AIM-HI: A framework for request routing in large-scale IT global service delivery
by A. Khan,
H. Jamjoom,
and J. Sun
In many network and IT (information technology) systems, users
submit loosely defined (or "fuzzy") requests to obtain answers,
solutions, or resources. Fuzzy requests are often presented in
problem tickets and processed by an IT service management
system. In such a system, problems are typically reported using
vague user-generated descriptions of the symptoms (e.g., "my
e-mail is not working"). Making use of the reported symptoms, the
incident management system is then responsible for identifying the
component causing the problem. An accurate and quick diagnosis
from the fuzzy symptoms becomes critical for an efficient and
timely resolution of the problem. In this paper, we propose a system
for automated incident management using historical information
(AIM-HI), a framework for autonomous routing of requests in
large-scale IT global service delivery. AIM-HI incorporates
historical request resolution information and frequency, together
with queue bouncing trends to extrapolate algorithms for
streamlining and automating the dispatch of requests or work
among support groups and IT specialists. The simplicity and
scalability of AIM-HI should lead to deployment in actual real
operational systems in the future.