What do intelligent data extraction capabilities in Document Automation primarily process?

Intelligent data extraction capabilities in Document Automation focus on processing semi-structured documents, such as invoices. These capabilities leverage advanced technologies, including Optical Character Recognition (OCR) and machine learning, to accurately capture and interpret data contained within documents that do not adhere to a strict format.

Semi-structured documents, like invoices, conduct a range of data formats and layouts, making them ideal candidates for intelligent automation. Invoices, for instance, may contain varying fields for amounts, dates, vendor information, and line items, each laid out in different ways according to the issuing organization’s standards. Intelligent data extraction systems are equipped to identify and extract relevant data from these documents by recognizing patterns and context, thereby enhancing accuracy and efficiency in processing.

Other options like structured databases are typically organized in defined formats that are straightforward to query, while manual input forms often require human intervention to fill out. Raw data from sensors, on the other hand, usually lacks the textual complexity found in semi-structured documents, making it less relevant to the capabilities of intelligent data extraction in this context. The ability to handle the varied formats found in semi-structured documents is what makes this option the correct choice.