The post Using AI Builder with UI Flow to test capability of Robotic Process Automation in Power Automate appeared first on Microsoft Dynamics 365 Blog.

In the last post, I have explained how to use text recognizer fo the aim of detecting the text in a picture using the AI builder in Power Apps.

In this post and video, you will how to call it in Power Automate and extract the text from an image that is located in Onedrive and the result will be written back in Azure Blob Storage.

To start open the Power Apps and click on the AI Builder and Build and choose the text recognition.

then use the option the use in flow (Power Automate)

Next, in the Power Automate, click on the flow and create a new flow with a trigger of the When a file is created.

Next, the Predict module with the Model: TerxtRecognition model and the image from the previous trigger.

Next, use the Create blob for the output in Microsoft Azure.

for the name of the file, I will put the current time plus the file type that is a text file

Next, for the Blob content, use the function concat and from the Dynamic content select the PredictionOutput.

All done!

just put an image file like this on in the folder in one drive and run the flow to see the result in the blob storage!

See the video from

The post Power Automate for OCR appeared first on RADACAD.

Follow Source

The post Power Automate for OCR appeared first on Microsoft Dynamics 365 Blog.

Thanks to AI Builder in Microsoft Power Apps and Flow, now we have access to sentiment analysis,

Keyword extraction and Language detection inside Microsoft Flow is now available.

In this post, I am going to show how to do sentiment analysis inside Power Automate.

First What is sentiment Analysis and what sort of analysis we have inside AI Builder for text analytics.

Text Analytics

in Power Automate and Power Apps three analytics is available as sentiment analytics, keyword extraction, and Language detection as below

As you can see in the below picture in AI builder under Build we have these three modules.

In this example, I am going to show sentiment analytics. The first login to account with AI builder account, then click on the Build and then click on the sentiment analysis

Then the new windows show the main purpose of the sentiment analysis. As you can see in the below picture, the only option to use is on Microsoft Power Automate (flow).

Next, you able to see some hints about using it in the Microsoft power Automate

Note: For long Text, analyze each sentence, not the whole document

Note: Use the same language for a document not multiple languages in a document

Then click on the Use in a Flow,

IN the Power Automate ( make sure you are in the same environment), then click on the solution and then click on the New then Flow.

In the new flow, click on the When a new email arrives

then choose the folder as inbox and the subject as Hotel

Next search for the predict for CDS, and for the model choose the SentimentAnalysis model, Then for the text choose the Body Preview,

Next for the language choose the language you will have as it is en for me

In the next step,  we are going to store the result in one drive for example, that you can provide a specific name for the file using the Concat function. In this example, I use the Utcnow to get the current time and date and the file type that is Text file as .txt.

for the file content, I am going to use the sentence to put in the file, before creating it, just click on the run you had from the previous example

as you can see we have a sentence-level sentiment analysis and a global level. I am going to Concat both of them.

then after the run code you should see below text file in the onedrive.

The post Sentiment Analysis Application: Microsoft Power Automate, Power Apps and AI Builder appeared first on RADACAD.

Follow Source

The post Sentiment Analysis Application: Microsoft Power Automate, Power Apps and AI Builder appeared first on Microsoft Dynamics 365 Blog.

In the previous posts ( Post 1, Post 2, and Post 3) the process of analyzing the forms using the Form processing feature in AI Builder has been explained.
from last month some changes happen in the Prediction module in Microsoft Power Automate that will impact the form processing experience using flow.
In this post, I will show you how to work with the new one. The previous of you created still working.
the changes happen in the Predict module.

What we Have

in the below flow we have a module Predict that has a Request Payload, and we need to specify the type of the image and the file as a string, also later we need to parse the result by another component name Parse JSON.

What to Change

Now everything gets a bit easier, we have a Predict module that in the separate box it gets the document type and document itself, next in the create type we just need to use the Concat function to get the result and values.

