{"id":9200,"date":"2022-10-14T06:00:00","date_gmt":"2022-10-14T13:00:00","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/power-platform\/blog\/power-automate\/automate-document-processing-end-to-end-with-ai-builder\/"},"modified":"2025-06-11T07:48:00","modified_gmt":"2025-06-11T14:48:00","slug":"automate-document-processing-end-to-end-with-ai-builder","status":"publish","type":"post","link":"https:\/\/www.microsoft.com\/en-us\/power-platform\/blog\/power-automate\/automate-document-processing-end-to-end-with-ai-builder\/","title":{"rendered":"Automate Document Processing end-to-end with AI Builder"},"content":{"rendered":"
At Microsoft Ignite 2022, we were pleased to share advances in Intelligent Document Processing as well as new AI capabilities that will allow you to automate more scenarios with better performance, using <\/span>Power Automate and <\/span>AI Builder.\u00a0<\/span><\/span>\u00a0<\/span> Most documents used in the enterprise are based off free-form layouts that don\u2019t have a specific content structure. This is true for documents like contracts, statements of work, letters or resumes. Visualizing and extracting content from these documents is even more difficult than with a structured form, as the fields aren\u2019t properly labeled and can be anywhere in the document. AI Builder helps to solve this problem with the Unstructured Document Processing capability based off Azure Form Recognizer\u2019s Custom Document Neural Model.<\/p>\n With Unstructured Document Processing<\/a>\u00a0generally available, you can train a custom AI model to identify and extract specific fields that will help you automate how to process information from all types of documents.<\/p>\n AI Builder\u2019s document processing models now leverage Azure Form Recognizer v3.0, improving detection accuracy and extending language support. Highlights of improvements include:<\/p>\n Documents across the enterprise like invoices often include large tables of data that can span across multiple pages, making it difficult to accurately extract information. AI Builder has re-built its multi-page table capability, allowing makers to tag tables across pages ensuring that the table data is extracted reliably.<\/p>\n The multi-page table functionality is currently being rolled out and will be available in all regions by the end of October.<\/p>\n When fields to extract span across two lines in a document, AI models struggle to extract data correctly. With AI Builder\u2019s new continue tagging capability, we make it easy to train a model to identify and extract fields like an address that can be split across multiple lines in a document.<\/p>\n What happens when you try to process documents that are too different from the original samples you used to train AI Builder? When new documents are processed with specific layouts that differ too much from what you trained for, a low accuracy score can be returned. To help users manage this use case and improve model performance, we\u2019ve created the Feedback Loop capability. Using the AI Builder feedback loop action in Power Automate, makers can automate the process of monitoring documents that weren\u2019t processed correctly and send them back into a queue for re-training. Makers can now easily track new documents with low quality processing and improve their model\u2019s performance.<\/p>\n The Feedback loop\u00a0functionality is currently being rolled out and it will be available in all regions by the end of October.<\/p>\n With increased adoption of AI models to automate content processing, teams of makers want to collaborate on models to speed up the training cycle and transfer ownership rights. This is now possible with Model co-ownership. From the Model Details Page, users can share model ownership rights with other users, granting them the ability to re-train and re-publish models.<\/p>\n Model co-ownership\u00a0will be available in all regions by the end of 2022.<\/p>\n To improve model governance, AI Builder models are now also visible in the Power Platform Center of Excellence (CoE) Starter Kit<\/a>. Admins can monitor which AI models were created across environments and how they are being used in their tenant, giving the ability to better govern and foster AI innovation within their organization.<\/p>\n
\nBe sure to check out our <\/span>breakout session<\/span>, \u201c<\/span><\/span>Automate your document processes with AI Builder<\/span><\/span><\/a>\u201d for <\/span>live demos of the latest capabilities being introduced.<\/span><\/span>\u00a0<\/span><\/p>\nNew model capabilities<\/h2>\n
Unstructured Document Processing<\/h3>\n
<\/p>\nImproved accuracy and language support with Azure Form Recognizer 3.0<\/h3>\n
\n
<\/li>\n
\n<\/h3>\n
Multi-page Tables<\/h3>\n
<\/p>\nMulti-Line Tagging<\/h3>\n
<\/p>\nManaging Model Performance<\/h2>\n
Feedback Loop<\/h3>\n
<\/p>\nGoverning and sharing models<\/h3>\n
Getting Started<\/h2>\n