Microsoft AI School - Mining For Knowledge

An Introduction to Azure Cognitive Search

Every organization relies upon data that can either be structured or unstructured. The problem is not the lack of information; rather, it’s the mining of data that presents the real challenge. Data mining refers to the process of finding, analyzing, and extracting the necessary information from huge volumes of available resources like databases, files, and other sources that store data. Thus, to mitigate this hassle, Microsoft Azure provides a highly efficient cloud-based solution known as Cognitive Search. 

Azure Cognitive Search is Microsoft’s cloud-based solution with built-in AI capabilities that allow you to create comprehensive and high-scale solutions for indexing and querying a wide range of data sources. Using Azure Cognitive search, you can not only uncover insights from all types of content but also use advanced machine learning techniques to understand user intent and contextually rank the most relevant search results. Here’s what you can do with Azure Cognitive Search:

• Index and rank search data from a range of sources.
• Use cognitive skills to enrich indexed data.
• Extract insights from data and store them in a knowledge store for analysis and integration.

MS AI School features an amazing learning path that allows you to master the concepts of Azure Cognitive search with the help of hands-on practice exercises. You can dive into that learning path at the following link - “Implement knowledge mining with Azure Cognitive Search.” This learning path has three modules. Read ahead to get a quick peek at each module of this learning path.

Prerequisites

Before proceeding with this learning path, you should fulfill the following prerequisites:

• You should be familiar with Microsoft Azure and must be able to navigate the Azure portal.
• You should have a minimal experience in programming with C# or Python.

Module 1: Create an Azure Cognitive Search Solution

The first module of this learning path aims to teach you how to use Azure cognitive search to unlock the hidden insights in your data. Azure Cognitive Search APIs or SDKs can be used to create and manage index objects and implement client applications that can be used to retrieve information by querying the index. 

Thus, after completing this module, you will be able to create a cognitive search solution that consists of the following:

• A data source that allows you to store the data to be indexed. You can also use an API to push the data directly into an index.
• A skillset that allows you to define an enrichment pipeline of cognitive skills.
• An index that defines the fields that can be queried by a user.
• An indexer that is used to populate the fields of the index with values derived from the source data.

Here’s an overview of the units covered in this module:

Module 2: Create a custom skill for Azure Cognitive Search

You can use predefined skills within the Azure Cognitive Search to enrich an index through the extraction of additional information from the source data. However, in certain scenarios, you might have specific data extraction needs that cannot be met by predefined skills. You will need to define custom functions in such cases. For example - consuming an Azure Machine Learning model in order to integrate the predicted values into an index.

Hence, after you have completed the first module, the second module will guide you through lessons to implement a custom skill as an Azure function. You can then integrate this function into an Azure Cognitive Search skillset. Thus, the learning objectives of this module are as follows:

• Help you learn how to:
  • Implement a custom skill for Azure Cognitive Search.
  • Integrate a custom skill with an Azure Cognitive Search skillset.

Here’s an overview of the units covered in this module:

Module 3: Create a knowledge store with Azure Cognitive Search

Once you have completed the second module, the next module of this learning path will take you through an amazing hands-on example where you will learn how to implement a knowledge store for a fictitious travel agency that uses information in brochures and hotel reviews to help customers plan their trips. 

Thus, the learning objectives of the final module are as follows:

• Help you learn how to create a knowledge store for an Azure Cognitive Search pipeline.
• View the data in projections in a knowledge store.

Note: Before proceeding with the final module, you must have completed the “Create an Azure Cognitive Search solution.”

Here’s an overview of the units covered in this module:

Conclusion

Thus, if you wish to master the art of mining knowledge using Azure Cognitive Search, then this learning path will serve as the perfect guide to your learning expeditions.

Please feel free to dive into this learning path at the following link:- https://docs.microsoft.com/en-us/learn/paths/implement-knowledge-mining-azure-cognitive-search/