Watson4TSS - Watson based search system for problem resolution - overview
Improving productivity of practitioners is a critical goal for IT services organizations. Today support agents read numerous pieces of information including many searches, log files and case history from disparate datasources to suggest solutions to customer problems.This work involves some interesting and challenging problems in the areas of information retrieval, information extraction, machine learning and data management.
The goal of the project is to build a full-scale Watson technology based search system to effectively and efficiently diagnose customer problems documented by call center agents and identify the best action plan to resolve them. There are several research challenges that we are addressing:
- Mining the logs to detect anomalies for root cause analysis
- Visualization for search results
- Representation of IT domain knowledge and its leverage
- Scaling the analysis to large amounts of disparate data like logs, ticket history, technical documents from disparate datasources like DB2, mainframe etc.