公开(公告)号：US12118294B2

公开(公告)日：2024-10-15

申请号：US18309857

申请日：2023-05-01

Applicant: Open Text Corporation

Inventor： David Comeau ,  Jeffrey Williams ,  Evgeny Kolesnikov ,  Michael Itkin ,  June Qiang ,  James Relunia ,  Brian Sue

IPC: G06F40/16 ,  G06F40/154 ,  G06N20/00 ,  G06V30/413

CPC classification number: G06F40/16 ,  G06F40/154 ,  G06N20/00 ,  G06V30/413

Abstract: Systems, methods, and products for auto tagging structured PDF documents that do not have accessibility tags. In one embodiment, structured PDF documents having accessibility tags are first parsed and analyzed to organize the visual components of the documents. The relationships of the identified objects to DOM elements (e.g., tags) are determined, and the objects and related DOM elements are stored in training files. The training files are used to train various classifiers. Untagged PDF documents are then parsed to identify included visual objects, and the classifiers are used to determine DOM elements that should be associated with visual objects identified in the untagged PDF documents. This information is used to construct a DOM structure corresponding to each untagged document. A new PDF is then generated corresponding to each untagged document using the generated DOM structure and visual object information.

公开(公告)号：US20230315974A1

公开(公告)日：2023-10-05

申请号：US18309857

申请日：2023-05-01

Applicant: Open Text Corporation

Inventor： David Comeau ,  Jeffrey Williams ,  Evgeny Kolesnikov ,  Michael Itkin ,  June Qiang ,  James Relunia ,  Brian Sue

IPC: G06F40/16 ,  G06F40/154 ,  G06N20/00 ,  G06V30/413

CPC classification number: G06F40/16 ,  G06F40/154 ,  G06N20/00 ,  G06V30/413

Abstract: Systems, methods, and products for auto tagging structured PDF documents that do not have accessibility tags. In one embodiment, structured PDF documents having accessibility tags are first parsed and analyzed to organize the visual components of the documents. The relationships of the identified objects to DOM elements (e.g., tags) are determined, and the objects and related DOM elements are stored in training files. The training files are used to train various classifiers. Untagged PDF documents are then parsed to identify included visual objects, and the classifiers are used to determine DOM elements that should be associated with visual objects identified in the untagged PDF documents. This information is used to construct a DOM structure corresponding to each untagged document. A new PDF is then generated corresponding to each untagged document using the generated DOM structure and visual object information.

公开(公告)号：US11675970B2

公开(公告)日：2023-06-13

申请号：US17174686

申请日：2021-02-12

Applicant: Open Text Corporation

Inventor： David Comeau ,  Jeffrey Williams ,  Evgeny Kolesnikov ,  Michael Itkin ,  June Qiang ,  James Relunia ,  Brian Sue

IPC: G06F40/16 ,  G06F40/154 ,  G06N20/00 ,  G06V30/413

CPC classification number: G06F40/16 ,  G06F40/154 ,  G06N20/00 ,  G06V30/413

Abstract: Systems, methods, and products for auto tagging structured PDF documents that do not have accessibility tags. In one embodiment, structured PDF documents having accessibility tags are first parsed and analyzed to organize the visual components of the documents. The relationships of the identified objects to DOM elements (e.g., tags) are determined, and the objects and related DOM elements are stored in training files. The training files are used to train various classifiers. Untagged PDF documents are then parsed to identify included visual objects, and the classifiers are used to determine DOM elements that should be associated with visual objects identified in the untagged PDF documents. This information is used to construct a DOM structure corresponding to each untagged document. A new PDF is then generated corresponding to each untagged document using the generated DOM structure and visual object information.

公开(公告)号：US20210271805A1

公开(公告)日：2021-09-02

申请号：US17174686

申请日：2021-02-12

Applicant: Open Text Corporation

Inventor： David Comeau ,  Jeffrey Williams ,  Evgeny Kolesnikov ,  Michael Itkin ,  June Qiang ,  James Relunia ,  Brian Sue

IPC: G06F40/16 ,  G06N20/00 ,  G06F40/154

Abstract: Systems, methods, and products for auto tagging structured PDF documents that do not have accessibility tags. In one embodiment, structured PDF documents having accessibility tags are first parsed and analyzed to organize the visual components of the documents. The relationships of the identified objects to DOM elements (e.g., tags) are determined, and the objects and related DOM elements are stored in training files. The training files are used to train various classifiers. Untagged PDF documents are then parsed to identify included visual objects, and the classifiers are used to determine DOM elements that should be associated with visual objects identified in the untagged PDF documents. This information is used to construct a DOM structure corresponding to each untagged document. A new PDF is then generated corresponding to each untagged document using the generated DOM structure and visual object information.