I have used the below code for the File Content:

concat(‘ Session Title: ‘,outputs(‘Predict’)?[‘body/responsev2/predictionOutput/labels/Session_85648318f538ad191ff5651a30c24966/value’],’ ,Speaker Name: ‘,outputs(‘Predict’)[‘body/responsev2/predictionOutput/labels/Speaker_64a30215a5867855cdcb495ee6eef3ec/value’],’ ,Comments: ‘,outputs(‘Predict’)?[‘body/responsev2/predictionOutput/labels/What_0027580d34b848d69176d3f4a73de5c5450/value’])

also, watch below video

The post Recent Update in Predict Module in Power Automate Predict- Part 4 appeared first on RADACAD.

Follow Source

The post Recent Update in Predict Module in Power Automate Predict- Part 4 appeared first on Microsoft Dynamics 365 Blog.

In the last Post, I will explain how to analyze a JSON file that has been generated in the Sentiment Analysis process .

some explanation, this is a JSON file that contains the sentiment analysis for the comments one traveler put on the hotel website as below

The suite was awesome. We did not have much interaction with the staff. We did sleep on the queen size sofa bed in the living room instead of the queen size bed in the actual bedroom due to the temperature. It was very hot and humid. The air conditioner in the living room does not cool off the bedroom. This suite is very close to shopping and dining. After each day of adventures, we would walk to dinner at different joints. I will stay here again when I return.

the JSON file is like below

{“predictionOutput”:{“result”:{“sentiment”:”mixed”,”documentScores”:{“positive”:0.64,”neutral”:0.05,”negative”:0.31},”sentences”:[{“sentiment”:”positive”,”sentenceScores”:{“positive”:1.0,”neutral”:0.0,”negative”:0.0},”offset”:0,”length”:22},{“sentiment”:”neutral”,”sentenceScores”:{“positive”:0.01,”neutral”:0.83,”negative”:0.16},”offset”:23,”length”:48},{“sentiment”:”neutral”,”sentenceScores”:{“positive”:0.0,”neutral”:1.0,”negative”:0.0},”offset”:72,”length”:134},{“sentiment”:”neutral”,”sentenceScores”:{“positive”:0.03,”neutral”:0.93,”negative”:0.04},”offset”:207,”length”:26},{“sentiment”:”negative”,”sentenceScores”:{“positive”:0.01,”neutral”:0.06,”negative”:0.93},”offset”:234,”length”:69},{“sentiment”:”positive”,”sentenceScores”:{“positive”:0.92,”neutral”:0.08,”negative”:0.0},”offset”:304,”length”:48},{“sentiment”:”neutral”,”sentenceScores”:{“positive”:0.02,”neutral”:0.96,”negative”:0.02},”offset”:353,”length”:73},{“sentiment”:”neutral”,”sentenceScores”:{“positive”:0.03,”neutral”:0.92,”negative”:0.05},”offset”:427,”length”:37}]}},”operationStatus”:”Success”,”error”:null}

The related JSON file allocate an overall score to the whole comment, then for each sentence, you can get a separate sentiment score, the result in the JSON format is not able to analyze, so I decided to use Power Query to solve this problem

First Open Power BI desktop and navigate to Power Query, import the JSON file, then load the data, click on the record to expand it and to see the record and list. Right-click on both of them and add them as a separate query.

Then click on the To Table, and expand the records to see the inside, finally, you should see the 7 rows of data with label positive, negative and neutral, and the two last columns for the offset and length of each sentence.

Now we need to add the original text to merge them together, import the text file, then use the dot separator and Transpose to make them as a table. Then use the Add Column and add index column, to both the Sentence query and the hotel comment. Then in the Home Tab click on the Merge columns and merge them based on the Index

The post Analyse the JSON File with Power Query appeared first on RADACAD.

Follow Source

The post Analyse the JSON File with Power Query appeared first on Microsoft Dynamics 365 Blog.

