OCR is a technology that converts scanned images of text into machine-readable text. It can be used to extract text from printed or handwritten documents, such as invoices, receipts, forms, etc. OCR is useful for simple text extraction tasks, such as converting printed books into digital formats, or extracting data from structured documents with fixed layouts2.
Document Understanding is a framework that leverages OCR and other technologies, such as machine learning, natural language processing, and computer vision, to analyze and understand the meaning and structure of documents. It can be used to extract data from semi-structured or unstructured documents, such as contracts, resumes, emails, etc. Document Understanding is suitable for more complex tasks that require a deeper understanding of document content and context, such as sentiment analysis, natural language understanding, document classification, etc1.
References:
1: Document Understanding - UiPath Documentation Portal
2: OCR - UiPath Activities