Hi, it is possible to use JSON output from other extraction engines and apply it in the varification module?
The current model is limited in language and date setup, so I have another extraction solution that provides info in JSON format with boxes and different headers. Would it be possible to combine that with the human validation screen?
Long story short, you will only need to put your own algorithm in the activity, and use the existing inputs (original file path, text version, document object model, and list of required fields) to provide the requested output format.
You will find all the documentation you need in the first link
I am not sure if i was clear enough, but I use a 3rd party extractor that can handle danish language and dates. The output is JSON with boxes (coordinates on the PDF) and the different fields values.
Can i integrate that into the validation screen in order to use it for validation and nothing else?
You can do that, but you need to do a mapping between the output of the 3rd party and the expected input for the Validation Station.
The best way to do this is to ask the 3rd party vendor to build the custom activity so that you can use it in your flow. It can be a full fledged data extraction activity (recommended by far), or just a data mapper.
I recommend a proper integration because this way you will not need to do calls to external tools separately from the mapping and you would very easily manage your workflow nd configure it according to the use case you are implementing.