Umwandlung eines Unstrukturierten Dokuments in ein Strukturiertes Dokument

Details

Veröffentlichungs-Nr.

EP4811205

Anmeldetag

17. März 2026

Veröffentlichung

23. September 2026

Rechtsraum

EP

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for transforming an unstructured document into a structured document. In methods, a visual representation of a page of a flat document and raw text data of the page are extracted. A first model input including the visual representation of the page, the raw text, and a first prompt is created. The first model input to at least a first model, from which structural data of the page is obtained. Based on the structural data, a second model input is generated and submitted to a second model, and thereby causes the second model to generate a response specifying attributes of a specific type of content in the page. A hierarchically structured page is created based on the structural data, raw text, and attributes.

Anmelder

Firma

Vertesia, Inc.

Land

🇺🇸 USA