Hybrid AI Application Forecasting for Dynamic Resource Allocation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems struggle to efficiently allocate computational and physical resources for application processing and approval due to inflexible redeployment and inaccurate, qualitative predictions of application volume changes, leading to strain or underutilization of resources.

Innovation Solution

Implementing a time-series-based, hybrid artificial intelligence process coupled with multiplier-based extrapolation processes to predict application volumes in real-time, enabling flexible resource allocation based on precise, short-term and long-term volume estimates.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If manual and programmatic processing methods are used for application approval, then processing capability is maintained, but resource allocation becomes inflexible and inefficient

Engineering Contradiction:

Improveapplication processing capabilityVSAvoidresource allocation flexibility

Core Design Contradiction:

ProductivityVSAdaptability or versatility

Solution Approach 1:

The patent implements dynamic resource allocation by continuously monitoring application volumes and automatically adjusting computational resource assignments. The system transitions from static resource provisioning to dynamic adjustment based on real-time AI predictions of application patterns, allowing resources to be allocated flexibly according to actual demand rather than fixed schedules.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system incorporates feedback loops where AI models continuously learn from actual application processing data and adjust their predictions. This feedback mechanism enables the system to refine its resource allocation strategies over time, improving both accuracy of volume predictions and efficiency of resource distribution based on actual performance data.

Inventive Principle:

Principle #23Feedback

2Device complexity

If qualitative predictions of application volume changes are used, then prediction process remains simple, but accuracy of resource allocation planning deteriorates

Engineering Contradiction:

Improveprediction process complexityVSAvoidapplication volume prediction accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent replaces manual qualitative prediction methods with automated AI-based predictive models. The system substitutes human judgment and experience-based forecasting with machine learning models that process historical data, identify patterns, and generate quantitative predictions, thereby improving accuracy while the automation handles the increased computational complexity.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system transforms prediction from qualitative to quantitative by changing the parameter representation. Instead of using descriptive categories or subjective assessments, the AI models work with numerical parameters and statistical patterns, enabling precise measurement and calculation of application volume changes while maintaining manageable process complexity through automation.

Inventive Principle:

Principle #35Parameter changes

3Device complexity

If resources are allocated based on fixed schedules, then allocation process remains simple, but resource strain or underutilization increases

Engineering Contradiction:

Improveallocation process complexityVSAvoidresource allocation effectiveness

Core Design Contradiction:

Device complexityVSReliability

Solution Approach 1:

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system performs preliminary actions by using AI predictions to forecast future application volumes and proactively adjusting resource allocation before peak demand occurs. This predictive approach allows the system to prepare computational resources in advance, preventing resource strain during high-demand periods and eliminating underutilization during low-demand periods.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS20250278638A1Training and deploying hybrid artificial intelligence processes and coupled extrapolation processes in distributed computing environments

Publication Date: 2025.09.04 THE TORONTO DOMINION BANK

AI summary

The disclosed embodiments include computer-implemented apparatuses and processes that train and deploy hybrid artificial intelligence processes and coupled extrapolation processes within distributed computing environments. For example, an apparatus obtains event data and indicator data associated with a first temporal interval, and based on an application of a trained artificial intelligence process to portions of the event data and the indicator data, the apparatus generates first output data indicating an expected number of occurrences of a first event during each of a plurality of second temporal intervals. Further, and based on an application of an extrapolation process to the output data, the apparatus generates second output data indicating an expected number of occurrences of a second event during each of the second temporal intervals and modifies an allocation of a computational resource at a computing system in accordance with the first output data and the second output data.