Probabilistic Precedence Network for Dynamic Process Dependency Discovery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional process analysis software tools lack real-time end-to-end process dependency determination and monitoring, rely on static knowledge, and are inadequate for large-scale, complex processes, failing to account for dynamic variability and historic performance.
Innovation Solution
A computerized method and system that processes historic data to generate a probabilistic precedence network, identifying robust dependencies and root causes of process delays by filtering out less likely dependencies and presenting mission-critical task relationships, enabling efficient management of dynamic processes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional process analysis software tools use general purpose scheduling and CPM modeling, then static and well-defined process knowledge can be utilized, but real-time dynamic process dependency determination and monitoring capability is lacking
Solution Approach 1:
The system transitions from static CPM modeling to dynamic dependency discovery by continuously mining process event data to update the probabilistic precedence network in real-time, allowing the system to adapt to changing process conditions while maintaining manageable complexity through automated data-driven updates
Solution Approach 2:
The system automatically discovers process dependencies and updates the probabilistic precedence network by mining historical and real-time process data without requiring manual intervention, enabling self-updating process models that adapt to dynamic conditions
2Adaptability or versatility
If conventional tools take a knowledge-centric approach, then well-defined process knowledge can be utilized, but the capability to address large-scale complex processes with dynamic variability is reduced
Solution Approach 1:
The system replaces manual knowledge-centric process analysis with automated data mining and machine learning algorithms that discover process dependencies from event data, significantly improving analysis efficiency while maintaining high adaptability to dynamic large-scale processes
Solution Approach 2:
The system changes from fixed process models to probabilistic precedence networks with dynamically updated dependency probabilities, enabling the system to adapt to varying process conditions while maintaining computational efficiency through optimized data structures
3Measurement precision
If the system aggregates historic dependency graph into probabilistic precedence network, then robust dependencies can be identified, but computational complexity increases
Solution Approach 1:
The system pre-processes historical process data to build the probabilistic precedence network in advance, storing aggregated dependency probabilities that can be quickly queried and updated in real-time, reducing processing time for ongoing analysis while maintaining high measurement precision
Solution Approach 2:
The system focuses computational resources on mining and updating only the most significant dependency relationships in the probabilistic precedence network, rather than processing all possible task combinations, thereby reducing processing time while maintaining accurate measurement of critical dependencies
Data Source
AI summary
The embodiments described herein describe a computerized system and method for retrieving and processing data to provide dependency and root cause information for a process. The computerized system and method include receiving historic data of the process, detecting temporal dependency or precedence tasks in the process from the historic data, generating a historic dependency graph, aggregating the historic dependency graph into a probabilistic precedence network (PPN), pruning the PPN, and presenting results to a user.