Flow prediction multi-task model generation method, scheduling method, device and equipment

Abstract

The embodiment of the invention discloses a flow quantity prediction multi-task model generation method, a scheduling method, a device and equipment. A specific embodiment of the method comprises the steps of obtaining a historical order information set and a historical value reduction information set of a target article in a target historical time period; based on each order date and a historical value reduction information set included in the historical order information set, performing feature processing on the historical order information set and the historical value reduction information set to obtain a processed historical order information set as a sample historical order information set; and generating a flow prediction multi-task model according to a preset loss function and each value reduction flow feature, non-value reduction flow feature and value reduction feature included in the sample historical order information set. According to the embodiment, the accuracy of the flow volume prediction result is improved, and the waste of transportation resources is reduced.

Description

technical field [0001] The embodiments of the present disclosure relate to the field of computer technology, and in particular, to a method for generating a multi-task model for traffic forecasting, a scheduling method, a device, and a device. Background technique [0002] The value reduction is to reduce the value that the user needs to pay when the item is circulated, so as to achieve the preset goal (for example, to increase the circulation of the item). At present, before the value reduction of items, the commonly used method of forecasting the circulation volume is: replace the baseline forecast circulation volume corresponding to the value reduction time point with the circulation volume of the value of the predicted payment after the value reduction. [0003] However, when the above-mentioned method is used to predict the circulation volume, there are often the following technical problems: only the value of the paid value has been reduced by the value of the circulat...

AI Technical Summary

Problems solved by technology

[0003] However, when the above-mentioned method is used to predict the circulation volume, there are often the following technical problems: only the value of the paid value has been reduced by the value of the circulation volume, and it is impossible to obtain the value of the value reduction circulation during the value reduction period and the value affected by the value reduction. Non-value-reduced circulation volume, and the influence of the period before and after the value reduction period on the circulation volume cannot be considered, resulting in low accuracy of the forecast results of the circulation volume, which in turn leads to more times that the number of items dispatched according to the forecast results cannot meet the demand. More items need to be dispatched, resulting in waste of transportation resources

Images