Incident Ticket Classification Using Divergence Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current incident ticket classification systems are inefficient due to reliance on historical data, which often contains errors, leading to incorrect classifications and delays in issue resolution, as they fail to accurately distinguish between user-defined and pre-defined classes.
Innovation Solution
An incident ticket classification system that identifies user-defined classes, determines divergence from pre-defined classes using a dampening parameter and weight assignment, and updates classifications based on this divergence to improve accuracy by generating negative classifications and reprioritizing or removing less accurate pre-defined classes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If historical ticket data is used for classification, then automation is achieved, but classification accuracy deteriorates due to erroneous historical data
Solution Approach 1:
The system implements feedback by comparing user-defined classes (ground truth) with pre-defined automated classes, calculating divergence between them, and using this feedback to iteratively update and improve the classification model, thereby resolving the accuracy issue while maintaining automation
Solution Approach 2:
The system changes parameters by introducing a dampening parameter and weight assignment mechanism that adjusts the influence of historical data over time, allowing the model to adapt and improve classification accuracy while retaining automated classification functionality
2Productivity
If pre-defined classes from historical data are used, then classification speed is improved, but reliability deteriorates due to incorrect historical classifications
Solution Approach 1:
The system performs preliminary action by pre-processing historical data to identify and weight reliable patterns before deployment, and by implementing a dampening mechanism that prepares the model for gradual adaptation, ensuring both speed and reliability from the start
Solution Approach 2:
The system uses parameter changes by adjusting the dampening parameter and class weights to balance the trade-off between using historical data for speed and ensuring reliability, allowing the model to leverage historical patterns while mitigating their errors
3Measurement precision
If user feedback is incorporated to update classifications, then accuracy is improved, but system complexity increases
Solution Approach 1:
The system uses feedback from user-defined classes to calculate divergence and update the classification model, improving accuracy through a structured feedback loop that adds manageable complexity rather than uncontrolled complexity
Solution Approach 2:
The system manages complexity through parameter changes by using a dampening parameter and weight assignment that provide a mathematically tractable way to incorporate user feedback, avoiding the need for complex retraining procedures
Data Source
AI summary
This disclosure relates generally to automatic classification of incident ticket, and more particularly to a system and method for improving the incident ticket classification. An incident ticket classification system to update an incident ticket classification, the system comprising: a memory; and a processor coupled to the memory storing processor executable instructions which when executed by the processor causes the processor to perform operations comprising: identifying one or more user-defined classes from one or more classes assigned to one or more incident tickets; determining, divergence of the one or more user-defined classes from one or more pre-defined classes associated with the incident ticket classification; and updating, the incident ticket classification based on the divergence.