LLM Troubleshooting Agent for Network Ticket Aggregation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional network troubleshooting in organizations is time-consuming and resource-intensive due to the tiered process involving multiple support engineers, especially for complex issues, leading to potential duplication of efforts and wasted resources.
Innovation Solution
A large language model (LLM)-based agent is integrated into the support workflow to aggregate support tickets, identify root causes, and provide automated troubleshooting instructions, leveraging plugins for data retrieval from network controllers and monitoring systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional tiered troubleshooting process is used, then comprehensive human expertise is utilized, but troubleshooting time and resource consumption increase significantly
Solution Approach 1:
The system performs preliminary actions by automatically gathering troubleshooting data, analyzing logs, and identifying potential root causes before human engineers intervene. This pre-processing of diagnostic information reduces the time engineers need to spend on basic analysis while maintaining comprehensive expertise evaluation.
Solution Approach 2:
An AI assistant acts as an intermediary between support tickets and human engineers, automatically analyzing ticket data, gathering diagnostic information, and presenting structured findings to engineers. This intermediary layer filters and prepares information, reducing manual investigation time while preserving expert judgment for complex decisions.
2Reliability
If multiple support tiers are involved in troubleshooting, then complex issues are thoroughly investigated, but resource efficiency decreases due to potential duplication of efforts
Solution Approach 1:
The system merges troubleshooting efforts across multiple tiers by consolidating diagnostic data, analysis results, and investigation findings into a unified view. This prevents duplicate data collection and analysis while maintaining thorough investigation through aggregated insights from different expertise levels.
Solution Approach 2:
The AI assistant provides continuous feedback to engineers throughout the troubleshooting process, presenting relevant diagnostic information, suggesting potential solutions, and updating analysis results as new data becomes available. This feedback mechanism ensures comprehensive investigation while reducing redundant efforts by keeping all engineers informed of current findings.
3Measurement precision
If manual troubleshooting processes are used, then detailed human analysis is performed, but automation level remains low
Solution Approach 1:
The system enables self-service troubleshooting by automatically gathering diagnostic data, analyzing logs, identifying patterns, and generating troubleshooting recommendations without requiring immediate human intervention. This automated self-diagnosis maintains high diagnostic precision while significantly increasing the extent of automation in the troubleshooting process.
Solution Approach 2:
The patent replaces manual mechanical troubleshooting processes with an AI-based automated system that uses machine learning models and natural language processing to analyze ticket data, gather diagnostic information, and generate solutions. This substitution maintains or improves diagnostic accuracy while dramatically increasing automation levels.
Data Source
AI summary
In one implementation, a device performs, using a using a large language model-based troubleshooting agent, troubleshooting of a plurality of issues in a network indicated by a plurality of support tickets opened by users of the network. The device aggregates, based on results of the troubleshooting, the plurality of support tickets into a master support ticket. The device obtains a resolution to the master support ticket from a support engineer. The device uses the resolution to the master support ticket in conjunction with the large language model-based troubleshooting agent to troubleshoot a new support ticket.