Microsoft Technology Licensing, LLC

Microsoft Corporation

Milos Raskovic

Milos Lazarevic

Milan Sesum

Aljosa Obuljen

Drazen Zaric

Dragan Slaveski

Vanja Petrovic Tankovic

Nikola Terzic

Filip Panjevic

Dusan Lukic

Nenad Bozidarevic

Victor Jitlin

Non-limiting examples of the present disclosure describe processing that generates intelligent inferences of authoring from analysis of attributes associated with a digital file being imported in an application/service. Examples described herein are configured to work with any type of application/service including an authoring application/service. For instance, a request to import a digital file is received in an application/service. The application/service may be configured to analyze the digital file and generate authoring inferences based on an analysis of attributes of the digital file. For example, a conversion data model may be utilized to identify a file type of the digital file, analyze attributes of the identified digital file (e.g. content portions, layout, formatting, metadata, etc.) and output file data in a format that is tailored for the application/service based on authoring inferences. A converted representation of the digital file is surfaced in the application/service based on output of the file data.

Intelligent inferences of authoring from document layout and formatting

Detection of East Asian layout features and reconstruction of East Asian layout features is provided. Vertically written text in the fixed format document is detected and rotated for layout analysis. After layout analysis, the rotated text is rotated back and restructured in a flow format document. When a plurality of characters is written horizontally in a vertical line of text, vertically overlapping text runs are detected, designated as horizontal-in-vertical text, and are restructured as horizontal-in-vertical text in a flow format document. Lines of text are analyzed for attributes of a ruby line and are designated as ruby text, associated with corresponding text in a ruby base line, and restructured as ruby text in a flow format document. Text in a fixed format document is analyzed for detection of a particular East Asian language so that a font for the language is designated in a flow format document.

Detection and reconstruction of East Asian layout features in a fixed format document

Embodiments of the present disclosure provide for analyzing paragraphs in a fixed format document to determine style clusters or groupings of each paragraph. In certain embodiments, the paragraphs are grouped into style clusters based on a first property. Each style cluster is then further divided into sub-groups based on a second property. Once the sub-groups have been determined, a third property associated with each paragraph in each sub-group is normalized based on a dominant one of the at least the third property.

Paragraph property detection and style reconstruction engine

A borderless table detection engine and associated method for identifying borderless tables appearing in data extracted from a fixed format document. Due to the lack of visible borders, reliable automated detection of a borderless table is difficult. The borderless table detection engine uses whitespace, rather than content, to detect borderless table candidates. Applying heuristic analysis, the borderless table detection engine discards borderless table candidates with a layout that lacks sufficient characteristics of a table and is unlikely to be a valid borderless table.

Borderless table detection engine

A vector graphics classification engine and associated method for classifying vector graphics in a fixed format document is described herein and illustrated in the accompanying figures. The vector graphics classification engine defines a pipeline for categorizing vector graphics parsed from the fixed format document as font, text, paragraph, table, and page effects, such as shading, borders, underlines, and strikethroughs. Vector graphics that are not otherwise classified are designated as basic graphics. By sequencing the detection operations in a selected order, misclassification is minimized or eliminated.

Vector graphics classification engine

A paragraph alignment detection engine and a section reconstruction engine. The paragraph alignment detection engine determines the paragraph alignment of a paragraph and updates the paragraph alignment property of the paragraph in the data store for single line and multi-line paragraphs. The paragraph alignment detection engine employs per paragraph comparisons and relative comparisons to other paragraphs to determine the paragraph alignment of a single line paragraph. The paragraph alignment detection engine employs per paragraph comparisons and relative comparisons of the lines of a paragraph to determine the paragraph alignment of a multi-line paragraph. The section reconstruction engine minimizes the number of sections created in the flow format document by identifying the columns on each page, combining contiguous pages with the same column layout into a single section, and creating alternative objects to contain regions associated special cases in lieu of creating additional sections.

Paragraph alignment detection and region-based section reconstruction

A formula detection engine and associated method. The formula detection engine locates formulas within a fixed format document portion by identifying formula seeds. The formula detection engine creates and expands a boundary around the formula seed to define a formula area. To eliminate overlap with surrounding normal text, the formula area is divided into multiple formula areas based on vertical position and horizontal spacing between the formula elements. After being vertically ordered, horizontally overlapping formula areas are merged to reconstruct the formula as a flowable element.

Formula detection engine

Footnote detection is provided. When converting a fixed format document to a flow format document, footnotes, which may include a footnote description and a footnote reference mark, may be detected and linked with a corresponding footnote reference mark in a main document flow on a page. Additionally, a footnote numbering scheme may be determined and applied to detected footnotes. By providing footnote detection when converting a fixed format document to a flow format document, footnotes may be statically positioned at the end of a page containing the corresponding footnote reference mark.

Footnote zone detection in a fixed format document using number of paragraphs in footnote description

A multi-level list detection engine. The multi-level list detection engine detects text obtained from a fixed format document that is formatted as a static multi-level list and creates a dynamic multi-level list object in a flow format document. The resulting dynamic multi-level list object automatically updates as the end user edits the multi-level list in the flow format document. The multi-level list detection engine identifies list elements in the fixed format text based on the presence of a list identifier. The list elements are grouped into lists based on the properties of each list element relative to other list elements. List elements are then assigned to a list level based on the relative properties of the list elements within a list. Finally, level list assignments are verified and corrected, the levels are merged, as necessary, and the lists are consistently formatted as appropriate to create a final well-formed dynamic multi-level list object.

Growing community of inventors

Belgrade, Republic of Serbia

Milos Raskovic