Predictive Incident Reduction for IT Infrastructure

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current technologies manage technology incidents reactively, leading to significant productivity loss due to unanticipated changes, component failures, and latent problems, without proactive predictive measures.

Innovation Solution

A method and system using predictive analytics and machine learning to analyze proposed changes in computer applications or infrastructure, predicting failure probabilities and impacts, and either approving or rejecting changes based on these predictions, employing algorithms like Naïve Bayes, k-nearest neighbors, and ensemble classifiers, and continuously learning from actual outcomes to refine models.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If changes are implemented without predictive analysis, then productivity is maintained through rapid deployment, but system reliability deteriorates due to unanticipated failures and incidents

Engineering Contradiction:
Improvesystem reliabilityVSAvoiddeployment speed
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The system performs predictive analysis of change impacts before implementation by analyzing historical incident data, change data, and configuration information to forecast potential failures. This preliminary assessment allows organizations to prepare mitigation strategies in advance, ensuring system reliability is maintained while enabling confident deployment decisions without sacrificing productivity.

Inventive Principle:
Principle #10Preliminary action

2Reliability

If predictive modeling is implemented to analyze change impacts, then incident reduction is achieved, but system complexity increases due to multiple data sources and algorithms

Engineering Contradiction:
Improveincident reductionVSAvoidsystem complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The predictive system is divided into distinct functional modules: a data collection module that gathers information from multiple sources (incident data, change data, configuration management), a predictive analysis module that applies machine learning algorithms, and an output module that delivers risk assessments. This segmentation allows each component to be independently developed, maintained, and optimized, reducing overall system complexity while maintaining comprehensive incident reduction capabilities.

Inventive Principle:
Principle #1Segmentation

3Measurement precision

If comprehensive data analysis is performed on multiple data sources, then prediction accuracy is improved, but processing time increases

Engineering Contradiction:
Improveprediction accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system pre-processes and stores historical incident data, change data, and configuration information in structured formats before predictive analysis is needed. This preliminary data preparation includes cleaning, normalizing, and organizing data from multiple sources into ready-to-analyze formats, which significantly reduces processing time during actual predictive operations while maintaining comprehensive data analysis for high prediction accuracy.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3642714B1System and method for predictive technology incident reduction
Publication Date: 2023.03.15 JPMORGAN CHASE BANK NA
  • EP3642714B1 patent drawingFigure 1
  • EP3642714B1 patent drawingFigure 2
  • EP3642714B1 patent drawingFigure 3A

AI summary

Systems and methods for predictive technology incident reduction are disclosed. In one embodiment, in an information processing apparatus comprising at least one computer processor, a method for predictive technology incident reduction may include: (1) receiving a change record for a proposed change to a computer application or a computer network infrastructure; (2) analyzing the potential change for an adverse potential cross impact with another computer application or a computer system; (3) predicting a probability of failure and an impact of the proposed change using a model; (4) in response to a low predicted probability of failure, or a high predicted probability of failure with a low predicted impact: approving the proposed change; and implementing the proposed change; and (5) in response to a high predicted probability of failure and a high predicted impact, rejecting the proposed change.