Incident Similarity Graph Embeddings for Faster IT Resolution

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing computing systems lack the ability to efficiently identify historically similar incidents to facilitate quick resolution of current issues, leading to increased costs and downtime due to the inability to analyze and utilize past incidents effectively.

Innovation Solution

A computer-implemented method using graph modeling to determine historically similar incidents by generating embeddings for subtrees within a configurable item graph, applying clustering techniques, and calculating similarity scores based on Euclidean distance to identify past incidents with similar characteristics.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional incident analysis methods are used, then incident resolution can proceed with existing manual techniques, but the ability to identify historically similar incidents is lost, leading to increased resolution time and costs

Engineering Contradiction:

Improveincident similarity identificationVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent introduces an intermediary system comprising embedding vectors, graph models, and similarity calculation mechanisms that mediate between current incidents and historical incident data. This intermediary enables automated similarity identification without requiring direct manual comparison, thus improving measurement precision while managing system complexity through structured data representation

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces manual incident analysis mechanisms with automated computational systems. By substituting human analysts' mechanical comparison processes with algorithmic embedding and similarity calculations, the system achieves precise incident matching while reducing the operational complexity of manual review processes

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If manual incident analysis is performed, then system complexity remains low, but incident resolution time increases due to inability to quickly identify similar past incidents

Engineering Contradiction:

Improveincident resolution speedVSAvoidtime to identify similar incidents

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The patent applies preliminary action by pre-processing historical incident data into embedding vectors and organizing them in graph structures before they are needed for comparison. This advance preparation enables rapid similarity identification during incident resolution, significantly improving productivity while minimizing the time loss associated with real-time analysis

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent introduces dynamic similarity calculation that adapts to different incident types and contexts. By using configurable graph models and flexible embedding comparisons, the system can dynamically adjust its analysis approach to quickly identify relevant historical incidents, thereby improving resolution speed without sacrificing accuracy

Inventive Principle:

Principle #15Dynamics

3Reliability

If no incident similarity analysis is implemented, then system costs are lower, but companies incur higher costs due to extended downtime and resource expenditure on incident resolution

Engineering Contradiction:

Improveservice availabilityVSAvoidresource expenditure on incident resolution

Core Design Contradiction:

ReliabilityVSLoss of energy

Solution Approach 1:

The patent implements feedback mechanisms where identified similar incidents and their resolution outcomes are fed back into the historical database. This continuous feedback loop improves the system's ability to prevent future incidents by learning from past resolutions, thereby enhancing service availability while optimizing resource expenditure through increasingly accurate incident matching

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent applies beforehand cushioning by preparing embedding vectors and graph structures in advance, creating a cushion of pre-processed data that enables rapid incident response. This preparatory work cushions against the potential resource expenditure and downtime that would otherwise occur during urgent incident analysis, improving reliability while managing energy loss

Inventive Principle:

Principle #11Beforehand cushioning (Prior cushioning)

Data Source

PatentUS20260037581A1Systems and methods for determining historical incident similarity predictions using signal similarities based on graph modelling

Publication Date: 2026.02.05 FIDELITY INFORMATION SERVICES LLC

AI summary

A method for finding historically similar incidents is disclosed. The method may include obtaining a plurality of historical embedding vectors for a plurality of historical data objects; receiving a current data object indicating an occurrence of a current incident associated with a configurable item, the current data object being associated with a line of business data object; determining a configurable item graph including one or more subtrees, wherein the configurable item graph is a graph of logical associations of the line of business data object and related IT operation events; generating embeddings for each of the one or more subtrees; computing a feature embedding vector for the current data object by averaging the embeddings for each of the one or more subtrees; and determining a set of historically similar incidents by applying a Euclidean distance formula to the feature embedding vector and the plurality of historical embedding vectors.