Recovery Strategy Modeling for Asset Disruption Risk Evaluation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current generative machine learning models are inadequate in providing accurate predictions and recovery strategies for organizational challenges stemming from incidents that negatively impact supply chains, work sites, and asset allocation, failing to address severe but plausible scenarios and identify vulnerabilities.

Innovation Solution

A generative adversarial network-based model generates synthetic data for plausible disruptive events and complex asset disruptions, evaluates recovery strategies, and calculates risk profiles, using probabilistic time series models and chaos engineering to simulate and test asset availability, ultimately recommending optimal recovery plans.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If current generative ML models are used, then basic language generation is achieved, but accurate predictions for adverse incidents and recovery strategies are not provided

Engineering Contradiction:

Improveprediction accuracyVSAvoidmodel reliability for incident response

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The system segments the incident response process into distinct phases: event detection, impact analysis, recovery strategy generation, and evaluation. Each phase is handled by specialized models (event detection model, impact analysis model, strategy generation model, evaluation model) rather than a single generic model, improving both accuracy and reliability for each specific task.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system introduces intermediate structures including event databases, impact analysis layers, and evaluation frameworks that mediate between the input incident data and final recovery recommendations. These intermediaries structure the information flow and enable more precise processing at each stage.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Adaptability or versatility

If generic generative models are used, then general responses can be generated, but severe but plausible scenarios and vulnerability identification are not addressed

Engineering Contradiction:

Improveresponse customizationVSAvoidscenario coverage

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The system performs preliminary actions by pre-populating event databases with historical incident data, pre-defining impact analysis frameworks, and pre-establishing evaluation criteria. This preparation enables the system to quickly adapt to new incidents while maintaining comprehensive scenario coverage through established patterns and lessons learned.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system dynamically adapts its response generation based on the specific characteristics of each incident. The impact analysis model adjusts its evaluation depth and scope based on event severity, and the strategy generation model tailors recommendations to the specific vulnerabilities identified, enabling both customization and comprehensive coverage.

Inventive Principle:

Principle #15Dynamics

3Measurement precision

If detailed impact analysis is performed, then comprehensive recovery strategies can be generated, but processing time and complexity increase

Engineering Contradiction:

Improveimpact analysis completenessVSAvoidstrategy generation time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system applies partial action by focusing impact analysis on the most critical assets and dependencies first. The evaluation model prioritizes first-order impacts (direct consequences) over second-order impacts (indirect consequences), enabling comprehensive analysis of essential elements without exhaustive analysis of all possible effects, thus reducing time while maintaining completeness for critical factors.

Inventive Principle:

Principle #16Partial or excessive action

4Reliability

If multiple recovery strategies are evaluated, then optimal recommendations can be provided, but computational complexity increases

Engineering Contradiction:

Improverecommendation qualityVSAvoidevaluation system complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The evaluation model applies local quality by using different evaluation criteria and depth levels for different types of incidents and assets. Critical infrastructure assets receive more rigorous evaluation with additional criteria, while less critical assets use streamlined evaluation. This enables high-quality recommendations for important cases without uniformly complex evaluation for all cases.

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS20250390366A1Systems and methods for recovery strategy creation, evaluation, and recommendation

Publication Date: 2025.12.25 JPMORGAN CHASE BANK NA

AI summary

In some aspects, the techniques described herein relate to a method comprising determining an event associated with a threshold probability of causing inaccessibility to an asset; retrieving, by a model executed by a processor and from a database, event data; determining, from a database of a plurality of assets, a set of assets affected by the event based on the event data; generating cause synthetic data related to the event for the set of assets to determine a category for the event based on a location of the event; generating effect synthetic data related to the event for the set of assets; generating a recovery strategy including a response detail based on the cause synthetic data and the effect synthetic data for each asset; generating a risk profile including the response detail for each asset and a probability of the event; and calculating a degree of risk.