add paul hsu updates

Author: laujan

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

@@ -38,7 +38,7 @@ Content Understanding serves as a cornerstone for Media Asset Management solutio
 
 * **Transcription**. Converts conversational audio into searchable and analyzable text-based transcripts in WebVTT format. Customizable fields can be generated from transcription data. Sentence-level and word-level timestamps are available upon request.
 
-* **Diarization**. Distinguishes between speakers in a conversation, attributing parts of the transcript to specific speakers.
+* **`Diarization`**. Distinguishes between speakers in a conversation, attributing parts of the transcript to specific speakers.
 
 * **Speaker role detection**. Identifies agent and customer roles within contact center call data.
 
@@ -53,11 +53,11 @@ Content Understanding offers advanced audio capabilities, including:
 
 * **Customizable data extraction**. Tailor the output to your specific needs by modifying the field schema, allowing for precise data generation and extraction.
 
-* **Generative models**. Utilize generative AI models to specify in natural language the content you want to extract, and the service will generate the desired output.
+* **Generative models**. Utilize generative AI models to specify in natural language the content you want to extract, and the service generates the desired output.
 
 * **Integrated pre-processing**. Benefit from built-in preprocessing steps like transcription, diarization, and role detection, providing rich context for generative models.
 
-* **Scenario adaptability**. Adapt the service to your requirements by generating custom fields to extract relevant data.
+* **Scenario adaptability**. Adapt the service to your requirements by generating custom fields and extract relevant data.
 
 ## Content Understanding audio analyzer templates
 

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

@@ -21,7 +21,7 @@ ms.custom: ignite-2024-understanding-release
 
 Content Understanding is a cloud-based [Azure AI Service](../../what-are-ai-services.md) designed to efficiently extract content and structured fields from documents and forms. It provides a comprehensive suite of APIs and an intuitive UX experience for optimal efficiency.
 
-Using Content Understanding, organizations can streamline data collection and processing, enhancing operational efficiency, data-driven decision-making, and innovation. With customizable analyzers, Content Understanding allows for easy extraction of content or fields from documents and forms, tailored to specific business needs.
+Content Understanding enables organization to streamline data collection and processing, enhance operational efficiency, optimize data-driven decision making, and empower innovation. With customizable analyzers, Content Understanding allows for easy extraction of content or fields from documents and forms, tailored to specific business needs.
 
 ## Business use cases
 
@@ -41,7 +41,7 @@ Content extraction enables the extraction of both printed and handwritten text f
 
 ### Add-on capabilities
 
-Enhance your document extraction with optional add-on features, which may incur additional costs. These features can be enabled or disabled based on your needs. Currently supported add-ons include:
+Enhance your document extraction with optional add-on features, which can incur added costs. These features can be enabled or disabled based on your needs. Currently supported add-ons include:
 
 * **Layout**: Extracts layout information such as paragraphs, sections, tables, and more.
 * **Barcode**: Identifies and decodes all barcodes in the documents.

articles/ai-services/content-understanding/glossary.md

@@ -6,7 +6,7 @@ author: laujan
 manager: nitinme
 ms.service: azure
 ms.topic: conceptual
-ms.date: 11/5/2024
+ms.date: 11/19/2024
 ms.author: lajanuar
 ---
 
