It makes it possible to easily and practically create extraction templates to obtain data from PDF, TXT, XLS or CSV files.
Specifically, it consists of automatic and intelligent data extraction logics. The transformation and subsequent automation can be performed in the various formats mentioned above.
Once the document type has been chosen and the file has been loaded, it is possible to select and define initial and final cuts of the document, eliminating unnecessary information such as headers or titles.
You can also indicate which parameters are considered useful for extraction, such as amounts, dates, descriptions, among others, thus being able to create a template with certain criteria that in the future will automate the extraction of information from this file format.
All this information will be transferred to a gridded instance that, in the same way, can be further automated by deleting rows, adding useful headings, replacing texts or removing unnecessary elements.