There are many usages of  AI Builder for Object detection, form processing, Binary Prediction, Text classification, business card Reader. However, besides them, there is another one that is available now in Power Automate. In this post, I am going to show you how to use this feature, for creating a process for automatically apply sentiment analysis and create an output file to store back to Onedrive and then clean the result using Power Query.

Power Automate

navigate to Power Automate 

login to the account you have AI Builder environment, Then under the solution, create a new flow with the trigger of “When a file is Created” in Onedrive

In the next step, you need to select the Predict to component from the Next Step action, in the model section please choose the SentimentAnalysisModel 

Then in the Request Payload section, you need to first click in the box, then write the below code

{“text”:””,”language”:”en”} (make sure the it is “)

new window chooses the Expression and clicks on the ” ” in front of the text and from the Dynamic Content, choose the File content.

now choose a new action, and select the Create file to send back the result to the Onedrive.

for the Folder path just choose the location you want to save, for the file name you can use the Expression box to create a simple name and type like

then in the File content select the ResponsePayload from Dynamic Content

Now just save the flow and test it you should upload a text file that has some comments like Hotel comment in the text format, then you need to run the flow.

below text can be a sample from hotel review

“The suite was awesome. We did not have much interaction with the staff. We did sleep on the queen size sofa bed in the living room instead of the queen size bed in the actual bedroom due to the temperature. It was very hot and humid. The air conditioner in the living room does not cool off the bedroom. This suite is very close to shopping and dining. After each day of adventures we would walk to dinner at different joints. I will stay here again when I return.”

Now a JSON file should created and you can use Power BI to analyze it in an easy way.

In the next post, I will explain how to analyze the result with Power Query.

see the full video from here

The post Automation of Sentiment Analysis using AI Builder appeared first on RADACAD.

Follow Source

The post Automation of Sentiment Analysis using AI Builder appeared first on Microsoft Dynamics 365 Blog.

AI Builder brings a huge change to creating smart self-service Applications. In this post we are going to see how to create a smart application that able to read the Business Card content and extract them, then import them using Power Automate to the Outlook contact list.

Creat Business Card Reader using Power Apps and AI Builder

First login in the environment that supports the AI Builder.

Now in the new  Canvas app, create a new Phone layout

In the new page, click on the Insert option, then click on the AI Builder –> Business Card Reader

In the next step, click on the Insert Lable, and for the label write the below formula, BusinessCardReader1.FullName

Copy and paste two times for the email and Phone number

BusinessCardReader1.Email

and

BusinessCardReader1.BusinessPhone

Next, Save the App and Navigate to the Power Automate (Microsoft Flow)

Create Flow in Power Automate

Now navigate to the same Environment in Power Automate with the same account, First, create a new Flow, and the trigger should be Power Apps that do not get any input from the Power Automate,

Next, click on the Next step and add the “Create contact(V2)”

we need to set up some part of this component.

First the Folder ID, for me is Contacts

Next, the Given Name which is mandatory, click on the box, choose to Ask in Power Apps, then another component fir the GivenName will show choose that one and remove the Ask in pOwer APPs, do the same for the Home Phone and Email address

Then save the Flow and back to the Power Apps

Connect the Power Apps and Power Automate

Back to Power Apps to connect the Apps with Power Automate. Click on the Insert, then click on the button, and change the name of the Button to the Add

Next, click on the Button, then Action, then Power Automate, and in the list at the right sides of the page choose the Flow you just created, then at the formula bar you should it.

The list of required parameters has been listed also there.

Next, add the parameters as below

GettheContact_powerapps.Run(BusinessCardReader1.FullName,BusinessCardReader1.BusinessPhone,BusinessCardReader1.Email)

As you can see all the elements we already add in the Flow to be added in the Contact have been requested here as input parameters.

Run the application using the Run button at the top right

you should see the details and also you should see the contacts have been added to the contact section in outlook

see the video from here

https://youtu.be/lcQoQOhw_uA 

The post Business Card Reader Automation with AI Builder, Power Automate and Power Apps appeared first on RADACAD.

