Скачать или смотреть UIPATH'S DOCUMENT UNDERSTANDING with ML - Data Extraction and Validation (ENG)

In this video you’ll see how we do the fourth step of Document Understanding: the Data Extraction.

In the Extraction we collect all the information from the processed documents, based on Fields that were defined in the Taxonomy. This step garantees that the cofigured extractors will be called at the right order, and directed to correct Field’s list and page range.

This means that if in one file has two or more typesof documnts to be identified, you should execute the data extraction many times, one time for each classification result.

Just like in the Classification step, the Data extraction is done trhough pre-trained extractors. The UiPath’s 3 main Extractors are the Form Extractor, o Intelligent Form Extractor, e o Machine Learning Extractor.