CN114239989A - Method, system, equipment and storage medium for calculating material demand plan - Google Patents

Method, system, equipment and storage medium for calculating material demand plan Download PDF

Info

Publication number
CN114239989A
CN114239989A CN202111600569.8A CN202111600569A CN114239989A CN 114239989 A CN114239989 A CN 114239989A CN 202111600569 A CN202111600569 A CN 202111600569A CN 114239989 A CN114239989 A CN 114239989A
Authority
CN
China
Prior art keywords
training
purchase
model
plan
demand
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202111600569.8A
Other languages
Chinese (zh)
Inventor
赵辉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Sichuan Qiruike Technology Co Ltd
Original Assignee
Sichuan Qiruike Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Sichuan Qiruike Technology Co Ltd filed Critical Sichuan Qiruike Technology Co Ltd
Priority to CN202111600569.8A priority Critical patent/CN114239989A/en
Publication of CN114239989A publication Critical patent/CN114239989A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/048—Activation functions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G06Q10/06315—Needs-based resource requirements planning or analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
    • G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/04—Manufacturing
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Abstract

The invention provides a method for calculating a material demand plan, which comprises the following steps: training a prediction model; acquiring a main production plan, and decomposing the main production plan into a plurality of material demand orders according to a bill of material (BOM); querying the warehouse system to calculate the net demand; predicting the predicted purchase lead of each material based on the prediction model; determining an actual purchase lead based on the required arrival date according to the predicted purchase lead; and determining the MRP plan of each material based on the actual purchase advance. The accuracy of the MRP calculation can be improved.

