Steve Vranas

US Patent:

8489538, Jul 16, 2013

Filed:

Sep 21, 2012

Appl. No.:

13/624854

Inventors:

Jan Puzicha - Bonn, DE
Steve Vranas - Ashburn VA, US

Assignee:

Recommind, Inc. - San Francisco CA

International Classification:

G06F 9/44
G06N 7/02
G06N 7/06

US Classification:

706 52

Abstract:

Systems and methods for analyzing documents are provided herein. A plurality of documents and user input are received via a computing device. The user input includes hard coding of a subset of the plurality of documents, based on an identified subject or category. Instructions stored in memory are executed by a processor to generate an initial control set, analyze the initial control set to determine at least one seed set parameter, automatically code a first portion of the plurality of documents based on the initial control set and the seed set parameter associated with the identified subject or category, analyze the first portion of the plurality of documents by applying an adaptive identification cycle, and retrieve a second portion of the plurality of documents based on a result of the application of the adaptive identification cycle test on the first portion of the plurality of documents.

US Patent:

8554716, Oct 8, 2013

Filed:

Mar 28, 2011

Appl. No.:

13/074005

Inventors:

Jan Puzicha - Bonn, DE
Steve Vranas - Reston VA, US

Assignee:

Recommind, Inc. - San Francisco CA

International Classification:

G06F 9/44
G06N 7/02
G06N 7/06

US Classification:

706 52

Abstract:

Systems and methods for analyzing documents are provided herein. A plurality of documents and user input are received via a computing device. The user input includes hard coding of a subset of the plurality of documents, based on an identified subject or category. Instructions stored in memory are executed by a processor to generate an initial control set, analyze the initial control set to determine at least one seed set parameter, automatically code a first portion of the plurality of documents based on the initial control set and the seed set parameter associated with the identified subject or category, analyze the first portion of the plurality of documents by applying an adaptive identification cycle, and retrieve a second portion of the plurality of documents based on a result of the application of the adaptive identification cycle test on the first portion of the plurality of documents.

US Patent:

7933859, Apr 26, 2011

Filed:

May 25, 2010

Appl. No.:

12/787354

Inventors:

Jan Puzicha - Bonn, DE
Steve Vranas - Reston VA, US

Assignee:

Recommind, Inc. - San Francisco CA

International Classification:

G06F 15/18

US Classification:

706 62, 706 15, 706 20, 706 21, 706 45, 706 46, 706 52, 715700, 715701

Abstract:

Systems and methods for analyzing documents are provided herein. A plurality of documents and user input are received via a computing device. The user input includes hard coding of a subset of the plurality of documents, based on an identified subject or category. Instructions stored in memory are executed by a processor to generate an initial control set, analyze the initial control set to determine at least one seed set parameter, automatically code a first portion of the plurality of documents based on the initial control set and the seed set parameter associated with the identified subject or category, analyze the first portion of the plurality of documents by applying an adaptive identification cycle, and retrieve a second portion of the plurality of documents based on a result of the application of the adaptive identification cycle test on the first portion of the plurality of documents.

US Patent:

20220188708, Jun 16, 2022

Filed:

Mar 1, 2022

Appl. No.:

17/684186

Inventors:

- Wilmington DE, US
Steve Vranas - Ashburn VA, US

International Classification:

G06N 20/10
G06N 20/00
G06F 16/93
G06N 5/04
G06N 7/00

Abstract:

Systems and methods for analyzing documents are provided herein. A plurality of documents and user input are received via a computing device. The user input includes hard coding of a subset of the plurality of documents, based on an identified subject or category. Instructions stored in memory are executed by a processor to generate an initial control set, analyze the initial control set to determine at least one seed set parameter, automatically code a first portion of the plurality of documents based on the initial control set and the seed set parameter associated with the identified subject or category, analyze the first portion of the plurality of documents by applying an adaptive identification cycle, and retrieve a second portion of the plurality of documents based on a result of the application of the adaptive identification cycle test on the first portion of the plurality of documents.

US Patent:

20210224693, Jul 22, 2021

Filed:

Apr 1, 2021

Appl. No.:

17/220445

Inventors:

- Wilmington DE, US
Steve Vranas - Ashburn VA, US

International Classification:

G06N 20/10
G06N 20/00
G06F 16/93
G06N 5/04
G06N 7/00

Abstract:

Systems and methods for analyzing documents are provided herein. A plurality of documents and user input are received via a computing device. The user input includes hard coding of a subset of the plurality of documents, based on an identified subject or category. Instructions stored in memory are executed by a processor to generate an initial control set, analyze the initial control set to determine at least one seed set parameter, automatically code a first portion of the plurality of documents based on the initial control set and the seed set parameter associated with the identified subject or category, analyze the first portion of the plurality of documents by applying an adaptive identification cycle, and retrieve a second portion of the plurality of documents based on a result of the application of the adaptive identification cycle test on the first portion of the plurality of documents.

US Patent:

20210224694, Jul 22, 2021

Filed:

Apr 5, 2021

Appl. No.:

17/222283

Inventors:

- Wilmington DE, US
Steve Vranas - Ashburn VA, US

International Classification:

G06N 20/10
G06N 20/00
G06F 16/93
G06N 5/04
G06N 7/00

Abstract:

Systems and methods for analyzing documents are provided herein. A plurality of documents and user input are received via a computing device. The user input includes hard coding of a subset of the plurality of documents, based on an identified subject or category. Instructions stored in memory are executed by a processor to generate an initial control set, analyze the initial control set to determine at least one seed set parameter, automatically code a first portion of the plurality of documents based on the initial control set and the seed set parameter associated with the identified subject or category, analyze the first portion of the plurality of documents by applying an adaptive identification cycle, and retrieve a second portion of the plurality of documents based on a result of the application of the adaptive identification cycle test on the first portion of the plurality of documents.

US Patent:

20180121831, May 3, 2018

Filed:

Dec 21, 2017

Appl. No.:

15/851645

Inventors:

- San Francisco CA, US
Steve Vranas - Ashburn VA, US

International Classification:

G06N 99/00
G06N 7/00

Abstract:

Systems and methods for analyzing documents are provided herein. A plurality of documents and user input are received via a computing device. The user input includes hard coding of a subset of the plurality of documents, based on an identified subject or category. Instructions stored in memory are executed by a processor to generate an initial control set, analyze the initial control set to determine at least one seed set parameter, automatically code a first portion of the plurality of documents based on the initial control set and the seed set parameter associated with the identified subject or category, analyze the first portion of the plurality of documents by applying an adaptive identification cycle, and retrieve a second portion of the plurality of documents based on a result of the application of the adaptive identification cycle test on the first portion of the plurality of documents.

US Patent:

20170132530, May 11, 2017

Filed:

Jan 13, 2017

Appl. No.:

15/406542

Inventors:

- San Francisco CA, US
Steve Vranas - Ashburn VA, US

International Classification:

G06N 99/00
G06N 7/00

Abstract:

Systems and methods for analyzing documents are provided herein. A plurality of documents and user input are received via a computing device. The user input includes hard coding of a subset of the plurality of documents, based on an identified subject or category. Instructions stored in memory are executed by a processor to generate an initial control set, analyze the initial control set to determine at least one seed set parameter, automatically code a first portion of the plurality of documents based on the initial control set and the seed set parameter associated with the identified subject or category, analyze the first portion of the plurality of documents by applying an adaptive identification cycle, and retrieve a second portion of the plurality of documents based on a result of the application of the adaptive identification cycle test on the first portion of the plurality of documents.