Feeds:
Posts
Comments

I am being frequently asked about KCM applications.  The answer is ultimately Knowledge Models will be used for any complex task including "design" and "planning". However today there are four main category of KCM applications:

 

  • Monitoring and Detection
    Think of network security breach or credit card fraud detection systems. In these applications a Knowledge Model is designed to detect abnormalities and certain patterns and as a result trigger an action, such as notification or automated case handling (see automation below)

  • Decision Support
    In this category Knowledge Models empower applications to provide decision support to their users. This could be as simple as spellchecker in word processing or as complex as credit risk prediction in financial applications or automatic contouring in volumetric medical imaging.
     
  • Adaptation 
    Knowledge models are actively leveraged in profiling and adaptation to users and customers needs. This for example allows for more effective personalization in applications such as targeted advertizing and recommendation systems or metabolic min personalized medicine.

  • Automation
    Many things from ABS (Antilock Braking System) in your car to various order fulfillment systems are using some kind of automation. In this scenario a Knowledge Model dictates and coordinates the conditional execution of automation process.  

In each category models are built around certain concepts in domain of interest with the objective to achieve a certain goal. It is a common to see applications that provide overlapping usages of Knowledge Models.

 

Defining Knowledge Modeling

 

Lets start this blog by defining what KCM is and what it is not!

 

Knowledge Capture and Modeling, or in short KCM is a prescriptive approach (and not a technology or standard) to construct and codify knowledge to be reused by human, intelligent agents or applications. 

It encourages to proactively construct, synthesis, reuse and exchange knowledge models and provides a methodology for doing so.