microsoft / mcw-ai-led-business-process-automation

AI led business process automation

AI-led business process automation

This workshop is archived and no longer being maintained. Content is read-only.

Contoso Healthcare is a major hospital network consisting of multiple locations across the United States. One of Contoso Healthcare's most significant needs is to have the ability to process handwritten and electronically filled medical claims forms. Currently, each hospital uploads image representations of completed forms via an Azure File Share. Employees then review each document and enter data manually into the claims system. Contoso Healthcare is looking to automate the business process of extracting claims form data and provide valuable reporting visualizations from the claims data ingested.

In addition to claims processing, Contoso Healthcare needs to transcribe, translate, and store patient/doctor visit audio recordings. A key benefit to obtaining audio transcripts is the ability to surface valuable medical terms, dosage instructions, and diagnoses discussed. Therefore, the information transcribed needs to be analyzed and enhanced with medical labeling and provided as a source for search functionality in their web portal.

December 2021

Target audience

• Application developer
• AI developer
• Data engineer

Abstracts

Workshop

In this workshop, you will learn to automate a business process end-to-end using a variety of Azure Cognitive Services.

At the end of this workshop, you will be better able to architect and implement a business process automation solution that leverages Azure Cognitive Services.

Whiteboard design session

In this whiteboard design session, you will work in a group to automate the business process of extracting data from form documents and perform visit audio transcription (and translation where required). You will evaluate Azure tools and services to design an optimal architecture that will fulfill Contoso Healthcare's business process automation requirements.

At the end of this whiteboard design session, you will be better able to architect a solution to automate and enrich an existing business process and provide further insight into data using Azure Cognitive Services.

Hands-on lab

In this hands-on lab, you will learn to train a Form Recognizer model to extract data from images of documents and use Speech services to transcribe and translate audio. You will also learn to analyze transcribed text with Healthcare text analytics to extract medical terminology, medication dosages, and diagnoses.

At the end of this hands-on lab, you will be better able to implement a business process automation solution that leverages Azure Cognitive Services.

Azure services and related products

• App Service
• Application Insights
• Cognitive Services Forms Recognizer
• Cognitive Services Speech to Text
• Cognitive Services Text Analytics
• Cognitive Services Translator
• Cognitive Search
• Cosmos DB
• Event Grid
• Forms Recognizer
• Function App
• Power BI
• Storage Blobs
• Visual Studio

Related references

• MCW
• Azure application architecture guide

Help & Support

We welcome feedback and comments from Microsoft SMEs & learning partners who deliver MCWs.

Having trouble?

• First, verify you have followed all written lab instructions (including the Before the Hands-on lab document).
• Next, submit an issue with a detailed description of the problem.
• Do not submit pull requests. Our content authors will make all changes and submit pull requests for approval.

If you are planning to present a workshop, review and test the materials early! We recommend at least two weeks prior.

Please allow 5 - 10 business days for review and resolution of issues

mcw-ai-led-business-process-automation's Issues

Issue in Exercise-2 Task-4, unable to get Transcriptions Collections under Contoso in Cosmos DB.

In Exercise-2 Task-4, unable to get Transcriptions Collections under Contoso in Cosmos DB data explorer even after waiting for more than 30 minutes. We have cross-checked with all the Endpoints, Connection Strings and Keys are correctly configured in the Function App.

Please find the below screenshot:

./post-provisioning.ps1 Fails

In Azure Cloud shell

Enter the name of the resource group you have created for your MCW environment.: "RG-MCW-AI"
Get-AzStorageAccount: /home/shep/MCW/Hands-on lab/lab-files/ARM-template/post-provisioning.ps1:17
Line |
17 | … ountName = (Get-AzureRmStorageAccount -ResourceGroupName $resourceGro …
| ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
| 'resourceGroupName' does not match expected pattern '^[-\w._()]+$'.

Get-AzStorageAccountKey: /home/shep/MCW/Hands-on lab/lab-files/ARM-template/post-provisioning.ps1:18
Line |
18 | … GroupName $resourceGroupName -AccountName $storageAccountName).Value[ …
| ~~~~~~~~~~~~~~~~~~~
| Cannot validate argument on parameter 'Name'. The argument is null or empty. Provide an argument that is not null or empty, and then try the
| command again.

New-AzStorageContext: /home/shep/MCW/Hands-on lab/lab-files/ARM-template/post-provisioning.ps1:19
Line |
19 | … New-AzStorageContext -StorageAccountName $storageAccountName -Storag …
| ~~~~~~~~~~~~~~~~~~~
| Cannot validate argument on parameter 'StorageAccountName'. The argument is null or empty. Provide an argument that is not null or empty, and
| then try the command again.

New-AzStorageContainerSASToken: /home/shep/MCW/Hands-on lab/lab-files/ARM-template/post-provisioning.ps1:20
Line |
20 | … nerSASURI = New-AzStorageContainerSASToken -Context $destinationConte …
| ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
| Could not get the storage context. Please pass in a storage context or set the current storage context.

Before the HOL - deployment fails on notebookWorkspaces

Deployment of Before the HOL Azure Template fails for 'west europe' and 'east us', the resource resposible for the failure:

Microsoft.DocumentDB/databaseAccounts/notebookWorkspaces

Error messages I was getting:

{"code":"DeploymentFailed","message":"At least one resource deployment operation failed. Please list deployment operations for details. Please see https://aka.ms/DeployOperations for usage details.","details":[{"code":"BadRequest","message":"The requested region 'west europe' is not supported.\r\nActivityId: 69f157d6-8a0c-4acb-80c0-6ea672d0bbeb, Microsoft.Azure.Documents.Common/2.14.0, Microsoft.Azure.Documents.Common/2.14.0, Microsoft.Azure.Documents.Common/2.14.0, Microsoft.Azure.Documents.Common/2.14.0, Microsoft.Azure.Documents.Common/2.14.0, Microsoft.Azure.Documents.Common/2.14.0"}]}

{"code":"DeploymentFailed","message":"At least one resource deployment operation failed. Please list deployment operations for details. Please see https://aka.ms/DeployOperations for usage details.","details":[{"code":"BadRequest","message":"The requested region 'east us' is not supported.\r\nActivityId: aa4a4b00-2f24-4807-9ca1-98dbb3302162, Microsoft.Azure.Documents.Common/2.14.0, Microsoft.Azure.Documents.Common/2.14.0, Microsoft.Azure.Documents.Common/2.14.0, Microsoft.Azure.Documents.Common/2.14.0, Microsoft.Azure.Documents.Common/2.14.0, Microsoft.Azure.Documents.Common/2.14.0"}]}

Edit:
I was able to finish the HOL despite the error during the deployment. Great HOL:)

Add Events Grid Greyed out, Exercise 1 Task 2 Step 4 HOL

Add Event Grid Subscription in Function Apps is grey out for both Audio Processing and ClaimsProcessing due to which the lab is not performable in later steps. Any idea what could be causing the issue? I have followed all the steps closely. and also receive an error that states "function runtime is unable to start", maybe this would be the culprit? I was unable to debug it after trying multiple fixes like changing "FUNCTIONS_EXTENSION_VERSION".