Azure AI Services

Uploaded by

Sojol Hamid

We take content rights seriously. If you suspect this is your content, claim it here.

Available Formats

Download as DOCX, PDF, TXT or read online on Scribd

0% found this document useful (0 votes)

6 views4 pages

Azure AI Services

Uploaded by

Sojol Hamid

We take content rights seriously. If you suspect this is your content, claim it here.

Available Formats

Download as DOCX, PDF, TXT or read online on Scribd

You are on page 1/ 4

Azure AI Content Safety service can be used to detect harmful content within text or

images, including violent or hateful content, and report on its severity.

Azure AI Language service can be used to summarize text, classify information, or

extract key phrases.

Azure AI Speech service provides powerful speech to text and text to speech
capabilities, allowing speech to be accurately transcribed into text, or text to natural
sounding voice audio.

in education, Immersive Reader is being used to support students by adapting to

their requirements. Learners can have varying needs, such as wanting to read more
slowly, get words or text translated into another language, or see pictures to aid
their understanding. Immersive Reader helps students with different needs learn at
their own pace, and in their own way
Most AI services have a free price tier to allow you to explore their capabilities. After
clicking Create for the resource you require, you will be prompted to complete
details of your subscription, the resource group to contain the resource, the region,
a unique name, and the price tier

Studio interfaces provide a friendly user interface to explore Azure AI services.

There are different studios for different Azure AI services, such as Vision Studio,
Language Studio, Speech Studio, and the Content Safety Studio.

Azure AI Studio, which combines multiple Azure AI services into one platform.
Developers can use the web platform to create AI applications with the latest APIs
and models.

Azure AI Document Intelligence

Organizations can use Azure AI Document Intelligence to automate data extraction
across document types, such as receipts, invoices, and more.

Use the General Document, Read, and Layout models

The Azure AI Document Intelligence read model extracts printed and handwritten
text from documents and images. It's used to provide text extraction in all the other
prebuilt models.
Azure Document Intelligence is a Vision API that extracts key-value pairs and table
data from form documents.
Custom models: custom models extract data from forms specific to your business.
Custom models can be trained through the Azure Document Intelligence
Studio.
Understand Azure Document Intelligence file input requirements
Azure Document Intelligence works on input documents that meet these
requirements:
 Format must be JPG, PNG, BMP, PDF (text or scanned), or TIFF.
 The file size must be less than 500 MB for paid (S0) tier and 4 MB for
free (F0) tier.
 Image dimensions must be between 50 x 50 pixels and 10000 x 10000
pixels.
 The total size of the training data set must be 500 pages or less.

Decide what component of Azure Document

Intelligence to use
After you have collected your files, decide what you need to accomplish.

 To use OCR capabilities to capture document analysis, use

the Layout model, Read model, or General Document model.
 To create an application that extracts data from W-2s, Invoices,
Receipts, ID documents, Health insurance, vaccination, and
business cards, use a prebuilt model. These models do not need to
be trained. Azure Document Intelligence services analyze the
documents and return a JSON output.
 To create an application to extract data from your industry-
specific forms, create a custom model. This model needs to be
trained on sample documents. After training, the custom model
can analyze new documents and return a JSON output.

Depending on the use case, you might find that a confidence score of 80% or
higher is acceptable for a low-risk application. For more sensitive cases,
like reading medical records or billing statements, a score of 100% is
recommended.

In addition to SDKs and the REST API, Azure Document Intelligence services can be
accessed through a user interface called the Azure Document Intelligence
Studio (preview), an online tool for visually exploring, understanding, and
integrating features from the Azure Document Intelligence service. The Studio can
be used to analyze form layouts, extract data from prebuilt models, and train
custom models.

Composed Document Intelligence Model:

If you've created and trained custom models in Azure AI Document Intelligence, you
can combine them into a single composite model and publish that as a single
service. Composite models help when there are multiple versions of a form in use or
when users find it difficult to keep track of the correct model for each form. They
can also assist when you want customers to upload different types of documents to
a single location for analysis and you don't know which type was uploaded.

If you've created multiple custom models in Azure AI Document Intelligence, it can

be difficult to determine the best model to use when you submit a form or
document for analysis. Azure AI Document Intelligence can help with this if you
create a composed model from two or mode of the custom models. When you
submit a form to a composed model, Forms Analyzer automatically classifies it and
determines the best custom model to use for the analysis.

Indexing content in AI Search

During the indexing process, AI Search crawls your content, processes it, and
creates a list of words that will be added to the index, together with their
location. There are five stages to the indexing process:

1. Document Cracking. In document cracking, the indexer opens

the content files and extracts their content.
2. Field Mappings. Fields such as titles, names, dates, and more
are extracted from the content. You can use field mappings to
control how they're stored in the index.
3. Skillset Execution. In the optional skillset execution stage,
custom AI processing is done on the content to enrich the final
index.
4. Output field mappings. If you're using a custom skillset, its
output is mapped to index fields in this stage.
5. Push to index. The results of the indexing process are stored in
the index in Azure AI Search.

AI Search is a flexible search solution that can index many different types of
content. However, if your content includes scanned or photographed forms,
AI Search might not be able to index fields from those forms. You can
address this issue by adding a custom skill to the AI Search indexing pipeline
that calls Azure AI Document Intelligence. Scanned forms are sent to your
Azure AI Document Intelligence models, which can extract the fields they've
been trained to recognize and return their values for inclusion in the index.

The result of this integration is that users can locate the completed forms
they need by searching for the values of fields in them.