By Gina Renner, executive vice president of product marketing at Key2Act. This post was originally published on the KEY2ACT blog.
This is the first part in a two-part series. Join us next time for the second post.
There are tons of articles afloat these days that speak to the radical shift in field service capabilities driven by Internet of Things initiatives, connected assets and the proliferation of information they generate once turned into useful analytics. Useful is key, when it comes to analytics.
The data that’s captured and subsequent analysis used to facilitate improved field service falls generally into five categories:
The first three are the most common categories of data analysis performed today. We’ll discuss those in this blog post. We’ll address the latter two categories in our next post.
Descriptive data is essentially the documentation of the issue at hand. What’s broken, what’s not working, what’s the error message. That’s the category of all, whether you’re using an automated system where errors or alerts are being communicated to you electronically via an intelligent asset or you’re taking a phone call from a customer and manually entering the description of the issue into a field service software solution.
It’s the “tell me all about it” stage where you have an opportunity to ask qualifying questions to derive an accurate picture of the situation, like “how hot is it?”
Diagnostic data requires a more skilled and symptomatic approach to converting the descriptive information into actionable insight. It requires a level of technical skill that enables the field service technician to observe, investigate and distinguish the characteristics of the issue at hand and sometimes requires the use of diagnostic tools. This diagnostic phase usually uncovers the underlying issue, which facilitates the transition to the repair process. Diagnostic information usually transitions the “it’s really hot” description into “it’s hot because….”
Predictive data, as it relates specifically to field service of an asset, assimilates the descriptive and diagnostic information and forecasts potential future issues that could result in such things as asset failure and/or reduced performance. Predictive analysis, to be most accurate, needs to include ambient data, not limited to data generated specifically from and related to an asset. Environmental data points can become extremely relevant. Consider the impact of an asset’s proximity to an extreme heat or cold source, proximity to vibrations from another asset, or even external humidity. Your ability to predict the future is more likely to be accurate if you have all the relevant data to consider. It improves the odds of accuracy more so than using that shiny crystal ball, so you can say with unquestionable clarity, “it won’t get hot if you….”
Join me again in our next post to continue the conversation with a deeper dive into prescriptive and preemptive analysis. Let’s discuss the improved delivery of field service when you listen, you learn and you act before your customer notices a thing!
Call Conexus SG today to discuss how we can help you optimize your data for field service with Dynamics GP & Key2Act:
email@example.com or 469-828-3274