Dynamic Question Answer Framework for Process Mining

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Traditional process mining tools require technical skills to analyze data, limiting their adoption and slowing down data-driven decision-making in organizations due to the complexity and cognitive challenges they pose for users without such skills.

Innovation Solution

A computer-implemented method enabling coding-free analysis of recorded process data through a user interface that allows users to select verbal approaches, which are executed as commands to generate analysis results, with recommended follow-up approaches and visualization, reducing the need for technical expertise.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If traditional process mining tools are used, then analysis capability is provided, but technical skills are required which limits user adoption

Engineering Contradiction:
Improveease of useVSAvoidcomplexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The patent introduces an intermediary layer between the user and the complex process mining engine. This intermediary translates natural language questions into execution commands that the mining engine can process, shielding users from technical complexity while maintaining full analysis capability. The system acts as a mediator that converts simple verbal queries into sophisticated data mining operations.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the mechanical system of manual data preparation and technical analysis with an automated natural language processing system. Instead of requiring users to manually configure tools, prepare data, and execute complex queries, the system substitutes these mechanical operations with automated language-based interactions that trigger the same analytical processes.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If traditional process mining tools are used, then data analysis is performed, but time is lost due to training requirements

Engineering Contradiction:
Improvedecision-making speedVSAvoidtraining time
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The patent enables business users to perform process mining analysis independently without requiring external technical support or training. The system provides self-service capabilities where users can directly formulate questions in natural language and receive analysis results, eliminating the need for data engineers or analysts to mediate the process and removing training requirements entirely.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system performs preliminary actions by pre-configuring the analysis framework, data structures, and execution commands in advance. This preparation work is done beforehand so that when users submit questions, the system can immediately execute pre-prepared analysis routines without requiring users to spend time on data preparation or tool configuration.

Inventive Principle:
Principle #10Preliminary action

3Loss of information

If traditional process mining tools are used, then analysis results are generated, but cognitive challenge remains high for untrained users

Engineering Contradiction:
Improveinsight extractionVSAvoidcognitive challenge
Core Design Contradiction:
Loss of informationVSDifficulty of detecting and measuring

Solution Approach 1:

The patent changes the parameter of interaction from complex technical parameters to simple natural language parameters. Instead of requiring users to understand data structures, query languages, and analysis methodologies, the system accepts questions in everyday language and automatically translates them into the appropriate technical parameters for execution, dramatically reducing cognitive challenge while maintaining full insight extraction capability.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP4361848A1Dynamic question and answer framework
Publication Date: 2024.05.01 CELONIS SE
  • EP4361848A1 patent drawingFigure 1
  • EP4361848A1 patent drawingFigure 2a~2f
  • EP4361848A1 patent drawingFigure 3

AI summary

The present invention relates to a computer-implemented method enabling a coding-free analysis of process data. Accordingly, a dynamic question and answer framework is provided according to which a user may select specific process mining questions and automatically receive related answers based on the attached data model. The answers are generated by querying the data model using query statements that are associated to the selected process mining question.