IP Library Granted Patent US 9,064,264
Granted Patent B2
US 9,064,264 · App. 13/546,978 · Granted Jun 23, 2015

Predicting visibility of content items

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 9,064,264
App. No.
13/546,978
Granted
Jun 23, 2015
Kind
B2
Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer-readable storage medium, and including a method for predicting visibility of web pages. The method comprises identifying web pages that include slots for presenting content. The method further comprises, for each slot, creating a fingerprint based on a URL associated with the page and structural information associated with the slot's location on the page, determining a likelihood of the slot being visible when the web page is initially presented, the likelihood in the form of a predictive model, and saving the fingerprint and predictive model in a data structure. The method further comprises receiving a request for content from a web page, creating fingerprints associated with the web page, and comparing the fingerprints to fingerprints in the data structure. When a matching fingerprint is located, prediction data is used that is associated with a matching fingerprint for the web page.

Claims (30)

1. A method comprising:

identifying a plurality of web pages, each web page including one or more slots for presenting content served by a serving system in response to presentation of the web page to a user;

for each slot on each of the plurality of web pages:

creating a fingerprint based at least in part on a URL associated with the web page and structural information at least indicating where the slot is located on the page;

determining a predictive model that includes indicating a likelihood of the slot being visible when the web page is initially presented to the user; and

saving the fingerprint in a data structure at a first level including creating an entry that includes the fingerprint and the predictive model or a pointer to the predictive model;

receiving a request for content from a web page;

determining that the web page does not have reliable prediction data associated with it;

creating one or more fingerprints associated with the web page from which the request is received that are similar to fingerprints saved in the data structure; and

comparing the one or more fingerprints created for the web page from which the request is received to the fingerprints in the data structure, and when a matching fingerprint is located, using prediction data that is associated with the matching fingerprint for the web page that does not have reliable prediction data.

2. The method of claim 1 further comprising:

grouping ones of the fingerprints that have a logical relation and similar structure;

creating a group fingerprint for each group; and

saving the group fingerprint in the data structure at a second level including creating an entry that includes the group fingerprint and a predictive model associated with the group;

wherein comparing the one or more fingerprints includes comparing fingerprints at the first level prior to comparing fingerprints at a second level for matches.

3. The method of claim 2 further comprising:

for each web page in the plurality of web pages:

repeating the grouping, fingerprinting and saving a predetermined number of times including grouping previously created groups that have a logical relation and similar structure and storing new groups at an appropriate hierarchical level in the data structure; or

repeating the grouping, fingerprinting and saving a non-fixed number of times until an improvement in prediction capability, based on analyzing test data, falls below a threshold value;

and wherein comparing the one or more fingerprints includes comparing fingerprints in level order from most specific to least specific for matches.

4. The method of claim 3 wherein creating a fingerprint based at least in part on a URL associated with the page and structural information further includes creating a fingerprint at the first level from the URL and a page structure hash.

5. The method of claim 4 wherein creating a fingerprint at the second level includes creating a fingerprint from a shortened version of the URL and the page structure hash.

6. The method of claim 1 further comprising indexing the data structure using the fingerprints.

7. The method of claim 1 wherein using the prediction data further comprises using the prediction data to determine which content item to serve responsive to the request.

8. The method of claim 1 further comprising:

creating a type fingerprint based at least in part on a type associated with the slot;

determining a type likelihood of the slot being visible when the web page is initially presented to the user using a respective type, the likelihood being of the form of a type prediction; and

saving the type fingerprint in the data structure at another level.

9. The method of claim 8 wherein the type is selected from a group comprising text ads, image ads, graphics ads, and combinations thereof and the other level is a zero level.

10. The method of claim 1 wherein using the prediction data includes using the prediction data to adjust a bid in an auction for selecting an advertisement for an advertisement slot.

Assignments (2)
CHANGE OF NAME Recorded Oct 2, 2017
From: GOOGLE INC.
To: GOOGLE LLC
Reel/Frame 044334/0466 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 8, 2013
From: REITSMA, PAUL SCHELTE ALBERT; IV, THOMAS J. MURRAY; ZHANG, PENG
To: GOOGLE INC.
Reel/Frame 030375/0265 →