Order allocation method and device

Abstract

The invention discloses an order allocation method and device. The method comprises the steps: firstly training an adjustment model, and then enabling the trained adjustment model to be used for orderallocation; when the adjustment model is trained, inputting the obtained information of the historical orders and the determined information of the virtual service provider into the adjustment modelto be trained to obtain a grading threshold, allocating the historical orders to the virtual service provider according to the obtained grading threshold, and then applying the trained adjustment model to allocation of the current orders. According to the order allocation method, when the current order is allocated, the adjustment model outputs the appropriate grading threshold according to the information of the current order and the information of the actual service provider, so that the problem that the grading threshold is fixed in the prior art is solved; therefore, the effect of reasonably distributing the order to the actual service provider according to the output grading threshold is achieved.

Description

technical field [0001] The present application relates to the technical field of intelligent distribution, in particular to a method and device for order distribution. Background technique [0002] With the continuous exploration of "Internet +" applications, the Online To Offline (O2O) model has been widely used. [0003] In the O2O model, a common practice is to assign the order to the service provider after the user places the order, and the service provider provides the corresponding order service after receiving the order. Generally speaking, orders can be divided into different levels according to different standards. For example, according to the relationship between the order amount and the preset grading threshold, orders can be divided into high-value orders and general orders. Correspondingly, service providers It is also divided into advanced service providers and ordinary service providers. Therefore, when allocating orders to service providers, high-value ord...

AI Technical Summary

Problems solved by technology

[0005] However, when the number of high-value orders does not match the number of high-level service providers, for example, the number of high-value orders to be allocated is too large, the number of high-level service providers is small, and the number of orders received by high-level service providers is already saturated , because the above-mentioned preset grading thresholds in the prior art are fixed, the high-value orders to be allocated cannot be allocated to ordinary service providers, resulting in the high-value orders to be allocated timeout and unmanned processing, etc., thus The problem of unreasonable order distribution occurs

Images