We are using the new machine learning invoice processing stuff for template-less invoice processing right now. The product is great and works awesome for most cases, but I have found some examples where the dollar amount text pulls in correctly, but the actual value is way off. In this case, a credit memo shows -13.94 for taxes, but the value shows -1394.00. The total shows -162.19 and the value shows -16219.00. Obviously these discrepancies could be a major problem if the person validating was not paying attention.
I am wondering if this is some type of bug in the machine learning extractor that does not deal well with negative values. I have only seen this on credit memos so far. Could someone look into this?
This issue is because of the values being digitized. The model is trained to extract the comma separators and decimal points too. At times, when the quality of the scanned file is low the Model tends to extract the commas as decimal points and vice-versa.
Have you tried using any other OCR other than the one currently being used? Please let me know if you getting the same results.
We are facing similar issue too, in our case commas, were getting extracted as decimals. Fortunately we were able to find a work-around for this using few conditional validations.
Eagerly waiting @Uipath to come up with resolution for this too. I think they are already aware of this.
ashokkarale
Yoichi
Jacqui_M
aariz
TUSHAR_DIWASE
lrtetala
J0ska
sven.wullum1
lakshman
Speziman