Method for abstracting document data information appeared in newspaper

Abstract

This invention discloses a method for picking up data information of materials appearing in the newspaper including: picking up information of printed sheets and all manuscript regions based on the printed sheet information structure of typeset documents, picking up all manuscripts in the manuscript regions based on the manuscript information of said sheet files, picking up the association relation among manuscripts based on the position relations of these regions and merging the associated manuscripts based on said relation, sequencing them in terms of the importance of them and the region information, modifying and labeling the sheet information content and their information to get the data information of the materials appearing in the newspaper.

Description

technical field [0001] The invention relates to the field of computer information processing, in particular to the extraction technology of newspaper materials. Background technique [0002] Newspaper information is the core digital asset of a newspaper office. It includes data information including: manuscript content information, such as articles (text, paragraphs, titles, etc.) on the newspaper page, text and picture content in tables; manuscript layout information, including manuscript The location information (such as coordinate information), format information such as the font and font size of the title and text; the association information between articles and pictures, pictures and text descriptions; newspaper layout information, including newspaper edition, layout name, date, etc. The extraction of these data information is carried out after the completion of the newspaper layout process. Usually, the method of extracting the data information in the newspaper mater...

AI Technical Summary

Problems solved by technology

[0005] Since the layout description files, such as PS (PostScript language defined by Adobe) and S2 (layout result description language defined by Founder) are mainly used to describe the output information of layout printing, it is meaningless for printing, but for newspaper materials Very meaningful data information, such as article paragraphs, sequence, position and title, etc. have been changed or lost, and the associated information between articles and pictures, pictures and text descriptions, etc. have also been lost. When it comes to the data information in the materials, there are generally problems such as incomplete article content, wrong order of paragraphs, titles or pictures, and misclassification and miscombination of different articles. Carry out meticulous and cumbersome manual indexing, modification and proofreading, which not only consumes a lot of manpower and material resources, but also makes it difficult to guarantee the quality of the data information in the newspaper materials (that is, completeness and accuracy)

Images