Neural Database Training Using Metadata for Supplier Entity Matching

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Discovering raw material suppliers for business-to-business transactions is challenging due to the inefficiency and inaccuracies in traditional supplier databases, which require significant time and manual effort to maintain and often lead to outdated information.

Innovation Solution

A neural database is trained using structured entity data and metadata generated by a machine learning model, such as GPT-4, to efficiently match entities by generating key-value pairs that map goods or services to relevant supplier entities, leveraging reinforcement learning for continual improvement.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional supplier databases are used, then supplier information can be stored and retrieved, but the databases require significant time and manual effort to maintain and often lead to outdated information

Engineering Contradiction:

Improveaccuracy of supplier informationVSAvoidtime to maintain database

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system enables automatic self-updating of supplier databases through web crawlers that autonomously scrape supplier information from external sources, eliminating the need for manual database maintenance while ensuring information remains current and accurate

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system performs preliminary data collection and validation by crawling supplier information from multiple external sources before it becomes obsolete, proactively updating the database to prevent outdated information from being stored or queried

Inventive Principle:

Principle #10Preliminary action

2Productivity

If traditional supplier databases are used, then supplier information can be retrieved, but the search process is inefficient and inaccurate

Engineering Contradiction:

Improvespeed of supplier discoveryVSAvoidaccuracy of supplier matching

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The system replaces manual mechanical search processes with an automated neural network-based entity matching system that uses machine learning to automatically match entities with their suppliers based on extracted features and relationships, dramatically improving both speed and accuracy

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system transforms unstructured supplier data into structured entity representations with extracted features and relationships, changing the data parameters from raw text to organized entities that can be efficiently queried and matched by the neural network

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentEP4703968A1Training a neural database for entity matching

Publication Date: 2026.03.04 INTUIT INC

Figure 1
Figure 2
Figure 3

AI summary

Certain aspects of the disclosure provide a method of training a neural database for entity matching. In examples, a method may include: extracting, from an electronic data repository, entity data related to a first entity that provides a good or a service; transforming the entity data into structured entity data configured to be processed by a machine learning model; processing the structured entity data with the machine learning model to generate metadata associated with the structured entity data; augmenting the structured entity data with the metadata associated with the structured entity data; and training the neural database based on the augmented structured entity data to predict one or more second entities that supply materials for the first entity and associated with the good or the service.