Structuring unstructured data via optical character recognition and analysis
US11900289B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Oct 30, 2020 |
| Grant date | Feb 13, 2024 |
| Priority date | — |
| Expiry date | Aug 24, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V30/19
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
The present disclosure describes devices and methods of providing a technology environment for analyzing unstructured data to generate structured data. A set of electronic documents, each electronic document associated with a type of product, may be accessed. A data instance for each of the documents may be generated. The data instance may include a plurality of data fields that are based on the type of product. The electronic documents may be analyzed to identify values for each of the plurality of data fields. Analyzing the electronic documents may comprise applying a respective character recognition algorithm to respective electronic documents, and assigning a confidence factor to each of the values. The data instances comprising the values for each of the plurality of data fields may be stored in a second database.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.