Merge pull request #4988 from MicrosoftDocs/release-preview-2-cu

release-preview-2-cu -> main -- 05/19/2025 - 10:00 AM PT

Author: Albertyang0

articles/ai-services/.openpublishing.redirection.ai-services.json

@@ -1149,6 +1149,22 @@
       "source_path_from_root": "/articles/ai-services/speech-service/how-to-async-meeting-transcription.md",
       "redirect_url": "/azure/ai-services/speech-service/multi-device-conversation",
       "redirect_document_id": false
+    },
+    {
+      "source_path_from_root": "/articles/ai-services/content-understanding/concepts/capabilities.md",
+      "redirect_url": "/azure/ai-services/content-understanding/concepts/analyzer-templates",
+      "redirect_document_id": true
+    },
+    {
+      "source_path_from_root": "/articles/ai-services/content-understanding/concepts/retrieval-augmented-generation.md",
+      "redirect_url": "/azure/ai-services/content-understanding/tutorial/build-rag-solution",
+      "redirect_document_id": true
+    },
+    {
+      "source_path_from_root": "/articles/ai-services/content-understanding/concepts/accuracy-confidence.md",
+      "redirect_url": "/azure/ai-services/content-understanding/concepts/best-practices",
+      "redirect_document_id": true
     }
+
   ]
 }

articles/ai-services/content-understanding/audio/overview.md

@@ -7,11 +7,10 @@ ms.author: kabrow
 manager: nitinme
 ms.service: azure-ai-content-understanding
 ms.topic: overview
-ms.date: 05/01/2025
-ms.custom: ignite-2024-understanding-release
+ms.date: 05/19/2025
 ---
 
-# Analyzer templates offered with Content Understanding
+# Analyzer templates offered with Azure AI Content Understanding
 
 Content Understanding analyzer templates give you a head start in developing your Content Understanding solution by allowing you to build your analyzer without creating schemas from scratch.
 There are analyzer templates specific to common scenarios in each modality, such as call center audio analytics and advertising analysis for videos. Templates are also fully customizable, allowing you to adjust any

articles/ai-services/content-understanding/concepts/accuracy-confidence.md

@@ -7,10 +7,10 @@ ms.author: jfilcik
 manager: nitinme
 ms.service: azure-ai-content-understanding
 ms.topic: overview
-ms.date: 02/24/2025
+ms.date: 05/19/2025
 ---
 
-# Best practices for Content Understanding
+# Best practices for Azure AI Content Understanding
 
 Azure AI Content Understanding is an innovative Generative AI service designed to facilitate the precise and accurate analysis of extensive data sets. The service processes various content modalities, including documents, images, videos, and audio, transforming them into user-specified output formats.
 
@@ -87,4 +87,17 @@ When you're working with audio and video content, selecting a narrow set of lang
 
 By default, Content Extraction information such as speech transcripts, document text extracted by `OCR`, and video key frames can be accessed directly from the analyzer output for immediate review or custom processing. There's no need to define a field in the schema for these items. Fields can be used when more processing is needed, for example, summarizing transcripts, identifying entities, or extracting specific items from `OCR`. Each field can instruct the system to extract or generate the content you need.
 
+## Classifier category names and descriptions
+
+To improve the classifier and splitting accuracy, it's important to give a good category name and description with context.
+
+ #####   ***Example 8***
+
+   * For category names, make sure to use common titles (ex. Annual Financial Report, SEC Form 10-K).
+     
+   * For category descriptions, make sure to give context that distinguishes one category from another.
+
+     * Semantic definition: for example, `receipts for expense reporting`
+     * Key content: any content that can uniquely identify a category, such as  `2025` on tax forms to distinguish from older tax forms
+     * Common layout: layout that is distinguishable from others, such as `two-column form` or filled/unfilled checkbox