In modern organizational settings, the problem of optimally assigning tasks to field workers represents a significant operational challenge.
In the absence of an appropriate scheduling system, task allocation is typically performed manually, which increases time and organizational workload and reduces the efficiency of resource utilization.
For this reason, we decided to develop a system for automatic task scheduling.
In this thesis, I will develop a system for automatic task scheduling among workers in the MightyFields Measurement Control Device environment.
The system will use machine learning methods to optimize task scheduling based on geographic coordinates, worker availability, and other parameters.
The web service implementation will use clustering algorithms and route optimization using external web APIs.
The system will enable mass task scheduling for the entire company or individual organizational units.
Results will be stored in a database and displayed in the user interface with map visualization.
User feedback from the pilot testing indicates satisfaction with the solution,
primarily due to reduced manual effort, improved transparency, and faster preparation of schedules.
Based on tests we conclude, the developed application meets the key functional requirements and enables more efficient task scheduling.
|
