Merge pull request #164525 from yingqunpku/MVAD-improvement

[Anomaly Detector] Adding univariate labels and wording fixes

Author: v-ccolin

articles/cognitive-services/Anomaly-Detector/How-to/deploy-anomaly-detection-on-container-instances.md

@@ -12,7 +12,7 @@ ms.date: 04/01/2020
 ms.author: mbullwin
 ---
 
-# Deploy an Anomaly Detector container to Azure Container Instances
+# Deploy an Anomaly Detector univariate container to Azure Container Instances
 
 Learn how to deploy the Cognitive Services [Anomaly Detector](../anomaly-detector-container-howto.md) container to Azure [Container Instances](../../../container-instances/index.yml). This procedure demonstrates the creation of an Anomaly Detector resource. Then we discuss pulling the associated container image. Finally, we highlight the ability to exercise the orchestration of the two from a browser. Using containers can shift the developers' attention away from managing infrastructure to instead focusing on application development.
 

articles/cognitive-services/Anomaly-Detector/How-to/deploy-anomaly-detection-on-iot-edge.md

@@ -12,7 +12,7 @@ ms.date: 12/03/2020
 ms.author: mbullwin
 ---
 
-# Deploy an Anomaly Detector module to IoT Edge
+# Deploy an Anomaly Detector univariate module to IoT Edge
 
 Learn how to deploy the Cognitive Services [Anomaly Detector](../anomaly-detector-container-howto.md) module to an IoT Edge device. Once it's deployed into IoT Edge, the module runs in IoT Edge together with other modules as container instances. It exposes the exact same APIs as an Anomaly Detector container instance running in a standard docker container environment. 
 

articles/cognitive-services/Anomaly-Detector/How-to/identify-anomalies.md

@@ -12,11 +12,11 @@ ms.date: 10/01/2019
 ms.author: mbullwin
 ---
 
-# How to: Use the Anomaly Detector API on your time series data  
+# How to: Use the Anomaly Detector univariate API on your time series data  
 
 The [Anomaly Detector API](https://westus2.dev.cognitive.microsoft.com/docs/services/AnomalyDetector/operations/post-timeseries-entire-detect) provides two methods of anomaly detection. You can either detect anomalies as a batch throughout your times series, or as your data is generated by detecting the anomaly status of the latest data point. The detection model returns anomaly results along with each data point's expected value, and the upper and lower anomaly detection boundaries. you can use these values to visualize the range of normal values, and anomalies in the data.
 
-## Anomaly detection modes 
+## Anomaly detection modes
 
 The Anomaly Detector API provides detection modes: batch and streaming.
 

articles/cognitive-services/Anomaly-Detector/anomaly-detector-container-configuration.md

@@ -12,7 +12,7 @@ ms.date: 05/07/2020
 ms.author: mbullwin
 ---
 
-# Configure Anomaly Detector containers
+# Configure Anomaly Detector univariate containers
 
 The **Anomaly Detector** container runtime environment is configured using the `docker run` command arguments. This container has several required settings, along with a few optional settings. Several [examples](#example-docker-run-commands) of the command are available. The container-specific settings are the billing settings. 
 

articles/cognitive-services/Anomaly-Detector/concepts/anomaly-detection-best-practices.md

@@ -1,5 +1,5 @@
 ---
-title: Best practices when using the Anomaly Detector API
+title: Best practices when using the Anomaly Detector univariate API
 titleSuffix: Azure Cognitive Services
 description: Learn about best practices when detecting anomalies with the Anomaly Detector API.
 services: cognitive-services
@@ -12,7 +12,7 @@ ms.date: 01/22/2021
 ms.author: mbullwin
 ---
 
-# Best practices for using the Anomaly Detector API
+# Best practices for using the Anomaly Detector univariate API
 
 The Anomaly Detector API is a stateless anomaly detection service. The accuracy and performance of its results can be impacted by:
 

articles/cognitive-services/Anomaly-Detector/concepts/best-practices-multivariate.md

@@ -13,7 +13,7 @@ ms.author: mbullwin
 keywords: anomaly detection, machine learning, algorithms
 ---
 
-# Multivariate Anomaly Detector best practices
+# Best practices for using the Anomaly Detector multivariate API
 
 This article will provide guidance around recommended practices to follow when using the multivariate Anomaly Detector (MVAD) APIs. 
 In this tutorial, you'll:

articles/cognitive-services/Anomaly-Detector/concepts/multivariate-architecture.md

