Order dispatching method and device and storage medium

Abstract

The invention provides an order dispatching method and device, and a storage medium. The method comprises the steps of obtaining the remaining assessment time and available riders of each current unallocated order; taking the unallocated orders as nodes, clustering the nodes according to the categories of the nodes, filtering out the orders with only one node and the remaining assessment time greater than a preset value, and obtaining a final cluster of the orders; and obtaining a cost matrix based on the final cluster and the available riders, and updating the cost matrix after the class order corresponding to the minimum cost is delivered to the optimal rider selected by the cost matrix until all classes are traversed. According to the scheme of the invention, the hierarchical clustering algorithm based on geographic information is utilized to carry out order combination, and then the cost matrix is generated to select the optimal rider for delivery. The order sending result better conforms to the behavior habits of the rider, and the experience of the rider and the efficiency of executing the distribution task by the rider are improved. Moreover, the order dispatching objective function estimation is more accurate, and the KPI index of the dispatching system and the order delivery punctuality rate are improved.

Description

technical field [0001] The present invention relates to bill dispatching technology, in particular to a bill dispatching method, device and storage medium. Background technique [0002] The main features of food delivery are high concurrency and low latency. In the rider intelligent scheduling system, new orders need to be assigned to the most suitable riders in real time. Riders generally carry multiple orders. Before dispatching new orders, it is necessary to calculate the old orders and possible new orders on the current rider, and select the order with the least timeout and shortest distance to the corresponding rider according to the result of the cost matrix. Therefore, the definition of the cost matrix has an important impact on the accuracy of dispatching orders in the dispatching system. [0003] The existing order allocation method uses a greedy heuristic method, taking the sum of the total timeout duration and the total distance of all pickup and delivery tasks ...

AI Technical Summary

Problems solved by technology

[0004] In the actual distribution scenario, due to differences in the timeliness requirements of orders, there is a correlation between regional transportation capacity and time, and the actual distribution situation becomes complicated.

The existing greedy-based heuristic algorithm cannot accurately evaluate the cost of delivery, so it cannot provide an accurate basis for dispatching orders, resulting in inaccurate dispatch results

This will reduce the operating efficiency of the scheduling system, cause waste of rider capacity, and reduce user experience

The existing method of dispatching orders still has the problem of long calculation time, that is, the calculation time increases exponentially with the increase of task points in the route. If there are too many task points in the route, the calculation time will be very long, which will lead to a longer dispatch time

Images