Semantically-Enriched Diagnosis Model Automation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current diagnostic methods lack the ability to automatically and efficiently derive semantically enriched diagnosis models from data points, which limits their effectiveness in identifying potential causes of system abnormalities in real-time or historical contexts.
Innovation Solution
A computing system that retrieves data points from sensors or databases, semantically annotates them, creates variables representing physical conditions, identifies relationships, and parameterizes a diagnosis model using statistical or data mining techniques to map potential causes to system abnormalities, enabling automatic detection of causes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated derivation of diagnosis models is implemented, then diagnostic efficiency is improved, but system complexity increases
Solution Approach 1:
The diagnosis model creation process is segmented into distinct modules: data retrieval from sensors/databases, semantic annotation, variable creation, relationship identification, and parameterization. Each module handles a specific aspect of the complex process, making the overall system more manageable and maintainable while achieving automated diagnostic model generation.
Solution Approach 2:
Semantic annotations serve as an intermediary layer between raw data points and the diagnosis model. The system introduces semantic concepts that bridge the gap between sensor data and diagnostic rules, enabling automated model creation without requiring complex direct mappings between all data elements and diagnostic outcomes.
2Measurement precision
If semantic enrichment is applied to diagnosis models, then diagnostic accuracy is improved, but data processing time increases
Solution Approach 1:
The system performs semantic annotation and enrichment activities in advance during the model creation phase, rather than in real-time during diagnosis execution. Historical data is pre-processed and semantically enriched to build the diagnosis model beforehand, allowing rapid querying during actual diagnostic operations without sacrificing accuracy.
Solution Approach 2:
The system transforms raw sensor data into semantically enriched variables with defined relationships and parameters. By changing the representation format from raw data points to structured semantic variables with predefined relationships, the system achieves both high diagnostic accuracy and efficient processing during model execution.
3Reliability
If statistical and data mining techniques are used for parameterization, then model reliability is improved, but computational resources required increase
Solution Approach 1:
The system applies statistical and data mining techniques selectively to the most critical parameters and relationships in the diagnosis model, rather than uniformly processing all data. This partial application of complex techniques focuses computational resources on high-impact areas, achieving model reliability where it matters most while conserving overall computational resources.
Data Source
AI summary
A system, method and a computer program product may be provided for automatically creating and parameterizing a semantically-enriched diagnosis model for an entity. The system receives a list of data points, from sensors or a database, to be used to create a diagnosis model. The system automatically creates the diagnosis model based on the received list of data points and data stored in a database and parameterizes the diagnosis model. The parameterized diagnosis model reflects rules that determine one or more potential causes of one or more abnormalities of one or more physical conditions in the entity.