Expert System for Engineering Knowledge Retrieval
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Engineering personnel in manufacturing and industrial environments face challenges in accessing consistent and timely knowledge, as experienced colleagues may not be available 24/7, and written manuals are slow to update with new information, leading to inefficient problem-solving.
Innovation Solution
An expert system with kiosks that allows users to enter queries in natural language, parsing keywords to search a database for solutions, and includes a feedback mechanism to update the database with user feedback, enabling consistent and timely access to knowledge.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If engineers consult with experienced colleagues for information, then the quality of information is high, but the availability is limited to working hours
Solution Approach 1:
The patent creates a digital copy of expert knowledge stored in a database, allowing engineers to access information 24/7 without needing the actual experts to be physically present. The system copies the knowledge and experience of available experts into a searchable database that can be accessed at any time.
Solution Approach 2:
The patent introduces an intermediary system (the expert system database and search interface) that mediates between the engineer and the expert knowledge. This intermediary allows queries to be submitted and answered automatically, bridging the gap between when engineers need information and when experts are available.
2Reliability
If written manuals are used for information storage, then the information is consistent, but the update speed is slow
Solution Approach 1:
The patent transforms the static manual system into a dynamic digital database that can be updated in real-time. When new information becomes available, the database can be updated immediately and automatically, allowing the system to adapt to changing conditions without requiring manual rewriting of documentation.
Solution Approach 2:
The patent incorporates feedback mechanisms where engineers can submit corrections or updates to the knowledge base, and the system can learn from actual problem resolutions to improve future answers. This feedback loop ensures the information remains current and accurate while maintaining consistency.
3Reliability
If engineers search for information manually, then they can access detailed information, but the time required is excessive
Solution Approach 1:
The patent replaces the mechanical manual search process with an automated computer-based search system. Engineers can submit queries in natural language, and the system automatically searches the database, processes the information, and provides answers, eliminating the need for manual browsing through documentation.
Solution Approach 2:
The patent changes the parameters of information retrieval by transforming it from a manual, sequential process to an automated, parallel processing approach. The system can search through large amounts of data simultaneously and return relevant information instantly, changing the time complexity of the search operation.
Data Source
AI summary
An expert system aids engineering personnel working in a manufacturing or other industrial environment by answering questions relating to machines, processes, systems or other elements of the environment. Users can interact with the system using kiosks in the relevant areas of the plant to enter queries and receive answers. A user can enter a query in a natural language format, which the system parses for keywords or keyterms. The system can use a backward chaining method to reach a solution, based upon the user's answer to further questions that the system asks the user.