Tony H Scott

US Patent:

20120321188, Dec 20, 2012

Filed:

Aug 16, 2012

Appl. No.:

13/587520

Inventors:

Michael Benjamin Selkowe Fertik - Palo Alto CA, US
Tony Scott - Sunnyvale CA, US
Thomas Dignan - Mountain View CA, US

International Classification:

G06K 9/34

US Classification:

382176

Abstract:

Presented are systems and methods for identifying information about a particular entity including acquiring electronic documents having unstructured text, that are selected based on one or more search terms from a plurality of terms related to the particular entity. Tokenizing the acquired documents to form a data matrix and then calculating a plurality of eigenvectors, using the data matrix and the transpose of the data matrix. The variance is then acquired for determining the amount of intra-clustering between the documents and then the acquired documents are clustered using some of the eigenvectors and the variance.

US Patent:

20120321202, Dec 20, 2012

Filed:

Jun 20, 2011

Appl. No.:

13/164641

Inventors:

Michael Benjamin Selkowe FERTIK - Palo Alto CA, US
Tony Scott - Sunnyvale CA, US
Thomas Dignan - Mountain View CA, US

International Classification:

G06K 9/62

US Classification:

382224

Abstract:

Presented are systems and methods for identifying information about a particular entity including acquiring electronic documents having unstructured text, that are selected based on one or more search terms from a plurality of terms related to the particular entity. Tokenizing the acquired documents to form a data matrix and then calculating a plurality of eigenvectors, using the data matrix and the transpose of the data matrix. The variance is then acquired for determining the amount of intra-clustering between the documents and then the acquired documents are clustered using some of the eigenvectors and the variance.

US Patent:

20120321204, Dec 20, 2012

Filed:

Aug 16, 2012

Appl. No.:

13/587562

Inventors:

Michael Benjamin Selkowe Fertik - Palo Alto CA, US
Tony Scott - Sunnyvale CA, US
Thomas Dignan - Mountain View CA, US

International Classification:

G06K 9/62

US Classification:

382225

Abstract:

Presented are systems and methods for identifying information about a particular entity including acquiring electronic documents having unstructured text, that are selected based on one or more search terms from a plurality of terms related to the particular entity. Tokenizing the acquired documents to form a data matrix and then calculating a plurality of eigenvectors, using the data matrix and the transpose of the data matrix. The variance is then acquired for determining the amount of intra-clustering between the documents and then the acquired documents are clustered using some of the eigenvectors and the variance.

US Patent:

20130086075, Apr 4, 2013

Filed:

Oct 4, 2011

Appl. No.:

13/252697

Inventors:

Tony Scott - Sunnyvale CA, US
Michael Benjamin Selkowe Fertik - Palo Alto CA, US
Thomas Gerardo Dignan - Mountain View CA, US

International Classification:

G06F 17/30

US Classification:

707747, 707E17044

Abstract:

Presented are systems and methods for creating a set of signatures including acquiring a data set and converting the data set into a plurality of data matrices. The system determines a prime number and determines a plurality of primitive roots to the prime number. The system calculates a template matrix using a first and second primitive root, of the plurality of primitive roots, and selects a data matrix property of interest. The system calculates a first hash function for each of the data matrices to create a first signature for each data matrix such that a main set of signatures is formed, wherein the first hash function is calculated using said property of interest, the prime number, and the template matrix. The system generates a main set of signatures based on the first hash functions, wherein the main set of signatures comprises a first signature for each data matrix.