Patents by Inventor Andrew Begun
Andrew Begun has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11822880Abstract: Machine learning, artificial intelligence, and other computer-implemented methods are used to identify various semantically important chunks in documents, automatically label them with appropriate datatypes and semantic roles, and use this enhanced information to assist authors and to support downstream processes. Chunk locations, datatypes, and semantic roles can often be automatically determined from what is here called “context”, to wit, the combination of their formatting, structure, and content; those of adjacent or nearby content; overall patterns of occurrence in a document, and similarities of all these things across documents (mainly but not exclusively among documents in the same document set).Type: GrantFiled: August 5, 2020Date of Patent: November 21, 2023Assignee: Docugami, Inc.Inventors: Andrew Begun, Steven DeRose, Taqi Jaffri, Luis Marti Orosa, Michael Palmer, Jean Paoli, Christina Pavlopoulou, Elena Pricoiu, Swagatika Sarangi, Marcin Sawicki, Manar Shehadeh, Michael Taron, Bhaven Toprani, Zubin Rustom Wadia, David Watson, Eric White, Joshua Yongshin Fan, Kush Gupta, Andrew Minh Hoang, Zhanlin Liu, Jerome George Paliakkara, Zhaofeng Wu, Yue Zhang, Xiaoquan Zhou
-
Patent number: 11816428Abstract: Machine learning, artificial intelligence, and other computer-implemented methods are used to identify various semantically important chunks in documents, automatically label them with appropriate datatypes and semantic roles, and use this enhanced information to assist authors and to support downstream processes. Chunk locations, datatypes, and semantic roles can often be automatically determined from what is here called “context”, to wit, the combination of their formatting, structure, and content; those of adjacent or nearby content; overall patterns of occurrence in a document, and similarities of all these things across documents (mainly but not exclusively among documents in the same document set).Type: GrantFiled: August 5, 2020Date of Patent: November 14, 2023Assignee: Docugami, Inc.Inventors: Andrew Begun, Steven DeRose, Taqi Jaffri, Luis Marti Orosa, Michael Palmer, Jean Paoli, Christina Pavlopoulou, Elena Pricoiu, Swagatika Sarangi, Marcin Sawicki, Manar Shehadeh, Michael Taron, Bhaven Toprani, Zubin Rustom Wadia, David Watson, Eric White, Joshua Yongshin Fan, Kush Gupta, Andrew Minh Hoang, Zhanlin Liu, Jerome George Paliakkara, Zhaofeng Wu, Yue Zhang, Xiaoquan Zhou
-
Patent number: 11507740Abstract: Machine learning, artificial intelligence, and other computer-implemented methods are used to identify various semantically important chunks in documents, automatically label them with appropriate datatypes and semantic roles, and use this enhanced information to assist authors and to support downstream processes. Chunk locations, datatypes, and semantic roles can often be automatically determined from what is here called “context”, to wit, the combination of their formatting, structure, and content; those of adjacent or nearby content; overall patterns of occurrence in a document, and similarities of all these things across documents (mainly but not exclusively among documents in the same document set).Type: GrantFiled: August 5, 2020Date of Patent: November 22, 2022Assignee: Docugami, Inc.Inventors: Andrew Begun, Steven DeRose, Taqi Jaffri, Luis Marti Orosa, Michael Palmer, Jean Paoli, Christina Pavlopoulou, Elena Pricoiu, Swagatika Sarangi, Marcin Sawicki, Manar Shehadeh, Michael Taron, Bhaven Toprani, Zubin Rustom Wadia, David Watson, Eric White, Joshua Yongshin Fan, Kush Gupta, Andrew Minh Hoang, Zhanlin Liu, Jerome George Paliakkara, Zhaofeng Wu, Yue Zhang, Xiaoquan Zhou
-
