Identifying a level of relevancy of a keyword cluster related to an event category for a given time period relative to the event

• US 9,779,144 B1
• Filed: 08/02/2014
• Issued: 10/03/2017
• Est. Priority Date: 08/02/2014
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Hampson, Courtney, Sanio, Jason Robert Richard
• Primary Examiner(s): Pyo, Monica
• Application Number:
  US14/450,213
• Time in Patent Office: 1,158 Days
• Field of Search: 707723, 707725, 707726, 707728, 707731
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/93 Document management systems

Abstract

Systems and methods for identifying relevancy scores of a keyword cluster related to an event category for a given time period relative to an event of the event category. Processors identify an event and determine event parameters of the event. Processors determine keyword clusters associated with the event parameters for serving content. Processors generate a relevancy score for each of the keyword clusters over plurality of time periods relative to the event. The relevancy score of a first subset of the keyword clusters is higher during a first time period than a second time period and the relevancy score of a second subset of the keyword clusters is higher during the second time period than the first time period. Processors create, for the event, a data structure including the keyword clusters and the generated relevancy scores for each of the keyword clusters over the time periods relative to the event.

Claims

1. A method of creating a data structure that includes a plurality of relevancy scores, each indicating a level of relevancy of a keyword cluster related to an event category for a given time period relative to an event of the event category, comprising:

identifying a calendar event associated with a device identifier;

determining, by one or more processors, event parameters of the identified calendar event;

determining, from the event parameters, a plurality of keyword clusters associated with the event parameters for serving content to a computing device associated with the device identifier;

generating a relevancy score for each of the plurality of keyword clusters over a plurality of time periods relative to the calendar event, the relevancy score of a first subset of the plurality of keyword clusters being higher during a first time period than a second time period and the relevancy score of a second subset of the plurality of keyword clusters being higher during the second time period than the first time period;

creating, for the event, a data structure including the plurality of keyword clusters and the generated relevancy scores for each of the plurality of keyword clusters over the plurality of time periods relative to the calendar event;

storing, to a memory, the created data structure;

receiving a request to serve content on the computing device associated with the device identifier;

determining a time period between a time at which the request was received and a time at which the calendar event is scheduled;

selecting, from the stored data structure, a keyword cluster from the plurality of keyword clusters based on the relevancy score of the keyword cluster for the determined time period and an event category to which the identified calendar event belongs;

using, during the determined time period, the keyword cluster selected from the plurality of keyword clusters to select a content item in response to the request; and

transmitting, to the computing device associated with the device identifier, in response to the request, the content item selected using the keyword cluster selected from the plurality of keyword clusters to cause the computing device to display the content item.

2. The method of claim 1, wherein determining, from the event parameters, a plurality of keyword clusters associated with the event parameters for serving content to a computing device associated with the device identifier, includes:

identifying, from the event parameters, an event category to which the calendar event corresponds; and

identifying the plurality of keywords associated with the event category.

3. The method of claim 1, wherein identifying the calendar event associated with the device identifier includes identifying the calendar event from a calendar of the device identifier.

4. The method of claim 1, wherein determining event parameters of the identified calendar event includes:

determining a time at which the calendar event is scheduled;

determining a location at which the calendar event is scheduled; and

determining a type of calendar event.

5. The method of claim 1, wherein determining, from the event parameters, the plurality of keyword clusters associated with the event parameters includes performing, in a database, a lookup for keyword clusters based on the event parameters.

6. The method of claim 1, wherein generating the relevancy score for each of the plurality of keyword clusters over the plurality of time periods relative to the calendar event includes determining, from historical data, performance of content associated with the keyword cluster across each of a plurality of time periods relative to calendar events similar to the calendar event associated with the device identifier.

7. The method of claim 6, wherein determining, from historical data, performance of content associated with the keyword cluster across each of a plurality of time periods relative to events similar to the event associated with the device identifier includes:

identifying, from historical data, a content item selected for display that is associated with a particular keyword cluster of the plurality of keyword clusters;

determining, for at least one device identifier to which the content item was served, an event corresponding to which the keyword cluster was determined;

determining a time associated with the calendar event;

determining a time period from the event at which the content item was served; and

determining if any action was taken responsive to providing the content for display.

