Unified Resource Capacity Data for Planning-Scheduling Alignment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The inconsistent granularity between resource scheduling and planning data models leads to inaccurate and time-consuming management of resource capacity, causing data mismatch and inefficiencies in scheduling and planning systems.
Innovation Solution
A unified resource capacity management system that leverages machine learning and artificial intelligence to synchronize and manage resource capacity at the lowest granularity, combining scheduling and planning data models for seamless and accurate updates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If resource capacity is managed separately in scheduling and planning data models, then each model can operate independently with its own granularity, but accuracy and synchronization between the models deteriorates
Solution Approach 1:
The patent merges the scheduling and planning data models into a unified resource capacity management system. The scheduling data model (lowest granularity) and planning data model (higher granularity) are integrated through a common resource capacity table that serves both models, eliminating data isolation and enabling consistent capacity management across both planning and scheduling operations.
Solution Approach 2:
The patent segments the resource capacity management into distinct operational layers: the scheduling data model handles detailed time-slot level capacity management, while the planning data model handles higher-level resource allocation. Both segments access the same unified resource capacity table, allowing independent operations while maintaining synchronization through shared data structures.
2Measurement precision
If resource capacity is managed at the lowest granularity, then detail and accuracy improve, but processing time and system complexity increases
Solution Approach 1:
The patent segments capacity management operations by granularity level. The scheduling data model operates at the lowest granularity (time slots) for detailed capacity tracking, while the planning data model operates at higher granularity for strategic allocation. This segmentation allows each model to process data at its appropriate detail level without unnecessary computational overhead from higher-level processing.
Solution Approach 2:
The patent performs preliminary aggregation of capacity data from the scheduling level to the planning level during the synchronization process. By pre-calculating and aggregating capacity information before it is needed for planning operations, the system reduces real-time processing requirements and minimizes delays in capacity management decisions.
3Productivity
If routing is flattened in planning data model, then simplicity and performance improve, but accuracy of capacity representation deteriorates
Solution Approach 1:
The patent merges the routing representations from both scheduling and planning data models into a unified resource capacity table. The scheduling model's detailed routing information (lowest granularity) is combined with the planning model's flattened routing structure, allowing the planning operations to benefit from simplified processing while maintaining accurate capacity representation through the integrated data structure.
Data Source
AI summary
Systems and techniques for unified resource capacity data management are described herein. An aggregate shift duration, a number of shifts, and an aggregate downtime duration within a specific calendar period may be determined, using a machine learning model, for each resource of a plurality of resources. A scheduling available capacity may be generated for the plurality of resources using the determined aggregate shift duration, the number of shifts, and the aggregate downtime duration. A planning available capacity may be generated using the scheduling available capacity and a retrieved efficiency factor. An optimal resource allocation may be calculated based on the planning available capacity and a customer demand. An indication that the set of training data was updated based on the optimal resource allocation may be received. The planning available capacity for each resource of the plurality of resources may be updated based on the updated set of training data.