Publication number: 20210081602Abstract: Machine learning, artificial intelligence, and other computer-implemented methods are used to identify various semantically important chunks in documents, automatically label them with appropriate datatypes and semantic roles, and use this enhanced information to assist authors and to support downstream processes. Chunk locations, datatypes, and semantic roles can often be automatically determined from what is here called “context”, to wit, the combination of their formatting, structure, and content; those of adjacent or nearby content; overall patterns of occurrence in a document, and similarities of all these things across documents (mainly but not exclusively among documents in the same document set).Type: ApplicationFiled: August 5, 2020Publication date: March 18, 2021Inventors: Andrew Begun, Steven DeRose, Taqi Jaffri, Luis Marti Orosa, Michael Palmer, Jean Paoli, Christina Pavlopoulou, Elena Pricoiu, Swagatika Sarangi, Marcin Sawicki, Manar Shehadeh, Michael Taron, Bhaven Toprani, Zubin Rustom Wadia, David Watson, Eric White, Joshua Yongshin Fan, Kush Gupta, Andrew Minh Hoang, Zhanlin Liu, Jerome George Paliakkara, Zhaofeng Wu, Yue Zhang, Xiaoquan Zhou
-
Publication number: 20210081613Abstract: Machine learning, artificial intelligence, and other computer-implemented methods are used to identify various semantically important chunks in documents, automatically label them with appropriate datatypes and semantic roles, and use this enhanced information to assist authors and to support downstream processes. Chunk locations, datatypes, and semantic roles can often be automatically determined from what is here called “context”, to wit, the combination of their formatting, structure, and content; those of adjacent or nearby content; overall patterns of occurrence in a document, and similarities of all these things across documents (mainly but not exclusively among documents in the same document set).Type: ApplicationFiled: August 5, 2020Publication date: March 18, 2021Inventors: Andrew Begun, Steven DeRose, Taqi Jaffri, Luis Marti Orosa, Michael Palmer, Jean Paoli, Christina Pavlopoulou, Elena Pricoiu, Swagatika Sarangi, Marcin Sawicki, Manar Shehadeh, Michael Taron, Bhaven Toprani, Zubin Rustom Wadia, David Watson, Eric White, Joshua Yongshin Fan, Kush Gupta, Andrew Minh Hoang, Zhanlin Liu, Jerome George Paliakkara, Zhaofeng Wu, Yue Zhang, Xiaoquan Zhou
-
Publication number: 20210081608Abstract: Machine learning, artificial intelligence, and other computer-implemented methods are used to identify various semantically important chunks in documents, automatically label them with appropriate datatypes and semantic roles, and use this enhanced information to assist authors and to support downstream processes. Chunk locations, datatypes, and semantic roles can often be automatically determined from what is here called “context”, to wit, the combination of their formatting, structure, and content; those of adjacent or nearby content; overall patterns of occurrence in a document, and similarities of all these things across documents (mainly but not exclusively among documents in the same document set).Type: ApplicationFiled: August 5, 2020Publication date: March 18, 2021Inventors: Andrew Begun, Steven DeRose, Taqi Jaffri, Luis Marti Orosa, Michael Palmer, Jean Paoli, Christina Pavlopoulou, Elena Pricoiu, Swagatika Sarangi, Marcin Sawicki, Manar Shehadeh, Michael Taron, Bhaven Toprani, Zubin Rustom Wadia, David Watson, Eric White, Joshua Yongshin Fan, Kush Gupta, Andrew Minh Hoang, Zhanlin Liu, Jerome George Paliakkara, Zhaofeng Wu, Yue Zhang, Xiaoquan Zhou
-
Publication number: 20210081411Abstract: Machine learning, artificial intelligence, and other computer-implemented methods are used to identify various semantically important chunks in documents, automatically label them with appropriate datatypes and semantic roles, and use this enhanced information to assist authors and to support downstream processes. Chunk locations, datatypes, and semantic roles can often be automatically determined from what is here called “context”, to wit, the combination of their formatting, structure, and content; those of adjacent or nearby content; overall patterns of occurrence in a document, and similarities of all these things across documents (mainly but not exclusively among documents in the same document set).Type: ApplicationFiled: August 5, 2020Publication date: March 18, 2021Inventors: Andrew Begun, Steven DeRose, Taqi Jaffri, Luis Marti Orosa, Michael Palmer, Jean Paoli, Christina Pavlopoulou, Elena Pricoiu, Swagatika Sarangi, Marcin Sawicki, Manar Shehadeh, Michael Taron, Bhaven Toprani, Zubin Rustom Wadia, David Watson, Eric White, Joshua Yongshin Fan, Kush Gupta, Andrew Minh Hoang, Zhanlin Liu, Jerome George Paliakkara, Zhaofeng Wu, Yue Zhang, Xiaoquan Zhou
-
