Intelligent replenishment method, system and device based on end-to-end learning, and storage medium

A replenishment method and replenishment system technology, applied in the fields of systems and devices, intelligent replenishment methods, and storage media, can solve the problem of affecting the decision-making of the optimal recommended replenishment quantity, insufficient accuracy of sales forecast, and ignoring the space for optimization and other issues to achieve the effect of improving data utilization, improving algorithm efficiency, and reducing replenishment decision-making errors
CN110348635AInactive Publication Date: 2019-10-18创新奇智(成都)科技有限公司
5 Cites 8 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
创新奇智(成都)科技有限公司
Publication Date
2019-10-18
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses an intelligent replenishment method based on end-to-end learning. The method comprises the following steps: S1, acquiring data required by a mathematical model; S2, generatingsales features related to the sales volume according to the obtained data; S3, taking the characteristics predicted by the sales volume as original input values; establishing a mathematical model according to the total operation cost; the total operation cost being used as a loss function; solving and directly outputting suggest replenishment amount. Different from reduction of manual preprocessing and follow-up processing, direct output from original input to final output and direct output of results after replenishment by taking sales prediction features as original input values, end-to-endalgorithm learning is realized, so that the algorithm efficiency is improved, and the optimization space is expanded. The invention further provides a storage medium. The invention further provides anintelligent replenishment system. The invention further provides an intelligent replenishment device.
Need to check novelty before this filing date? Find Prior Art

Description

【Technical field】

[0001] The present invention relates to the field of data prediction, in particular to an intelligent replenishment method, storage medium, system and device based on end-to-end learning. 【Background technique】

[0002] Forecasting is an important part of the operation process, by studying the past, understanding the present, and predicting the future, so as to maximize the benefits.

[0003] Replenishment forecasting is one of them, and reasonable arrangements are made through supplementary testing; in the quantitative forecasting technology related to replenishment, goods are purchased and replenished by intelligently predicting sales volume, but the existing intelligent replenishment The delivery method is divided into two modules for implementation, generally sales forecast and replenishment decision. Sales forecast and replenishment decision are two sequential independent modules. The sales forecast result is input into the replenishment module, and th...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More