Google Inc.

Microsoft Technology Licensing, LLC

Karthik Gopalratnam

Michael Alex Frumkin

Khanh B Nguyen

Gregory J Friedman

Ralph U Gasser

Marc Berndl

Myles A Sussman

Dan Liu

John David Dunagan

Jiahe Helen Wang

Sumit Basu

Diane L Tang

Sridhar Ramaswamy

Adam Isaac Juda

Nicholas Charles Fox

Amir Najmi

Edward A Baltz

Jonathan G Alferness

Levent Ertöz

Advertisement quality measures (e.g., predicted click through rates) are modified in accordance with a user's preferences with respect to domains to which the advertisements relate.

User-based ad ranking

Technologies relating to determining online advertisement statistics are described. In general, one aspect of the subject matter described in this specification can be embodied in a method that includes receiving a prediction value for a click-through rate for an online advertisement, the prediction value indicating a probability that the online advertisement will be accessed when displayed in an online medium, the prediction value based on a ratio of a number of times the advertisement has been accessed by users to a number of times the advertisement has been displayed to users, identifying at least one condition that is present when the online advertisement is to be displayed, the condition affecting accuracy of the prediction value, and generating a corrected prediction value based on at least one stored shift value associated with the at least one condition.

Determining online advertisement statistics

In general, in one aspect, a first request to provide one or more advertisements on a first web page is received, the first web page comprising one or more items of web content related to a query. A first quality score is calculated for a first advertisement included in a set of one or more candidate advertisements. The first advertisement is presented on the first web page based at least in part on the first quality score. A second request is received to provide one or more advertisements on a second web page, the second web page comprising one or more different items of web content related to the query. A second quality score for the first advertisement is calculated based at least in part on the previous presentation of the first advertisement. It is determined whether to present the first advertisement on the second web page based at least in part on the second quality score.

Advertisement selection

Methods and systems to modify the number and/or positioning of advertisements presented to a user based on that user's activity patterns (e.g., previous queries, query result selections, ad selections, etc.) and the order in which events constituting the activity patterns occurred. For example, the methods and systems can be based on a Markov model utilizing the user's activity patterns.

User-based advertisement positioning using markov models

An active learning framework is provided to extract information from particular fields from a variety of protocols. Extraction is performed in an unknown protocol, in which the user presents the system with a small number of labeled instances. The system then automatically generates an abundance of features and negative examples. A boosting approach is then used for feature selection and classifier combination. The system then displays its results for the user to correct and/or add new examples. The process can be iterated until the user is satisfied with the performance of the extraction capabilities provided by the classifiers generated by the system.

Active learning framework for automatic field extraction from network traffic

Growing community of inventors

San Francisco, CA, United States of America

Karthik Gopalratnam