Call Screen Query Verification Using Dynamic ML Database Updates

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems for updating call screens on computing devices are inefficient due to the need for manual comparison of incoming call numbers with known entities, leading to delays in identifying ownership changes of data records.

Innovation Solution

A computer-based system utilizing a trained machine learning algorithm to perform cross-reference analysis, dynamically updating databases by removing and restoring data records based on indicative markers, and predicting data correctness confidence values to optimize the call screen updates.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual comparison of incoming call numbers with known entities is used, then the system can identify known entities, but the efficiency and speed of updating call screens decreases

Engineering Contradiction:

Improveaccuracy in identifying known entitiesVSAvoidefficiency of updating call screens

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The patent replaces the manual comparison process with a machine learning-based automated system. The ML model analyzes call screen data, phone numbers, and user interactions to automatically identify known entities and update call screens, eliminating the need for manual comparison while maintaining or improving accuracy.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service by allowing the call screen update mechanism to autonomously learn from user interactions and automatically update itself. The ML model continuously improves by processing user confirmations and corrections, making the system self-optimizing without requiring manual intervention for each update.

Inventive Principle:

Principle #25Self-service

2Reliability

If manual comparison methods are used to update call screens, then the system can display known entities, but delays occur in identifying ownership changes of data records

Engineering Contradiction:

Improveaccuracy in displaying known entitiesVSAvoiddelay in identifying ownership changes

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent implements continuous learning and updating through the machine learning model, which processes data continuously rather than through periodic manual updates. The system maintains an ever-updating understanding of entity ownership by continuously analyzing call screen data, phone numbers, and user interactions, eliminating delays in identifying ownership changes.

Inventive Principle:

Principle #20Continuity of useful action

Solution Approach 2:

The system performs preliminary analysis by pre-processing and storing call screen data, phone numbers, and entity information in structured formats before updates are needed. The ML model is pre-trained on existing data, enabling rapid identification of ownership changes when they occur without requiring time-consuming manual comparison.

Inventive Principle:

Principle #10Preliminary action

3Productivity

If automated machine learning algorithms are used to update databases, then the efficiency of call screen updates improves, but the system complexity increases

Engineering Contradiction:

Improveefficiency of updating call screensVSAvoidcomplexity of the updating system

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent introduces an intermediary layer between raw data and the call screen update process. The machine learning model acts as a mediator that transforms complex multi-source data (call screens, phone numbers, user interactions) into simplified entity identification results, managing system complexity by encapsulating the analytical logic within the ML algorithm.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system segments the update process into distinct functional components: data collection from multiple sources, ML-based analysis and entity identification, verification through user interactions, and database updates. This segmentation allows each component to be independently optimized and managed, reducing overall system complexity despite the advanced capabilities.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS12530337B2Computer-based systems configured for automatically updating a database based on an initiation of a dynamic machine-learning verification and methods of use thereof

Publication Date: 2026.01.20 CAPITAL ONE SERVICES LLC

AI summary

In some embodiments, the present disclosure provides an exemplary method that may include steps of receiving input data from at least one external data aggregator; utilizing a trained machine learning algorithm to generate a database of known queries; receiving subsequent input data from the at least one external aggregator; automatically updating the database of known queries associated with the plurality of users; utilizing the trained machine learning algorithm to perform a cross-reference analysis to determine a presence of a data record within the database of known queries; dynamically removing the data record from the database of known queries; utilizing the trained machine learning algorithm to predict a trigger associated with the presence of the at least one data record; and instructing a computing device to initiate a verification of the presence of the at least one data record.