In Analytics

The service call seems like a dying art. For repairs at your home, it can be hard to pin down a repair technician to a four-hour arrival window. When the technician arrives, will he or she have the right training, tools, and supplies to diagnosis and repair the problem? If not, you’re stuck with follow-up appointment sometime within another four-hour arrival window. Magnify this problem for mission-critical equipment costing thousands or millions of dollars, and service calls become a critical event in asset-intensive industries.

Field service embodies complexity that can benefit from situational intelligence. One large utility in Canada found that it could save millions of dollars a year simply by better scheduling of field work crews. The utility supplies power to a sprawling, rural service territory. There are more power poles than people, and drive times are long. When you’re paying repair crews by the hour to drive great distances, reducing the number of trips quickly produces savings.

The first way to optimize crew dispatch is accurately locating and diagnosing the problem. This is easy when a homeowner calls to say that their dishwasher doesn’t work. It’s much harder with geographically large and diverse networks such as utilities and transportation. The growing ubiquity of sensors leading to the Internet of Things can assist in location and diagnosis. Sensor data benefits from situational intelligence’s enrichment with IT and external data, such as financial information and weather data.

Once the problem has been located and properly diagnosed, optimization depends on sending the right personnel at the right time with the right tools and supplies. This requires correlating information from multiple data sources such as personnel records (to determine skill sets of repair technicians), workforce management, customer service, fleet management, inventory management and more. Many of these sources could be manually queried and correlated given enough time and staff; because repairs are often rush jobs, situational intelligence simplifies data correlation to arrive at the optimal repair strategy.

For proactive organizations, optimizing crew dispatch means doing double duty. As long as a crew is repairing a fault on a particular device, is there any other upcoming maintenance that they should perform? This would save dispatching another crew to the same spot in the near future. Likewise, are there any other repair or maintenance needs near the item to be fixed? Doing work while in the vicinity increases efficiency, and possibly reliability as well. The only way to quickly spot opportunities for doing double duty is having situational intelligence in place for your asset maintenance and operations. And of course, serendipitous work needs to be factored into planning personnel, tools, and supplies.

How could, or does, your organization use situational intelligence to restore the lost art of service calls?

Recommended Posts

Leave a Comment

This site uses Akismet to reduce spam. Learn how your comment data is processed.