Follow Source

The post Business Card Reader Automation with AI Builder, Power Automate and Power Apps appeared first on Microsoft Dynamics 365 Blog.

Text classification is one of the important tasks for the aim of classifying the texts based on the allocated tags.
In the previous blog, the process of how to create Text classification in the Power Apps using AI builder has been explained,

In this Blog Post, you will see how to use the created Text classification model in the Power Automate (Microsoft Flow).

to strat

1- Login to Power Automated Account and to the same environment you have your own Text classify model created in the previous steps in the same environment.

2- In the next step, you need to login to the Power Automate,  just make sure to log in to the Power Automate in the same environment. Same as Other AI Builder solution in Power Automate, you need to create a new solution and other that create the Microsoft flow.

then click on the new Solution, “AICourse”. Then create a new Flow.

In the new page, create the Microsoft Flow, by trigger by ” Manually trigger a flow”, and add Input for the Text

in the new page call the text as “Mytext”. Next, we need to call the AI Builder using Predict for Common Data Services (CDS). So click on the “New Step” and search for the Predict.

In the list of the model, you can see the “textclassification”, we created alongside with other models. For the Request Payload

write the

{“text”:” “}

and

for the formula for the white space click on the “Mytext” which is the output of the previous step.

Next, change the name of the Flow and save the flow to click on the text at the top right of the window .

For the first time, you need to trigger manually.

Next, run the flow to get the JSON schema

When the  run finished, click on the output and copy the respond Payload

{“predictionOutput”:{“results”:[{“type”:”Care”,”score”:0.603922}]},”operationStatus”:”Success”,”error”:null}

Click on the Edit, and add a new Step for the Pars JSON.  then Click on the “Geberate from Sample” to extract the JSON code. The yu should see something like below

Just save and run the code. This time after a click on the Test Flow, I choose the Using data from Previous runs.

Now check the output, as you can see in the JSON code the output id Type is Care and the Score is 0.60.

The output is on the JSON format, you can then use it to automatically send the result to other platforms.

https://docs.microsoft.com/en-nz/ai-builder/text-classification-model-in-flow

The post Text Classification using AI Builder inside Power Automate (Microsoft Flow) appeared first on RADACAD.

Follow Source

The post Text Classification using AI Builder inside Power Automate (Microsoft Flow) appeared first on Microsoft Dynamics 365 Blog.

Another exiting new update in AI Builder is Form Processing. With for Processing you able to train the model with forms you have and AI builder able to detect each session of the form and the related values. This feature is so exiting form as for 5 years I am one of the organizer of SQL Saturday Auckland and always I have challenge with evaluation. In some strange way people prefer to evaluate the sessions via paper rather online link. So I need to create an application with cognitive service that able to detect the elements in a form. Such as title of the session, speaker name and the comments from the attendees. In this post and the next one, I will explain the process from creating the form processing model to Flow application that helps me.

in this post and next One, I will explain the process.

First: Set up the Form Processing in AI Builder

Before start Make sure

! Make sure you have forms and at least 5 forms with less than 4 MB size and if it is handwritten form, the quality of form in jpg/png or PDF make sure to be good.

! You already access to AI Builder environment see Post. 

Now, you can start logging into the Power Apps make sure to access the environment you can see the AI Builder. You should see the AI Builder icon in left side of the window.

Next, under the AI Builder, choose the Build Option, then from AI model, choose the Form Processing.

In the new page, Form Processing put a name for the Model Name then select the create

The first step is Analyse Documents, you need to import at least 5 samples of the filled form you have. Just make sure the quality be good and the size of all file does not exceed 4MB.

As I mentioned before, I want to use this form processing for the aim of session evaluation, so I import 6 different session evaluation like below :

After importing the forms, you need to analyse the documents, so AI Builder can detect each section of the forms and related values.

Analysing the form take a couple of minutes, after that, you need to check the identified fields and choose the one that is matter to you

As you can see in the below picture, in this example three fields have been identified, and you able to see the confidence of each part by hovering your mouse over each field. Choose the fields you are happy about. The selected fields will be shown in the right panel.

