How WSDOT Leverages ILINX Workflow for Auto-Matching Vouchers & Receipts


Richard Norrell, Washington State Department of Transportation

Washington State Department of Transportation (WSDOT) has a lot of processes where transaction documents are created in a system, printed, processed then scanned into the Enterprise Content Management (ECM) system for search and Retention Management. In addition to these documents, there are summary reports that are produced, and in the old days these reports were manually verified to confirm that each transaction document referenced was actually processed and captured in the ECM. Sometimes it would take several days or even weeks for the various geographically dispersed offices of the agency to get the paper documents processed and scanned, so the manual matching process had to be repeated on a daily basis until all documents were present. With the implementation of the new ILINX Capture system this process is now completely automated, only requiring human intervention if documents fail to show up after a designated grace period. Here are some screen shots and explanations of how it all works for the newest implementation, Payment Vouchers.


The ILINX Capture Workflow

The main section of the workflow, shown above, handles the scanning, indexing and processing of the Payment Vouchers and routing of the Register reports into the Register Subflow. 

The Register Subflow is where the matching process takes place. This process uses two custom Server Extension ILINX Extension Modules (IXM). The first Server Extension (Parse RAM 0051) takes the Summary Report and parses it into individual rows in a Line Item table. Each line is a reference to one or more documents that require matching. The second Server Extension (RAM Auto Match) reads through the entries in the Line Item table and conducts a search for documents that match the Line Item reference. When documents are found they are updated indicating the Line Item that they match and then the Line Item itself is updated to indicate it has been matched to the documents. After the Auto-Matching is attempted the workflow checks to see if all the Line Items were matched or if the prescribed number of cycles has been attempted. Based on these checks the Register batch will either go into the Pending Match Cycle queue, the Warrant Manual Match queue, or Complete the subflow.

Here is what the actual summary report looks like: As you can see it could be pretty tedious to sit and manually match each of these lines to the documents they represent in the system.

Should a manual review be necessary, a Workflow Form is used. On this form, workflow fields are shown that keep track of how many documents are referenced in each summary report. At a quick glance, the user can see how many documents have been matched, how many are missing and the number of times the workflow has attempted to do the matching process.

The table on the left side of the form shows the documents that have been previously matched, indicated by the padlock icon, and the remaining documents that are available for matching. The table on the right shows all of the documents that are referenced in the report. If manual matching is desired, the user simply selects a document in the left table, not already matched, and presses the Match button on the corresponding line on the right table.

WSDOT has now automated the process of matching several business areas including Payment Vouchers, Journal Vouchers and Cash Receipts. Once documents are matched, the properties on the documents can be used creating a cross reference to the summary report. Also, using the Full Text capabilities of ILINX Content Store, users are now able to research both the summary report information and their corresponding documents without having to return to the source system. In this case, the source system is a mainframe application so the users are really loving that little side benefit.

If you are interested in more details of how these processes work, please contact ImageSource.

Richard Norrell is a Senior ECM Systems Engineer at Washington State Department of Transportation in Olympia, WA. He was instrumental in helping them move from Oracle IPM and Kofax to ILINX technologies for migration, capture, workflow, repository, retention management and COLD processing.

300 Million Pounds of Frozen Vegetables

If you haven’t seen our National Frozen Foods customer success video yet, take a break for less than 3 minutes and see how this corporation that produces over 300 million pounds of frozen vegetables a year utilizes their Enterprise Content Management system to increase their business efficiencies.

Continue reading

Save Time and Money With Advanced Capture

Does your organization waste valuable time and resources to manually prep documents? Are you tired of manually typing in data which oftentimes isn’t inputted accurately and error-free? If you want to venture away from these tedious slow processes, there are solutions out there! Advanced capture technologies will streamline and automate the transformation of documents into structured electronic information for your business processes.

Continue reading

How Intelligent Capture Utilizes Machine Learning for Template-free Training

There has recently been a lot of chatter in our industry about machine, and I want to share a few thoughts about how ImageSource’s ILINX Advanced Capture 8.5 platform tackles this topic. Our approach is to deploy a neural network-based document processing model that does not rely on templates. Our machine-learning platform supports custom-developed content classification projects with much faster turnaround than traditional rules-based models. The result is significantly faster time-to-production with more reliable and accurate results for our customer partners. ILINX machine learning offers:

  • Dynamic data location and extraction of information on complex documents
  • Image comparison to support check fraud applications
  • Feature extraction and classification to support medical imaging diagnostics

Our solutions leverage machine learning to create pre-built form classification algorithms in the lab, which provides a more-flexible and efficient way to develop new document processes.

For the sake of this article, I’d like to focus on the goals of almost every AP automation project:

  • Reduce paper handling and workload
  • Simplify processes down to one system for all invoices and other types of documents whether paper or digital
  • Gain visibility into where each invoice is in the process

For the initial document discovery, a technique called “clustering” can be used to automate the logical grouping of like documents. Clustering, in this example, refers to different categories of like invoices, checks, receipts and remittances. Documents can be organized automatically. Invoices from one vendor can be grouped together, such as receipts to travel documents. The result is a set of documents grouped by likeness that can then be further evaluated.

Next, each cluster, if part of a required document, can be given a document type (or class). The training set can then be imported into the machine learning ILINX solution designed to automatically identify key characteristics of each document type (often called “feature extraction”). This trains the neural network for each document type. When performance is not ideal for a specific class, the customer can add those misclassified or unclassified documents to the class sample set to “re-train” the neural network.

Data extraction is simplified by taking sample invoices that have been processed, along with the data required for each document. Together, these automatically train the software to locate the matching data and derive positional algorithms for each data field. The software uses the processed data for each page and locates the corresponding data on every document. The solution will do this for each sample and then automatically create algorithms based upon exact location, changes in placement across each example and relative position to other data, among other elements. The knowledge worker simply examines the results.

The technology used to configure the system also makes real-time adjustments. Complicated projects that typically would take weeks, if not months, are significantly reduced. Machine learning technology streamlines the manual processes used in production and helps reduce overall labor costs.
This effort can be applied to automate both paper-based and electronic document-based processes in a single workflow.

by Terry Sutherland, CEO, ImageSource

If you would like to learn more about how ILINX machine learning can automate your business please contact us at inforequest@imagesourceinc.com or

ROI of Document Imaging

Forrester Research analyzed and evaluated ECM technologies and came out with The ROI of Imaging. Forrester Research, Inc. is a global leader in business and technology. They define imaging as software for scanning, capturing, indexing, retrieving, processing and archiving digital images of documents and electronic forms. Many organizations rely on paper intensive business processes and because of that, imaging is a very important component of Enterprise Content Management’s value.

Continue reading