LLM Activity Mapping for Accurate Process Mining
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current process mining technologies rely on manual activity mapping, which is time-consuming and requires expertise, and similarity measures that focus on activity labels rather than their actual meaning.
Innovation Solution
The use of large language models to determine mappings between activities extracted from a process model and those executed during process instances, based on textual descriptions and instructions provided as prompts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual activity mapping is performed, then mapping accuracy can be maintained through expert knowledge, but time consumption and operational complexity increase significantly
Solution Approach 1:
The patent introduces an automated mapping system that acts as an intermediary between process models and event logs. This system uses machine learning algorithms to automatically match activities without requiring manual expert intervention, thereby resolving the contradiction by maintaining accuracy through algorithmic methods while eliminating time consumption associated with manual mapping.
Solution Approach 2:
The patent replaces the mechanical manual process of expert-driven activity mapping with an automated computational system. By substituting human experts with an automated mapping algorithm, the system maintains mapping quality through systematic analysis while eliminating the time and operational complexity associated with manual expert work.
2Extent of automation
If similarity measures based on activity labels are used, then mapping can be automated, but the actual meaning and context of activities are not considered
Solution Approach 1:
The patent changes the parameters used for mapping from simple activity labels to more comprehensive features that capture the actual meaning and context of activities. By transforming the input parameters from basic labels to enriched representations that include contextual information, the system achieves both automation and improved mapping accuracy.
3Measurement precision
If manual activity mapping is performed, then expertise and knowledge can ensure accurate mappings, but ease of operation deteriorates due to high skill requirements
Solution Approach 1:
The patent implements a self-service automated mapping system that performs activity mapping without requiring external expert intervention. The system independently analyzes process models and event logs, automatically generating accurate mappings through algorithmic methods, thereby eliminating the need for specialized knowledge while maintaining mapping quality.
Data Source
AI summary
Systems and methods for determining a mapping between activities are provided. One or more prompts defining 1) instructions and 2) activities executed during one or more instances of execution of a process are received. A mapping between one or more activities extracted from a process model of the process and one or more of the activities executed during the one or more instances of execution is determined using a large language model based on the instructions. The mapping is output.