Patent

Data Identification and Extraction from Unstructured Documents

Arpit Narechania, Fan Du, Atanu R. Sinha, Nedim Lipka, Alexa F. Siu, Jane Hoffswell, Eunyee Koh, Vasanthi Holtcamp

USPTO · 2026

★ Granted US 12,699,851

Teaser for Data Identification and Extraction from Unstructured Documents

Abstract

Aspects of the method, apparatus, non-transitory computer readable medium, and system include obtaining a document and an information element. The aspects further include identifying, from the document, an anchor element that has an anchor type and a relationship type, wherein the anchor type describes a structure of a set of anchor elements, and the relationship type describes a relationship between the anchor element and the information element. The aspects further include extracting information corresponding to the information element based on the anchor element, the anchor type, and the relationship type, and displaying the extracted information to a user.

Citation

@patent{narechania2023dataidentification,
  author = {Narechania, Arpit and Du, Fan and Sinha, Atanu R. and Lipka, Nedim and Siu, Alexa F. and Hoffswell, Jane Elizabeth and Koh, Eunyee and Holtcamp, Vasanthi},
  title = {{Data identification and extraction from unstructured documents}},
  number = {US12699851B2},
  year = {2026},
  month = aug,
  day = {4},
  nationality = {US},
  assignee = {Adobe Inc.},
  url = {https://image-ppubs.uspto.gov/dirsearch-public/print/downloadPdf/12699851},
  note = {US patent 12,699,851, granted 4 August 2026}
}