Inventory material demand predicting method and device

Abstract

The invention discloses an inventory material demand predicting method and device. The method comprises: according to an initial investment plan, a planned investment volume of each project and an engineering attribute corresponding to each project are obtained; on the basis of the engineering attribute corresponding to each project, material subclasses included by each project are obtained, a preset correspondence relationship list of material subclasses, engineering attributes, and prediction models is searched, and a prediction model corresponding to each material subclass is obtained; the planned investment volumes are inputted into the prediction models corresponding to the material subclasses and calculation is carried out to obtain a predicted demand quantity of each material subclass in each project; and the predicted demand quantities of the material subclasses in different projects are added and calculation is carried out to obtain a total predicted demand quantity of each material subclass. According to the predicting method and device disclosed by the invention, the corresponding prediction models are constructed in advance for different material subclasses of each project, so that the efficiency and accuracy of inventory material prediction can be improved.

Description

technical field [0001] The invention relates to the technical field of material demand forecasting, in particular to a method and device for forecasting inventory material demand. Background technique [0002] For many large companies, units or departments, due to the large number and variety of materials required for large-scale projects, it is necessary to ensure that the materials are complete when the project really needs to start. On the one hand, this requires the relevant inventory department to be able to purchase and store the corresponding materials in advance, otherwise it will lead to a lot of time wasted on material procurement in the early stage of the project, delaying the progress and efficiency of the project. On the other hand, if the inventory materials are purchased too much or too early, it will take up a large capital cost, and if the purchase is too little or too late, it will affect the ability to guarantee the supply of materials for the project, and...

AI Technical Summary

Problems solved by technology

There are two main reasons for the inaccurate demand forecast caused by this method: first, the project to be constructed is uncertain when compiling the demand forecast, and the project management department often only has a preliminary investment plan or a comprehensive plan when submitting the agreement inventory demand forecast The project list after release is quite different from the actual projects to be implemented in the future

The demand for materials is closely related to the projects to be implemented, so it is difficult for the business department to make accurate forecasts without completely determining the projects to be constructed in the future

Second, the forecasting method needs to be improved. When the project management department forecasts the demand for the agreement inventory, the detailed engineering design has not yet been completed. The main forecasting method is that relevant professionals refer to historical data and put forward demand forecasting based on personal experience.

However, due to the lack of analysis of relevant influencing factors for material demand forecasting, the overall performance in forecasting accuracy will not be very good

At the same time, in view of the different real-time deadlines of some special inventories, for example, some distribution network agreement inventories of the State Grid have only been implemented for 3 years. At the same time, the procurement scope and material codes have also changed greatly during these periods, resulting in a small amount of data when actually making predictions. Reduced prediction accuracy

[0006] Taking the relevant material plan in the State Grid as an example, the material plan management business of the State Grid Electricity Rural Distribution Network is facing the following challenges: the project design information is lagging behind, and the material demand forecast is made completely based on the project design information, which cannot ensure the timeliness of on-site supply ;There are sometimes discrepancies between the investment plan information issued in advance at the beginning of the year and the actual project information, which increases the difficulty of material demand forecasting; the government investment in agricultural distribution network projects is increasing day by day, and the temporarily increased government projects interfere with the material demand forecasting business; The construction time is relatively concentrated, the demand declaration is relatively concentrated, some suppliers have insufficient production capacity, and the delivery cycle is long; the ERP system has insufficient support for the matching of materials in the same region and the same project, and manual matching operations are required, which is heavy workload, low efficiency, and easy. go wrong

[0007] Therefore, in the process of realizing the present invention, the inventor finds that the prediction accuracy of inventory materials in the prior art is not only low, but also the prediction efficiency is low

Images