Inference of query relationships based on retrieved attributes

• US 9,330,201 B2
• Filed: 02/12/2014
• Issued: 05/03/2016
• Est. Priority Date: 09/12/2007
• Status: Active Grant

• Current Assignee: eBay Inc.
• Original Assignee: eBay Inc.
• Inventors: Parikh, Nishith, Sundaresan, Neelakantan
• Primary Examiner(s): Cao, Phuong Thao
• Application Number:
  US14/178,685
• Publication Number:
  US 20140164427A1
• Time in Patent Office: 811 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/334 Query execution G06F16/335 takes precedence
• CPC Class Codes: G06F 16/3349 Reuse of stored results of previous queries
• CPC Class Codes: G06F 16/90335 Query processing
• CPC Class Codes: G06Q 30/06 Buying, selling or leasing transactions
• CPC Class Codes: G06Q 30/0601 Electronic shopping [e-shopping]

Abstract

Various example embodiments are provided for inferring relationships between queries. In an example, queries are related based on the identification of common terms between the queries. Another example is to relate queries based on the identification that the queries are associated with a single search session. Yet another example is to infer relationships based on the identification of relationships between item attributes retrieved from the submission of the queries.

Claims

1. A method of inferring a relationship between a first query and a second query, the method comprising:

accessing a first attribute of a first item retrieved from the first query;

accessing a second attribute of a second item retrieved from the second query;

identifying, using a hardware processor, a further relationship between the first attribute and the second attribute;

relating the first query to the second query based on the identifying of the further relationship between the first attribute and the second attribute; and

assigning a weight to the relationship between the first query and the second query that is derived from a weight assigned to the first attribute and a weight assigned to the second attribute.

2. The method of claim 1, wherein the first attribute is a property belonging to the first item that is extracted based on buying behavior of at least one user as a result of a submission of the first query and the weight assigned to the first attribute is incremented each time the first item is purchased as a result of a submission of the first query.

3. The method of claim 1, wherein the second attribute is a property belonging to the second item that is extracted based on buying behavior of at least one user as a result of a submission of the second query and the weight assigned to the second attribute is incremented each time the second item is purchased as a result of a submission of the second query.

4. The method of claim 1, wherein the weight assigned to the relationship is based on a dot product between the weight assigned to the first attribute and the weight assigned to the second attribute.

5. The method of claim 1, wherein the identifying the further relationship is based on a textual similarity match of the first attribute with the second attribute.

6. The method of claim 1, wherein the identifying the further relationship is based on an identification of the first attribute being semantically related to the second attribute.

7. The method of claim 1, wherein the first item is a purchase resulting from a search based on the first query.

8. A non-transitory machine-readable medium storing instructions that, when executed by at least one processor of a machine, cause the machine to perform operations comprising:

accessing a first attribute of a first item retrieved from the first query;

accessing a second attribute of a second item retrieved from the second query;

identifying a further relationship between the first attribute and the second attribute;

relating the first query to the second query based on the identifying of the further relationship between the first attribute and the second attribute; and

assigning a weight to the relationship between the first query and the second query that is derived from a weight assigned to the first attribute and a weight assigned to the second attribute.

9. The non-transitory machine-readable medium of claim 8, wherein the first attribute is a property belonging to the first item that is extracted based on buying behavior of at least one user as a result of a submission of the first query and the weight assigned to the first attribute is incremented each time the first item is purchased as a result of a submission of the first query.

10. The non-transitory machine-readable medium of claim 8, wherein the second attribute is a property belonging to the second item that is extracted based on buying behavior of at least one user as a result of a submission of the second query and the weight assigned to the second attribute is incremented each time the second item is purchased as a result of a submission of the second query.

11. The non-transitory machine-readable medium of claim 8, wherein the weight assigned to the relationship is based on a dot product between the weight assigned to the first attribute and the weight assigned to the second attribute.

12. The non-transitory machine-readable medium of claim 8, wherein the identifying the further relationship is based on a textual similarity match of the first attribute with the second attribute.

13. The non-transitory machine-readable medium of claim 8, wherein the identifying the further relationship is based on an identification of the first attribute being semantically related to the second attribute.

14. The non-transitory machine-readable medium of claim 8, wherein the first item is a purchase resulting from a search based on the first query.

15. The non-transitory machine-readable medium of claim 8, wherein the first query is received from a first user and the second query is received from a second user.

16. The non-transitory machine-readable medium of claim 8, wherein the first attribute is defined in a title associated with the first item.

17. The non-transitory machine-readable medium of claim 8, wherein the first attribute is a category associated with the first item.

18. The non-transitory machine-readable medium of claim 8, wherein the first attribute is a brand associated with the first item.

19. A system comprising:

at least one processor; and

memory in communication with the at least one processor, the memory being configured to store a relationship identification module that is executable by the at least one processor, the relationship identification module having instructions that, when executed by the at least one processor, cause operations to be performed comprising;

accessing a first attribute of a first item retrieved from the first query;

accessing a second attribute of a second item retrieved from the second query;

identifying, using the at least one processor, a further relationship between the first attribute and the second attribute;

relating the first query to the second query based on the identifying of the further relationship between the first attribute and the second attribute; and

assigning a weight to the relationship between the first query and the second query that is derived from a weight assigned to the first attribute and a weight assigned to the second attribute.

20. The system of claim 19, wherein the operation of identifying the relationship is based on a textual similarity match of the first attribute with the second attribute or an identification of the first attribute being semantically related to the second attribute.