Alan J Halverson

Address:

511 Smt Dr, Santa Cruz, CA 95060

Phone:

8314260108

VIN:

4S4BRDJC0B2412484

Make:

SUBARU

Model:

OUTBACK

Year:

2011

US Patent:

8139495, Mar 20, 2012

Filed:

Sep 13, 2007

Appl. No.:

11/854918

Inventors:

Sreenivas Gollapudi - Cupertino CA, US
Alan D. Halverson - Sunnyvale CA, US
Krishnaram G. Kenthapadi - Mountain View CA, US

Assignee:

Microsoft Corporation - Redmond WA

International Classification:

H04L 1/00
H04J 3/14
G01R 31/08
G06F 11/00
G08C 15/00

US Classification:

370252, 370432

Abstract:

A method, computer-readable medium, and system for providing a quality measurement based on communications within a communication application. Communication attributes that include information associated with a user's communications are obtained. In embodiments, such communication attributes may pertain to communication duration and communication frequency. Upon obtaining communication attributes, a quality measurement may be determined based on the communication attributes. Such a quality measurement provides an indication of the quality of the user's communications. In embodiments, the quality measurement may be stored, communicated to a user, or implemented within a communication application.

US Patent:

20090157644, Jun 18, 2009

Filed:

Dec 12, 2007

Appl. No.:

11/954218

Inventors:

Sreenivas Gollapudi - Cupertino CA, US
Alan Halverson - Sunnyvale CA, US

Assignee:

MICROSOFT CORPORATION - Redmond WA

International Classification:

G06F 7/06

US Classification:

707 5, 707E17014

Abstract:

Large numbers of lists of entities may be mined for similar entities to related searches. A representation for each list may be determined to provide for a comparison between lists and to support membership checks. A score for an element in a list may be computed that represents the validity of an item in the corpus of lists. Thus, a spurious element would receive a very low score, where a valid element would receive a higher score. A list weight is then computed using the constituent element weights, and the element and list weight are used to compute the nearest neighbors of a given query element.

US Patent:

20090306996, Dec 10, 2009

Filed:

Jun 5, 2008

Appl. No.:

12/133370

Inventors:

Panayiotis Tsaparas - Palo Alto CA, US
Krishnaram N. G. Kenthapadi - Mountain View CA, US
Alan Halverson - Sunnyvale CA, US

Assignee:

MICROSOFT CORPORATION - Redmond WA

International Classification:

G06Q 99/00

US Classification:

705 1

Abstract:

A social network may be used to determine a rating of a user with no prior history. The ratings for unrated nodes may be inferred from the existing ratings of users associated with the unrated node in either or both the underlying social network or other social networks. Additionally in some implementations, the effect of the rating of a rated node to an unrated node diminishes as the strength of their relationships decreases. In some cases, a social network may be modeled as an electrical network, and ratings may be modeled as voltages on the nodes of the social network, relationships in the social network may be modeled as connections in the electrical network, and in some cases the strength of relationships may be modeled as conductance of the connections. Ratings for nodes may be determined using Kirchhoff's Law and in some cases by solving a set of linear equations or by propagating positive and negative ratings using a random walk with absorbing states.

US Patent:

20090313286, Dec 17, 2009

Filed:

Jun 17, 2008

Appl. No.:

12/140272

Inventors:

Nina Mishra - Newark CA, US
Rakesh Agrawal - San Jose CA, US
Sreenivas Gollapudi - Cupertino CA, US
Alan Halverson - Sunnyvale CA, US
Krishnaram N. G. Kenthapadi - Mountain View CA, US
Rina Panigrahy - Mountain View CA, US
John C. Shafer - Los Altos CA, US
Panayiotis Tsaparas - Palo Alto CA, US

Assignee:

MICROSOFT CORPORATION - Redmond WA

International Classification:

G06F 7/00
G06F 17/30

US Classification:

707102, 707E17005

Abstract:

Data from a click log may be used to generate training data for a search engine. The pages clicked as well as the pages skipped by a user may be used to assess the relevance of a page to a query. Labels for training data may be generated based on data from the click log. The labels may pertain to the relevance of a page to a query.