ML-Based Task Resource Assignment Optimization

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Optimizing task/resource assignment in complex systems is inefficient and computationally intensive, especially as the number of resources and entities increases, making brute force optimization impractical due to high processing power requirements and time consumption.

Innovation Solution

Employing artificial intelligence and machine learning to randomly assign tasks/resources, calculate scores, select subsets, and iteratively change assignments using techniques like swapping or replacing resources, until specific criteria are met, thereby optimizing task/resource assignment without brute force methods.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If brute force optimization is used to optimize task/resource assignment, then the optimization completeness is improved, but the processing power and time required increase exponentially

Engineering Contradiction:

Improveoptimization completenessVSAvoidprocessing power

Core Design Contradiction:

Manufacturing precisionVSUse of energy by moving object

Solution Approach 1:

The patent changes the optimization approach from exhaustive brute force enumeration to a scoring-based selection method. Instead of evaluating all possible assignments (ra combinations), the system assigns scores to resources based on multiple factors (capacity, relationship, utilization, impact) and selects assignments based on these scores, dramatically reducing computational requirements while maintaining optimization quality

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent evaluates and optimizes each resource assignment locally by calculating specific scores for each resource-entity pair based on relevant factors (capacity, relationship, utilization, impact). This localized scoring approach allows the system to make optimized decisions without needing to evaluate all global combinations, reducing processing power requirements

Inventive Principle:

Principle #3Local quality

2Manufacturing precision

If brute force optimization is used to optimize task/resource assignment, then the optimization completeness is improved, but the time consumption increases exponentially

Engineering Contradiction:

Improveoptimization completenessVSAvoidtime consumption

Core Design Contradiction:

Manufacturing precisionVSLoss of time

Solution Approach 1:

The patent transforms the optimization problem from evaluating all possible solutions (exponential time complexity) to evaluating scored assignments (polynomial time complexity). By changing from exhaustive search to score-based selection, the system achieves optimization completeness without the exponential time penalty of brute force methods

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent performs preliminary scoring of resources based on multiple factors (capacity, relationship, utilization, impact) before making assignments. This preliminary evaluation creates a ranked framework that guides subsequent assignments, eliminating the need for time-consuming exhaustive search while maintaining optimization quality

Inventive Principle:

Principle #10Preliminary action

3Adaptability or versatility

If the number of resources and entities increases, then the system capacity and coverage are improved, but the number of possible solutions increases making optimization impractical

Engineering Contradiction:

Improvesystem capacityVSAvoidnumber of possible solutions

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent introduces scoring parameters for each resource based on multiple factors (capacity, relationship, utilization, impact) to transform the combinatorial explosion problem into a manageable scoring and selection process. This parameter-based approach scales efficiently even as the number of resources and entities increases

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent replaces the mechanical brute force enumeration approach with an intelligent scoring and selection system. Instead of mechanically generating and evaluating all possible assignments, the system uses scoring mechanisms to efficiently identify optimal assignments, making the system scalable to large numbers of resources and entities

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS11755376B2Automatic assignment of hardware/software resources to different entities using machine learning based on determined scores for assignment solutions

Publication Date: 2023.09.12 CALLIDUS SOFTWARE INC

AI summary

Task/resources are randomly assigned a number of times and a score for each solution of the random assignment is calculated. Using machine learning and artificial intelligence, a subset of the solutions is selected. Assignment of task/resource within the subset may be randomly changed, e.g., a task/resource assignment between two entities, a task/resource within the selected subset may be replaced with another task/resource (without swapping), etc. The additional solutions form a super solution with the selected subset and the score associated with the additional solutions are calculated. The process of selection of assignments, random changes to the assignment and calculating the scores associated with the new solutions is repeated a number of times until a certain condition is met, e.g., a number of iterations, time out, improvement between two iterations is less than a certain threshold, etc. Once the certain condition is satisfied, a solution is selected.