Graph-Based Content Analysis With Attribute Icons for Decision Support
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing techniques for presenting content based on the shortest path in graph data require complex operations for specifying detailed information, complicating the user's understanding of the basis for content presentation.
Innovation Solution
An information processing device that trains a learning model using graph data and relationship data to identify optimized contents for a user's keyword input, generating display information with icons representing node attributes to intuitively show the basis of content presentation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If detailed information of nodes in graph data is presented to users, then information completeness is improved, but operation complexity increases requiring users to specify individual contents
Solution Approach 1:
The patent extracts and highlights only the essential attribute information of nodes along the shortest path, rather than presenting all detailed node information. This extraction approach provides sufficient basis information for users to understand the recommendation rationale without requiring them to manually specify or examine each node's complete details, thus resolving the contradiction between information completeness and ease of operation
Solution Approach 2:
The patent segments the graph data into the shortest path components and further segments the node information into essential attributes only. By dividing the complex graph structure into manageable path segments and extracting key attributes from each node, the system presents information in a structured, easy-to-understand format that maintains completeness while reducing operational complexity
2Measurement precision
If the basis of content presentation is made detailed, then recommendation accuracy is improved, but understanding difficulty increases for users
Solution Approach 1:
The patent extracts only the essential attributes of nodes that form the shortest path between source and target contents. By taking out and presenting only these critical attributes rather than all node details, the system maintains recommendation accuracy while significantly improving user understanding of the basis for content presentation
Solution Approach 2:
The patent applies local quality by presenting different levels of information detail in different contexts. For nodes on the shortest path, essential attributes are highlighted to provide accurate recommendation basis, while non-essential details are omitted. This localized information presentation ensures accuracy where needed while maintaining overall simplicity for user comprehension
Data Source
AI summary
In the information processing device, the training means trains a learning model using graph data and relationship data. The graph data includes a plurality of nodes corresponding to a plurality of contents, and the graph data is provided with attribute data indicating attributes of the plurality of nodes. The relationship data indicates known relationships between the nodes linked in the graph data. The analysis means performs an analysis for identifying contents optimized for a keyword inputted by a user, by using the trained learning model. The display information generation means generates a graph for showing an analysis result obtained by the analysis together with a basis, and generates a display information in which an icon corresponding to the attribute of each node is applied to each node constituting the basis in the graph. The information processing device can be used for user's decision making relating to healthcare.