Hi All,
I am extraction a pdf file which is containing 40 pages in it out of which any one of page will contains invoice page . I have used 3 keywords to detect invoice page using intelligent keyword identifier and process it.
Problem - Above mentioned 3 keywords may contain in other pages too,so detecting multiple pages for matching and results in multiple pages DU Processing .
Looking for best solution approach in OnPrem orchestrator for document classifier to detect single invoice match .
Note :
1.A single multipage pdf is splitted into a 40 single page pdf files.
2. stored in a folder location
3.Processing one by one digitizing document
4.Looking for String Match in before DU Processing
5.Once string match processing for DU Processing