8. A system for creating a data structure that includes a plurality of relevancy scores, each indicating a level of relevancy of a keyword cluster related to an event category for a given time period relative to the event, comprising:

a memory; and

one or more processors configured to;

identify a calendar event associated with a device identifier;

determine event parameters of the identified calendar event;

determine, from the event parameters, a plurality of keyword clusters associated with the event parameters for serving content to a computing device associated with the device identifier;

generate a relevancy score for each of the plurality of keyword clusters over a plurality of time periods relative to the calendar event, the relevancy score of a first subset of the plurality of keyword clusters being higher during a first time period than a second time period and the relevancy score of a second subset of the plurality of keyword clusters being higher during the second time period than the first time period;

create, for the event, a data structure including the plurality of keyword clusters and the generated relevancy scores for each of the plurality of keyword clusters over the plurality of time periods relative to the calendar event;

store, to a memory, the created data structure;

receive a request to serve content at the computing device associated with the device identifier;

determine a time period between a time at which the request was received and a time at which the calendar event is scheduled; and

select, from the stored data structure, a keyword cluster from the plurality of keyword clusters based on the relevancy score of the keyword cluster for the determined time period and an event category to which the identified calendar event belongs;

use, during the determined time period, the keyword cluster selected from the plurality of keyword clusters to select a content item in response to the request; and

transmit, to the computing device associated with the device identifier, in response to the request, the content item selected using the keyword cluster selected from the plurality of keyword clusters to cause the computing device to display the content item.

9. The system of claim 8, wherein determining, from the event parameters, a plurality of keyword clusters associated with the event parameters for serving content to a computing device associated with the device identifier, includes:

identifying, from the event parameters, an event category to which the event corresponds; and

identifying the plurality of keywords associated with the event category.

10. The system of claim 8, wherein to identify an event associated with a device identifier, the one or more processors are configured to identify the event from a calendar of the device identifier.

11. The system of claim 8, wherein to determine event parameters of the identified event, the one or more processors are configured to:

determine a time at which the event is scheduled;

determine a location at which the event is scheduled; and

determine a type of event.

12. The system of claim 8, wherein to determine, from the event parameters, a plurality of keyword clusters associated with the event parameters, the one or more processors are configured to perform, in a database, a lookup for keyword clusters based on the event parameters.

13. The system of claim 8, wherein to generate a relevancy score for each of the plurality of keyword clusters over a plurality of time periods relative to the event, the one or more processors are configured to determine, from historical data, performance of content associated with the keyword cluster across each of a plurality of time periods relative to events similar to the event associated with the device identifier.

14. The system of claim 13, wherein to determine, from historical data, performance of content associated with the keyword cluster across each of a plurality of time periods relative to events similar to the event associated with the device identifier, the one or more processors are configured to:

identify, from historical data, a content item selected for display that is associated with a particular keyword cluster of the plurality of keyword clusters;

determine, for at least one device identifier to which the content item was served, an event corresponding to which the keyword cluster was determined;

determine a time associated with the event;

determine a time period from the event at which the content item was served; and

determine if any action was taken responsive to providing the content for display.

15. A non-transitory computer-readable storage medium having computer-executable instructions stored thereon, which when executed by one or more processors, cause the one or more processors to perform operations comprising:

identifying a calendar event associated with a device identifier;

determining event parameters of the identified calendar event;

determining, from the event parameters, a plurality of keyword clusters associated with the event parameters for serving content to a computing device associated with the device identifier;

generating a relevancy score for each of the plurality of keyword clusters over a plurality of time periods relative to the event, the relevancy score of a first subset of the plurality of keyword clusters being higher during a first time period than a second time period and the relevancy score of a second subset of the plurality of keyword clusters being higher during the second time period than the first time period;

creating, for the event, a data structure including the plurality of keyword clusters and the generated relevancy scores for each of the plurality of keyword clusters over the plurality of time periods relative to the event;

storing, to a memory, the created data structure;

receiving a request to serve content on the computing device associated with the device identifier;

determining a time period between a time at which the request was received and a time at which the calendar event is scheduled; and

selecting, from the stored data structure, a keyword cluster from the plurality of keyword clusters based on the relevancy score of the keyword cluster for the determined time period and an event category to which the identified calendar event belongs;

using, during the determined time period, the keyword cluster selected from the plurality of keyword clusters to select a content item in response to the request; and

transmitting, to the computing device associated with the device identifier, in response to the request, the content item selected using the keyword cluster selected from the plurality of keyword clusters to cause the computing device to display the content item.

16. The computer-readable storage medium of claim 15, wherein determining, from the event parameters, a plurality of keyword clusters associated with the event parameters for serving content to a computing device associated with the device identifier, includes:

identifying, from the event parameters, an event category to which the event corresponds; and

identifying the plurality of keywords associated with the event category.

17. The computer-readable storage medium of claim 15, wherein identifying an event associated with a device identifier includes identifying the event from a calendar of the device identifier.