Machine Learning Interaction Scheduling for Computing Systems

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems lack efficient methods to optimize interactions between computing systems by analyzing user behavior patterns and resource management, leading to suboptimal computational efficiency and resource utilization.

Innovation Solution

Implementing machine learning models to analyze user behavior patterns and generate adjustments for improving computational efficiency and resource management by switching services or altering interaction schedules based on historical data and user characteristics.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If machine learning models are implemented to analyze user behavior patterns and optimize interactions, then computational efficiency and resource management are enhanced, but system complexity increases

Engineering Contradiction:

Improvecomputational efficiencyVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent introduces machine learning models as intermediary components that analyze user behavior patterns and generate optimization recommendations. These models act as mediators between raw interaction data and system configuration adjustments, enabling intelligent optimization without directly complicating the core interaction handling logic. The models process historical data and user characteristics to produce actionable adjustments that improve computational efficiency while isolating complexity within the ML layer.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system segments the interaction optimization problem into distinct components: data collection module, machine learning model layer, and configuration adjustment module. This segmentation allows each component to be developed, trained, and maintained independently. The machine learning models are trained separately on historical interaction data, then deployed to generate recommendations without requiring changes to the underlying system architecture, thus managing complexity through modular design.

Inventive Principle:

Principle #1Segmentation

2Loss of energy

If interactions are optimized based on user behavior patterns, then resource consumption is reduced, but measurement and analysis difficulty increases

Engineering Contradiction:

Improveresource consumptionVSAvoidbehavior pattern analysis difficulty

Core Design Contradiction:

Loss of energyVSDifficulty of detecting and measuring

Solution Approach 1:

The patent implements feedback loops where machine learning models continuously analyze user interaction patterns and generate optimization recommendations that are applied to system configuration. The system monitors the effects of these adjustments and uses the resulting data to further refine behavior patterns. This feedback mechanism enables automatic adaptation to user behavior while systematically reducing resource consumption through data-driven optimization decisions.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system performs preliminary analysis of user behavior patterns using machine learning models before making interaction optimization decisions. Historical interaction data is preprocessed and analyzed in advance to identify behavior patterns, allowing the system to proactively adjust configurations before resource-intensive operations occur. This preliminary action enables predictive optimization that reduces resource consumption while managing analysis complexity through advance processing.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS20250306961A1Applying machine learning to handling interactions between computing systems

Publication Date: 2025.10.02 TRUIST BANK

AI summary

A system can input a set of usage data associated with an account into a machine-learning model. The set of usage data can include historical data for the account associated with interactions between computing systems. The machine-learning model can generate an output indicating a score for a pattern of behavior associated with the interactions. The system can generate, based on historical data of interactions performed by multiple accounts, an adjustment to an interaction for the account. The adjustment can be used to increase the score for the pattern of behavior. The system can provide a user interface displaying the adjustment. The system can receive, through the user interface, a selection to initiate the adjustment to perform the interaction. In response, the system can automatically configure the system to fulfil the interaction according to the adjustment.