BIC creates workdocs from the files provided as input during the initial import step. The OCR step includes a layout analysis that identifies words and blocks within the document. All subsequent workflow steps add their results to the workdoc.
This includes the following results.
- The document’s text
- The location of words
- The geometrical relationship between words
- The classification results
- The fields for data extraction
- The candidates for field contents
- The selected correct candidate for each field
- The fields’ validation status.
The processing of a document is complete when the workdoc is assigned to a document class and all the fields for extraction are filled and valid.