Inference Device Knowledge Graph Update via User Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing inference devices using knowledge graphs struggle to produce desirable inference results due to reliance on node selection and graph structure, often leading to suboptimal outputs.
Innovation Solution
An inference device that acquires input information, executes inference based on a knowledge graph, and updates the graph based on user feedback to refine node associations and improve inference accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If inference is made based on fixed node selection and knowledge graph structure, then the inference process is simple and fast, but the inference result accuracy deteriorates
Solution Approach 1:
The patent applies dynamics by making the knowledge graph structure adaptable and changeable based on user feedback. The system dynamically updates the knowledge graph by adding new nodes and edges when inference results are evaluated as inappropriate, transforming the static graph into a dynamic learning system that improves accuracy over time without requiring complex manual reconfiguration
Solution Approach 2:
The patent implements feedback by introducing an evaluation mechanism where user responses to inference results are captured and used to update the knowledge graph. When users indicate that an inference result is inappropriate, the system uses this feedback to add corrective nodes and edges, creating a closed-loop system that continuously improves inference accuracy based on actual performance
2Adaptability or versatility
If the knowledge graph structure is fixed, then the system is simple to maintain, but the adaptability to user needs deteriorates
Solution Approach 1:
The patent applies self-service by enabling the knowledge graph to automatically update itself based on user feedback without requiring manual intervention. The system autonomously adds nodes and edges when inference results are evaluated as inappropriate, allowing the graph to adapt to user needs while maintaining simplicity in the overall system architecture
Data Source
AI summary
An inference device includes a first acquisition unit that acquires first input information, a storage unit that stores a knowledge graph, an inference execution unit that executes the inference based on the knowledge graph, an output unit that outputs information, a second acquisition unit that acquires second input information indicating a user's intention in regard to the result of the inference and including a first word, and a control unit that judges whether the result of the inference is appropriate or not based on the information based on the result of the inference and the second input information, and when the result of the inference is inappropriate, determines a node of the first word among the plurality of nodes, adds an AND node to the knowledge graph, and associates an inference start node and the node of the first word with each other via the AND node.