Incident Clustering System for Network Trend Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional incident reporting systems are inadequate for detecting long-term trends or common incidents across computer networks, leading to undetected issues and high operational costs.
Innovation Solution
An incident clustering system that processes incident text strings through data intake, pre-processing, tokenization, and clustering modules to identify and group similar incidents based on score values, utilizing AI, ML, and NLP techniques.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional incident reporting systems are used to record incident reports individually, then the system is simple and easy to operate, but long-term trends and common incidents cannot be detected and frequently go undetected
Solution Approach 1:
The patent introduces an incident clustering system as an intermediary layer between traditional incident reporting and analysis. This system processes incident reports through multiple modules (data intake, pre-processing, tokenization, clustering) to detect patterns and trends that individual reports would miss, thereby improving detection capability without replacing the simple reporting mechanism itself
Solution Approach 2:
The incident clustering system is divided into distinct functional modules: data intake module, pre-processing module, token module, and clustering module. Each module performs a specific function in the incident analysis pipeline, allowing the complex detection task to be broken down into manageable segments that can be processed systematically
2Productivity
If teams address incidents individually using different terms to describe the incident and resolution, then each incident can be handled with specific attention, but fixable root causes incur high overall operational costs and business losses
Solution Approach 1:
The system transforms incident data by changing its representation parameters through pre-processing (lemmatization, stop word removal) and tokenization (creating phrases-of-interest and concatenated tokens). This parameter transformation allows incidents described in different terms to be recognized as similar, enabling efficient clustering and root cause identification that reduces operational costs
Solution Approach 2:
The clustering module generates feedback by identifying patterns and relationships among incident reports. This feedback mechanism allows the system to recognize recurring issues and root causes, enabling teams to address underlying problems rather than treating each incident individually, thereby improving resolution efficiency and reducing operational costs
Data Source
AI summary
An incident clustering system for detecting clusters among incident reports can include a data intake module configured to receive incident text strings associated with respective incident reports input by a user, a pre-processing module operatively connected to the data intake module to receive the incident text strings from the data intake module and to pre-process the incident text strings to output pre-processed text strings associated with the respective incident reports, and a token module operatively connected to the pre-processing module to receive the pre-processed text strings. The token module can be configured to identify one or more phrases-of-interest having a plurality of words in the pre-processed text strings and concatenate the plurality of words of each of one or more phrases-of-interest to output concatenated tokens associated with the respective incident reports. The system can also include a clustering module configured to receive the concatenated tokens associated with the respective incident reports and to cluster similar concatenated tokens together to cluster associated incident reports.