The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Jul. 07, 2020

Filed:

Oct. 30, 2018
Applicant:

Abbyy Production Llc, Moscow, RU;

Inventor:
Assignee:

ABBYY Production LLC, Moscow, RU;

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06K 9/00 (2006.01); G06K 9/62 (2006.01); G06K 9/46 (2006.01);
U.S. Cl.
CPC ...
G06K 9/6202 (2013.01); G06K 9/00442 (2013.01); G06K 9/00469 (2013.01); G06K 9/46 (2013.01); G06K 9/626 (2013.01); G06K 9/628 (2013.01); G06K 9/6262 (2013.01); G06K 9/6281 (2013.01); G06K 2209/01 (2013.01);
Abstract

Disclosed are systems and method for determining document type of a digital document. An example method comprises: executing a first MLA classifier in order to determine a document type for a digital document, wherein the first MLA classifier is associated with a first hierarchical order of execution, and wherein the first MLA classifier is trained on a first trained dataset containing a first document type and a second document type, wherein the first document type is confidently predictable by the first MLA classifier and the second document type is not confidently predictable by the first MLA classifier; and responsive to determining that the first MLA classifier produced the second document type for the digital document, executing a second MLA classifier in order to determine the document type for the digital document, wherein the second MLA classifier is associated with a second hierarchical order of execution following the first hierarchical order of execution, and wherein the second MLA classifier is trained on a second trained dataset containing no documents of the first document type.


Find Patent Forward Citations

Loading…