AI Data Feed Validation and Error Correction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing electronic systems face challenges in efficiently evaluating, validating, correcting, and loading data feeds due to errors, network issues, and inadequate resources, which can lead to service level agreement breaches and resource wastage.

Innovation Solution

A system utilizing artificial intelligence input to analyze metadata and historical feed data to determine the likelihood of data feed failures, allowing for proactive loading, subdivision, and error correction of data feeds, thereby mitigating loading failures and conserving resources.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If data feeds are loaded without prior evaluation and validation, then loading speed is improved, but loading failures occur due to errors and network issues

Engineering Contradiction:

Improveloading speedVSAvoidloading success rate

Core Design Contradiction:

SpeedVSReliability

Solution Approach 1:

The system performs preliminary evaluation and validation of data feeds before loading them into the data structure. This includes checking data quality, validating formats, and assessing network conditions in advance to prevent loading failures, thereby maintaining both high loading speed and high success rate.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system proactively identifies and mitigates potential loading failures by detecting errors and network issues before they occur. Correction mechanisms are prepared in advance to counteract anticipated problems, ensuring reliable loading without sacrificing speed.

Inventive Principle:

Principle #9Preliminary anti-action

2Reliability

If data feeds are extensively evaluated and validated before loading, then loading failures are reduced, but resource consumption increases

Engineering Contradiction:

Improveloading success rateVSAvoidresource consumption

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system applies different levels of evaluation and validation to different portions or types of data feeds based on their specific characteristics and risk profiles. Critical data receives more thorough validation while less critical data undergoes lighter checks, optimizing resource usage while maintaining necessary reliability.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system dynamically adjusts validation parameters and thresholds based on data feed characteristics, historical performance, and current system conditions. This allows the evaluation process to be more efficient for certain data types while maintaining high success rates where needed.

Inventive Principle:

Principle #35Parameter changes

3Reliability

If data feeds are subdivided and corrected iteratively, then loading failures are mitigated, but processing time increases

Engineering Contradiction:

Improveloading success rateVSAvoidprocessing time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system divides data feeds into smaller, manageable segments that can be processed independently. This allows parallel processing of multiple segments and enables targeted correction of only the problematic portions, reducing overall processing time while maintaining high loading success rates.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system performs correction only on the specific portions of data feeds that contain errors or are likely to cause loading failures, rather than reprocessing entire data sets. This partial action approach minimizes processing time while still achieving high reliability.

Inventive Principle:

Principle #16Partial or excessive action

4Reliability

If AI-driven analysis is performed on metadata and historical data, then loading failures are predicted and prevented, but system complexity increases

Engineering Contradiction:

Improveloading success rateVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system introduces AI-driven analysis as an intermediary layer between data feed reception and loading operations. This intermediary analyzes metadata and historical data to predict potential failures, providing actionable insights without requiring complete redesign of the core loading infrastructure, thus managing complexity while improving reliability.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS12292784B2Systems and methods for evaluating, validating, correcting, and loading data feeds based on artificial intelligence input

Publication Date: 2025.05.06 BANK OF AMERICA CORP

AI summary

Systems, computer program products, and methods are described herein for evaluating, validating, correcting, and loading data feeds based on artificial intelligence input. The present invention may be configured to receive a data feed from a source for loading to a target data structure, analyze, based on historical feed data, metadata of the data feed to determine a likelihood of the data feed failing to load, and determine whether the likelihood of the data feed failing to load satisfies a threshold. The present invention may be configured to load the data feed to the target data structure, determine, after loading the data feed to the target data structure, whether the data feed failed to load, and either correct errors in the data feed or add error-containing portions of the data feed to a failed data log.