Publication number: 20210081601Abstract: Machine learning, artificial intelligence, and other computer-implemented methods are used to identify various semantically important chunks in documents, automatically label them with appropriate datatypes and semantic roles, and use this enhanced information to assist authors and to support downstream processes. Chunk locations, datatypes, and semantic roles can often be automatically determined from what is here called “context”, to wit, the combination of their formatting, structure, and content; those of adjacent or nearby content; overall patterns of occurrence in a document, and similarities of all these things across documents (mainly but not exclusively among documents in the same document set).Type: ApplicationFiled: August 5, 2020Publication date: March 18, 2021Inventors: Andrew Begun, Steven DeRose, Taqi Jaffri, Luis Marti Orosa, Michael Palmer, Jean Paoli, Christina Pavlopoulou, Elena Pricoiu, Swagatika Sarangi, Marcin Sawicki, Manar Shehadeh, Michael Taron, Bhaven Toprani, Zubin Rustom Wadia, David Watson, Eric White, Joshua Yongshin Fan, Kush Gupta, Andrew Minh Hoang, Zhanlin Liu, Jerome George Paliakkara, Zhaofeng Wu, Yue Zhang, Xiaoquan Zhou
-
Publication number: 20070162479Abstract: Various embodiments are disclosed relating to a compression of documents. According to an example embodiment, a document may be compressed by replacing one or more language constructs in the document with a language-based replacement code. In addition, the document may be compressed by replacing one or more text strings in the document with a schema-based replacement code.Type: ApplicationFiled: January 9, 2006Publication date: July 12, 2007Applicant: Microsoft CorporationInventors: Andrew Begun, Thomas Lawrence
-
Publication number: 20070162579Abstract: Various embodiments are disclosed relating to dynamic storage of documents. According to an example embodiment, a location may be dynamically determined from a group of locations to store a state associated with a document based on one or more criteria.Type: ApplicationFiled: January 9, 2006Publication date: July 12, 2007Applicant: Microsoft CorporationInventors: Thomas Lawrence, Andrew Begun
-
Publication number: 20070061706Abstract: Various embodiments provide a translation mechanism in which property architectures associated with various objects are translated into a schema that maintains the semantics of the property architecture. In at least some of the embodiments, the property architectures are translated into hierarchical, standards-based schemas which enhance the environments in which associated objects can be consumed and processed.Type: ApplicationFiled: September 14, 2005Publication date: March 15, 2007Applicant: Microsoft CorporationInventors: Shiraz Cupala, Andrew Begun, Raj Merchant, Dragos Barac, Hani Saliba
-
Publication number: 20060235829Abstract: Systems and/or methods that enable an electronic form to provide data external to the electronic form in response to a query while offline with respect to a data source from which the data originated are described. These systems and methods may also, in one embodiment, receive data from a data source that is capable of being inaccessible and associate that data with an electronic form, a user, and a query. These systems and methods may, in another embodiment, provide data in response to a query made by a user to an electronic form that was previously associated with the electronic form, the user, and the query.Type: ApplicationFiled: April 15, 2005Publication date: October 19, 2006Applicant: Microsoft CorporationInventors: Nima Mirzad, Andrew Begun, Michael Palmer, Laurent Mollicone
-
Publication number: 20060107252Abstract: Systems and methods enabling creation and/or use of an electronic form capable of allowing a user to select from mutually exclusive options without the electronic form being in an invalid state are described. One of the described electronic forms remains valid to its schema by atomic swapping of data substructures corresponding to the form's mutually exclusive options. A method and a user interface for creating some of these electronic forms are also described.Type: ApplicationFiled: November 15, 2004Publication date: May 18, 2006Applicant: Microsoft CorporationInventors: Michael Smuga, Alessandro Catorcini, Scott Roberts, Willson Raj David, Andrew Begun