Knowledge-Based AI System for Industrial Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Developing artificial intelligence (AI) solutions for industrial systems is time-consuming due to the lack of large-scale data and ineffective communication between data scientists and subject matter experts, often resulting in inaccurate and incomplete results.
Innovation Solution
A knowledge-based AI system that incorporates expert knowledge through a chatbot interacting with various tools, using a knowledge-first architecture that combines domain-specific models and machine learning models to provide accurate predictions, and utilizes ensemble models to aggregate outputs from both knowledge and ML models.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional machine learning models are used for industrial systems, then the system can make predictions, but the development time is excessive and requires large-scale data that is unavailable
Solution Approach 1:
The system segments the prediction task into two distinct components: a knowledge-based model that handles domain-specific reasoning using expert knowledge graphs, and a machine learning model that handles pattern recognition from available data. This segmentation allows each model to operate within its strengths, reducing overall development time while maintaining prediction accuracy.
Solution Approach 2:
The system performs preliminary action by pre-processing and structuring domain expert knowledge into knowledge graphs before the prediction task begins. This pre-organized knowledge base is readily available when predictions are needed, eliminating the time-consuming process of extracting and structuring expert knowledge during the prediction phase.
2Reliability
If traditional AI development approaches are used, then models can be trained, but effective communication between data scientists and subject matter experts is lacking, leading to incomplete results
Solution Approach 1:
The system introduces an intermediary layer consisting of knowledge engineers who act as mediators between data scientists and subject matter experts. These intermediaries translate domain expertise into structured knowledge graphs that both parties can understand and utilize, improving result completeness while reducing communication complexity.
3Productivity
If domain expert knowledge is incorporated into AI systems, then development time is reduced and accuracy is improved, but the system complexity increases
Solution Approach 1:
The system segments expert knowledge into modular knowledge graphs organized by domain-specific categories and relationships. This modular structure allows the system to incorporate only the necessary knowledge subsets for each prediction task, reducing overall system complexity while maintaining high development efficiency.
Solution Approach 2:
The system employs intermediary components including knowledge graph databases, natural language processing interfaces, and automated reasoning engines that mediate between raw expert knowledge and the prediction models. These intermediaries automate the integration process, reducing the perceived complexity for users while enabling efficient knowledge incorporation.
Data Source
AI summary
A system captures and utilizes expert knowledge in artificial intelligence. The system includes a knowledge capture module for extracting expert knowledge from subject matter experts in a conversational format and a knowledge management module for cataloging and summarizing the extracted knowledge. The system also includes a digital subject matter expert (dSME) module for ingesting the cataloged knowledge and using it to guide users in building AI models. A chatbot interacts with a user and selects the appropriate dSME module that is relevant to the user request. The system attempts to answer the user request based on the dSME module. If the dSME module lacks knowledge to solve the problem, the system uses a set of tools, for example, internet based search engine to solve the problem.