Document Understanding with Action Center Asynchronously

So, I just created a simple workflow that integrates Document Understanding with Action Center: it creates a task for document classification if the confidence level is below determined threshold, and then waits for the task completion to start the classification of another document.

My question is, is there any way of making the workflow start the classification of another document regardless of the completion of other document tasks completion?

Hello @pedro.cavadas!

It seems that you have trouble getting an answer to your question in the first 24 hours.
Let us give you a few hints and helpful links.

First, make sure you browsed through our Forum FAQ Beginner’s Guide. It will teach you what should be included in your topic.

You can check out some of our resources directly, see below:

  1. Always search first. It is the best way to quickly find your answer. Check out the image icon for that.
    Clicking the options button will let you set more specific topic search filters, i.e. only the ones with a solution.

  2. Topic that contains most common solutions with example project files can be found here.

  3. Read our official documentation where you can find a lot of information and instructions about each of our products:

  4. Watch the videos on our official YouTube channel for more visual tutorials.

  5. Meet us and our users on our Community Slack and ask your question there.

Hopefully this will let you easily find the solution/information you need. Once you have it, we would be happy if you could share your findings here and mark it as a solution. This will help other users find it in the future.

Thank you for helping us build our UiPath Community!

Cheers from your friendly
Forum_Staff

Hi @pedro.cavadas,
Welcome to the Community!
If I got it right I think for such solution there is no simple method. You will need to predict it in your automation by having two paths where documents which will need further completion will be stacked in one bucket and there rest will be proceeded still. Then for example you could have another process which will handle only those which will need some action.

Thanks @Pablito!
I think you got the idea right, but I don’t know if it would solve my problem, because I’d still have to wait for the tasks completion on the second process… Still, I’ll try implementing it.

My idea at first was uploading the ActionObject of each task to a queue using a Dispatcher, and then with a Performer, checking which ActionObjects were completed and then proceeding with the processing. This way, I could keep classifying the documents with the Dispatcher independently of the tasks completion. But apparently, these ActionObject variables cannot be put into a JSON, and so cannot be uploaded to a queue. Do you know if there is any way of circumventing that?

Hi @pedro.cavadas , have you got a chance to look at
RPA Framework for Document Understanding and UiPath Action Center Workflow Templates

There are two ways you can create workflow for your scenario.

  1. You keep creating task and add task object to task object list for items have confidence level below threshold. You can loop thought the task object list in parallel foreach and wait for task at end of your workflow.
  2. You create task for items have confidence level below threshold and start a separate process with task object as argument for wait for task using StartJobAndGetReference

Hey @anupamtriwedi,
I’ve a similar issue but not only do I need to keep processing documents I need to use the document understanding results to help retrain the modle when ever the action center is used.
But on your second option above:
"You create task for items have confidence level below threshold and start a separate process with task object as argument for wait for task using StartJobAndGetReference"
How will this work if there is lots of awaiting task, I’m looking at a scenario where I have around 10,000 documents I need to process each month and have a similar process about 50%-60% don’t reach the confidence level threshold. So on an average day that would be 150-250(depending on if this is going to run on weekends or not) tickets that will need future action.
Am I right in saying you are presuming you are running these processes on different machine’s or is there any issues with running this on one unattended bot.
If it matters I’m using the cloud instance of uipath.