Engineering Ontology Model for Semiconductor Knowledge Reuse
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In semiconductor manufacturing, the lack of systematic documentation and reuse of engineering analysis procedures leads to loss of expert knowledge, longer learning curves for new engineers, and repeated experiments due to inadequate sharing of knowledge and data, resulting in wasted resources and time.
Innovation Solution
A system and method utilizing an engineering ontology model to collect, store, and reuse engineering knowledge, including an objective and tool mapping capability, an analysis plan generator, and a graphic symptom capturer to auto-capture fault symptoms from engineering data analysis tools, facilitating systematic storage and sharing of analysis processes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If engineering analysis procedures are not systematically documented, then engineers can work independently without documentation overhead, but expert knowledge is lost over time and new engineers have longer learning curves
Solution Approach 1:
The patent creates a digital copy of expert engineering knowledge by capturing analysis plans, procedures, and decisions in a structured ontology format. This allows knowledge to be replicated and reused across different engineers and projects, eliminating the need for repeated learning while maintaining accessibility without excessive complexity
Solution Approach 2:
The system performs preliminary documentation of engineering analysis procedures as they are executed, automatically capturing and storing knowledge before it can be lost. This proactive approach ensures knowledge is preserved in advance, reducing future learning time without requiring engineers to manually document afterward
2Productivity
If engineering analysis procedures are systematically documented and stored, then knowledge can be shared and reused, but the system requires complex infrastructure for collection, storage, and retrieval
Solution Approach 1:
The patent implements a universal ontology model that can represent multiple types of engineering knowledge (analysis plans, procedures, decisions, data) within a single unified framework. This multi-functional approach allows diverse knowledge to be stored and retrieved through one system, improving productivity while avoiding the need for separate complex systems for each knowledge type
Solution Approach 2:
The ontology model acts as an intermediary layer between raw engineering data and the knowledge management system. It structures and standardizes knowledge in a way that is both machine-processable and human-readable, simplifying the interface between storage and retrieval operations while enabling efficient knowledge reuse
3Loss of energy
If experiments are repeated due to inadequate knowledge sharing, then resource utilization decreases and time is wasted, but implementing comprehensive knowledge sharing systems increases system complexity
Solution Approach 1:
The system implements feedback mechanisms that automatically capture experiment results, analysis outcomes, and decisions back into the ontology repository. This closed-loop feedback ensures that knowledge from each experiment is immediately available for future queries, preventing repeated experiments and reducing resource waste without requiring complex manual knowledge transfer processes
Solution Approach 2:
The system creates reusable templates and patterns from past experiments that can be copied and adapted for similar future analyses. This allows successful experiment designs and solutions to be replicated without re-inventing them, reducing resource consumption while maintaining a manageable knowledge repository through pattern-based reuse
Data Source
AI summary
An engineering analysis tool comprises a unified resource model-based (URM) objective and tool mapping capability for linking engineering analysis objectives to analysis tools. A Markov chain-based analysis plan generator (APTG) for reusing engineering analysis plans may be included in the engineering analysis tool. Further, the engineering analysis tool comprises a graphic symptom capturer (GSC) that auto-captures engineering perceived fault symptoms from engineering data analysis (EDA) tools.