Ticket Mining Issue Extraction via N-gram Keyword Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for extracting issues from IT system tickets are inefficient due to unstructured user-generated text and varying system-generated text formats, leading to confusion and inaccuracy, with existing approaches relying on coarse-grained information, intuition-driven inputs, or incomplete manual reports.
Innovation Solution
A system and method for issue extraction through ticket mining, involving data cleaning, domain-specific customization, service catalog mapping, and employing techniques like stemming, synonym detection, and clustering to differentiate between structured and unstructured data, extracting issues from both user-generated and system-generated tickets.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual extraction methods are used for issue identification, then human understanding and contextual analysis are improved, but time consumption and operational costs increase significantly
Solution Approach 1:
The patent replaces manual mechanical extraction processes with an automated computational system that uses natural language processing, machine learning algorithms, and text mining techniques to extract issues from tickets, thereby eliminating human time consumption while maintaining or improving extraction accuracy
Solution Approach 2:
The patent introduces an intermediary automated processing layer between raw ticket data and issue identification, using natural language processing algorithms and text analytics as mediators to bridge the gap between unstructured ticket text and structured issue extraction, enabling fast automated processing
2Productivity
If coarse-grained information extraction is used, then processing speed is improved, but extraction accuracy and issue differentiation deteriorate
Solution Approach 1:
The patent segments the ticket text into meaningful components using natural language processing, dividing the unstructured text into sentences, phrases, and key terms that can be individually analyzed and extracted, enabling both efficient processing and accurate issue identification
Solution Approach 2:
The patent changes the parameters of text analysis by adjusting the granularity level dynamically, using techniques such as n-gram extraction, keyword frequency analysis, and semantic weighting to optimize between processing speed and extraction accuracy based on the specific ticket characteristics
3Device complexity
If unstructured user-generated text is processed without specialized techniques, then system complexity is reduced, but extraction reliability and consistency worsen
Solution Approach 1:
The patent applies preliminary text preprocessing actions to unstructured user-generated content before main extraction, including lowercasing, removing special characters, stopword removal, and basic normalization, which simplifies the text while improving extraction reliability without requiring overly complex processing systems
Solution Approach 2:
The patent replaces simple mechanical text processing with sophisticated natural language processing algorithms and machine learning models that can handle the variability and complexity of unstructured user-generated text, improving reliability while managing system complexity through modular architecture
4Adaptability or versatility
If varying text formats from different systems are processed uniformly, then system integration is simplified, but extraction accuracy and issue differentiation deteriorate
Solution Approach 1:
The patent creates a universal processing framework that can handle multiple text formats from different ticketing systems through a common natural language processing pipeline, making the system adaptable to various input formats while maintaining extraction precision through format-agnostic analysis techniques
Solution Approach 2:
The patent applies local quality adjustments by detecting the specific format or source of each ticket and applying tailored preprocessing or analysis parameters for that particular format, allowing the system to maintain high precision for each format type while still providing unified processing capabilities
Data Source
AI summary
Described herein are a method and a system for extracting issues based on ticket mining. In one implementation, a plurality of tickets comprising descriptions of the issues in computing systems are received. The received descriptions are then cleaned by removing unwanted details. Upon cleaning, the clean descriptions are mapped with descriptions stored in service catalog data to obtain unmapped clean descriptions. In an example, the unmapped clean descriptions include one of user-generated descriptions, system-generated descriptions, and both the user-generated descriptions and the system-generated descriptions. For the user-generated descriptions; the issues are extracted by pre-processing the user-generated descriptions, determining keywords from the processed unmapped clean descriptions, constructing n-grams of keywords from the extracted keywords, and extracting the n-grams of keywords as the issues present in the computing systems.