

12. The method of claim 7, wherein at least one applicable filter set of the identified plurality of applicable filter sets includes a first corresponding attribute-value pair comprising an attribute of color and a value indicating the color.

13. A non-transitory machine-readable hardware storage device storing a set of instructions that, when executed by a processor of a machine, causes the machine to perform operations comprising:

receiving a query, over a network, from a client machine, the query including a set of keywords;

applying, to the received query, classification rules that are each associated with one or more defined domains to identify a plurality of applicable filter sets, each filter set of the identified plurality of applicable filter sets comprising at least one attribute-value pair determined to correspond to at least one keyword in the set of keywords of the received query;

generating a score for each applicable filter set in the identified plurality of applicable filter sets based on a determined probability that the at least one attribute-value pair of the applicable filter set corresponds to titles of previously-transacted item listings of a network-based marketplace; and

generating search results from a plurality of item listings offered on the network-based marketplace by employing one of the identified plurality of applicable filter sets determined to have a highest generated score, wherein the search results are generated for communication to the client machine over the network as a response to the received query.

14. The non-transitory machine-readable hardware storage device of claim 13, wherein the score for each applicable filter set in the identified plurality of applicable filter sets is generated generating based further in part on a number of filters in the applicable filter set.