Personal Knowledge Graph Completion for Incomplete Node Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing AI-based systems face challenges in managing personal knowledge graphs due to incomplete nodes with missing knowledge property information, which hinder effective data integration and search functionality.

Innovation Solution

A method is provided to detect incomplete nodes in personal knowledge graphs, identify candidate knowledge property information, and complete these nodes by replacing or updating them with identified information, using electronic devices equipped with processors and memory to execute computer-executable instructions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If AI-based systems use personal knowledge graphs for data management, then data integration capability is improved, but incompleteness of knowledge nodes reduces system reliability

Engineering Contradiction:

Improvedata integration capabilityVSAvoidcompleteness of knowledge nodes

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The system performs preliminary actions by proactively detecting incomplete nodes in the knowledge graph and automatically searching for candidate knowledge property information before the incompleteness affects system operations. This advance completion ensures data reliability is maintained preemptively rather than reactively.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements self-service by autonomously identifying incomplete knowledge nodes, searching for relevant information, and completing the nodes without requiring manual intervention. The electronic device automatically manages its own knowledge graph completeness, improving both reliability and operational efficiency.

Inventive Principle:

Principle #25Self-service

2Measurement precision

If manual completion of incomplete knowledge nodes is performed, then accuracy of knowledge graph is improved, but time consumption and operational complexity increase

Engineering Contradiction:

Improveaccuracy of knowledge graphVSAvoidtime consumption for node completion

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system replaces the mechanical manual process of completing knowledge nodes with an automated information processing system. The electronic device uses algorithms to detect incomplete nodes, search for candidate information, and perform completions automatically, eliminating manual labor while maintaining or improving accuracy.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system introduces an intermediary automated process between the detection of incomplete nodes and their completion. This intermediary layer systematically searches for candidate knowledge property information and validates candidates before completion, ensuring accuracy while reducing time consumption compared to direct manual completion.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Productivity

If automated detection and completion of incomplete nodes is implemented, then productivity is improved, but system complexity increases

Engineering Contradiction:

Improveefficiency of knowledge graph maintenanceVSAvoidcomplexity of completion system

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system segments the knowledge graph maintenance process into distinct functional modules: detection of incomplete nodes, identification of candidate knowledge property information, validation of candidates, and completion execution. This modular segmentation manages system complexity by organizing functions into manageable, independent components that can be developed and maintained separately.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system implements a universal automated completion mechanism that can handle multiple types of knowledge nodes and various sources of candidate information through a single integrated process. This multi-functional approach improves productivity by using one system to address diverse completion needs rather than requiring separate specialized processes for each case.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS20250371379A1Method of managing personal knowledge graph and user device using the method

Publication Date: 2025.12.04 SAMSUNG ELECTRONICS CO LTD

AI summary

A method performed by an electronic device for managing a personal knowledge graph is provided. The method includes detecting, by the electronic device, an instance including an incomplete node having missing knowledge property information in a personal knowledge graph, identifying, by the electronic device, candidate knowledge property information corresponding to the missing knowledge property information of the incomplete node, and performing, by the electronic device, a task of completing the incomplete node based on the identified candidate knowledge property information.