Knowledge base maintenance using knowledge gap analysis

Abstract

As the web and e-business have proliferated, the practice of using customer facing knowledge bases to augment customer service and support operations has increased. This can be a very efficient, scalable and cost effective way to share knowledge. The effectiveness and cost savings are proportional to the utility of the information within the knowledge base and inversely proportional to the amount of labor required in maintaining the knowledge. To address this issue, we have developed an algorithm and methodology to increase the utility of the information within a knowledge base while greatly reducing the labor required. In this paper, we describe an implementation of an algorithm and methodology for comparing a knowledge base to a set of problem tickets to determine which categories and subcategories are not well addressed within the knowledge base. We utilize text clustering on problem ticket text to determine a set of problem categories. We then compare each knowledge base solution document to each problem category centroid using a cosine distance metric. The distance between the "closest" solution document and the corresponding centroid becomes the basis of that problem category's "knowledge gap". Our claim is that this gap metric serves as a useful method for quickly and automatically determining which problem categories have no relevant solutions in a knowledge base. We have implemented our approach, and we present the results of performing a knowledge gap analysis on a set of support center problem tickets.