@misc{10481/103728,
year = {2024},
month = {12},
url = {https://hdl.handle.net/10481/103728},
abstract = {Modern technology environments generate vast amounts of server logs, each potentially containing
critical information about system errors. Traditional methods of resolving these errors typically involve
time-consuming manual searches across multiple platforms—ranging from search engines like Google
and Bing to various online forums—in hopes of finding the correct solution. This process often proves
inefficient, as users must sift through extensive search results and compare inconsistent or irrelevant
information, risking further errors and delays. In response, this research aims to develop an AI-powered
server log management software that delivers accurate, automated solutions to errors by analyzing
historical log data and corresponding resolutions. By consolidating server logs and training a predictive
AI model, the proposed platform offers a one-stop solution capable of reducing the time, effort, and
complexity currently associated with error resolution. Users simply input an error, and the system
provides an intelligently derived, context-aware solution—eliminating the need for manual searches. In
doing so, the platform streamlines workflows, reduces user frustration, and improves overall efficiency
in managing complex technical issues in real-world environments.},
publisher = {Universidad de Granada},
keywords = {Server Log},
keywords = {Streamlining},
keywords = {Error Resolution},
keywords = {Burdensome},
keywords = {AI},
title = {AI-Powered Server Log Management for Automated Error Resolution},
author = {Baig, Ayub and Sowmya, M. and Amulya, G. and Jayasaumya, K.},
}