@@ -19,10 +19,10 @@ ms.author: lajanuar
 | **Analyzer** | A component that processes and extracts content and structured fields from files. Content Understanding offers a few analyzer templates for common scenarios. |
 | **Analyzer template** | A predefined configuration and field schema for an analyzer. It simplifies creating analyzers by allowing modifications to a template instead of starting from scratch. This feature is available only in AI Foundry, not via REST API/SDKs. |
 | **Analyzer result** | The output generated by an analyzer after processing input data. It typically includes extracted content in Markdown, extracted fields, and optional modality-specific details. |
-| **Add-ons** | Additional features that enhance content extraction results, such as layout elements, barcodes, and figures in documents. |
+| **Add-ons** | Added features that enhance content extraction results, such as layout elements, barcodes, and figures in documents. |
 | **Fields** | List of structured key-value pairs derived from the content, as defined by the field schema. [Learn more about supported field value types.](service-limits.md) |
 | **Field schema** | A formal description of the fields to extract from the input. It specifies the name, description, value type, generation method, and more for each field. |
 | **Generation method** | The process of determining the extracted value of a specified field. Content Understanding supports: <br/> &bullet; **Extract**: Directly extract values from the input content, such as dates from receipts or item details from invoices. <br/> &bullet; **Classify**: Classify content into predefined categories, such as call sentiment or chart type. <br/> &bullet; **Generate**: Generate values from input data, such as summarizing an audio conversation or generating scene descriptions from videos. |
-| **Span** | A reference indicating the location of an element (e.g., field, word) within the extracted Markdown content. It is represented by a character offset and length. Different programming languages use various character encodings, which may affect the exact offset and length values for Unicode text. To avoid confusion, spans are only returned if the desired encoding is explicitly specified in the request. Some elements may map to multiple spans if they are not contiguous in the markdown (e.g., page). |
+| **Span** | A reference indicating the location of an element (for example, field, word) within the extracted Markdown content. A character offset and length represent a span. Different programming languages use various character encodings, which can affect the exact offset and length values for Unicode text. To avoid confusion, spans are only returned if the desired encoding is explicitly specified in the request. Some elements can map to multiple spans if they aren't contiguous in the markdown (for example, page). |
 | **Grounding source** | The specific regions in content where a value was generated. It has different representations depending on the file type: <br>&bullet; **Image** - A polygon in the image, often an axis-aligned rectangle (bounding box). <br>&bullet; **PDF/TIFF** - A polygon on a specific page, often a quadrilateral. <br>&bullet; **Audio** - A start and end time range. <br>&bullet; **Video** - A start and end time range with an optional polygon in each frame, often a bounding box.|
 | **Confidence score** | The level of certainty that the extracted data is accurate. |

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

@@ -19,15 +19,15 @@ ms.custom: ignite-2024-understanding-release
 > * Features, approaches, and processes may change or have constrained capabilities, prior to General Availability (GA).
 > * For more information, *see* [**Supplemental Terms of Use for Microsoft Azure Previews**](https://azure.microsoft.com/support/legal/preview-supplemental-terms).
 
-Content Understanding standardizes the extraction of data from images, making it easier to analyze large volumes of unstructured data. This speeds up time-to-value and simplifies integration into downstream analytical workflows. With the Content Understanding APIs, you can define schema to specify the fields, descriptions, and output types for extraction. The service then analyses the images and provides structured data, which can be applied in various use cases, such as:
+Azure AI Content Understanding standardizes the extraction of data from images, making it easier to analyze large volumes of unstructured data. Standardized extraction speeds up time-to-value and simplifies integration into downstream analytical workflows. With the Content Understanding APIs, you can define schema to specify the fields, descriptions, and output types for extraction. The service then analyses the images and provides structured data, which can be applied in various use cases, such as:
 
 * **Retrieval-augmented generation (RAG) applications:** Extract key details from your images to build a robust index that powers user-facing chat experiences. This index enables users to ask questions and receive accurate answers based on the content of your images.
 
 * **Financial analysis and business intelligence:** Analyze business performance charts and trends to generate real-time reports that help analysts, managers, and executives make faster, more informed decisions.
 
 * **Manufacturing quality control:** Automate the detection of defects and anomalies, such as scratches, cracks, or misalignments, in production lines and manufacturing environments.
 
-* **Shelf analysis and inventory management:** Detect, count, and extract specific details about retail products, optimizing operations and improving customer satisfaction by ensuring products are well-stocked and properly organized.
+* **Shelf analysis and inventory management:** Detect, count, and extract specific details about retail products, optimizing operations, and improving customer satisfaction by ensuring products are well-stocked and properly organized.
 
