Equal-Sized Location Clusters Using Farthest-Point Iteration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional clustering models often produce overlapping clusters, leading to improper allocation and inefficiencies in customer segmentation and distribution, such as delayed food delivery due to incorrect assignment of orders to delivery agents.
Innovation Solution
A method and system for creating clusters by determining a centroid and farthest point, calculating angular distances, and iteratively forming clusters to ensure an equal number of entities within each cluster, using a processor and programmed instructions to manage location data points.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional clustering models are used to group customers into clusters, then customer segmentation and distribution can be performed, but overlapping clusters are produced leading to improper allocation
Solution Approach 1:
The patent segments the clustering process into distinct phases: initial centroid formation, farthest point identification, and iterative cluster formation. This segmentation allows each phase to focus on specific aspects of cluster creation, ensuring that clusters are formed systematically without overlap while maintaining equal-sized groups for reliable allocation.
Solution Approach 2:
Instead of assigning points to clusters based on proximity to centroids (conventional approach), the patent inverts the logic by identifying farthest points from centroids and forming clusters around these farthest points. This inversion ensures that clusters are formed to cover the entire space without overlapping, as each cluster is deliberately constructed to include points that are farthest from existing cluster centers.
2Productivity
If conventional clustering models are used to assign orders to delivery agents, then distribution can be performed, but delivery time limits are exceeded due to improper allocation
Solution Approach 1:
The patent performs preliminary cluster formation with equal-sized, non-overlapping clusters before order assignment. By pre-establishing clear cluster boundaries and assigning delivery agents to specific clusters, the system ensures that when orders arrive, they can be immediately and correctly routed to the appropriate agent without delays caused by cluster overlaps or improper allocation.
3Area of stationary object
If clusters are formed to cover the entire area, then all location data points are included, but cluster sizes become unequal
Solution Approach 1:
The patent changes the parameter of cluster formation from arbitrary or density-based to a systematic approach based on farthest point distance. By using the distance metric and iteratively selecting farthest points, the algorithm ensures that each cluster receives an equal number of points while maintaining comprehensive coverage of the entire area. This parameter change transforms the cluster formation process to simultaneously achieve equal sizes and complete coverage.
Data Source
AI summary
A system and a method to create clusters in an area. The system comprises obtaining a plurality of location data points associated with a plurality of entities in an area. It may be noted that each location data point includes geographic coordinates. Further, the system comprises computing a range of location data points required in each cluster. Furthermore, the system comprises forming a farthest point cluster by determining a farthest location data point from a centroid based on an angular distance. It may be noted that the farthest point cluster comprises a set of location data points having a farthest distance lesser than a centroid distance. The system iteratively forms a new farthest point cluster by excluding the set of location data points present in the farthest point cluster from the plurality of location data points.