Syntex Extracts Data from Documents via Machine Learning

• Microsoft Syntex automatically analyzes, extracts, and classifies information from content stored in a SharePoint library.
• The service uses customer-trained machine learning models and the AI Builder service.
• Syntex could help automate business processes that ingest large volumes of content, such as processing purchase orders.
• Using the service at scale could require expensive capacity add-ons.

Microsoft Syntex (formerly SharePoint Syntex) is a service that uses machine learning to automatically extract relevant content from documents and images as part of a document processing workflow. The service can also classify and label documents, as well as converting extracted data into standardized documents. The service can process large volumes of structured documents (like purchase orders and incident report forms), unstructured documents (like résumés and contracts), and image data, a process Microsoft calls Content AI.

Syntex could benefit users by streamlining document-intensive workflows like accounts payable processing and by creating metadata that can be ingested by other services such as the Microsoft Information Protection data labeling and protection service. However, service costs can quickly exceed budgets due to capacity licensing.