Description

Method, system, equipment and storage medium for calculating material demand plan
Technical Field
The invention relates to the technical field of manufacturing industry, in particular to a method, a system, equipment and a storage medium for calculating a material demand plan.
Background
Material Requirements Planning (MRP) refers to a Material planning management method for guiding the purchasing and production of an enterprise in the manufacturing industry, in which the enterprise decomposes products into Bill of materials (BOM) according to a structural relationship, each Material is used as a planning object, a product delivery date is used as a time reference, a list-placing time plan is inverted according to the purchasing lead of each Material, and a Material requirement plan is finally formulated.
In order to accurately calculate the MRP of the material demand plan, four elements of a main production plan, inventory information, a material list and purchase lead are needed. The main production plan refers to a demand list of products obtained according to sales orders or prediction, namely the demand of the products at a certain time point; the inventory information refers to the material surplus inventory condition of the current warehouse system of the enterprise; the bill of materials is a file describing the composition of the product and is used for decomposing the product requirements in the main production plan into material requirements; the purchase lead is the interval between the order placement and arrival time of each material from purchase. Only if the four elements are accurate, the MRP can be accurately made. When a material plan is formulated, the main production plan, the material list and the inventory information can be accurately obtained when the MRP is calculated, but the purchase lead needs to be estimated by personnel according to experience and is not easy to be accurately estimated, so that the accuracy of the purchase lead has great influence on the accuracy of the MRP.
In the prior art, the purchase advance is determined by purchasing personnel according to experience, and the computed MRP is inaccurate due to the experience difference of the personnel. Enterprises accumulate a great deal of valuable historical data in past purchasing activities, and the data can be fully used for predicting purchasing lead, but the data is not utilized in the prior art.
Disclosure of Invention
The invention aims to provide a method and a system for calculating a material demand plan. So as to solve the technical problems existing in the background technology.
In order to achieve the purpose, the invention adopts the following technical scheme:
a method for calculating a material demand plan, comprising:
training a prediction model;
acquiring a main production plan, and decomposing the main production plan into a plurality of material demand orders according to a bill of material (BOM);
querying the warehouse system to calculate the net demand;
predicting the predicted purchase lead of each material based on the prediction model;
determining an actual purchase lead based on the required arrival date according to the predicted purchase lead;
and determining the MRP plan of each material based on the actual purchase advance.
In some embodiments, the training a predictive model comprises:
acquiring historical data and preprocessing the historical data;
extracting data features based on the historical data;
generating a training set and a verification set based on the extracted data features;
setting network parameters and activation functions;
training an initial model based on the training set;
and verifying the trained initial model based on the verification set.
In some embodiments, the data characteristics include at least one of:
supplier code, material code, purchase price, purchase quantity, historical price first derivative.
In some embodiments, the criteria for training the predictive model are:
constructing a loss function according to the training set and the prediction result of the initial prediction model, and iteratively updating the parameters of the model based on the loss function; when the trained model meets the preset condition, finishing the training; wherein the preset condition is that the number of times of convergence or iteration of the loss function reaches a threshold value.
Meanwhile, the invention also discloses a calculation system of the material demand plan, which comprises the following components:
the training module is used for training the prediction model;
the decomposition module is used for training to obtain a main production plan and decomposing the main production plan into a plurality of material demand orders according to a bill of material (BOM);
the calculation module is used for inquiring the warehouse system to calculate the net demand;
the prediction module is used for predicting the predicted purchase advance of each material based on the prediction model;
the first determination module is used for determining the actual purchase advance based on the required arrival date according to the predicted purchase advance;
and the second determination module is used for determining the MRP plan of each material based on the actual purchase advance.
In some embodiments, the training module is further to:
acquiring historical data and preprocessing the historical data;
extracting data features based on the historical data;
generating a training set and a verification set based on the extracted data features;
setting network parameters and activation functions;
training an initial model based on the training set;
and verifying the trained initial model based on the verification set.
Meanwhile, the invention also discloses computer equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor realizes the method of any one of the preceding items when executing the computer program.
Meanwhile, the invention also discloses a computer-readable storage medium, wherein the storage medium stores computer instructions, and after the computer reads the computer instructions in the storage medium, the computer executes the method of any one of the preceding items.
Advantageous effects
Compared with the prior art, the invention has the following remarkable advantages:
by using the machine learning to analyze the historical data, the corresponding predicted purchase lead of each material in each main production order can be predicted, so that the purchase lead is more accurate, and the calculation of MRP is accurate.
Drawings
FIG. 1 is a schematic diagram of a computing system for material demand planning according to an embodiment;
fig. 2 is a schematic flow chart of a method for calculating a material demand plan according to the present embodiment;
fig. 3 is a schematic diagram of training of the prediction model according to the present embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
On the contrary, this application is intended to cover any alternatives, modifications, equivalents, and alternatives that may be included within the spirit and scope of the application as defined by the appended claims. Furthermore, in the following detailed description of the present application, certain specific details are set forth in order to provide a better understanding of the present application. It will be apparent to one skilled in the art that the present application may be practiced without these specific details.
A method for calculating a material demand plan according to an embodiment of the present application will be described in detail below with reference to fig. 1 to 3. It is to be noted that the following examples are only for explaining the present application and do not constitute a limitation to the present application.
The invention also discloses a computing system 100 for a material demand plan, comprising:
a training module 101 for training a prediction model;
the decomposition module 102 is used for training to obtain a main production plan and decomposing the main production plan into a plurality of material demand orders according to a bill of material (BOM);
a calculation module 103, configured to query the warehouse system to calculate a net demand;
the prediction module 104 is used for predicting the predicted purchase advance of each material based on the prediction model;
a first determining module 105, configured to determine an actual purchase advance based on the required arrival date according to the predicted purchase advance;
and a second determination module 106, configured to determine an MRP plan for each material based on the actual procurement lead.
In some embodiments, the training module 101 is further configured to:
acquiring historical data and preprocessing the historical data;
extracting data features based on the historical data;
generating a training set and a verification set based on the extracted data features;
setting network parameters and activation functions;
training an initial model based on the training set;
and verifying the trained initial model based on the verification set.
In some embodiments, the data characteristics include at least one of: supplier code, material code, purchase price, purchase quantity, historical price first derivative.
In some embodiments, the criteria for training the predictive model are: constructing a loss function according to the training set and the prediction result of the initial prediction model, and iteratively updating the parameters of the model based on the loss function; when the trained model meets the preset condition, finishing the training; wherein the preset condition is that the number of times of convergence or iteration of the loss function reaches a threshold value.
In some embodiments, the computing system 100 based on the material demand plan may be used to predict the advance of procurement for each material: preprocessing such as missing value filling, data unit unifying, price normalization and the like is carried out on historical data of an enterprise; selecting data characteristics, and dividing a data set into a training set and a verification set; setting parameters and an activation function of the neural network model, and training the neural network model by using a training set; and (4) using the verification set verification model, predicting the data samples in the verification set by using the trained model to obtain a prediction result, and calculating the mean square error. If the mean square error exceeds a set threshold, retraining is triggered. And finally, training a machine learning model for predicting the purchase lead. The purchase lead calculated by the method is more accurate than the purchase lead estimated by the purchasing personnel.
In some embodiments, the principles of application of the computing system 100 for material demand planning are: firstly, according to an obtained main production plan, the production plan comprises product information and products; decomposing the main production plan into material demands according to a bill of materials (BOM); acquiring real-time inventory information; predicting the purchase advance of each material by using the machine learning model trained in the first aspect; and (4) according to the purchase advance, the purchase order is inverted based on the required arrival date, and the MRP purchase ordering time is more accurate than that in the prior art. And finally, counting the consumption of the materials in the ordering time and the arrival time interval period, and finally obtaining the accurate MRP demand.
Fig. 2 illustrates a method for calculating a material demand plan according to the present invention, which includes:
s201, training a prediction model.
For example, a machine learning model for predicting purchase lead is trained, and purchase history data accumulated by enterprises is imported into the system of the invention to train the model.
In some embodiments, training the predictive model as shown in fig. 3 includes:
and S2011, acquiring and preprocessing historical data.
For example, tools such as numpy and pandas are used to preprocess the purchase history data, in this embodiment, each piece of purchase order data is preprocessed according to the following fields (supplier code, material code, purchase price, purchase quantity, first derivative of the history price, actual delivery cycle, and warehousing inspection qualification rate, and centofpass), and the missing value, the unified data unit, and the price normalization are filled.
S2012, extracting data characteristics based on the historical data. In some embodiments, the data characteristics include at least one of: supplier code, material code, purchase price, purchase quantity, historical price first derivative.
In some embodiments, the historical data is characterized by a supplier code supplierCode, a material code materialCode, a purchase price, a purchase quantity qualification, and a historical price first derivative prividerivative, and the output is characterized by an actual delivery cycle, i.e., a required purchase lead.
S2013, generating a training set and a verification set based on the extracted data features.
For example, the processed historical data is used as a data set, 80% of the data is used as a training set, and 20% is used as a validation set.
S2014, sets network parameters and activation functions.
For example, let the neural network include L layers, and the parameters of the k-th layer be denoted as Wk and bk. And (4) adopting sigmoid activation functions for each layer. Here, the output of the L-th layer (output layer) is a scalar.
S2015, training the initial model based on the training set. The neural network model can be trained using the training set.
And S2016, verifying the trained initial model based on the verification set.
For example, the trained model is used to predict the data samples in the validation set, obtain the prediction result, and calculate the mean square error. If the mean square error exceeds a set threshold, retraining is triggered. And obtaining a final training model. The method can obtain purchase lead ratio.
In some embodiments, the criteria for training the predictive model are:
constructing a loss function according to the training set and the prediction result of the initial prediction model, and iteratively updating the parameters of the model based on the loss function; when the trained model meets the preset condition, finishing the training; wherein the preset condition is that the number of times of convergence or iteration of the loss function reaches a threshold value.
Through the steps S2011-S2016, a machine learning model which can be used for predicting the material purchase advance is obtained, and the material purchase advance of the material can be predicted according to a supplier code supplierCode, a material code materialCode, a purchase price and a purchase quantity qualification.
S202, obtaining a main production plan, and decomposing the main production plan into a plurality of material demand orders according to a bill of materials (BOM).
For example, in some embodiments, based on obtaining a master production plan and decomposing the master production plan into material demand orders according to the bill of materials BOM as follows:
Figure BDA0003431578370000071
the calculation method is the same for each material pair, so the first row is taken as an example.
S203, inquiring the warehouse system to calculate the net demand.
For example, the query warehouse system calculates the net demand, obtains the current inventory of material a as N, and then the net demand this time is M-N.
And S204, predicting the predicted purchase advance of each material based on the prediction model.
For example, a demand order (including a supplier code S1, a material code a1, a purchase price of 1, and a purchase quantity of 10) is transmitted to the model trained in the first step, and the purchase lead of this time is predicted by using the material characteristic information in the demand order, so that the purchase lead is obtained as X days.
And S205, determining the actual purchase advance based on the required arrival date according to the predicted purchase advance.
For example, according to the purchase advance, the purchase is inverted based on the arrival date, and the purchase ordering time is yyy-mm-dd minus the predicted purchase advance. The MRP ordering time calculated in this way is more accurate than that obtained by the prior art according to the experience of people.
And S206, determining the MRP plan of each material based on the actual purchase advance.
For example, according to the time period from order placing time to required delivery time counted by the production plan, the consumption is P, and the MRP demand of each material is finally calculated to be M-N + P. The prior art does not consider the consumption of the inventory in the purchasing process, and the addition of the step can make the MRP demand quantity more accurate.
The MRP required quantity and the ordering time of the material A are calculated through S201 to S206 and are shown in the following table:
Figure BDA0003431578370000081
in summary, the technical scheme of the invention provides a method for calculating the MRP material requirement in the manufacturing industry, and the system uses machine learning to analyze historical data and predict the purchase advance, so that the calculation of the MRP is more accurate.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.