After selecting the fields, you are in the second step of building form processing, to navigate to the third step, click on the Next.

Now, you imported your sample forms, at this stage you can train your model, you can see a summary of the model as the number of forms and number of selected fields. Then click on the Train option to navigate to the last step.

Training will take about a couple of minutes, depends on the number of documents for training, after training complete, Go to details page.

In the details page, you can see the number of documents you uploaded for training, the number of detected fields in each form, You can also test the model and then publish it.

for testing the mode, you need to import a sample of the form that you have, then wait to see the result in the Quick Test page.

In the sample, all trained fields should be identified. Next Back to the details page and Publish the model so you can use it in other applications

I want to create a workflow so I can upload pictures in OneDrive, then using this model and store back to OneDrive the result as a text file so I can use it Power BI report. As a result, after creating a model, I navigate to the Microsoft Flow. and I log in in the same environment I created the form processing model.

To make sure I can see the model I just created in Microsoft Flow, click on the model and you should see the Form Processing model is available with Publish Status as Live.

In the next post, I will explain how I create a Workflow that able to read scanned file from the OneDrive folder then apply the created model and store back in a text file in the OneDrive again.

The post Form Processing Work flow- Create Form Processing Model Part 1 appeared first on RADACAD.

Follow Source

The post Form Processing Work flow- Create Form Processing Model Part 1 appeared first on Microsoft Dynamics 365 Blog.

As I mentioned in Post 1 and Post 2, AI builder is a game-changer in Power Apps and Flow, it provides the facility to easy embed AI in applications and process without writing any code. Also, there is no need to set up other environment and applications to make it work.

In this post, I am going to show you how to activate your Power Apps trial account to see and practice the AI Builder.

There is some note:

AI Builder in Power Apps available in Europe and the USA region.

There is a Trial (29 Days) and Production plan

for this scenario, I choose the USA and Trial plan to examine the AI Builder

Set Up Environment in Power Apps

To setup, the environment needs to login into Microsoft Power Apps Portal. Login

In the next step, you need to navigate to the Gear icon at the top, then click on the Admin Centre

this, navigate you to the admin centre environment.

As you can see in the environment page, all of my available account under RADACAD has been shown with their type, region and name. As the default region for RADACAD account in Australia, and AI Builder for now just available in USA and Europe, I need to create a new environment.  In this new page, you will see the Environments option.

In the new page, you need to provide the environment name, region ( in my scenario I choose the USA) and the environment Type.

It will take a couple of seconds to create the environment, and you will receive a message about it as well.

After creating the new environment to access to AI Builder, you need to create a database in Common Data Services(CDS)

another important note

AI Builder need to access to Common Data Service

Click on the Create database.

During the creating the database, it will ask you about the data filed for Currency and Language. in CDS, you able to mention, if you have a currency field what currency be the default one, or in what language you want to store your data.

after setting up all required parameters click on the Create database so your new environment access to CDS. Now you able to see the new environment with the name AI Builder 

Now you need to back to Power Apps main page, click on the Environment dropdown at the top, and select the AIBuilder option. As you can see in the below picture, on the left panel, the AI Builder (Preview) has been shown.

after setting up the AI Builder for Power Apps, you can see the same functionalities in Microsoft Flow.

you need to Login to Microsoft Flow,

at the top right click on the account name, and choose the environment that you already set up for  AI Builder. The same as Power Apps, you able to see the AI Builder on the left side.

to see how AI Builder Works see Post 2 and also more post on it coming soon.

Special thanks to Joe Fernandez from Power Apps team to help to examine these features.

1- https://docs.microsoft.com/en-us/power-platform/admin/create-environment 

The post Activate AI Builder In Power Apps and Microsoft Flow appeared first on RADACAD.

Follow Source

The post Activate AI Builder In Power Apps and Microsoft Flow appeared first on Microsoft Dynamics 365 Blog.