Graph Reconciliation for Automatic Entity Discovery

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Large data graphs lack information about certain entities and their relationships, making them less useful for querying, as manually adding this information is slow and does not scale.

Innovation Solution

A system analyzes and clusters source data graphs from web-based sources to identify potential entities and relationships, using determinative predicates to split and merge graphs, thereby suggesting new entities and facts for inclusion in the target data graph.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If manual addition of missing entity information is used, then data graph completeness can be improved, but the process is slow and does not scale

Engineering Contradiction:

Improvedata graph completenessVSAvoidspeed of information addition

Core Design Contradiction:

Loss of informationVSProductivity

Solution Approach 1:

The system enables automatic self-service by having the data graph completion process perform itself through automated entity discovery. The system automatically identifies missing entities from source documents, extracts relationships, and integrates them into the data graph without requiring manual human intervention, thus resolving the contradiction between improving completeness and maintaining slow manual addition speed

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical manual addition process with an automated computational system. Instead of humans manually adding entity information, the system uses automated processes including document analysis, entity extraction, relationship identification, and graph integration algorithms to complete the data graph, thereby increasing productivity while maintaining completeness

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If automated entity discovery is implemented, then productivity increases, but system complexity increases

Engineering Contradiction:

Improvespeed of entity discoveryVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system segments the complex entity discovery process into distinct manageable modules: source document analysis, entity extraction, relationship extraction, entity verification, and graph integration. Each module handles a specific aspect of the task independently, making the overall complex system more manageable and maintainable while achieving high productivity through automated processing

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces intermediary components that mediate between the input source documents and the target data graph. These intermediaries include entity normalization layers, relationship validation modules, and conflict resolution mechanisms that simplify the interaction between different system components, reducing perceived complexity while maintaining automated high-speed operation

Inventive Principle:

Principle #24Intermediary (Mediator)

3Loss of information

If multiple source documents are processed, then data graph completeness improves, but processing time increases

Engineering Contradiction:

Improvedata graph completenessVSAvoidprocessing time

Core Design Contradiction:

Loss of informationVSLoss of time

Solution Approach 1:

The system performs preliminary actions by pre-processing source documents to identify and extract potential entities and relationships before final integration. The system pre-analyzes document structure, identifies candidate entities, and extracts potential relationships in advance, then filters and validates them during the main processing phase, thereby reducing overall processing time while maintaining high completeness through comprehensive multi-source processing

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS10331706B1Automatic discovery of new entities using graph reconciliation

Publication Date: 2019.06.25 GOOGLE LLC

AI summary

Systems and methods can identify potential entities from facts generated from web-based sources. For example, a method may include generating a source data graph for a potential entity from a text document in which the potential entity is identified. The source data graph represents the potential entity and facts about the potential entity from the text document. The method may also include clustering a plurality of source data graphs, each for a different text document, by entity name and type, wherein at least one cluster includes the potential entity. The method may also include verifying the potential entity using the cluster by corroborating at least a quantity of determinative facts about the potential entity and storing the potential entity and the facts about the potential entity, wherein each stored fact has at least one associated text document.