Probability Process Model Deviation Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current solutions fail to accurately detect deviations between an event log and a process model, particularly in scenarios with temporal constraints and duplicated activities, leading to potential errors in verifying event sequences against predefined criteria.
Innovation Solution
A method is introduced that converts the process model into a probability process model with multiple nodes and associated probability distributions, allowing for the detection of differences between event sequences and the model using linear temporal logic, and updates the process model based on identified deviations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If current solutions are used to verify event sequences against process models, then basic conformance checking can be performed, but temporal constraints among phases cannot be checked and duplicated activities cannot be distinguished by phase
Solution Approach 1:
The process model is segmented into multiple hierarchical levels with phases as intermediate structures. Each phase contains specific activities, creating a tree-like hierarchy that allows distinction between duplicated activities (e.g., HbAlc testing) based on their phase context. This segmentation enables precise tracking of which phase each activity belongs to, resolving the ambiguity of duplicated activity names.
Solution Approach 2:
Phases are introduced as intermediary structures between the root process model and individual activities. These phases act as mediators that provide contextual information for verifying temporal constraints and distinguishing duplicated activities. The phase hierarchy serves as an intermediate layer that connects high-level process structure with specific activity instances.
2Reliability
If process models include temporal constraints among phases, then more comprehensive validation can be performed, but existing solutions fail to check whether event sequences satisfy these constraints
Solution Approach 1:
Temporal constraints among phases are pre-defined and encoded into the hierarchical process model structure before event log analysis. The model预先 establishes the expected sequence and timing relationships between phases, allowing automated verification against actual event sequences. This preliminary structuring enables systematic checking of whether observed events conform to the predefined temporal constraints.
3Adaptability or versatility
If duplicated activities exist in different phases, then more comprehensive process coverage is achieved, but error occurs when verifying event sequences because the phase context is lost
Solution Approach 1:
The process model采用嵌套结构，将活动嵌套在相位中，将相位嵌套在根过程中。这种嵌套关系使得每个活动都带有其所在的相位上下文信息。当遇到重复活动时，系统可以通过追溯活动的嵌套路径（即所属相位）来精确定位活动实例，从而区分同名活动。
Data Source
AI summary
A method for detecting deviations between an event log and a process model includes converting the process model into a probability process model, the probability process model comprising multiple nodes in multiple hierarchies and probability distribution associated with the multiple nodes, a leaf node among the multiple nodes corresponding to an activity in the process model; detecting differences between at least one event sequence contained in the event log and the probability process model according to a correspondence relationship; and identifying the differences as the deviations in response to the differences exceeding a predefined threshold; wherein the correspondence relationship describes a correspondence relationship between an event in one event sequence of the at least one event sequence and a leaf node in the probability process model.