Knowledge Graph Problem-Solving Method for Automated Issue Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Entities such as users or companies may not be aware of issues or their causes, leading to sub-optimal device performance or abandoned transactions, as existing systems lack effective problem-solving mechanisms.
Innovation Solution
A computer-implemented method using knowledge graphs to retrieve rules based on trigger data, query the graph for problem data, and derive solution data to address the identified issues, involving actions like troubleshooting or recommending solutions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a knowledge graph-based problem-solving mechanism is implemented, then problem detection capability and solution effectiveness are improved, but system complexity increases
Solution Approach 1:
The patent introduces a knowledge graph as an intermediary structure that mediates between trigger data and problem detection. The knowledge graph stores predefined relationships between concepts, triggers, and problems, allowing the system to query and infer problems without complex direct analysis logic. This intermediary layer simplifies the overall system architecture while enhancing problem detection capability through structured knowledge representation.
Solution Approach 2:
The system performs preliminary action by pre-populating the knowledge graph with structured relationships between concepts, triggers, and problems before actual problem detection occurs. This advance preparation of knowledge structures enables rapid problem identification when triggers occur, eliminating the need for complex real-time analysis and reducing system complexity during operation.
2Productivity
If automated problem-solving is implemented, then productivity is improved, but ease of operation deteriorates
Solution Approach 1:
The system implements self-service by automatically querying the knowledge graph and generating problem diagnoses and solutions without requiring user intervention. When trigger data is received, the system autonomously performs queries, retrieves relevant problems and solutions, and presents results to the user, thereby maintaining high productivity while keeping the user interface simple and easy to operate.
Solution Approach 2:
The system incorporates feedback mechanisms where the results of knowledge graph queries are fed back to users in an easily digestible format. This feedback loop provides users with clear problem diagnoses and suggested solutions, maintaining ease of operation while achieving automated problem-solving efficiency. The feedback is presented in a user-friendly manner that does not require users to understand the underlying complex query processes.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Summarizing the invention, a computer-implemented method is provided. The computer-implemented method comprises: receiving trigger data comprising at least one trigger concept; retrieving at least one rule based on the trigger data, wherein a rule comprises: a main label relating two concept variables and a concatenated set of defining labels, each defining label relating two concept variables; obtaining problem data by querying a knowledge graph using the at least one rule and the at least one trigger concept, wherein the knowledge graph comprises a plurality of nodes and a plurality of edges, each node being associated with a respective concept and each edge being associated with a respective label, and wherein at least one node is associated with the at least one trigger concept; obtaining solution data based on the problem data; performing an action based on the solution data.