Digital Twin Schema Inference From Distributed Event Streams
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Creating digital twins for numerous physical objects or processes is time-consuming and difficult to scale due to the manual effort required and lack of automated methods for inferring these digital representations from event data.
Innovation Solution
A computer-implemented method involving the receipt of event data streams, computation of schemas, participation in distributed inference processes with other digital twins, and aggregation or definition of relationships between them, allowing for automated inference and management of digital twins without prior knowledge of the physical entities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If digital twins are manually created by operators or experts, then the accuracy and understanding of physical object behavior is improved, but the time consumption and difficulty of scaling increases
Solution Approach 1:
The system enables digital twins to automatically create their own representations by inferring schemas from event data streams they generate. Each digital twin serves itself by analyzing its own operational data to build an accurate model, eliminating the need for manual creation while maintaining high accuracy through self-observation of actual behavior patterns.
Solution Approach 2:
The patent replaces the manual mechanical process of expert operators creating digital twins with an automated computational system. Event data streams are automatically processed through schema inference algorithms that compute digital twin representations without human intervention, substituting manual labor with automated data-driven computation.
2Reliability
If digital twins are manually created for each physical object, then the understanding of physical object behavior is maintained, but the scalability to huge numbers of digital twins deteriorates
Solution Approach 1:
Each digital twin automatically infers its own schema from its event data stream, enabling self-creation without requiring external manual effort. This self-service mechanism allows unlimited scaling because each digital twin independently generates its representation, eliminating the bottleneck of manual creation that limits scalability.
Solution Approach 2:
The system divides the digital twin creation process into independent, autonomous units where each digital twin operates separately to infer its own schema from its own event data. This segmentation allows parallel processing of multiple digital twins simultaneously, enabling linear or near-linear scaling as more physical objects need digital representations.
3Productivity
If automated methods are used to infer digital twins from event data, then the scalability and efficiency are improved, but the complexity of the inference process increases
Solution Approach 1:
The schema inference process is designed to be self-contained within each digital twin, using only the event data stream that the digital twin itself generates. This self-service approach simplifies the overall system architecture by eliminating the need for centralized complex processing, as each digital twin independently performs inference using its own data, reducing system-wide complexity.
Solution Approach 2:
The system uses event data streams as direct copies of physical object behavior to infer schemas. By working with actual operational data rather than abstract models or simulations, the inference process becomes more straightforward and data-driven, reducing the need for complex theoretical modeling while maintaining high efficiency.
4Manufacturing precision
If manual creation methods are used, then the initial quality of digital twins is improved, but the loss of time and resources increases
Solution Approach 1:
Digital twins automatically generate high-quality representations by inferring schemas from their own event data streams. This self-service mechanism ensures that each digital twin is created with high precision based on actual operational data, while simultaneously eliminating the time and resource costs associated with manual expert creation.
Solution Approach 2:
The patent substitutes manual expert creation with automated schema inference that processes event data streams computationally. This replacement maintains or improves digital twin quality through data-driven accuracy while dramatically reducing the time and human resources required, as automated computation is faster and more scalable than manual analysis.
Data Source
AI summary
In various examples there is a computer-implemented method performed by a digital twin at a computing device in a communications network. The method comprises: receiving at least one stream of event data observed from the environment. Computing at least one schema from the stream of event data, the schema being a concise representation of the stream of event data. Participating in a distributed inference process by sending information about the schema or the received event stream to at least one other digital twin in the communications network and receiving information about schemas or received event streams from the other digital twin. Computing comparisons of the sent and received information. Aggregating the digital twin and the other digital twin, or defining a relationship between the digital twin and the other digital twin on the basis of the comparison.