Resource reservation amount determination method and device and storage medium

Abstract

An embodiment of the invention provides a resource reservation amount determination method and apparatus, and a storage medium, and can be applied to the technical field of big data processing. The method comprises the following steps: establishing an original resource transfer quantity sequence of a GM (1, 1) model based on an original resource transfer quantity in a historical time period; the original resource transfer quantity sequence comprises a plurality of original resource transfer quantities arranged according to a time sequence; performing accumulation processing on the original resource transfer quantity sequence to obtain an accumulated resource transfer quantity sequence; generating a background value sequence of the GM (1, 1) model according to the accumulated resource transfer quantity sequence by using an integral reconstruction method; the background value sequence represents an adjacent value generation sequence of the accumulated resource transfer quantity sequence; calculating parameters of the GM (1, 1) model according to the background value sequence; and determining a resource reservation amount sequence corresponding to the original resource transfer amount sequence according to the parameters of the GM (1, 1) model, thereby improving the determination efficiency of the resource reservation amount.

Description

technical field [0001] The embodiments of this specification relate to the technical field of big data processing, and in particular to a method, device, and storage medium for determining a reserved resource amount. Background technique [0002] Big data forecasting is the core application of big data. Big data forecasting extends the traditional meaning of "prediction" to "real-time measurement". The advantage of big data prediction is that it transforms a very difficult prediction problem into a relatively simple description problem, which is beyond the reach of traditional small data sets. From the perspective of forecasting, the results of big data forecasting are not only simple and objective conclusions for dealing with real business, but also can be used to help enterprises make business decisions. The collected data can also be planned to guide the development of greater consumption power . For example, for the expenditure data of the business scenario of overseas...

AI Technical Summary

Problems solved by technology

[0005] BP network has highly nonlinear and strong generalization ability, but it also has the defects of slow convergence speed, large number of iteration steps, easy to fall into local minimum and poor global search ability. A large number of samples are required for training before making predictions, and the dependence on computing power is strong, making the prediction of expenditure data less efficient

Images