| 摘要 |
<p>A method for creating an enrichment file associated with a page of an electronic document formed by a plurality of thematic entities and having a content comprising text distributed in the form of one or more paragraphs, the method comprising determining text content areas, each comprising at least one paragraph, by means of a layout analysis, associating each content area with one of the thematic entities, and storing metadata identifying the geometric coordinates of the text content areas of the page and the thematic entities associated with said content areas of the page.</p> |
