Annotating embedded tables
US9870351B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Sep 24, 2015 |
| Grant date | Jan 16, 2018 |
| Priority date | — |
| Expiry date | Sep 24, 2035 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06F40/169
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Embodiments of the present invention provide systems and methods for extracting and annotating text. Heuristics are applied to extracted text data in order to detect the readability of the text data. The text data is converted to an intermediate form. The transformed intermediate form is converted back to the original text format. Character and feature correspondence; positional logic; and queries to determine if the text data within a line corresponds with a token header are used to maintain the formatting and annotate the original text.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.