Maintenance Service Recommendation Using Probability Graph and Knowledge Graph
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Maintenance engineers spend a significant amount of time manually diagnosing the causes of damage in electronic products, which is inefficient and time-consuming.
Innovation Solution
A maintenance service recommendation method utilizing a trained probability graph model and a knowledge graph to infer and provide explainable prediction results, enabling the identification of probable causes of machine damage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If manual diagnosis by maintenance engineers is used, then the ability to identify cause of damage is maintained, but the time required for diagnosis is excessive
Solution Approach 1:
The patent replaces the manual mechanical diagnosis process with an AI-based automated system. The probability graph model and knowledge graph work together to automatically analyze machine data, identify failure causes, and generate repair recommendations, eliminating the need for engineers to manually check numerous components and significantly reducing diagnosis time.
Solution Approach 2:
The patent introduces an intermediary AI system between the machine and the maintenance engineer. The probability graph model processes machine data and generates predictions, while the knowledge graph provides contextual information and causal relationships. This intermediary layer automates the analysis process and presents only relevant information to engineers, reducing their workload and diagnosis time.
2Productivity
If AI algorithms are used to estimate damage causes, then diagnosis time is reduced, but the complexity of the system increases
Solution Approach 1:
The patent segments the AI system into two distinct but complementary components: the probability graph model for pattern recognition and prediction, and the knowledge graph for storing domain knowledge and causal relationships. This segmentation allows each component to specialize in specific tasks, making the overall system more manageable and easier to implement while maintaining high productivity.
Solution Approach 2:
The patent performs preliminary actions by pre-training the probability graph model and pre-populating the knowledge graph with domain knowledge before actual maintenance operations. This preparation phase allows the system to quickly analyze new machine data without requiring complex real-time computations, reducing operational complexity while maintaining high efficiency.
3Measurement precision
If detailed analysis of all variables is performed, then the accuracy of damage cause identification is improved, but the time required for analysis increases
Solution Approach 1:
The patent applies local quality by focusing the analysis on specific variables and relationships that are most relevant to the current machine state and failure mode. The probability graph model identifies and prioritizes the most significant causal factors based on learned patterns, while the knowledge graph provides detailed information only for those selected variables. This selective deep analysis maintains high accuracy while significantly reducing the time required compared to examining all variables exhaustively.
Data Source
AI summary
A maintenance service recommendation method and electronic apparatus thereof are provided. Relevant data of a faulty machine is input into a probability graph model through an interactive interface, and a recommended factor is obtained. A search is performed in the knowledge graph to pick up multiple selected categories related to the recommended factor among multiple variable categories. Based on the importance of each selected category, a hierarchical structure diagram is established and displayed on the interactive interface.