Probabilistic Digital Twins Using Knowledge Graph Inference

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current digital twin creation tools are limited to specific use cases and often incompatible, requiring multiple tools and frequent re-designs, especially in industries with frequent changes, limiting analysis and insight capabilities.

Innovation Solution

Ontology-driven processes are used to define and create digital twins, transforming data into knowledge graphs and then probabilistic graph models to infer implicit knowledge, enabling robust inferencing, prediction, and decision-making through Bayesian learning.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If multiple digital twin creation tools are used to cover different use cases, then the coverage and versatility of digital twins is improved, but the compatibility and integration between different tools deteriorates

Engineering Contradiction:

Improvecoverage of digital twinsVSAvoidintegration complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent merges multiple digital twin creation tools into a single unified platform that can handle various use cases (physical space, process, system) within one integrated environment, eliminating the need for multiple separate tools and their associated integration complexities

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The digital twin platform is designed with universal capabilities to create and manage different types of digital twins (building twins, process twins, system twins) using a common set of tools and methodologies, allowing one platform to serve multiple functions that previously required separate specialized tools

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Reliability

If digital twins are frequently redesigned to address changes in the real world counterpart, then the accuracy and relevance of digital twins is improved, but the time and resources required for maintenance deteriorates

Engineering Contradiction:

Improveaccuracy of digital twinsVSAvoidmaintenance time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The digital twin platform incorporates dynamic capabilities that allow it to automatically adapt and update in response to changes in the real world counterpart, rather than requiring manual redesign. The system can dynamically modify its representation, update parameters, and adjust its behavior to reflect current conditions without time-consuming redesign processes

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The platform implements feedback mechanisms that continuously monitor changes in the real world and automatically trigger updates to the digital twin, ensuring accuracy is maintained through ongoing information flow rather than periodic manual redesign

Inventive Principle:

Principle #23Feedback

3Ease of manufacture

If knowledge graphs are used to represent semantic relationships, then the structure and organization of data is improved, but the ability to infer implicit knowledge deteriorates

Engineering Contradiction:

Improvedata organizationVSAvoidimplicit knowledge

Core Design Contradiction:

Ease of manufactureVSLoss of information

Solution Approach 1:

The patent introduces probabilistic graphical models as an intermediary layer between the structured knowledge graph and the inference process. This intermediary enables the system to capture implicit relationships and uncertainties that are not explicitly represented in the knowledge graph, allowing for richer inference while maintaining the organizational benefits of graph structure

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system transforms the deterministic knowledge graph representation into a probabilistic representation by introducing probability parameters and distributions. This parameter change enables the system to represent uncertainty and infer implicit knowledge while maintaining the structured organization of the graph framework

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS12530605B2System for probabilistic reasoning and decision making on digital twins

Publication Date: 2026.01.20 ACCENTURE GLOBAL SOLUTIONS LTD

AI summary

Aspects of the present disclosure provide systems, methods, and computer-readable storage media that support ontology driven processes to create digital twins that extend the capabilities of knowledge graphs. A dataset including an ontology and domain data corresponding to a domain associated with the ontology is obtained. A knowledge graph is constructed based on the ontology and the domain data is incorporated into the knowledge graph. The knowledge graph is exploited to derive random variables of a probabilistic graph model. The random variables may be associated with probability distributions, which may include unknown parameters. A learning process is executed to learn the unknown parameters and obtain a joint distribution of the probabilistic graph model, which may enable querying of the probabilistic graph model in a probabilistic and deterministic manner.