📄️ Overview
The BDM - Document Extraction function helps to extract the details from unstructured documents like Invoices and PO. The service makes use of API’s provided by ABBYY Vantage/SAP Document Information Extraction (DOX)/Azure Form Recognizer/Generative AI as configured to extract the document details and provide the structured output in JSON format.
📄️ Key Features
- Multiple OCR Engine Configuration: Supports ABBYY Vantage, SAP Document Information Extraction (DOX) , Azure Form Recognizer, Tessaract and Generative AI for processing unstructured documents. Based on the license procured for any of these tools can be configured
📄️ Architecture
- The Document Extractor component is built to be highly flexible and extensible, supporting the following architecture:
📄️ Use Cases
Invoice details can be extracted from PDFs and images, enabling automated processing for use cases like Accounts Payable (AP) automation.
📄️ Benefits
If the OCR engine configuration is changed, no changes are required to be made to the upstream applications like AP Automation or Sales Order Automation. The creation of standard JSON response will be taken care of by the Document Extraction application. This reduces the rework by upstream applications
📄️ FAQs / Help / Training Videos
- For any clarification and concerns, kindly write to: CAF@incture.com