Content item selection

• US 8,201,089 B2
• Filed: 07/14/2008
• Issued: 06/12/2012
• Est. Priority Date: 07/14/2008
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Perrow, Mike, Macgill, James Robert, Zhang, Dana, Verne, Nicholas, Symonds, David
• Primary Examiner(s): Hong, Stephen
• Assistant Examiner(s): LUDWIG, MATTHEW J
• Application Number:
  US12/172,335
• Publication Number:
  US 20100010958A1
• Time in Patent Office: 1,429 Days
• Field of Search: 715/246, 715/273, 715/712, 707/708, 707/728
• US Class Current: 715/273
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 16/9537 Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
• CPC Class Codes: G06Q 30/0261 based on user location

Abstract

A content item, e.g., an icon or advertisement content, is selected for placement in a display environment (e.g., on a map or adjacent to a map) in response to a request for the display environment based on a probability that the content item is relevant to a user that is requesting the display environment. The selection is facilitated by content targeting data (e.g., feature selection and query submission) that can be received from user devices while the map space is presented.

Claims

1. A method performed by one or more computers, the method comprising:

receiving requests for a map space, wherein the map space is a portion of a map for presentation in a display region on a user device;

receiving input data from display interfaces in the display region in response to presentations of the map space;

generating content targeting data for the map space, the content targeting data being generated based on the input data and semantic rules, wherein generating content targeting data based on the input data and semantic rules comprises generating expansion topics that are semantically related to the data input;

identifying the generated content targeting data that satisfies a threshold measure of relatedness to the map space, wherein the measure of relatedness is a probability that the content targeting data is relevant to a user that requests the map space;

associating the identified content targeting data with a map location corresponding to the map space;

ranking the associated content targeting data based on a measure of relatedness to the map space;

receiving a new request for the map space;

in response to the new request, determining that the map location is associated with the map space;

selecting the content targeting data that have been associated with the map location;

identifying a content item for display with the map space based on the selected content targeting data; and

providing the content item for display in the display region on the user device in response to the new request for the map space.

2. The method of claim 1, wherein identifying content targeting data that correspond to the map space comprises selecting all content targeting data for which the measure of relatedness meets the threshold measure of relatedness.

3. The method of claim 2, further comprising:

providing the content targeting data to a content item selector; and

receiving data that specify the content item selected for display in the display region on the user device in response to the request for the map space.

4. The method of claim 3, wherein the content item is selected based on a feature density of the map space.

5. The method of claim 1, wherein the input data are search queries.

6. A system comprising:

a content targeting data store storing content targeting data associated with a map space; and

one or more computers that are configured to interact with the content targeting data store, the one or more computers being further configured to perform operations including;

receiving requests for a map space, wherein the map space is a portion of a map for presentation in a display region on a user device;

receiving input data from display interfaces in the display region in response to presentations of the map space;

generating content targeting data for the map space, the content targeting data being generated based on the input data and semantic rules, wherein generating content targeting data based on the input data and semantic rules comprises generating expansion topics that are semantically related to the data input;

identifying the generated content targeting data that satisfies a threshold measure of relatedness to the map space, wherein the measure of relatedness is a probability that the content targeting data is relevant to a user that requests the map space;

associating the identified content targeting data with a map location corresponding to the map space;

ranking the associated content targeting data based on a measure of relatedness to the map space;

storing the ranked content targeting data in the content targeting data store;

receiving a new request for the map space;

in response to the new request, determining that the map location is associated with the map space;

selecting the content targeting data that have been associated with the map location;

identifying a content item for display with the map space based on the selected content targeting data; and

providing the content item for display in the display region on the user device in response to the new request for the map space.

7. Software stored in computer readable media and comprising instructions executable by a processing device and upon such execution cause the processing device to perform operations comprising:

receiving requests for a map space, wherein the map space is a portion of a map for presentation in a display region on a user device;

receiving input data from display interfaces in the display region in response to presentations of the map space;

generating content targeting data for the map space, the content targeting data being generated based on the input data and semantic rules, wherein generating content targeting data based on the input data and semantic rules comprises generating expansion topics that are semantically related to the data input;

identifying the generated content targeting data that satisfies a threshold measure of relatedness to the map space, wherein the measure of relatedness is a probability that the content targeting data is relevant to a user that requests the map space;

associating the identified content targeting data with a map location corresponding to the map space;

ranking the associated content targeting data based on a measure of relatedness to the map space;

receiving a new request for the map space;

in response to the new request, determining that the map location is associated with the map space;

selecting the content targeting data that have been associated with the map location;

identifying a content item for display with the map space based on the selected content targeting data; and

providing the content item for display in the display region on the user device in response to the new request for the map space.