Knowledge Graph State Prediction for Road Users
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems lack an effective method to determine the state and behavior of technical systems, such as infrastructure elements and road users, to enable real-time control and prediction of interactions within complex environments.
Innovation Solution
A computer-implemented method using a knowledge graph representation, where nodes represent objects like infrastructure elements and road users, and edges represent relationships, allowing for the prediction of behavior based on training data and environment information to control the technical system.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If current systems are used to determine state and behavior of technical systems, then existing infrastructure can be monitored, but accurate prediction and control of interactions in complex environments cannot be achieved
Solution Approach 1:
The system segments complex environmental interactions into discrete objects (infrastructure elements, road users, environment information) and their relationships, representing them as separate nodes and edges in a knowledge graph. This segmentation enables manageable processing of complex interactions while maintaining prediction accuracy.
Solution Approach 2:
The patent transitions from traditional state monitoring to a multi-dimensional knowledge representation space where objects and their relationships are encoded as vectors. This dimensional transformation enables the system to capture complex interactions and predict behaviors that cannot be achieved with conventional monitoring approaches.
2Measurement precision
If detailed information about objects and relationships is stored, then prediction accuracy improves, but data storage and processing requirements increase
Solution Approach 1:
The system transforms detailed object and relationship information into parameterized vector representations with fixed dimensions. This parameterization allows the system to maintain high measurement precision for state determination while controlling data volume through standardized vector formats and dimensionality reduction techniques.
Solution Approach 2:
Instead of storing raw detailed information about all objects and relationships, the system creates compressed vector copies that capture essential characteristics. These vector representations preserve the necessary information for accurate prediction while significantly reducing storage requirements compared to storing complete detailed data.
3Speed
If real-time control of technical systems is implemented, then system responsiveness improves, but computational requirements and processing time increase
Solution Approach 1:
The system performs preliminary actions by pre-processing environmental information and maintaining updated knowledge graphs of objects and relationships. This preliminary structuring of data enables faster real-time inference and control decisions, reducing the computational energy required during actual control operations.
Solution Approach 2:
The patent replaces traditional mechanical control systems with information-based control using knowledge graphs and predictive modeling. This substitution enables more efficient real-time control by using computational inference based on pre-processed knowledge rather than reactive mechanical responses, improving responsiveness while managing computational energy requirements.
Data Source
AI summary
Device and computer-implemented method for determining a state of a technical system, in particular of an infrastructure element or of a road user. A first node represents a first object, in particular the technical system, a second node represents a second object, in particular a further infrastructure element or a further road user. An edge between the first node and the second node represents a relationship between the objects. A prediction is determined which characterizes a behavior of one of the objects. The determination is in accordance with information about the objects and in accordance with a representation of a knowledge graph which includes the first node, the second node, and the edge. The state is determined in accordance with the prediction.