From the Microsoft Project Cortex blog:

Microsoft announced SharePoint Syntex, the first product from Project Cortex. SharePoint Syntex uses advanced AI and machine teaching to amplify human expertise, automate content processing, and transform content into knowledge, and will be available to purchase for all Microsoft 365 commercial customers on October 1, 2020.

Machine teaching accelerates the creation of AI models by acquiring knowledge from people rather than from large datasets alone. Any information processing skill, that an expert can teach a human, should be easily teachable to a machine. SharePoint Syntex mainstreams machine teaching, enabling your experts to capture their knowledge about content in AI models they can build with no code. Your experts train SharePoint Syntex to understand content like they do, to recognize key information, and to tag content automatically. For example, a contract processing expert can teach SharePoint Syntex to extract the contract’s value, along with the expiration date and key terms and conditions.

SharePoint Syntex then uses your models to automate the capture, ingestion, and categorization of content, extracting valuable information as metadata. Metadata is critical to managing content, and seamless integration with Microsoft Search, Power Automate, and Microsoft Information Protection enable you to improve knowledge discovery and reuse, accelerate processes, and dynamically apply information protection and compliance policies.

SharePoint Syntex content center
Syntex introduces a new experience for managing content at scale, integrating metadata and workflow, and delivering compliance automation – the content center. Content centers supply capabilities to teach the cloud how to read and process documents the same way you would manually. SharePoint Syntex uses those insights to automatically recognize content, extract important information, and apply metadata tags. SharePoint Syntex uses advanced AI to automate the capture, ingestion, and categorization of content, to accelerate processes, improve compliance, and facilitate knowledge discovery and reuse. SharePoint Syntex mainstreams AI to process three major types of content: digital images, structured or semi-structured forms, and unstructured documents.

Digital image processing
SharePoint Syntex can automatically tag images using a new visual dictionary with thousands of commonly recognized objects. In addition, SharePoint Syntex can recognize convert extracted handwritten text into tags for search and further processing.

Document understanding
Most organizations generate vast amounts of unstructured documents such as manuals, contracts, or resumes. You can teach SharePoint Syntex to read your content the way you would using machine teaching to build AI models with no code. SharePoint Syntex can automatically suggest or create metadata, invoke custom Power Automate workflows, and attach compliance labels to enforce retention or record management policies. Document understanding models are based on Language Understanding models in Azure Cognitive Services.

Form processing
SharePoint Syntex includes a powerful form processing engine, based on AI Builder, that lets you automatically recognize and extract common values from semi structured or structured documents, such as dates, figures, names, or addresses. These models are built with no code and only require a small number of documents for reliable results.

https://techcommunity.microsoft.com/t5/project-cortex-blog/announcing-sharepoint-syntex/ba-p/1681139

Share