form on a top of a colored shape background.


How to report on order form readiness with OCR and Impira AutoML

Good order form compliance is critical to fulfilling orders efficiently. Gain the visibility you need with real-time insights into the readiness of your orders using optical character recognition (OCR) enhanced by automated machine learning (AutoML) from Impira.

Download sample files

Spending too much time reviewing orders?

We hear our customers remark all too often that it would be so much easier for them to process orders if there was good form compliance. The reality is that with complex orders, documentation can be missing or simply doesn’t include the necessary supplementary information. Manually reviewing each individual order form to filter on “order completeness” is a costly and time-consuming process for your customer service or operations team. Additionally, we can’t forgo the importance of maintaining a set of rules that determine the eligibility criteria for each order.

Process orders with greater speed with increased visibility

Eliminate the bottleneck created by reviewing orders one-by-one, and get the visibility your fulfillment and operations teams demand. Let Impira filter and classify your orders in just a few snaps and enjoy the peace of mind that comes from knowing that, once your orders are routed to the right place, any pertinent information is transformed into business-ready data. Your products will be on your customers’ doorsteps faster than ever before.

Streamline your order preparation process with smarter OCR

Impira AutoML technology elevates traditional OCR with artificial intelligence and machine learning to fully realize the dream of document automation. With Impira, you can easily turn your custom order forms into business-ready data in seconds. Using Impira’s powerful search capability, you can configure smart collections to set aside orders that are missing information and automatically extract information from orders that are ready to go. Save time and money by letting Impira filter your inbound orders and immediately output the results of orders ready for processing. 

Let’s give it a go using the sample order form packet available to download at the top of this page.

Step 1: Sign-Up for a free Impira account

If you haven’t already done so, head on over to to create your free account. There’s no need for any credit card or personal information to get started, just an email address. Our free plan includes 200 file units (pages), so there’s no cost to follow along with this tutorial.

Screenshot of where you can sign up to try smarter ocr with Impira AutoML

Step 2: Upload the sample files

After you have created your account and successfully logged in, go ahead and click on “All files” in the left-hand side. Drag and drop the sample order packets onto the browser window. Alternatively, click on the “Upload” menu in the upper right corner and select “From computer” to select the sample files from the location where they are stored.

Screenshot of the upload button and the various ways you can upload to Impira AutoML.

Impira AutoML will get to work immediately to process the data within your documents. As soon as it finishes, you’ll see that each file has its own row in a spreadsheet.

Screenshot of Impira's table view after running the initial ocr and ml models on your files.

Step 3: Automatically report on order form readiness

As each of your files are loaded into Impira, it’ll perform a number of tasks behind the scenes. One of these tasks is to run optical character recognition (OCR) on your documents. The results are made available via a powerful search feature which you can use to route files to smart collections for data extraction using Impira AutoML. We’ll walk through creating smart collections in step 4 below.

A powerful feature of Impira is the Impira Query Language (IQL). It was designed to make it really easy for power users to interactively search, filter, and transform the semi-structured data trapped in your files. IQL can also be used to create advanced queries within the Impira UI.

Each of the sample files that you uploaded has a mix of documents: a medical equipment order form, a health insurance card, and in some instances, a sleep study. For the sake of this tutorial, an order form will be considered complete or ready if it includes all three documents in a single file. If any file is missing a sleep study document, the order form will be considered incomplete and voided.

Required documents for an order that's ready to process.

Using IQL, we’ll build an advanced search that joins together all of the extracted words across the entire document and checks for the presence of various terms that we know are mentioned in the sleep study. (This example can be expanded to include other terms and check for additional criteria.)

To begin, enable IQL mode in your search bar by clicking the drop-down button in the top-right corner of the search bar, selecting IQL, and clicking Save.

Screenshot of where to select IQL.

Using IQL will allow you to include additional functionality in your search and obtain more detailed insights about your files. In this example, we’re going to check for the presence of the term “Polysomnography” (the technical term for “sleep study”) in order packets that are for CPAP machines. Together, these terms will provide visibility into how many orders can be automatically processed and which others require additional information from the submitter.

Copy and paste the query below into the search bar and hit the enter or return key. 

[File, `Has sleep study?`: regex_match( text_join(' ', File.text.words.word), '(Polysomnography)')] cpap apnea

This query gives you instant visibility into the readiness of the inbound orders for processing, and shows which orders need review or are missing required information.

Screenshot of which files have all the documents needed to be processed. Impira uses optical character recognition to detect that the sleep study is there.

IQL makes it extremely easy to iterate on your queries. For example, with a minor tweak, we can count how many files include the required sleep study, similar to how you’d perform the same task in Business Intelligence tools or with formulae in Microsoft Excel and Google Sheets. 

[`Has sleep study?`: regex_match( text_join(' ', File.text.words.word), '(Polysomnography)'), count(File)] cpap apnea
Screenshot of Impira telling you how many of your files have the sleep study needed to process the order.

Click here for more information on how to use Impira Query Language (IQL).

Step 4: Create smart collections

Now that we have analyzed our files and understand the key terms that define our readiness criteria, we can use those to create smart collections.

Click the menu button in the search bar and change the mode back to “Search,” and click Save. If you aren’t already, select “All files” from the left-hand menu. Perform a search for all cpap orders for patients diagnosed with apnea that do include the required polysomnography report by typing “cpap apnea polysomnography” into the search bar. You should see 17 files in your search results, just like we obtained by running the initial analysis. 

From here, you can create a smart collection by clicking on “Create collection” and then “Collection matching filters.” In the window that appears, give the collection the name “CPAP Orders - Ready” and click on “Add selected files to smart collection.” Smart collections automatically stay up-to-date with new files that match their filters. Your new smart collection will be created automatically include all complete orders. 

Screenshot of how to make a smart collection, that automatically updates based on your criteria using machine learning.

Next, we’ll repeat the process for the incomplete orders that do not include a reference to a polysomnography report. Click on “All files” again and search for “cpap apnea -polysomnography.” Note the inclusion of the minus symbol before the word polysomnography. This indicates that we want to search for files that do not include that keyword. 

Create another smart collection from this new search filter and call it “CPAP Orders - Incomplete.”

Congratulations, you now have two collections that will automatically route incoming orders to their respective collections where you can then leverage Impira AutoML to extract requisite information and make it available for downstream systems or teams to process and fulfill those orders.

For more information on how to use machine learning and artificial intelligence to automate the extraction of data in your smart collections, see our guide on how to automate order form intake for medical devices using OCR and Impira AutoML.

Related resources

An illustration showing a financial space that contains a sheet with a pie chart, bar graph, and line graph, with money in front of it.

Unlock the data that’s stuck in your AR/AP invoices, contracts, expense reports, and paystubs. Impira automatically extracts key fields without any manual data entry, so you can instantly build an accurate database of your financial documents.

Text Button
Illustration of a creative space that contains a container with a paint brush, pen, and pencil, photo, and canvas with a shape drawn.

Effortlessly find the assets you need with the confidence that you can use them. Impira’s technology will automatically tag your assets, extract usage terms from contracts, and link everything together so you can focus on delivering world-class creative.

Text Button
An illustration of an IT setting containing a computer with email, security and a database.

Automatically process invoices, contracts, forms, expenses, and other documents to free up your colleagues to do their best work. We make it easy to create document extraction models that continue to improve as you provide more data and review results.

Text Button

Get started in minutes.

Already using Impira? Sign in.