@@ -13,7 +13,7 @@ ms.author: mbullwin
 keywords: anomaly detection, machine learning, algorithms
 ---
 
-# Predictive maintenance solution with Anomaly Detector multivariate
+# Predictive maintenance solution with Anomaly Detector (multivariate)
 
 Many different industries need predictive maintenance solutions to reduce risks and gain actionable insights through processing data from their equipment. Predictive maintenance evaluates the condition of equipment by performing online monitoring. The goal is to perform maintenance before the equipment degrades or breaks down.
 

articles/cognitive-services/Anomaly-Detector/concepts/troubleshoot.md

@@ -17,9 +17,9 @@ keywords: anomaly detection, machine learning, algorithms
 
 This article provides guidance on how to troubleshoot and remediate common error messages when using the multivariate API.
 
-### Multivariate error codes
+## Multivariate error codes
 
-#### Common Errors
+### Common Errors
 
 | Error Code                 | HTTP Error Code | Error Message                                  | Comment                                                      |
 | -------------------------- | --------------- | ---------------------------------------------- | ------------------------------------------------------------ |
@@ -30,7 +30,7 @@ This article provides guidance on how to troubleshoot and remediate common error
 | `StorageReadError`         | 403             |                                                | Same as `StorageWriteError`.                                 |
 | `UnexpectedError`          | 500             |                                                | Please contact us with detailed error information. You could take the support options from [this document](/azure/cognitive-services/cognitive-services-support-options?context=/azure/cognitive-services/anomaly-detector/context/context) or email us at [[email protected]](mailto:[email protected])           |
 
-#### Train a Multivariate Anomaly Detection Model
+### Train a Multivariate Anomaly Detection Model
 
 | Error Code               | HTTP Error Code | Error Message                                                | Comment                                                      |
 | ------------------------ | --------------- | ------------------------------------------------------------ | ------------------------------------------------------------ |
@@ -46,13 +46,13 @@ This article provides guidance on how to troubleshoot and remediate common error
 | `RequiredEndTime`        | 400             | The `'endTime'` field is required in the request.            | Your training request has not specified a value for the `'startTime'` field. Example: `{"endTime": "2021-01-01T00:00:00Z"}`. |
 | `InvalidSlidingWindow`   | 400             | The `'slidingWindow'` field must be an integer between 28 and 2880. | `'slidingWindow'` must be an integer between 28 and 2880 (inclusive). |
 
-#### Get Multivariate Model with Model ID
+### Get Multivariate Model with Model ID
 
 | Error Code      | HTTP Error Code | Error Message             | Comment                                                      |
 | --------------- | --------------- | ------------------------- | ------------------------------------------------------------ |
 | `ModelNotExist` | 404             | The model does not exist. | The model with corresponding model ID does not exist. Please check the model ID in the request URL. |
 
-#### Anomaly Detection with a Trained Model
+### Anomaly Detection with a Trained Model
 
 | Error Code        | HTTP Error Code | Error Message                                                | Comment                                                      |
 | ----------------- | --------------- | ------------------------------------------------------------ | ------------------------------------------------------------ |
@@ -61,13 +61,14 @@ This article provides guidance on how to troubleshoot and remediate common error
 | `ModelNotReady`   | 400             | The model is not ready yet.                                  | The model is not ready yet. Please wait for a while until the training process completes. |
 | `InvalidFileSize` | 413             | File \<file> exceeds the file size limit (\<size limit> bytes). | The size of inference data exceeds the upper limit (2GB currently). Please use less data for inference. |
 
-#### Get Detection Results
+### Get Detection Results
 
 | Error Code       | HTTP Error Code | Error Message              | Comment                                                      |
 | ---------------- | --------------- | -------------------------- | ------------------------------------------------------------ |
 | `ResultNotExist` | 404             | The result does not exist. | The result per request does not exist. Either inference has not completed or result has expired (7 days). |
 
-#### Data Processing Errors
+### Data Processing Errors
+
 The following error codes do not have associated HTTP Error codes.
 
