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:
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:
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 firstname.lastname@example.org or
Starting with ILINX Capture v6, the Release configurations are stored within the ILINX database. In ILINX Capture v5x, the ILINX Release configurations were stored in XML files on a disk. ILINX Capture called ILINX Release using a SendAndReceivedReply IXM. The change to store the settings within the ILINX database is very useful for a number of reasons: Release settings are part of the batch profile allowing for simpler migrations between environments, Release is much easier to configure, all configurations are in the database, etc. However, this change can create some extra work when upgrading from ILINX Capture 5x to ILINX Capture 6x. Because of the different architecture, ILINX Release needs to be completely reconfigured for the existing batch profiles. In addition, the Release XML doesn’t change, but there is a shortcut that can be taken. After you have upgraded ILINX Capture to v6, you’ll notice a new IXM in the palette:
The existing ILINX workflow will likely have a SendAndReceiveReply IXM on the map that the 5x version of ILINX Capture used to call ILINX Release. Most likely, it would look like this:
To configure ILINX Release for ILINX Capture 6x, the SendAndReceiveReply IXM will need to be removed from the map and a Release IXM must be dragged onto the workflow map in its place. Once the new Release IXM is on the map, it will need to be configured. This is where the shortcut can be taken. Instead of having to manually enter in the correct URLs, map the metadata values, and configure any other settings, do this:
Configure and save Release with some place holder settings: I normally leave the settings at default and enter in the bare minimum:
Once ILINX Release configuration is saved and the workflow map is published, there will be a new entry in the ILINX Capture database Capture WorkflowAppSettings table. The CaptureWorkflowAppSettings.SettingsXML column is where the Release configuration is stored. Now it’s time to update the SettingsXML column with the XML from the ILINX Release 5x job settings file. The Release job should be on the ILINX Release 5.x server at c:ProgramDataImageSourceILINXReleaseSettingsJobs. The only caveat here is to be sure to place single quotes around the XML content. Here is what the SQL update statement would look like:
update [ILINX CAPTURE DATABASE].[dbo]. [CaptureWorkflowAppSettings]
set SettingsXml = ‘COPY AND PASTE ALL TEXT FROM 5.4 OR PRIOR RELEASE JOB SETTINGS FILE HERE’
where settingsID = ‘APPROIATE ID HERE’
Following this procedure can save some time if upgrading an ILINX Capture 5x system that has a lot of batch profiles. A lot of the time spent on the upgrade could be in the ILINX Release configuration. If I was upgrading a system with only a few batch profiles, I would probably just reconfigure them. If I was upgrading a system with a lot of batch profiles, I would go through the above steps to save some time.
Sr. Systems Engineer
There’s nothing quite like logging in to a customer’s system first thing Monday morning only to be greeted with this:
I discovered this when I wasn’t able to log into the customer’s ILINX Capture implementation. The logged error (failure to locate the SQL Server) led me to take a look at the SQL Server’s configuration to confirm that its service was not running on either node of the cluster, and the error I got when trying to start that (a clustered resource could not be activated) led me to check on the clustered resources themselves.
I have been doing document conversion for roughly 15 years and there are numerous applications you can choose from that are a complete waste of time. I have unfortunately had the opportunity to work with some very cumbersome and complicated applications over the years. One of the applications we were using had modules you would have to open separately for every step in the conversion process. After scanning you would have to open the import module then you would have to open another module for document classification then another module for indexing then another module for Quality Control and another module for releasing the final product. I was introduced to a new application called ILINX Capture that changed my entire workflow. I fell in love with it. Now, I no longer have to open a bunch of separate modules to complete the conversion process. The conversion process takes place all in the same window document classification, QC, indexing, etc. ILINX Capture is so easy to use and a complete time saver. I recommend checking it out if you find yourself wasting time going through unnecessary steps when capturing and indexing your content.
Conversion Services Manager
ImageSource recently announced the release of ILINX 6.0. The new version of ILINX Capture includes a workflow IXM (ILINX Extension Module) that allows a C# programmer to add their own code to the workflow. As a Sr. Systems Engineer for ImageSource, I would like to give you a quick overview of how to setup and add the code so that you can perform this action yourself.
Once ILINX Capture 6.0 is installed, you should find a subfolder under the install folder (c:Program FilesImageSourceILINX Capture) named “Sample Code”. This subfolder contains a zip file that you can use to unzip the contents to a folder on your hard drive. You can then use the provided Visual Studio shell (Visual Studio Express 2013 for Windows Desktop is free) to open and code/de-bug/build the Server Side Extension. The files listed in the zip file are:
As you can see, there is a solution file that you can open in Visual Studio Express 2013 for Windows Desktop that will allow you to access the layout for each section listed. When you open this file you will get Continue reading