Software Incident Classification via Vector Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current IT infrastructure management systems face inefficiencies due to the high volume of unwanted and redundant alerts or tickets, which delays and complicates the resolution of critical issues, as existing optimization tools do not effectively filter out non-automatable tickets, thereby impacting the overall functioning of organizations.
Innovation Solution
A method and system for classifying software production incident tickets by extracting keywords, deriving query vectors, and comparing them to vectors from past tickets to automatically classify tickets as either positive or negative mechanization candidates, allowing for automated resolution of possible mechanization incidents and manual handling of non-automatable ones.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automation is used to resolve alerts or tickets, then resolution efficiency is increased and cost is reduced, but identification of automation candidates and invocation of resolution scripts still requires manual efforts
Solution Approach 1:
The system enables incident tickets to be automatically classified and routed to appropriate resolution scripts without human intervention. The classification engine self-evaluates each ticket against learned patterns from historical data, automatically determining automation candidacy and invoking the correct resolution script, thereby eliminating the need for manual identification and invocation steps
Solution Approach 2:
The patent replaces manual mechanical processes (human analysis and decision-making) with an automated machine learning classification system. The system uses trained models to automatically analyze incident tickets, classify them into automation candidates or non-candidates, and trigger appropriate resolution scripts, substituting human cognitive work with automated computational processes
2Reliability
If the support team addresses all alerts or tickets, then comprehensive coverage is achieved, but the sheer load of unwanted and redundant alerts delays resolution of critical issues
Solution Approach 1:
The classification engine extracts and separates incident tickets into distinct categories: automation candidates, non-automation candidates, and critical issues requiring manual attention. By filtering out unwanted and redundant alerts into separate categories, the system enables the support team to focus exclusively on critical issues while maintaining comprehensive coverage through automated handling of other tickets
Solution Approach 2:
The system segments the incident ticket workload into multiple categories based on automation candidacy and criticality. This segmentation divides the monolithic ticket queue into manageable segments that can be processed differently - automated scripts handle routine tickets while human experts focus on complex critical issues, thereby reducing overall resolution time without compromising coverage
Data Source
AI summary
A system and method for classifying and resolving software production incident tickets includes receiving an incident ticket, extracting a plurality of keywords from the incident ticket, and deriving a query vector corresponding to the incident ticket based on the plurality of keywords. The system and method further comprises classifying the incident ticket into at least one of a positive mechanization incident ticket and a negative mechanization incident ticket based on a comparison of the query vector and a plurality of vectors derived from a plurality of past incident tickets. The plurality of vectors are derived based on a plurality of keywords and their corresponding occurrences in the plurality of past incident tickets.