 ## Key Benefits
 
@@ -37,7 +37,7 @@ Content Understanding offers several key benefits for extracting information fro
 
 * **Improved accuracy for specific use cases:** Content Understanding enables targeted data extraction that aligns directly with your unique requirements, helping to improve model accuracy by focusing on the most important data points.
 
-* **Faster and more cost-effective automation:** By extracting only the necessary fields, Content Understanding streamlines automation, allowing organizations to scale their data processing workflows efficiently and reduce the storage and processing of irrelevant data.
+* **Faster and more cost-effective automation:**  The extracting of only the necessary fields enables Content Understanding to streamlines automation. Thus allowing organizations to scale their data processing workflows efficiently and reduce the storage and processing of irrelevant data.
 
 
 ## Input requirements
@@ -51,12 +51,39 @@ For detailed information on supported input document formats, refer to our [Serv
 ## Supported languages and regions
 For a detailed list of supported languages and regions, visit our [Language and region support](../language-region-support.md) page.
 
+## Supported file formats
+
+> [!NOTE]
+> For best results, image schema should only be used to process non-document-based images.
+> Text heavy images of documents should be processed using a document schema.
+> Use cases that require extraction of text from document images or scanned documents in image formats should be processed using a document field extraction schema.
+
+Content Understanding supports the following image file formats in preview:
+
+|Supported file types| File size| Resolution (pixels)|
+|---|---|---|
+.jpg, .png, .bmp, .heif|≤ 20 MB | Minimum: 50 x 50 px</be>Maximum: 10,000 x 10,000 px|
+
+## Supported field types
+
+| Data type|Supported format|Schema limits|Example|
+| --- | --- |---|
+| **String**| √ Plain Text||
+|**Date** | √ Normalized to ISO 8601 (YYYY-MM-DD) format|2023-10-31|
+| **Time**| √ Normalized to ISO 8601 (hh:mm:ss) format|14:30:00|
+| **number**| √ Float number normalized to double precision floating point|1.14159|
+| **Integer**| √ Integer number, normalized to 64-bit signed integer|42, 1024|
+| **Boolean**| √ Boolean value, normalized to `true` or `false`||
+| **array**| √ List of subfields of the same type||
+| **Object**| √ Named list of subfields of potentially different types. ||
+
 ## Data privacy and security
-Developers using Content Understanding should review Microsoft's policies on customer data. For more information, visit our [Data, protection, and privacy](https://www.microsoft.com/trust-center/privacy) page.
+
+As with all the Azure AI services, developers using the Content Understanding service should be aware of Microsoft's policies on customer data. See our [**Data, protection and privacy**](https://www.microsoft.com/trust-center/privacy) page to learn more.
 
 > [!IMPORTANT]
 > If you are using Microsoft products or services to process Biometric Data, you are responsible for: (i) providing notice to data subjects, including with respect to retention periods and destruction; (ii) obtaining consent from data subjects; and (iii) deleting the Biometric Data, all as appropriate and required under applicable Data Protection Requirements. "Biometric Data" will have the meaning set forth in Article 4 of the GDPR and, if applicable, equivalent terms in other data protection requirements. For related information, see [Data and Privacy for Face](/legal/cognitive-services/face/data-privacy-security).
 
-## Next step
-* Try processing your image content using Content Understanding in [Azure AI Foundry](https://ai.azure.com/).
-* Learn more about image [**analyzer templates**](../quickstart/use-ai-foundry.md).
+## Next steps
+
+Try processing your content and data using Content Understanding in the [Azure AI Studio](https://ai.azure.com/?tid=888d76fa-54b2-4ced-8ee5-aac1585adee7).

