IP Library Granted Patent US 9,922,125
Granted Patent B1
US 9,922,125 · App. 15/367,462 · Granted Mar 20, 2018

Selecting content using entity properties

Inventor: Henrik Jacobsson (Zurich, CH)
Assignee: Google LLC
G06F17/30867G06F17/30905G06F17/30958
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 9,922,125
App. No.
15/367,462
Filed
Dec 2, 2016
Granted
Mar 20, 2018
Kind
B1
Examiner
PHAM, HUNG Q
Art Unit
2159
USPC
707/722
Abstract

Systems and methods of the disclosure relate to selecting content via a computer network. A search query provided by a user device can be received. An entity of a search query, a corresponding confidence score, and a property can be identified via a data structure having information about entities. A match between a property of an entity of content selection criteria and the property of the entity of the search query can be determined. The content item can be selected as a candidate for display on the user device based on the match and the confidence score.

Claims (45)

1. A method of selecting content for display on a user device via a computer network, comprising:

receiving, from a content provider associated with a content item and by a data processing system having one or more processors, content selection criteria specifying types of queries that make the content item eligible to be selected for display along with search results responsive to queries matching the specified types of queries;

generating, using a data structure that links related entities to each other, a content selection criteria structure that includes an entry for the content selection criteria, an entry for two or more entities that are related to the content selection criteria through a link in the data structure but do not appear in the received content selection criteria, and a connection between each pair of related entities in the content selection criteria structure, the generated content selection criteria structure being separate from the data structure;

receiving, by the data processing system, a search query provided via a user device;

generating a query structure that includes an entry for the search query, an entry for two or more entities that are related to the search query through a link in the data structure but do not appear in the search query, and a connection between each pair of related entities in the query structure, the generated query structure being separate from the content selection criteria structure and the data structure;

matching a topology and content of the content selection criteria structure to a topology and content of the query structure; and

selecting the content item as a candidate for display on the user device based on the match between the content selection criteria structure and the query structure.

2. The method of claim 1 , wherein the content selection criteria structure and the query structure each comprise a graph, and matching a topology and content of the content selection criteria structure to a topology and content of the query structure comprises comparing, on a node-by-node basis, the content selection criteria structure with the query structure.

3. The method of claim 1 , further comprising:

translating properties of the search query and the entities related to the search query into a flat data structure comprising information associated with the properties; and

identifying, using the flat data structure, a plurality of content selection criteria associated with the flat data structure.

4. The method of claim 3 , further comprising comparing each of the content selection criteria with the properties of the search query entity to identify matching content selection criteria.

5. The method of claim 1 , wherein matching the topology and content of the content selection criteria structure to the topology and content of the query structure comprises determining that a confidence score satisfies a first threshold.

6. The method of claim 1 , wherein the entities that are related to the search query each have a confidence score that satisfies a second threshold.

7. The method of claim 1 , wherein matching the topology and content of the content selection criteria structure to the topology and content of the query structure comprises matching one or more entities related to the content selection criteria with one or more entities related to the search query.

8. A system for selecting content for display on a user device via a computer network, comprising:

an interface module of a data processing system having one or more processors configured to:

receive, from a content provider associated with a content item and by a data processing system having one or more processors, content selection criteria specifying types of queries that make the content item eligible to be selected for display along with search results responsive to queries matching the specified types of queries;

generate, using a data structure that links related entities to each other, a content selection criteria structure that includes an entry for the content selection criteria, an entry for two or more entities that are related to the content selection criteria through a link in the data structure but do not appear in the received content selection criteria, and a connection between each pair of related entities in the content selection criteria structure, the generated content selection criteria structure being separate from the data structure;

receive, by the data processing system, a search query provided via a user device; and

generate a query structure that includes an entry for the search query, an entry for two or more entities that are related to the search query through a link in the data structure but do not appear in the search query, and a connection between each pair of related entities in the query structure, the generated query structure being separate from the content selection criteria structure and the data structure;

a matching module of the data processing system configured to match a topology and content of the content selection criteria structure to a topology and content of the query structure; and

a content selector of the data processing system configured to select the content item as a candidate for display on the user device based on the match between the content selection criteria structure and the query structure.

