Systems and methods for selecting content

Patent metadata

Field	Value
Publication number	US-9501530-B1
Application number	US-201414242603-A
Country	US
Kind code	B1
Filing date	Apr 1, 2014
Priority date	Apr 1, 2014
Publication date	Nov 22, 2016
Grant date	Nov 22, 2016

Abstract

Systems and methods of the disclosure relate to selecting content via a computer network. The system can receive a query to generate content selection criteria. The system can identify an entity of the query and a query graph based on the entity. The system can access a database to identify a template corresponding to the query graph. The template can include a topology and a named variable. The system can determine multiple semantic criteria corresponding to the named variable that match the query graph. The system can use a statistical metric of each of the matching semantic criteria to select candidate content selection criteria.

First claim

What is claimed is:

1. A method comprising:
receiving, using one or more processors, a search query;
identifying, using the one or more processors, a plurality of entities referred to in the search query, wherein each of the entities is associated with an entity ID uniquely assigned to the particular entity;
generating, using the search query, a search query graph that comprises:
a) the search query;
b) for each of the plurality of entities, the entity ID uniquely assigned to the particular entity;
c) for each of the plurality of entities, one or more properties of the particular entity, wherein the one or more properties comprise one or more other entities; and
d) one or more relationship connections between the plurality of entities and the one or more properties;

based on the search query, identifying one or more candidate content selection criteria graphs from a database using the search query, wherein each of the candidate content selection criteria graphs relates to one or more of the identified entities referred to in the search query, wherein the one or more candidate content selection criteria graphs are associated with one or more content items;
identifying, from the one or more candidate content selection criteria graphs, a particular content selection criteria graph that matches the search query graph based, at least in part, on a similarity between the one or more entities, one or more properties, and one or more relationship connections of the search query graph and the particular content selection criteria graph, wherein identifying a particular content selection criteria graph comprises comparing entity confidence scores of the search query graph with threshold confidence scores of the one or more candidate content selection criteria graphs;
identifying content items associated with the particular content selection criteria graph that are distributed using the particular content selection criteria graph; and
providing, for display on a computing device that submitted the search query, one or more of the identified content items.

2. The method of claim 1 , wherein identifying a particular content selection criteria graph comprises performing a node-by-node comparison of the search query graph with the one or more candidate content selection criteria graphs.

3. The method of claim 2 , wherein performing a node-by-node comparison comprises determining whether a topology of the search query graph matches a topology of one or more candidate content selection criteria graphs.

4. The method of claim 1 , wherein identifying a particular content selection criteria graph comprises comparing a topology of the search query graph with topologies of the one or more candidate content selection criteria graphs.

5. The method of claim 1 , further comprising conducting an auction using bids submitted by content providers of the identified content items.

6. The method of claim 1 , wherein generating the search query graph comprises accessing a data structure having entity information and identifying one or more properties of the plurality of entities from the entity information.

7. The method of claim 1 , wherein identifying one or more candidate content selection criteria graphs from the database using the search query comprises identifying semantic criteria related to the plurality of entities.

8. The method of claim 7 , wherein the semantic criteria corresponds to annotated information of an entity of a search query provided by a content provider.

9. The method of claim 7 , further comprising:
after identifying the semantic criteria, determining the effectiveness of the semantic criteria in content selection using a metric indicative of the effectiveness of the semantic criteria.

10. The method of claim 9 , wherein the metric is determined based on a term frequency-inverse document frequency.

11. The method of claim 9 , wherein the metric is determined based on an odds ratio.

12. A system comprising:
one or more computer processors; and
one or more non-transitory computer readable devices that include instructions that, when executed by the one or more computer processors, causes the processors to perform operations, the operations comprising:
receiving, using the one or more processors, a search query;
identifying, using the one or more processors, a plurality of entities referred to in the search query, wherein each of the entities is associated with an entity ID uniquely assigned to the particular entity;
generating, using the search query, a search query graph that comprises:
a) the search query;
b) for each of the plurality of entities, the entity ID uniquely assigned to the particular entity;
c) for each of the plurality of entities, one or more properties of the particular entity, wherein the one or more properties comprise one or more other entities; and
d) one or more relationship connections between the plurality of entities and the one or more properties;

based on the search query, identifying one or more candidate content selection criteria graphs from a database using the search query, wherein each of the candidate content selection criteria graphs relates to one or more of the identified entities referred to in the search query, wherein the one or more candidate content selection criteria graphs are associated with one or more content items;
identifying, from the one or more candidate content selection criteria graphs, a particular content selection criteria graph that matches the search query graph based, at least in part, on a similarity between the one or more entities, one or more properties, and one or more relationship connections of the search query graph and the particular content selection criteria graph, wherein identifying a particular content selection criteria graph comprises comparing entity confidence scores of the search query graph with threshold confidence scores of the one or more candidate content selection criteria graphs;
identifying content items associated with the particular content selection criteria graph that are distributed using the particular content selection criteria graph; and
providing, for display on a computing device that submitted the search query, one or more of the identified content items.

13. The system of claim 12 , wherein identifying a particular content selection criteria graph comprises performing a node-by-node comparison of the search query graph with the one or more candidate content selection criteria graphs.

14. The system of claim 13 , wherein performing a node-by-node comparison comprises determining whether a topology of the search query graph matches a topology of one or more candidate content selection criteria graphs.

15. The system of claim 12 , wherein identifying a particular content selection criteria graph comprises comparing a topology of the search query graph with topologies of the one or more candidate content selection criteria graphs.

16. The system of claim 12 , the operations further comprising conducting an auction using bids submitted by content providers of the identified content items.

17. The system of claim 12 , wherein identifying one or more candidate content selection criteria graphs from the database using the search query comprises identifying semantic criteria related to the plurality of entities.

18. A non-transitory computer-readable medium comprising processor executable instructions to select content via a computer network, the instructions further comprising instructions to:
receiving a search query;
identifying a plurality of e

Assignees

• Google Inc

Inventors

• Jacobsson Henrik

Classifications

• G06F16/951 Primary

  Indexing; Web crawling techniques · CPC title

• G06F16/9024 Primary

  Graphs; Linked lists (G06F16/9027 takes precedence) · CPC title

• G06F17/30507 Primary

  Physics · mapped topic

• G06F17/30864

  Physics · mapped topic

• G06F16/288

  Entity relationship models · CPC title