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

@@ -27,7 +27,7 @@ Content Understanding offers a streamlined process to reason over large amounts
 
 ## Why process with Content Understanding?
 
-* **Simplify and streamline workflows**. Content Understanding standardizes the extraction of content, structure, and insights from various content types into a unified process.
+* **Simplify and streamline workflows**. Azure AI Content Understanding standardizes the extraction of content, structure, and insights from various content types into a unified process.
 
 * **Simplify field extraction**. Content Understanding's field extraction makes it easier to generate structured output from unstructured content. Define a schema to extract, classify, or generate field values with no complex prompt engineering
 
@@ -60,15 +60,15 @@ See [Quickstart](quickstart/use-ai-foundry.md) for more examples.
 |Component|Description|
 |:---------|:----------|
 |Analyzer|The analyzer is the core component of Content Understanding. It allows customers to configure content extraction settings and field extraction schema. Once configured, the analyzer consistently applies these settings to process all incoming data.|
-|Content extraction|Content extraction enables users to specify the types of information to be identified and extracted from incoming content. This includes options such as OCR for text, layout analysis, barcodes, tables, and more, allowing users to focus on the most relevant content elements.|
-|Add-ons| Content Understanding add-ons enhance content extraction by incorporating additional elements like barcodes, tables, and detected faces.|
-|Field extraction|Field extraction allows users to define the structure and schema of the desired fields to extract from input files. See [service limits](service-limits.md) for a complete list of field types supported. Fields can be generated via one of the following methods:</br></br>&bullet; **Extract**: Directly extract values as they appear in the input content, such as dates from receipts or item details from invoices.</br></br>&bullet; **Classify**: Classify content from a predefined set of categories, such as call sentiment or chart type.</br></br>&bullet; **Generate**: Generate values freely from input data, such as summarizing an audio conversation or creating scene descriptions from videos.|
-|Grounding source| Content Understanding identifies the specific regions in the content where the value was generated from. This allows users in automation scenarios to quickly verify the correctness of the field values, leading to higher confidence in the extracted data. |
+|Content extraction|Content extraction enables users to specify the types of information to be identified and extracted from incoming content. User-specified information includes options such as `OCR` for text, layout analysis, barcodes, tables, and more, allowing users to focus on the most relevant content elements.|
+|Add-ons| Content Understanding add-ons enhance content extraction by incorporating added elements like barcodes, tables, and detected faces.|
+|Field extraction|Field extraction allows users to define the structure and schema of the desired fields to extract from input files. See [service limits](service-limits.md) for a complete list of field types supported. Fields can be generated via one of the following methods:</br></br> &bullet; **Extract**: Directly extract values as they appear in the input content, such as dates from receipts or item details from invoices.</br></br>&bullet; **Classify**: Classify content from a predefined set of categories, such as call sentiment or chart type.</br></br>&bullet; **Generate**: Generate values freely from input data, such as summarizing an audio conversation or creating scene descriptions from videos.|
+|Grounding source| Content Understanding identifies the specific regions in the content where the value was generated from. Source grounding allows users in automation scenarios to quickly verify the correctness of the field values, leading to higher confidence in the extracted data. |
 |Confidence score | Content Understanding provides confidence scores from 0 to 1 to estimate the reliability of the results. High scores indicate accurate data extraction, enabling straight-through processing in automation workflows.|
 
 
 ## Responsible AI
- Azure AI Content Understanding is designed to guard against processing harmful content. For more information, *see* our [**Transparency Note**]() and our [**Code of Conduct**](/legal/cognitive-services/openai/code-of-conduct).
+ Azure AI Content Understanding is designed to guard against processing harmful content. For more information, *see* our **Transparency Note** and our [**Code of Conduct**](/legal/cognitive-services/openai/code-of-conduct).
 
 ## Data privacy and security
 Developers using the Content Understanding service should review Microsoft's policies on customer data. For more information, visit our [**Data, protection and privacy**](https://www.microsoft.com/trust-center/privacy) page.