Knowledge Mesh Graph Construction for Faster Entity Relationship Discovery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies face challenges in efficiently determining and processing relationships between entities from disparate data sources across different content types, leading to slower response times and limited understanding of data relationships due to the reliance on processor-intensive calculations in relational databases.
Innovation Solution
An open relationship-based approach using a graph database to create a knowledge mesh, which processes data from multiple streams, enhances it with attributes, applies machine learning models for triple identification, filters with ontologies, and disambiguates entities to establish relationships with confidence levels, storing the results in a graph database for efficient data understanding.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a relational database approach is used to store and process data relationships, then data can be stored in structured tables with defined schemas, but determining relationships between entities requires processor-intensive calculations leading to slower response times
Solution Approach 1:
The patent replaces the mechanical calculation system of relational databases with a graph database structure where relationships are explicitly stored as edges between nodes. This substitution eliminates the need for processor-intensive joins and queries, as relationships are directly accessible in the graph structure, thereby reducing response time while maintaining relationship accuracy
Solution Approach 2:
The system pre-computes and stores relationships in the graph database structure before queries are executed. By establishing the relationship network in advance through data ingestion and processing pipelines, the system avoids performing intensive calculations at query time, thus improving response time without sacrificing relationship determination accuracy
2Adaptability or versatility
If data from multiple disparate sources is processed to identify relationships, then comprehensive data understanding is achieved, but the complexity of processing different content types increases
Solution Approach 1:
The patent implements a universal data processing framework that handles multiple content types (text, audio, video, images) through a common pipeline. The system uses standardized entity extraction and relationship identification processes that work across different data sources, reducing processing complexity while maintaining versatility in handling disparate data types
Solution Approach 2:
The system introduces intermediary processing layers including natural language processing models, optical character recognition, and audio transcription services that convert different content types into standardized structured data. These intermediaries simplify the processing of disparate sources by transforming them into a common format that the graph database can uniformly process
3Measurement precision
If machine learning models are applied to identify triples and relationships in data, then more accurate entity relationships are discovered, but processing time and computational resources increase
Solution Approach 1:
The system applies machine learning models selectively to portions of data where relationship identification is most beneficial, rather than processing every data point with full ML complexity. By using heuristic filters and rule-based systems for straightforward cases and reserving ML models for ambiguous or complex scenarios, the system maintains relationship accuracy while improving overall processing speed
Data Source
AI summary
A method for creating a graph database implemented knowledge mesh is disclosed. The method includes receiving, by a computer system, data from a plurality of different streams and identifying, by the computer system executing at least one machine learning model, a plurality of triples included in the data. The method also comprises filtering, by the computer system, the plurality of triples to identify a relevant subset of triples by applying an ontological filter, applying, by the computer system, a disambiguation routine to the relevant subset of triples to correlate entities included in the relevant subset to other entities in a graph database and determine a degree of confidence with each correlation, and creating, by the computer system, a knowledge mesh using the graph database. The knowledge mesh comprises the relevant subset of triples, each correlation identified by application of the disambiguation routine, and the degree of confidence with each correlation.