Trouble Ticket Issue Extraction via Weighted Text Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing trouble ticketing systems face challenges in accurately extracting IT-related issues due to standardized but technical and non-standardized, verbose, and ambiguous ticket descriptions, which hinder efficient issue resolution and lead to poor customer experience and increased operational costs.
Innovation Solution
A processor-implemented method and system that infers and clusters machine-generated and user-generated trouble tickets using language variations, Part of Speech tagging, and domain-specific parameters, followed by weighted text matching with a service catalog to identify and label issues, thereby improving matching accuracy and efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Stability of the object's composition
If trouble tickets are standardized in structure, then data consistency is improved, but the tickets become harder to understand due to technical jargon and parameterized format
Solution Approach 1:
The patent introduces an intermediary processing layer that translates standardized ticket structures into human-readable descriptions. The system extracts meaningful information from the structured data and reformulates it into natural language explanations, acting as a mediator between the rigid standardized format and human understanding requirements.
Solution Approach 2:
The system changes the representation parameters of the trouble tickets by transforming them from structured data formats into natural language descriptions. This parameter transformation preserves the underlying standardized structure while presenting the information in an accessible, human-readable format that eliminates technical jargon barriers.
2Adaptability or versatility
If trouble tickets are generated by humans, then descriptive flexibility is improved, but the tickets become non-standardized, redundant, and ambiguous
Solution Approach 1:
The patent segments the trouble ticket processing into distinct stages: extracting key information from the varied human descriptions, standardizing this information into a unified structure, and then generating consistent responses. This segmentation allows the system to preserve the flexibility of human-generated descriptions while enforcing standardization in the processed output.
Solution Approach 2:
The system incorporates feedback mechanisms that learn from human-generated tickets and continuously improve the standardization process. By analyzing patterns in human descriptions and adjusting the extraction and transformation algorithms, the system progressively reduces redundancy and ambiguity while maintaining descriptive flexibility.
3Measurement precision
If issue extraction accuracy is improved through detailed analysis, then matching precision is improved, but the processing time and complexity increase
Solution Approach 1:
The patent applies preliminary actions by pre-processing and extracting key information from trouble tickets before the main matching process. The system identifies and extracts critical parameters, patterns, and semantic meanings in advance, preparing the data in an optimized format that accelerates subsequent matching operations while maintaining high precision.
Solution Approach 2:
The system uses partial action by focusing the detailed analysis only on the most critical portions of the trouble tickets rather than processing every detail uniformly. The extraction and matching algorithms prioritize high-impact information and apply intensive analysis selectively, reducing overall processing time while maintaining accuracy on essential issues.
Data Source
AI summary
A trouble ticket may contain various details of an observed issue and information of the actual issue which is hidden in the trouble ticket description along with other information. Embodiments herein describe an algorithm of algorithms (AoA) layer approach for extracting issues from trouble ticket descriptions. The method identifies the type of trouble ticket whether it is machine generated or user generated trouble tickets and accordingly selects the appropriate algorithm for issue extraction. It selects a relevant algorithm for the machine generated trouble tickets, and user generated trouble tickets based on trouble ticket data properties, historical performance, and a user feedback. It identifies right mix of columns from a service catalog to be used for matching based on presence of weighted keywords in the input data and identifies high-weighted keywords from input data descriptions and compares them with selected columns from catalog to generate accurate matches with their similarity score.