Cross-Ecosystem Event Clustering for Automated Incident Resolution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional approaches struggle to effectively analyze and respond to events across disparate ecosystems in software or service organizations, leading to incomplete, inaccurate, or delayed issue detection and resolution.
Innovation Solution
An automated method to cluster events from various ecosystems into noteworthy incidents, correlate them with entities, and convert incidents into tickets, issues, and assign them to responsible entities, using machine-learning techniques to facilitate cross-ecosystem analysis and communication.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual processes are used to analyze data from disparate ecosystems, then human effort can be devoted to individually analyzing events, but the approach is costly, reactive, and unable to accurately and efficiently process huge amounts of data
Solution Approach 1:
The patent replaces manual human analysis with an automated computer-based system that collects events from multiple disparate ecosystems, clusters them using machine learning algorithms, and generates incidents and tickets automatically. This substitution eliminates the limitations of human processing capacity while maintaining or improving analysis accuracy through systematic computational methods.
Solution Approach 2:
The system enables self-service by automatically performing data collection, clustering, incident generation, and ticket creation without requiring human intervention for each event. The machine learning models autonomously identify patterns and relationships across ecosystems, allowing the system to serve itself in processing and analyzing data at scale.
2Loss of information
If data is collected from disparate sources, then comprehensive coverage of events is achieved, but the organization is inundated with a high volume of events from many diverse sources
Solution Approach 1:
The patent merges events from multiple disparate ecosystems by collecting them into a unified system, applying machine learning clustering to group related events together, and consolidating them into single incidents or tickets. This combining approach maintains comprehensive event coverage while reducing the overall volume of individual events that need to be processed separately.
Solution Approach 2:
The system segments the high volume of events into meaningful clusters and groups using machine learning algorithms. By dividing the overwhelming stream of individual events into organized clusters based on similarity and relationship, the system makes the data manageable while preserving the complete information from all source ecosystems.
3Ease of operation
If conventional approaches are used to analyze events across ecosystems, then isolated ecosystem analysis is simple, but it is not possible to adequately perform analysis regarding events that cross the boundaries of isolated ecosystems
Solution Approach 1:
The patent creates a universal system that handles multiple ecosystem types simultaneously. The machine learning models are designed to process events from diverse sources with different schemas and characteristics, applying unified clustering and analysis methods that work across all ecosystems. This multi-functional approach enables accurate cross-ecosystem analysis while maintaining operational simplicity through standardized processes.
Solution Approach 2:
The system introduces an intermediary layer between disparate ecosystems that translates and harmonizes events from different sources into a unified format suitable for cross-ecosystem analysis. This intermediary processing layer enables accurate detection of relationships spanning multiple ecosystems while preserving the simplicity of individual ecosystem operations through standardized interfaces.
Data Source
AI summary
Disclosed is an improved approach to process data and events from disparate ecosystems pertaining to products. An approach is provided to automatically cluster events from various ecosystems into noteworthy incidents and to correlate them with entities extracted from each system. Incidents are correlated between ecosystems to classify the type of incidents and to give a coherent converged picture of the event streams coming from the various ecosystems. Noteworthy incidents are automatically converted into tickets and their severity is ascertained from the associated incidents. Tickets that reference underlying defects with the product or service are converted into issues.