Process documents in IQ Bot Extraction360 (Preview)
Upload sample invoices to train the learning instance, verify the extracted data, and fix validation errors.
- If you have not done so already, Create a learning instance in IQ Bot Extraction360 (Preview).
- Verify that your device is connected to the Control Room: Install Bot agent and register device
- If the learning instance uses a Google Document AI model, you must provide your
Google Document AI credentials to the Extraction bot:
- Navigate to and click the folder with the same name as the learning instance to configure the assets.
- Open the Extraction bot and click the IQ Bot Extraction360 (Preview) action to edit it.
- Provide the Document AI service account and endpoint URL. See Using Extract data action.
- Click Save.
- If the learning instance uses an Automation Anywhere model, ensure that each file
is 50 MB or less.
If the learning instance uses a Google Document AI model, ensure that each file is 20 MB or less, with a maximum of 10 pages.
- Ensure that the sample documents are in one of the following supported document
- The default output format for the extracted data is CSV file. To change the output to JSON, see Change output format from CSV to JSON.
Perform the following steps to upload sample invoices to the learning instance to test the data extraction capabilities of the learning instance.
This version of IQ Bot uses Automation Anywhere Robotic Interface technology to manage the end-to-end document extraction process. Each incoming document creates a new request, which triggers the extraction process. If a document requires manual validation, AARI creates a validation task and assigns it to a validation team.
After the documents are processed, the Download bot downloads the extracted
data to a file in the
Upload documents to the learning instance:
- Click Process documents.
- In the Process Documents window, click Browse to select the files to upload.
In the Download data to field, enter the file
path where the Download bot will download the extracted
When the Extraction bot runs, the process creates the following three folders in the provided file path:
Success: Contains the extracted data in the specified format (CSV or JSON).
Invalid: Holds documents marked invalid.
Failed: Holds documents that could not be processed.
You can provide an output folder path based on one of the following options:
- Option 1: The local device path if you have set
up document processing and validation on the same device.
This option is typically used when you are testing the learning instance.
- Option 2: The shared folder path if you have
set up distributed validation on separate devices.
This option is typically used for published learning instances. For example, \\10.239.192.60\Sharepath\Output.
Click Process documents.
The Bot Runner window appears. The window disappears when the documents are done processing. Refresh the Learning instances table to see the updated metrics.
If there is a value next to the Validate documents link, you must manually validate the fields that the Extraction bot could not extract data from. Otherwise, proceed to step 3.
Fix the validation errors and edit the rows:
Click Validate documents.
The AARI Task Manager opens in a new tab, with the first failed document in queue.
There are two view options: Table and Detail. You can change the view by clicking the respective button at the top left.
We recommend that you perform validation tasks in the Detail view because this view shows all the documents in the validation queue side by side with the document that you are currently validating. Additionally, when you finish validating a document, the next document in the queue automatically opens.
Use the Table view see document history. When you open a document from this view, the history appears in a panel on the left.
Review each field to verify that the correct value was extracted for
Alternatively, you can select Show fields that need validation from the drop-down list on the right panel.Note: If you make any edits to the learning instance while there are documents awaiting validation, open the Validator and click Reprocess to re-attempt extraction.
Reprocessing documents does not affect the uploaded documents metric.
Update the error fields.
Click the field or draw a box around the values that you want to extract.
- To skip a document without correcting errors, click Skip to proceed to the next document in the validation queue.
- To remove a document that cannot be processed, click Mark as Invalid.
After you make the necessary corrections, click
Submit so that the document can finish
The Validator shows the next document in queue. When all the documents are corrected, the system displays a message stating that no more tasks are available.
- Close the tab to return to the Learning Instances page.
- Click Validate documents.
Verify the output results:
Open the file in the
Successfolder that contains the extracted data and review the results to ensure that it matches your use case.
Review the Learning Instance dashboard.
The dashboard displays the total number of uploaded documents and the number of documents pending validation.
- Open the file in the
Build a bot that uploads documents from a source folder to the learning instance. Then, publish the learning instance assets (process, form, and bots) to the public repository so that the learning instance can be used in public mode to extract data from real documents, and validators can manually validate documents: Configure and publish learning instance assets in IQ Bot Extraction360 (Preview)