Uipath data extraction du multiple pages

Help Activities
1

1…I have a pdf of 12 pages
2. From pages 1-5 and 9-12 I need to extract some fields
3. I thought of training in AI Center however a 12 page pdf is getting rejected
4. Human in the loop is there
5. During feasibility form extractor is working fine
6. If I use form extractor and human in the loop then we can’t train form extractor right ?

2

Use the PDF Editors to delete the unwanted PDF pages and create a temporary file and use that as input to ML Extractor.

3

Hi @Ritaman_Baral

Yes you are correct, you cannot retrain the form extractor. If you are using ML extractor with ML skill you can retrain with the Machine learning trainer but here it’s not possible.

If you got that type of pdfs then upload it to form extractor and map the data again.

Hope it helps!!

4

What is the accurate size of acceptance of a pdf ?

5

My pdfs are getting rejected !!

6

Then you have to go with Machine learning extractor. If the input file format is keep changing and the fields are not stable at the same positions. We recommend to use the AI center and train the documents then use the ML skill in the Machine learning extractor to get the accurate results.

Form extractor will not work if the fields positions are not static. It have some limitations it will work untill there. If you need the accurate data extraction results go with AI center and train the documents.

Hope it helps!!