 | Error Code             | Error Message                                                | Comment                                                      |

articles/cognitive-services/Anomaly-Detector/index.yml

@@ -21,30 +21,33 @@ landingContent:
   linkLists:
     - linkListType: overview
       links:
-        - text: What is the Anomaly Detector univariate?
+        - text: What is Anomaly Detector (univariate)?
           url: overview.md
-        - text: What is the Anomaly Detector multivariate?
+        - text: What is Anomaly Detector (multivariate)?
           url: overview-multivariate.md
         - text: What's new in Anomaly Detector?
           url: whats-new.md
     - linkListType: get-started
       links:
-        - text: Anomaly Detector demo
+        - text: Demo web application (univariate)
           url: https://aka.ms/adDemo
     - linkListType: video
       links:
-        - text: Introducing the Anomaly Detector API
+        - text: Introducing the Anomaly Detector API (univariate) 
           url: https://channel9.msdn.com/Shows/AI-Show/Introducing-Azure-Anomaly-Detector?WT.mc_id=ai-c9-niner
-        - text: Algorithms used by the Anomaly Detection API 
-          url: https://www.youtube.com/embed/ERTaAnwCarM
+        - text: Introducing the new multivariate capabilities
+          url: https://channel9.msdn.com/Shows/AI-Show/New-to-Anomaly-Detector-Multivariate-Capabilities
+        - text: More videos ...
+          url: whats-new.md#videos
     - linkListType: reference
       links:
-        - text: Introducing Azure Anomaly Detector API
+        - text: Introducing Azure Anomaly Detector API (univariate) 
           url: https://techcommunity.microsoft.com/t5/AI-Customer-Engineering-Team/Introducing-Azure-Anomaly-Detector-API/ba-p/490162
-        - text: Overview of SR-CNN algorithm
-          url: https://techcommunity.microsoft.com/t5/AI-Customer-Engineering-Team/Overview-of-SR-CNN-algorithm-in-Azure-Anomaly-Detector/ba-p/982798  
-        - text: Algorithm used in anomaly detection (KDD paper)
-          url: https://arxiv.org/abs/1906.03821
+        - text: Introducing Multivariate Anomaly Detection
+          url: https://techcommunity.microsoft.com/t5/azure-ai/introducing-multivariate-anomaly-detection/ba-p/2260679
+        - text: More technical articles ...
+          url: whats-new.md#technical-articles
+       
 
 - title: "Detect anomalies in your data"
   linkLists:
@@ -56,6 +59,8 @@ landingContent:
           url: ../anomaly-detector/quickstarts/client-libraries.md?pivots=programming-language-javascript
         - text: Using Python (univariate)
           url: ../anomaly-detector/quickstarts/client-libraries.md?pivots=programming-language-python
+    - linkListType: quickstart
+      links:
         - text: Using C# (multivariate)
           url: ../anomaly-detector/quickstarts/client-libraries-multivariate.md?pivots=programming-language-csharp
         - text: Using JavaScript (multivariate)
@@ -64,8 +69,6 @@ landingContent:
           url: ../anomaly-detector/quickstarts/client-libraries-multivariate.md?pivots=programming-language-python
         - text: Using Java (multivariate)
           url: ../anomaly-detector/quickstarts/client-libraries-multivariate.md?pivots=programming-language-java
-
-
     - linkListType: tutorial
       links:
         - text: Learn Multivariate Anomaly Detection in one hour
@@ -77,30 +80,32 @@ landingContent:
   linkLists:
     - linkListType: concept
       links:
-        - text: Adjust anomaly detection modes and parameters for your data.
+        - text: Adjust anomaly detection modes and parameters for your data (univariate)
           url: how-to/identify-anomalies.md
-        - text: Use best practices to optimize your anomaly detection results.
+        - text: Use best practices to optimize your anomaly detection results (univariate)
           url: concepts/anomaly-detection-best-practices.md
+        - text: Use best practices to optimize your anomaly detection results (multivariate)
+          url: concepts/best-practices-multivariate.md
     - linkListType: video
       links:
-        - text: Anomaly Detector best practices
+        - text: Anomaly Detector best practices (univariate)
           url: https://channel9.msdn.com/Shows/AI-Show/Anomaly-Detector-v10-Best-Practices 
 
 - title: Use Docker containers
   linkLists:
     - linkListType: how-to-guide
       links:
-        - text: Install and run Anomaly Detector containers
+        - text: Install and run Anomaly Detector containers (univariate)
           url: anomaly-detector-container-howto.md
-        - text: Configure Anomaly Detector containers
+        - text: Configure Anomaly Detector containers (univariate)
           url: anomaly-detector-container-configuration.md
-        - text: Deploy a container instance to Azure
+        - text: Deploy a container instance to Azure (univariate)
           url: how-to/deploy-anomaly-detection-on-container-instances.md
-        - text: Deploy to IoT Edge
+        - text: Deploy to IoT Edge (univariate)
           url: how-to/deploy-anomaly-detection-on-iot-edge.md
     - linkListType: video
       links:
-        - text: Bring Anomaly Detector on-premises with containers support
+        - text: Bring Anomaly Detector on-premises with containers support (univariate)
           url: https://channel9.msdn.com/Shows/AI-Show/Bring-Anomaly-Detector-on-premise-with-containers-support
 
