I have different invoice in different structure i need to extract vendor name,invoice number ,item code,etc.how can do extract the data

Help Studio
, ,
1

Hi UiPath Community :waving_hand:,

I need some advice or best practices for extracting structured data from invoices that have different layouts and designs.
My goal is to automate data extraction for fields like:

  • Vendor Name
  • Invoice Number
  • Invoice Date
  • Item Code (SKU/HSN if available)
  • Item Description
  • Unit Price
  • Tax Amount
  • Total Amount

:small_blue_diamond: My scenario:

  • I receive multiple scanned PDF invoices via email.
  • The invoices come from different vendors and have different templates — each looks different (position of fields, table formats, headings, etc.).
  • I can’t rely on a single fixed position or line number.
  • Some invoices have multiple line items, some only one.
  • I want to automate extraction in UiPath Studio.
2

Hello @kavikumar_N,

If you know that the column names are the same, e.g., Vendor Name, Invoice Number, Invoice Date, Item Code (SKU/HSN if available), Item Description, Unit Price, Tax Amount, Total Amount, in all the PDFs, then you can use regex to extract the values of all the fields.

3

Hi @kavikumar_N you can do this using document understanding to extract the data from invoices for invoices we do have the mL model you can try this way