Engineering Program Ontology Generation and Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional engineering systems lack automated methods for generating engineering programs with specific specifications for technical installations, leading to inefficiencies in code development, error detection, and optimization, resulting in significant labor and time wastage due to manual coding and lack of automated assistance.
Innovation Solution
A method and system utilizing natural language processing and machine learning algorithms to analyze existing engineering programs, generate ontology schemas, and convert sequential representations to optimize engineering programs, automatically modifying code statements to ensure compatibility and efficiency with technical installations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual coding is used to generate engineering programs, then code compatibility with engineering objects can be ensured, but code development time and labor are significantly increased
Solution Approach 1:
The system performs preliminary analysis of the source engineering program to extract data flow and control flow relationships before code generation. This advance preparation enables automated generation of compatible code for target engineering objects without manual intervention, resolving the contradiction between automation and compatibility assurance.
Solution Approach 2:
The system uses trained machine learning models that have learned from pairs of source and target engineering programs to provide feedback-based code generation. The models predict appropriate code transformations based on extracted program characteristics, ensuring compatibility while automating the generation process.
2Productivity
If automated code generation is implemented, then code development efficiency is improved, but the ability to ensure code compatibility with engineering objects is reduced
Solution Approach 1:
The system extracts and analyzes data flow and control flow relationships from the source program before generation, preparing compatibility information in advance. This preliminary analysis enables the automated system to generate compatible code without sacrificing reliability.
Solution Approach 2:
Trained machine learning models provide intelligent feedback during code generation, using learned patterns from source-target program pairs to ensure the generated code maintains compatibility with the target engineering object while achieving automation.
3Manufacturing precision
If manual code optimization is performed, then code quality can be improved, but time and labor consumption are significantly increased
Solution Approach 1:
The system performs self-service optimization by automatically analyzing the generated code and applying optimizations based on extracted data flow and control flow relationships. This eliminates the need for manual code review and optimization, achieving both high quality and time efficiency.
Solution Approach 2:
The system replaces manual mechanical code optimization with automated machine learning-based optimization. The trained models automatically identify and apply optimization opportunities, substituting human effort with intelligent automation while maintaining or improving code quality.
4Measurement precision
If error detection is performed manually, then accuracy in identifying errors can be ensured, but the time required for error detection is significantly increased
Solution Approach 1:
The system replaces manual error detection with automated machine learning-based detection. The trained models analyze code patterns and relationships to identify errors automatically, maintaining accuracy while eliminating time-consuming manual review.
Solution Approach 2:
The system performs self-service error detection by automatically analyzing generated code for errors using extracted program relationships and trained models, eliminating the need for manual verification while maintaining detection accuracy.
Data Source
AI summary
A method and system for generating and optimizing an engineering program with a given specification from another engineering program is provided. The method includes receiving, by a processing unit, a request to generate a first engineering program, with a first specification, from a second engineering program, with a second specification. The method further includes generating, by the processing unit, a first ontology schema comprising information associated with a plurality of data flow and control flow interrelationships between a plurality of code statements in the second engineering program. The further includes generating, by the processing unit, a second ontology schema based on an application of a machine learning algorithm on the first sequential representation of the first ontology schema. The method includes generating, by the processing unit, the first engineering program from the second engineering program, based on an analysis of the second ontology schema.