Why Decipher not remembering ?

[KrishnaElapavul]

Hi,
I have around 10+  documents but still Decipher not  remembering  the region setting what i have done why ? let me explain in details 

1. .I have set Primary language as Finish for finish document 
2. Pushed  to Decipher and mapped
3. a name which come is finish is not  marked in filed. It marked as below
5. Then I have resized the area  and then i got correctly 
7. after summation i have pushed other docs like 9 more . but Decipher  marked all the times wrongly as #4
8. is it any issue with Decipher  capture ?   or I am doing any thing wrong or missing some thing ?

a different customer document (same language)   processed 30+ but still same issue as above 
Any light on this please ?
​

[Ben.Lyons1]

Hi Krishna,

It's quite difficult to fully appreciate the steps you have taken without seeing it, but I'll offer as much as I know on how you can explore a resolution.

- When training for a new document (with ML model disabled), I personally found that verifying a document, then making DFD changes would increase the number of documents required to successfully train. The best process I found was to create the DFD and upload 1 document, check how well it works in the verification screen. Then if there are changes required, return the document without saving or submitted and making the needed changes. In batches, restart your uploaded batch at the capture stage before going to verification. Following this may help produce better results.

- The only way to reset 100% of your training is to delete your training data, deleting your DFD will not remove any training. This is not recommended in 1.1 as you will delete training for all documents and would be unable to restore it. As such you will need to train a higher number of documents to resolve any updates. Once 1.2 is released this process can be easier where training can be exported/imported. This is due very shortly.

- In addition this could be a bug (unable to confirm without detailed investigation), of which a number have been resolved in 1.2. So I apologise for this experience and hope that upon the release of 1.2 you are able upgrade to get the latest improvements.

Thanks

Ben

[KrishnaElapavul]

Thanks Ben,
Yes I have trained in  the manner what you suggest

1. DFD  Document type and Batch created and mapped  ( ML disabled)
2. Processed one  documents checked in Data Verification ( Corrected the word  by re-sizing the region  which identified wrongly  as mentioned in image-1) 
3. Ensured i got correct value as in Image-2 , then  Submit 
4. Repeated the steps 2 and 3 for other 9 documents one after other 
5. At 10 th document also i see same issue 

Please suggest me if I am wrong in these steps.. as there is no changes require i have not return the batch and made any changes in DFD ...

[Ben.Lyons1]

Hi Krishna,

Is this the same document each time or different documents in the same format?

Thanks

Ben

[KrishnaElapavul]

Hi Bens
Each time different document and belongs to same customer same language .

[Ben.Lyons1]

On the surface I can't see that you're doing anything incorrect, but it would need a more detailed evaluation to be sure.

I would say you have 3 options to proceed.

1. Wait for the imminent release of v1.2, awaiting a date but will be very soon. Then test again to see if you still have the issue
2. Reach out to your Blue Prism account manager/support and see if they can offer additional direct support
3. Raise a support ticket for further investigation

Sorry I can't be of more help, but it seems you are doing all the right things.

Thanks

Ben