TY  - JOUR
AU  - Ch Yamini
AU  - P Aditya Ram
AU  - P Shravan Kumar
AU  - T Vinay Kumar
PY  - 2025
DA  - 2025/06/27
TI  - AI Powered Server Log Management System Using Random Forest Model
JO  - Global Journal of Engineering Innovations and Interdisciplinary Research
VL  - 5
IS  - 4
AB  - As technology continues to advance, system errors have become more frequent, and users often struggle
to find the right solutions. Traditionally, users had to search across multiple servers for answers, which
often resulted in a flood of responses, making it difficult to identify the correct one. This process can be
time-consuming and frustrating. To address this issue, we've created a solution that collects error logs
from all servers and utilizes Artificial Intelligence (AI) to build a smart system. By training the AI model
on past error questions and their solutions, the system can now analyse a user’s error and predict a
suitable solution. This means users no longer have to search through various sources. Instead, they can
get a quick and accurate answer from a single, centralized server. This AI-powered system simplifies
error resolution by providing more direct, relevant answers. Unlike Google or Bing, which may return
too many irrelevant results, our AI ensures users receive the most precise solution to their specific
problem. The system is built using a carefully selected dataset containing questions and answers related
to operating systems (OS), programming issues, and other technical problems. Over time, with the
addition of new questions and answers from users, the AI will learn and improve, solving an even wider
variety of errors. A key advantage of this system is that the dataset can be continuously updated with new
information from users. This ensures that the AI model remains current and is capable of addressing a
broader range of errors. Whether the issue relates to OS problems, software bugs, or network errors, the
AI will keep getting better, making it a valuable tool for troubleshooting.
SN  - 3066-1226
UR  - https://dx.doi.org/10.33425/3066-1226.1144
DO  - 10.33425/3066-1226.1144