 - title: Help and feedback
@@ -112,7 +117,7 @@ landingContent:
 
     - linkListType: reference
       links:
-        - text: Troubleshooting multivariate
+        - text: Error codes (multivariate)
           url: concepts/troubleshoot.md
         - text: Support and help options
           url: ../cognitive-services-support-options.md?context=/azure/cognitive-services/anomaly-detector/context/context
@@ -121,29 +126,29 @@ landingContent:
   linkLists:
     - linkListType: reference
       links:
-        - text: Univariate REST API
+        - text: REST API (univariate)
           url: https://aka.ms/anomaly-detector-rest-api-ref
-        - text: .NET SDK
+        - text: .NET SDK (univariate)
           url: https://aka.ms/anomaly-detector-dotnet-ref
-        - text: .Python SDK
+        - text: .Python SDK (univariate)
           url: https://go.microsoft.com/fwlink/?linkid=2090370
-        - text: Go SDK
+        - text: Go SDK (univariate)
           url: https://go.microsoft.com/fwlink/?linkid=2089915
-        - text: Node.js SDK
+        - text: Node.js SDK (univariate)
           url: https://go.microsoft.com/fwlink/?linkid=2090788
-        - text: Azure PowerShell
+        - text: Azure PowerShell (univariate)
           url: /powershell/module/az.cognitiveservices/#cognitive_services
-        - text: Azure CLI
+        - text: Azure CLI (univariate)
           url: /cli/azure/cognitiveservices#az_cognitiveservices_list
     - linkListType: reference
       links:
-        - text: Multivariate REST API
+        - text: REST API (multivariate)
           url: https://westus2.dev.cognitive.microsoft.com/docs/services/AnomalyDetector-v1-1-preview/operations/DetectAnomaly
-        - text: .NET SDK
+        - text: .NET SDK (multivariate)
           url: https://go.microsoft.com/fwlink/?linkid=2165601&clcid=0x409
-        - text: Python SDK
+        - text: Python SDK (multivariate)
           url: https://go.microsoft.com/fwlink/?linkid=2165298&clcid=0x409
-        - text: Java SDK
+        - text: Java SDK (multivariate)
           url: https://go.microsoft.com/fwlink/?linkid=2165600&clcid=0x409
-        - text: Node.js SDK
+        - text: Node.js SDK (multivariate)
           url: https://go.microsoft.com/fwlink/?linkid=2165523&clcid=0x409

articles/cognitive-services/Anomaly-Detector/overview-multivariate.md

@@ -1,7 +1,7 @@
 ---
 title: What is the Anomaly Detector Multivariate API?
 titleSuffix: Azure Cognitive Services
-description: Overview of new Anomaly Detector public preview multivariate APIs.
+description: Overview of new Anomaly Detector preview multivariate APIs.
 services: cognitive-services
 author: mrbullwinkle
 manager: nitinme
@@ -13,7 +13,7 @@ ms.author: mbullwin
 keywords: anomaly detection, machine learning, algorithms
 ---
 
-# Multivariate time series Anomaly Detection (public preview)
+# Multivariate time series Anomaly Detection (preview)
 
 The new **multivariate anomaly detection** APIs further enable developers by easily integrating advanced AI for detecting anomalies from groups of metrics, without the need for machine learning knowledge or labeled data. Dependencies and inter-correlations between up to 300 different signals are now automatically counted as key factors. This new capability helps you to proactively protect your complex systems such as software applications, servers, factory machines, spacecraft, or even your business, from failures.
 
@@ -36,7 +36,7 @@ To run the Notebook, you should get a valid Anomaly Detector API **subscription
 
 ## Region support
 
-The public preview of Anomaly Detector multivariate is currently available in six regions: West US2, West Europe, East US2, South Central US, East US, and UK South.
+The preview of Anomaly Detector multivariate is currently available in six regions: West US2, West Europe, East US2, South Central US, East US, and UK South.
 
 ## Algorithms