I don't see any information in the documentation about how to train the AI Document Extraction process. I thought that invoices were already trained, but that doesn't seem to be the case. Additionally how would we train a new document class, like insurance claims for example. I see doc'm about how to setup the fields, but how do we train for locate/extraction rules? Do we just run a bunch of docs thru manual reconcile? Is there a way to clean out bad documents/trainings? How do we get more insight into what's going on behind the scenes with extraction?
Thanks in advance!
Discussion posts and replies are publicly visible
Indeed, you run through a manual reconcile. You will have to add a data validation step after extraction anyways. In that XOR, either go to reconcile, where the training happens, or continue in the process when everything is good.