Reinforcement Learning Task Scheduler for Project Optimization

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing software solutions for scheduling large-scale capital projects require significant user input and expertise, often leading to projects exceeding budgets and timelines due to the complexity of resource management and constraints.

Innovation Solution

A system utilizing a trained reinforcement learning engine with neural networks to generate optimized task schedules based on inputs from total work, resource, and constraints databases, prioritizing objectives such as minimizing slowdown, completion time, and resource utilization.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If heuristic approaches are applied to schedule tasks, then scheduling complexity is reduced for small sets of tasks, but scheduling effectiveness deteriorates when applied to large projects

Engineering Contradiction:

Improvescheduling complexityVSAvoidscheduling effectiveness

Core Design Contradiction:

Device complexityVSReliability

Solution Approach 1:

The patent replaces traditional heuristic scheduling methods with a reinforcement learning-based artificial intelligence system. The RL agent learns optimal scheduling strategies through interaction with the scheduling environment, substituting rule-based mechanical approaches with adaptive intelligent decision-making that can handle large-scale project complexity while maintaining high scheduling effectiveness.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent transforms the scheduling problem by changing the approach from static heuristic rules to dynamic reinforcement learning policies. The RL agent continuously adapts scheduling decisions based on learned parameters and environmental feedback, enabling effective scheduling for large projects where traditional heuristics fail.

Inventive Principle:

Principle #35Parameter changes

2Reliability

If manual scheduling is performed by skilled experts, then scheduling quality is maintained for complex projects, but time consumption and cost increase significantly

Engineering Contradiction:

Improvescheduling qualityVSAvoidscheduling time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent implements an autonomous reinforcement learning agent that performs scheduling independently without requiring skilled expert intervention. The RL system learns and executes scheduling decisions autonomously, dramatically reducing the time and human resources needed while maintaining scheduling quality through its learned optimization capabilities.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent substitutes human expert scheduling with an automated reinforcement learning system. This replacement eliminates the time-consuming manual process while preserving scheduling quality through the RL agent's ability to learn optimal strategies from training data and apply them automatically to new projects.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Adaptability or versatility

If traditional scheduling software is used, then resource coordination is achieved, but project completion time extends beyond deadlines

Engineering Contradiction:

Improveresource coordinationVSAvoidproject completion time

Core Design Contradiction:

Adaptability or versatilityVSDuration of action of moving object

Solution Approach 1:

The patent replaces traditional scheduling software with a reinforcement learning-based system that learns optimal resource coordination strategies. The RL agent achieves superior resource allocation and sequencing decisions, coordinating resources effectively while significantly reducing project completion time compared to conventional approaches.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent fundamentally changes the scheduling approach from rule-based software to adaptive reinforcement learning. This parameter change enables the system to dynamically optimize resource coordination and task sequencing, achieving both effective resource utilization and reduced project duration through learned optimal policies.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS20230096811A1Scheduling with support for multiple scheduling objectives

Publication Date: 2023.03.30 HEXAGON TECH CENT GMBH

AI summary

A system for generating task schedules using an electronic device includes: a processor, the processor comprising neural networks; a memory coupled to the processor; a scheduler coupled to the processor, the scheduler is configured to: receive: a total work database configured to contain items representing work packages; a resources database configured to contain items representing resources required to fulfill items in the work packages; a constraints database configured to contain items representing constraints to fulfilling items in the work packages; and a scheduling objective database configured to designate a prime objective that is to be achieved by the optimum task schedule; provide a trained reinforcement learning engine for optimizing the task schedule based on inputs from the databases; and generate an optimum work package schedule to sequence the work packages using the trained reinforcement learning engine, wherein the optimum work package schedule maximizes the one or more prime objectives.