ML Vector Data Access System Minimizing Source Usage

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing database systems face challenges in efficiently accessing data through multiple trusted systems, leading to suboptimal data source usage.

Innovation Solution

A data access system utilizing machine learning to generate vector representations of requested parameters, which are then processed to identify the minimum number of data sources needed to retrieve the required data, optimizing data source usage.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If multiple trusted systems are used to access different parameters, then data accessibility is improved, but system complexity increases

Engineering Contradiction:

Improvedata accessibilityVSAvoidsystem complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent introduces a data access system as an intermediary layer between applications and multiple trusted systems. This mediator receives data requests, determines optimal data source combinations using machine learning, and coordinates access to minimize the number of trusted systems consulted while ensuring all required parameters are retrieved.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent transforms parameter requests into vector representations that can be processed by machine learning models. This parameter transformation enables the system to optimize data source selection by converting complex parameter sets into a format suitable for ML-based decision making, thereby reducing system complexity while maintaining accessibility.

Inventive Principle:

Principle #35Parameter changes

2Reliability

If all data sources are queried to ensure complete data retrieval, then data completeness is improved, but processing overhead increases

Engineering Contradiction:

Improvedata completenessVSAvoidprocessing overhead

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

Instead of querying all data sources, the patent uses machine learning to determine the minimum necessary subset of data sources required to fulfill the data request. This partial action approach ensures data completeness by selectively querying only the essential sources, thereby reducing processing overhead while maintaining reliability.

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The system incorporates feedback mechanisms where the machine learning model learns from historical data access patterns and performance metrics. This feedback loop enables the system to continuously improve its data source selection accuracy, optimizing the balance between data completeness and processing efficiency over time.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS20250156728A1Minimizing usage of sources of records with machine learning

Publication Date: 2025.05.15 CAPITAL ONE SERVICES LLC

AI summary

Methods and systems are described herein for minimizing data source usage. A data access system may receive an access request that includes a request for a multitude of parameters and generate a vector representation that includes those parameters. The data access system may then input the vector representation into a machine learning model to obtain a plurality of data sources that have access to the parameters within the request. Once the required data sources are obtained, the data access system may generate a message to each data source to retrieve the parameter data requested by the access request and transmit the messages to the appropriate data sources. Once the parameter data is received, the data access system may transmit a response to the request such that the response may include the parameter data.