Alert Group Summarization with BILSTM-CRF NER and LLMs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing alert management systems face challenges with alert overload, leading to alert fatigue and potential service outages due to the need for manual review of large volumes of alerts, which can result in errors and inefficiencies.
Innovation Solution
A system utilizing a Bi-directional-Long-Short Term Memory-Conditional Random Field Named Entity Recognition (BILSTM-CRF-NER) model and a pre-trained Large Language Model (LLM) to generate comprehensive alert group summaries, incorporating domain knowledge graphs for context, reducing the need for manual review and improving alert processing efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual review of alerts is performed, then alert accuracy can be maintained, but alert processing time increases and alert fatigue occurs
Solution Approach 1:
The patent introduces an alert summary generation system as an intermediary between alert generation and manual review. This system automatically creates concise summaries of alert groups, allowing operators to quickly grasp essential information without manually examining every alert detail, thus reducing processing time while maintaining accuracy
Solution Approach 2:
The system extracts key information from large volumes of alerts and presents only the most critical details in summarized form. By taking out and highlighting essential alert characteristics, the system enables rapid assessment without sacrificing accuracy in identifying important issues
2Reliability
If large volumes of alerts are processed manually, then comprehensive coverage is achieved, but operator fatigue increases and errors occur
Solution Approach 1:
The system extracts and highlights only the most critical alert information, removing unnecessary details that contribute to operator fatigue. This selective extraction maintains comprehensive coverage of important issues while reducing the cognitive burden on operators
Solution Approach 2:
An automated summarization intermediary processes alerts before they reach operators, filtering and organizing information to reduce workload. This intermediary layer maintains reliability by ensuring no critical information is lost while making the data more operator-friendly
3Measurement precision
If detailed analysis of each alert is performed, then accuracy is maintained, but network load increases and processing efficiency decreases
Solution Approach 1:
The system extracts only the most relevant alert features and generates concise summaries, eliminating the need to transmit and analyze complete alert datasets. This extraction approach maintains analysis accuracy for critical information while dramatically improving processing efficiency and reducing network load
Data Source
AI summary
Apparatuses, methods, systems, or computer-readable storage medium for generating alert group summaries in software management platforms. An alert group comprising a plurality of alert data objects may be identified. One or more alert features associated with the alert group may be extracted based on the plurality of alert data objects and using one or more feature extraction models. Action-related communication content for the alert group may be retrieved. An alert group summary for the alert group may be generated using one or more machine learning models and based on an input data set comprising the one or more alert features and the action-related communication content.