Dynamic Knowledge Graph Generation via Automated Data Extraction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventionally generated knowledge graphs in the process space are static and unable to be automatically updated as data changes, limiting their dynamic representation of relationships between processes, systems, people, and entities.

Innovation Solution

Systems and methods for automatically generating knowledge graphs by extracting entity, process, user, and system data from business sources using semantic meaning extraction, process mining, task mining, and RPA processes, with continuous tracking and updating of changes to maintain a dynamic representation of interactions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If knowledge graphs are manually generated by users defining relationships between data, then the knowledge graph can be created with user-defined relationships, but the knowledge graph becomes static and unable to be automatically updated as data changes

Engineering Contradiction:

Improveautomatic updating capabilityVSAvoidsystem complexity for automatic generation

Core Design Contradiction:

Extent of automationVSDevice complexity

Solution Approach 1:

The system enables self-service automatic generation of knowledge graphs by extracting data from existing business data sources and automatically identifying entities, processes, users, and systems without requiring manual user input for each update cycle

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The manual mechanical process of users defining relationships is replaced with automated computational processes including semantic meaning extraction, process mining, task mining, and process capture that automatically identify and establish relationships between data elements

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Adaptability or versatility

If conventional manual methods are used to generate knowledge graphs, then the generation process is simple to implement, but the knowledge graphs cannot dynamically reflect real-time changes in data

Engineering Contradiction:

Improvedynamic adaptation to data changesVSAvoidgeneration and update speed

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The system implements continuous tracking of changes in entity data, process data, user data, and system data, with the knowledge graph being continuously updated to reflect current state, ensuring uninterrupted dynamic representation of organizational data relationships

Inventive Principle:

Principle #20Continuity of useful action

Solution Approach 2:

The system establishes feedback loops where changes in source data are detected and automatically fed back into the knowledge graph generation process, triggering automatic updates to maintain synchronization between source data and the knowledge graph representation

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS20230289621A1Automatic generation of knowledge graphs

Publication Date: 2023.09.14 UIPATH INC

AI summary

Systems and methods for automatically generating a knowledge graph are provided. Entity data, process data, user data, and system data of an organization are extracted from one or more business data sources. A knowledge graph defining relationships between the entities data, the process data, the user data, and the system data is generated. The knowledge graph is output.