MACHINE LEARNING TECHNIQUES FOR IDENTIFYING LOGICAL SECTIONS IN UNSTRUCTURED DATA

    公开(公告)号:US20220156489A1

    公开(公告)日:2022-05-19

    申请号:US16951983

    申请日:2020-11-18

    Applicant: Adobe Inc.

    Abstract: Methods and systems disclosed herein relate generally to systems and methods for using machine learning techniques to generate section identifiers for one or more sections of the unstructured or unformatted text data. A document-processing application identifies, with a feature-prediction layer of a machine-learning model, a feature representation that represents a semantic structure of a text section within the unformatted and unstructured document. The document-processing application generates, with a sequence-prediction layer of the machine-learning model, a section identifier (e.g., heading, body, list) for a corresponding text section by applying the sequence-prediction layer to the feature representation and using contextual information of neighboring text sections.

    Propagating modifications made to an object to linked objects in a document

    公开(公告)号:US11763063B2

    公开(公告)日:2023-09-19

    申请号:US17499229

    申请日:2021-10-12

    Applicant: Adobe Inc.

    Abstract: Embodiments are disclosed for propagating modifications made to an object to linked objects in a document. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving a first input creating a first object in a first page of a document, analyzing first parameters associated with the first object, determining that the first object matches second objects in a first linked objects thread stored in a mapping of objects in the document, associating the first object with the first linked objects thread, receiving a second input including a modification to the first object, the modification including alterations to one or more of the first parameters, modifying the first object based on the alterations to the one or more of the first parameters, and automatically applying the modification to the second objects in the first linked objects thread.

Patent Agency Ranking