Process Prioritization via User Persona and Reinforcement Learning

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Information handling systems face challenges in efficiently prioritizing processes, leading to resource allocation issues that can negatively impact user experience, as manual prioritization is time-consuming and may not accurately reflect user needs, and automated methods can incorrectly prioritize processes based on resource consumption or designations.

Innovation Solution

An automated system adjusts priority levels for processes on an information handling system based on user persona classifications and dynamic system contexts, using reinforcement learning algorithms to continuously optimize resource allocation and improve user experience by calculating an optimization importance score weighted towards key performance indicators specific to the user and system state.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If manual prioritization is used to configure resource allocation, then users can prioritize important processes, but it is time-consuming and requires technical knowledge that users may not possess

Engineering Contradiction:

Improveease of prioritizationVSAvoidtime for configuration

Core Design Contradiction:

Ease of operationVSLoss of time

Solution Approach 1:

The system automatically performs process prioritization without requiring user configuration. The heuristic module autonomously analyzes process characteristics, user behavior patterns, and system state to determine priority levels, eliminating the need for manual user intervention while still achieving user-centric resource allocation

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The manual mechanical process of user configuration is replaced with an automated computational system using machine learning models and heuristic algorithms. The system substitutes human decision-making with algorithmic analysis of process metadata, resource consumption patterns, and user behavior to automatically establish priority configurations

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Extent of automation

If automated prioritization based on resource consumption is used, then resource allocation is automated, but processes requiring minimal resources may be incorrectly deprioritized despite being important to user experience

Engineering Contradiction:

Improveautomation of prioritizationVSAvoidaccuracy of prioritization

Core Design Contradiction:

Extent of automationVSMeasurement precision

Solution Approach 1:

The system moves beyond单一的 resource consumption metrics by introducing multiple parameters including process type classification, user behavior patterns, temporal context, and system state. The heuristic module dynamically adjusts priority based on combinations of these parameters, allowing accurate identification of important low-resource processes such as background updates or essential system services

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The system incorporates feedback loops where user interactions, process execution patterns, and system performance data are continuously monitored. This feedback refines the prioritization decisions over time, allowing the system to learn which processes are genuinely important to user experience and adjust priorities accordingly, improving measurement precision through iterative optimization

Inventive Principle:

Principle #23Feedback

3Productivity

If foreground processes are prioritized over background processes, then resource allocation follows conventional designations, but background processes may be more important to user experience than foreground processes

Engineering Contradiction:

Improveresource allocation efficiencyVSAvoidaccuracy of importance assessment

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The system applies different prioritization rules to different process types and contexts rather than a universal foreground-over-background rule. Background processes performing critical functions (updates, security scans, system maintenance) are identified and granted appropriate priority levels based on their specific characteristics and current system state, allowing each process to receive locally optimized treatment rather than blanket classification

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS11489928B2Prioritization of processes based on user persona and reinforcement learning

Publication Date: 2022.11.01 DELL PROD LP

AI summary

Settings on an information handling system may be adjusted to set priority levels for processes executing on the information handling system in view of desired operational characteristics of the information handling system for a user persona and in view of expected future events for the information handling system. A score may be generated based on a user persona (e.g., whether a user is a light gamer, heavy gamer, corridor warrior, or desk worker) and expected future computer contexts (e.g., an expectation that a user will play a game in one hour). That score may be used to determine policies (e.g., high performance, balanced, or battery saver) to implement through settings on the computer system. Consideration of user persona classifications, associated group behaviors, and dynamic system contexts (including resource extremas, location, temporal context, and predicted future events) improve use of system resources through prioritization and governing of diverse optimization methods.