I am working on a use case where we are having 5 types of document and we need to extract the same fields from these documents.
We are planning to use AI Center and DU. We can achieve it for these 5 types of documents.
However there is a scenario where other documents type can also come but we don’t have any samples. Those are totally dynamic. Can we use communication mining to extract those same fields from those new dynamic documents?
You can use ML in DU to train those types it should take fields automatically as per previous training and if not that you get validation stage where you define correct output and train your model on that same so next time if that same documents comes again your model will have better confidence
you can consider this video
We have 5types of document.
However if a 6th document type comes in then what to do ?
The first 5 document will be trained and the 6th one will be dynamic.
However the fields will be same.
if fields are same it will try to extract data from it if model thinks confidence is low then it will ask you to verify the data which has been extracted and if confidence is good it will provide direct extraction result to you
Happy Automation!
duplicate
Using Communication Mining not a good choice here. Communications Mining combines AI and automation so you can automate your most common business requests and time-consuming conversations.
If your documents going to be dynamic but the fields going to be similar, You can train your DU model with whatever data you will receive.
Thanks,
Ahok 