Time-Series Network Path Prescriber for Causal Node Simulation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data structures struggle to accurately capture and identify significant causal relationships between nodes in time series data, leading to stale or outdated information due to the complexity of analyzing thousands of nodes and changing relationships over time.
Innovation Solution
A method is introduced that simplifies the model by removing non-significant relationships, using partial delay equations, and simulating scenarios to identify driver nodes that can move time series data within a threshold distance of a target value, generating action pathways to execute and update the system dynamically.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the model includes all relationships between nodes in the time-series network, then the accuracy of identifying causal relationships is improved, but the computational complexity increases significantly
Solution Approach 1:
The patent extracts only the significant causal relationships from the complete network by calculating influence scores and filtering relationships based on thresholds. This extracts the essential information while removing computationally expensive redundant relationships, resolving the contradiction between completeness and complexity.
Solution Approach 2:
The patent segments the complex network analysis into distinct phases: initial influence calculation, significance filtering, and dynamic updates. By dividing the problem into manageable segments processed at different frequencies, it reduces overall computational complexity while maintaining accuracy.
2Loss of information
If the model is updated frequently to capture changing relationships, then the relevance of information is improved, but the computational resources required increase
Solution Approach 1:
The patent implements periodic updates where the complete influence calculation is performed only when necessary (e.g., when significant changes are detected), while less frequent or incremental updates are used otherwise. This periodic action maintains information relevance while significantly reducing computational resource consumption compared to continuous updates.
Solution Approach 2:
The patent makes the update frequency dynamic based on system conditions - updating more frequently when changes are detected and less frequently when the system is stable. This dynamic approach optimizes the balance between information relevance and computational resource usage.
3Reliability
If all nodes and relationships are analyzed in detail, then the completeness of the model is improved, but the time required for analysis increases
Solution Approach 1:
The patent performs partial analysis by focusing computational effort only on nodes and relationships that meet significance thresholds. Instead of analyzing all relationships equally, it applies excessive action only where needed (high-influence relationships) and minimal or no action elsewhere, reducing analysis time while maintaining model completeness for critical elements.
Data Source
AI summary
A method of creating and executing action pathways for time series data may include accessing a model of a system, where the system is represented by a hierarchy of nodes in a data structure representing time series of data. The method may also include simplifying the model by removing relationships between the nodes that affect parent nodes less than a threshold amount, and simulating the model to identify a node comprising a time series of data that risks missing a predefined target value. The method may further include generating a pathway of actions for changes to driver nodes that cause the time series of data to move within a threshold distance of the predefined target value in the future, and causing the pathway of actions to be executed.