AUTOMATED SEARCH INTENT DISCOVERY

• US 20160092550A1
• Filed: 09/30/2014
• Published: 03/31/2016
• Est. Priority Date: 09/30/2014
• Status: Abandoned Application

• Current Assignee: Excalibur IP, LLC (Acacia Research Corporation)
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Kraft, Reiner, Schonfeld, Uri
• Application Number:
  US14/501,222
• Publication Number:
  US 20160092550A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

A first named entity, in a first query, may be identified. A first type, of the first named entity, may be determined and a first prefix and a first postfix, associated with the first named entity in the first query, may be identified. The first prefix and the first postfix may be assigned to a first group. The first group may designate one or more prefixes and one or more postfixes as being associated with the first type. A second named entity, associated with the first prefix and the first postfix in the first group, may be identified in a second query. Responsive to the second named entity being associated with the first type, a first search intent case comprising the first prefix, the first postfix, and the first type may be added to a database.

Claims

1. A method of automated search intent discovery, comprising:

identifying a first named entity in a first query;

determining a first type of the first named entity;

identifying a first prefix and a first postfix associated with the first named entity in the first query;

assigning the first prefix and the first postfix to a first group, the first group designating one or more prefixes and one or more postfixes as being associated with the first type;

identifying a second named entity associated with the first prefix and the first postfix in a second query; and

responsive to the second named entity being associated with the first type, adding a first search intent case comprising the first prefix, the first postfix, and the first type to a database.

2. The method of claim 1, comprising:

identifying a first domain of a first search result selected by a first user, associated with the first search query, in response to the first query.

3. The method of claim 2, comprising:

assigning the first search intent case to at least one of;

a first domain group, the first domain group designating one or more search intent cases as being associated with the first domain;

a first pre and post fix group, the first pre and post fix group designating one or more search intent cases as being associated with the first prefix and the first postfix;

or

a first type group, the first type group designating one or more search intent cases as being associated with the first type.

4. The method of claim 1, comprising:

comparing at least one of the first domain, the first prefix and the first postfix, or the first type of the first search intent case to existing search intent cases in the database, the existing search intent cases comprising an existing domain, an existing prefix and postfix, and an existing first type; and

creating a second search intent case comprising at least one of;

the first domain, the existing prefix and postfix, and the existing type;

the existing domain, the first prefix and first postfix, and the existing type;

the existing domain, the existing prefix and postfix, and the first type;

the first domain, the first prefix and first postfix, and the existing type;

the existing domain, the first prefix and first postfix, and the first type;

or

the first domain, the existing prefix and postfix, and the first type.

5. The method of claim 1, comprising:

responsive to the second named entity not comprising the first type, removing the first prefix and the first postfix from the first group.

6. The method of claim 1, comprising at least one of:

responsive to the first prefix being associated with a threshold number of types, removing the first prefix from the first group;

or responsive to the first postfix being associated with the threshold number of types, removing the first postfix from the first group.

7. The method of claim 1, comprising:

responsive to identifying a duplicate search intent case in the database, where the duplicate search intent case is the same as the first search intent case, removing the duplicate search intent case from the database.

8. The method of claim 1, comprising:

responsive to determining that the first search intent case and named entities of the first type are not logically associated, removing the first search intent case from the database.

9. The method of claim 1, comprising:

identifying a first verb in at least one of the first prefix or the first postfix associated with the first type.

10. The method of claim 9, comprising:

responsive to the first verb satisfying a type cohesiveness metric, assigning the first verb to the first type within the database.

11. A system for automated search intent discovery, comprising:

a user intent component configured to;

determine a first type of a first named entity in a first query;

identify a first prefix and a first postfix associated with the first named entity in the first query;

assign the first prefix and the first postfix to a first group, the first group designating one or more prefixes and one or more postfixes as being associated with the first type;

identify a second named entity associated with the first prefix and the first postfix in a second query; and

responsive to the second named entity being associated with the first type, add a first search intent case comprising the first prefix, the first postfix, and the first type to a database.

12. The system of claim 11, the user intent component configured to:

identify a first domain of a first search result selected by a first user, associated with the first query, in response to the first query.

13. The system of claim 11, the user intent component configured to:

assign the first search intent case to at least one of;

a first domain group, the first domain group designating one or more search intent cases as being associated with the first domain;

a first prefix/postfix group, the first prefix/postfix group designating one or more search intent cases as being associated with the first prefix and the first postfix;

or

a first type group, the first type group designating one or more search intent cases as being associated with the first type.

14. The system of claim 11, the user intent component configured to:

comparing at least one of the first domain, the first prefix and the first postfix, or the first type of the first search intent case to existing search intent cases in the database, the existing search intent cases comprising an existing domain, an existing prefix and postfix, and an existing first type; and

creating a second search intent case comprising at least one of;

the first domain, the existing prefix and postfix, and the existing type;

the existing domain, the first prefix and first postfix, and the existing type;

the existing domain, the existing prefix and postfix, and the first type;

the first domain, the first prefix and first postfix, and the existing type;

the existing domain, the first prefix and first postfix, and the first type;

or

the first domain, the existing prefix and postfix, and the first type.

15. The system of claim 11, the user intent component configured to:

responsive to the second named entity not comprising the first type, remove the first prefix and the first postfix from the first group.

16. The system of claim 11, the user intent component configured to:

responsive to identifying a duplicate search intent case in the database, where the duplicate search intent case is the same as the first search intent case, remove the duplicate search intent case from the database.

17. The system of claim 11, the user intent component configured to:

identify a first verb in at least one of the first prefix or the first postfix associated with the first type; and

responsive to the first verb satisfying a type cohesiveness metric, assign the first verb to the first type within the database.

18. A non-transitory computer readable medium comprising computer executable instructions that when executed by a processor perform a method for automated search intent discovery, comprising:

grouping a first type of a first named entity within a first query, a first prefix within the first query, and the first postfix with the first query into a first group designating one or more prefixes and one or more postfixes as being associated with the first type;

identifying a second named entity associated the first prefix and the first postfix; and

at least one of;

responsive to the second named entity comprising the first type, adding a first search intent case, comprising the first prefix, the first postfix, and the first type, to a database;

or

responsive to the second named entity comprising a second type;

removing the first prefix and the first postfix from the first group; and

grouping the first type, a second prefix, and a second postfix into the first group based upon a second query, comprising the second prefix, the second postfix, and a second named entity associated with the first type.

19. The method of claim 18, comprising:

identifying a first domain of a first search result selected by a first user, associated with the first query, in response to the first query.

20. The method of claim 18, comprising:

responsive to identifying a duplicate search intent case in the database, where the duplicate search intent case is the same as the first search intent case, removing the duplicate search intent case from the database.