9. The system of claim 8 , wherein the content selection criteria structure and the query structure each comprise a graph, and matching a topology and content of the content selection criteria structure to a topology and content of the query structure comprises comparing, on a node-by-node basis, the content selection criteria structure with the query structure.

10. The system of claim 8 , wherein the data processing system is further configured to:

translate properties of the search query and the entities related to the search query into a flat data structure comprising information associated with the properties; and

identify, using the flat data structure, a plurality of content selection criteria associated with the flat data structure.

11. The system of claim 10 , wherein the data processing system is further configured to compare each of the content selection criteria with the properties of the search query entity to identify matching content selection criteria.

12. The system of claim 8 , wherein matching the topology and content of the content selection criteria structure to the topology and content of the query structure comprises determining that a confidence score satisfies a first threshold.

13. The system of claim 8 , wherein the entities that are related to the search query each have a confidence score that satisfies a second threshold.

14. The system of claim 8 , wherein matching the topology and content of the content selection criteria structure to the topology and content of the query structure comprises matching one or more entities related to the content selection criteria with one or more entities related to the search query.

15. A computer-readable storage device comprising processor executable instructions to select content via a computer network, the instructions further comprising instructions to:

receive, from a content provider associated with a content item and by a data processing system having one or more processors, content selection criteria specifying types of queries that make the content item eligible to be selected for display along with search results responsive to queries matching the specified types of queries;

generate, using a data structure that links related entities to each other, a content selection criteria structure that includes an entry for the content selection criteria, an entry for two or more entities that are related to the content selection criteria through a link in the data structure but do not appear in the received content selection criteria, and a connection between each pair of related entities in the content selection criteria structure, the generated content selection criteria structure being separate from the data structure;

receive, by the data processing system, a search query provided via a user device;

generate a query structure that includes an entry for the search query, an entry for two or more entities that are related to the search query through a link in the data structure but do not appear in the search query, and a connection between each pair of related entities in the query structure, the generated query structure being separate from the content selection criteria structure and the data structure;

match a topology and content of the content selection criteria structure to a topology and content of the query structure; and

select the content item as a candidate for display on the user device based on the match between the content selection criteria structure and the query structure.

16. The computer-readable storage device of claim 15 , wherein the content selection criteria structure and the query structure each comprise a graph, and matching a topology and content of the content selection criteria structure to a topology and content of the query structure comprises comparing, on a node-by-node basis, the content selection criteria structure with the query structure.

17. The computer-readable storage device of claim 15 , wherein the instructions are configured to:

translate properties of the search query and the entities related to the search query into a flat data structure comprising information associated with the properties; and

identify, using the flat data structure, a plurality of content selection criteria associated with the flat data structure.

18. The computer-readable storage device of claim 17 , wherein the instructions are configured to compare each of the content selection criteria with the properties of the search query entity to identify matching content selection criteria.

19. The computer-readable storage device of claim 15 , wherein matching the topology and content of the content selection criteria structure to the topology and content of the query structure comprises determining that a confidence score satisfies a first threshold.

20. The computer-readable storage device of claim 15 , wherein the entities that are related to the search query each have a confidence score that satisfies a second threshold.

Assignments (3)
CERTIFICATE OF CONVERSION Recorded Dec 28, 2017
From: GOOGLE INC.
To: GOOGLE LLC
Reel/Frame 044994/0140 →
CHANGE OF NAME Recorded Oct 20, 2017
From: GOOGLE INC.
To: GOOGLE LLC
Reel/Frame 044567/0001 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 29, 2016
From: JACOBSSON, HENRIK
To: GOOGLE INC.
Reel/Frame 040800/0360 →
Continuity (1)
Continuation 14242590 · Apr 1, 2014