Skip to main content
April 17, 2024
Question

Cannot extract Table data that run across multiple Pages through AI Skill Document Extraction

  • April 17, 2024
  • 7 replies
  • 0 views

Hi,

I'm trying to extract data through AI skill object with Document Extraction configuration.

I can extract the table data if the table is in one page.

In some documents, the grid/table data runs for multiple page. In that case, through the reconcile task I can select a table either in first page or in second page, but I cannot select the table data that runs on both pages.
In the below attached pdf, I need to extract 22 items on the grid, but unfortunately in the Reconcile Task I can select the table data either from Page one or Page 2.

Need help on how to retrieve all data that runs across multiple pages.
[View:/cfs-file/__key/communityserver-discussions-components-files/15/JEM_2D00_0063.pdf:320:240]

7 replies

shubhama926776
April 17, 2024

Hello [mention:5e908017e3df468298f000e1fe7863b1:e9ed411860ed4f2ba0265705b8793d05] 
AFAIK Extracting data from multi-page tables in Document Extraction has limitations.
Built-in AI skill can't handle it.

matthew.shutt
April 19, 2024

Hey [mention:dea33493db6342c9a73dc108d45120c0:e9ed411860ed4f2ba0265705b8793d05] , while the document extraction functionality cannot meet this directly, we recommend the following workaround to extract multi-page tables: https://docs.appian.com/suite/help/24.1/document-processing.html#extract-data-from-tables-across-multiple-pages

shubhama926776
April 20, 2024

Thanks [mention:51ca1a6fde224944b26f5e3109180334:e9ed411860ed4f2ba0265705b8793d05]  Looks good workaround to achieve this.

matthew.shutt
April 19, 2024

We recommend the following steps to extract multi-page tables: https://docs.appian.com/suite/help/24.1/document-processing.html#extract-data-from-tables-across-multiple-pages

Extract data from tables across multiple pages

  1. Use the PDF Tools plug-in to split the document into individual pages.
  2. Use the document extraction AI skill to extract table data from each page.
  3. Combine the results using post-processing logic.
December 10, 2024

Hi [mention:51ca1a6fde224944b26f5e3109180334:e9ed411860ed4f2ba0265705b8793d05] , is there any Tutorial for extract data from tables across multiple pages? I don't know how to split the PDF into individual pages to extract data, and then how to combine it into reconcile? Hope can received your reply, thanks. 

December 11, 2024

Now it is available in the 24.4 release to extract data which is from multiple page: