AI-Assisted Industrial Software Generation from Process Mining

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The aging workforce in process automation and control engineering is leading to a knowledge and experience gap, resulting in prolonged durations and increased errors in designing software applications for industrial processes due to the complexity and variety of factors involved.

Innovation Solution

A method utilizing artificial intelligence (AI) models, particularly machine learning, to process mine previous generations of software applications, generating assistance data that aids users in creating new applications by preserving the knowledge and experience of retiring engineers.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual input from experienced engineers is used to generate software applications, then the quality and accuracy of the software design is improved, but the design time and effort increase significantly

Engineering Contradiction:
Improvesoftware design qualityVSAvoiddesign time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary action by capturing and storing generation data from experienced engineers during their software design process. This data is mined and stored in advance, creating a knowledge base that can be automatically applied to future software generation tasks, eliminating the need to repeatedly perform the same complex manual design work.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system uses copying by creating artificial intelligence models that replicate the knowledge and experience of retired engineers. These models copy the patterns, rules, and best practices embedded in the generation data, enabling the system to generate software applications with the same quality as experienced engineers without requiring their direct involvement.

Inventive Principle:
Principle #26Copying

2Loss of information

If the aging workforce retires, then the loss of knowledge and experience is reduced in the long term, but the immediate capability to design software applications deteriorates

Engineering Contradiction:
Improveknowledge preservationVSAvoidsoftware generation capability
Core Design Contradiction:
Loss of informationVSProductivity

Solution Approach 1:

The system performs preliminary action by capturing generation data from experienced engineers before they retire. This advance data collection and mining process preserves their knowledge and experience in a structured format that can be automatically applied to future software generation tasks, preventing knowledge loss.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system introduces an intermediary layer between the retired engineers' knowledge and future software generation needs. Artificial intelligence models serve as mediators that translate and apply the captured generation data to new software projects, bridging the gap between retired expertise and current design requirements.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Ease of operation

If process mining with AI models is used to generate assistance data, then the need for manual engineer input is reduced, but the complexity of the generation system increases

Engineering Contradiction:
Improveuser effort in software generationVSAvoidgeneration system complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The system implements self-service by enabling automatic software generation through AI models that process generation data and produce software applications independently. The system serves itself by capturing its own operational data and using that data to automate future tasks, reducing the need for manual intervention while managing complexity through self-learning mechanisms.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP4679266A1Method for assisting a user in computer-aided generation of at least a part of a software application for an industrial process
Publication Date: 2026.01.14 ABB (SCHWEIZ) AG
  • EP4679266A1 patent drawingFigure 1~2
  • EP4679266A1 patent drawingFigure 3~4
  • EP4679266A1 patent drawing

AI summary

The disclosure relates to a method (100) for assisting a user in computer-aided generation of at least a part (11) of a software application (10) for an industrial process, the method (100) comprising: - obtaining assistance data (4) for assisting the user in the computer-aided generation of the at least part (11) of the software application (10), wherein the assistance data (4) is based on process mining of computer-aided generation data (1), the computer-aided generation data (1) relating to previous computer-aided generations of at least parts (11) of software applications (10) for other industrial processes by one or more users, the process mining being at least supported by an artificial intelligence, AI, model (3); and - providing the assistance data (4) for assisting the user in computer-aided generation of the at least part (11) of the software application (10) by the user.