Workflow Graph Symbolic Execution for Control-Flow Error Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for analyzing control-flow in business process models are inefficient in detecting control- and data-flow errors, particularly due to exponential time complexity and lack of diagnostic information, especially when dealing with acyclic workflow graphs containing AND-, XOR-, and IOR-types of nodes.
Innovation Solution
A computer-implemented method that represents a business process as an acyclic workflow graph and performs symbolic execution by labeling edges with unique identifiers, allowing for deadlock detection and characterization, while reducing computational resources by propagating labels based on node types and ensuring equivalence of incoming edges at AND-join nodes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If state space exploration is used to detect control-flow errors, then diagnostic information is provided, but the time complexity becomes exponential
Solution Approach 1:
The patent segments the workflow graph into smaller components and processes them independently using a region-based approach. By dividing the graph into regions and analyzing each region separately, the method avoids the exponential complexity of exploring the entire state space while still providing diagnostic information about control-flow errors.
Solution Approach 2:
The patent performs preliminary actions by pre-computing reachability information and control-flow relationships before the actual error detection. This includes computing the transitive closure of the workflow graph and pre-identifying potential error locations, which reduces the computational burden during the actual analysis phase.
2Measurement precision
If explicit execution of workflow graph is used to compute control-flow relations, then complete analysis is achieved, but the algorithm becomes exponential in worst case
Solution Approach 1:
The patent replaces the mechanical explicit execution approach with a mathematical computation approach. Instead of explicitly executing all possible paths through the workflow graph, the method uses matrix operations and transitive closure computations to determine control-flow relationships, achieving polynomial time complexity while maintaining analysis completeness.
Solution Approach 2:
The patent changes the parameters of the analysis by working with the structure of the workflow graph itself rather than its execution states. By analyzing the graph's topology, node types, and edge relationships directly, the method achieves complete control-flow analysis without enumerating exponential numbers of execution states.
3Productivity
If rank theorem technique is used to decide soundness, then polynomial time is achieved, but diagnostic information is not provided
Solution Approach 1:
The patent incorporates feedback mechanisms that allow the algorithm to generate diagnostic information during the polynomial-time analysis. By tracking which regions and edges contribute to control-flow violations, the method provides detailed diagnostic information about the nature and location of errors while maintaining computational efficiency.
Solution Approach 2:
The patent introduces intermediary structures such as region annotations and control-flow labels that serve as mediators between the efficient polynomial-time analysis and the diagnostic information requirement. These intermediaries carry additional information about error locations and types without significantly increasing computational complexity.
4Productivity
If reduction techniques are applied to industrial processes, then exponential complexity is reduced, but structural complexity of the method increases
Solution Approach 1:
The patent creates a universal region-based analysis framework that handles multiple types of workflow graph structures and error conditions through a single unified approach. This multi-functional method can analyze various process types (industrial, service, business processes) and detect different error kinds (deadlocks, synchronization errors, control-flow violations) using the same core algorithm, reducing overall method complexity.
Data Source
AI summary
A new technique to analyze the control-flow, i.e., the workflow graph of a business process model, which is called symbolic execution, is provided. Acyclic workflow graphs that may contain inclusive OR-gateways are considered; a symbolic execution for them is defined, which runs in quadratic time. In particular, this symbolic execution essentially comprises labeling edges of nodes of the graph such that a label assigned to a first edge comprises a set of one or more edge identifiers, each identifying a second edge that is an outgoing edge of an XOR-split or an IOR-split node in the graph, whereby executing the second edge ensures that the first edge will be executed. Such a scheme may permit a decision for any pair of control-flow edges or tasks of the workflow graph whether they are sometimes, never, or always reached concurrently. This has different applications in finding control- and data-flow errors.