Machine Learning Assignment for Computer Update Requirements

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Managing and implementing computer system updates and requirements in complex organizational networks is resource-intensive and often falls behind the pace of requirement arrival, leading to outdated implementations.

Innovation Solution

A data collection technique using a classification model trained with past assignment records, combined with a detection module and trigger module to optimize data collection by prompting users only when their devices are feasible, and a machine learning model to automate requirement assignment.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual evaluation and assignment of updates to each computer process is performed, then accuracy of update assignment is improved, but productivity and speed of implementation deteriorate

Engineering Contradiction:

Improveaccuracy of update assignmentVSAvoidspeed of update implementation

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The patent introduces a machine learning model as an intermediary between update requirements and computer processes. The model automatically matches updates to applicable processes by learning from historical assignment data, eliminating the need for manual evaluation while maintaining high accuracy through trained patterns and relationships.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system enables self-service automation where the machine learning model independently performs the update assignment task without human intervention. The model uses collected historical data to automatically determine which computer processes should receive specific updates, freeing administrators from manual evaluation work.

Inventive Principle:

Principle #25Self-service

2Measurement precision

If comprehensive data collection from multiple sources is performed, then training accuracy of classification model is improved, but use of energy and computational resources worsen

Engineering Contradiction:

Improvetraining accuracy of classification modelVSAvoidcomputational resources for data collection

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent collects and stores historical update assignment data in advance during normal system operation. This preliminary data collection creates a training dataset that can be used later to train the classification model, allowing the system to learn from past patterns without requiring intensive real-time computational resources during the actual update assignment process.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system performs data collection and model training periodically or in batches rather than continuously in real-time. This approach allows comprehensive data gathering to improve model accuracy while spreading computational resource consumption over time, avoiding peak resource demands.

Inventive Principle:

Principle #19Periodic action

Data Source

PatentUS12461733B2Method and system for computer update requirement assignment using a machine learning technique

Publication Date: 2025.11.04 CAPITAL ONE SERVICES LLC

AI summary

A novel data collection technique is disclosed. This data collection technique gathers data relating to various technical processes implemented in a computer network. A database including past assignment of requirements is also provided. These requirements can be software update requirements relating to a computer network. A classification model is trained using the assignment records fort these requirements and the data collected relating to the technical processes. Using the classification model, new requirements can be classified and implemented on the computer network.