Claims (10)

1. A method for calculating a material demand plan, comprising:
training a prediction model;
acquiring a main production plan, and decomposing the main production plan into a plurality of material demand orders according to a bill of material (BOM);
querying the warehouse system to calculate the net demand;
predicting the predicted purchase lead of each material based on the prediction model;
determining an actual purchase lead based on the required arrival date according to the predicted purchase lead;
and determining the MRP plan of each material based on the actual purchase advance.
2. The method of claim 1, wherein the step of calculating the material demand plan,
the training of the predictive model includes:
acquiring historical data and preprocessing the historical data;
extracting data features based on the historical data;
generating a training set and a verification set based on the extracted data features;
setting network parameters and activation functions;
training an initial model based on the training set;
and verifying the trained initial model based on the verification set.
3. The method of claim 2, wherein the data characteristics include at least one of:
supplier code, material code, purchase price, purchase quantity, historical price first derivative.
4. The method as claimed in claim 2, wherein the criteria for training the predictive model are:
constructing a loss function according to the training set and the prediction result of the initial prediction model, and iteratively updating the parameters of the model based on the loss function; when the trained model meets the preset condition, finishing the training; wherein the preset condition is that the number of times of convergence or iteration of the loss function reaches a threshold value.
5. A material demand plan computing system, comprising:
the training module is used for training the prediction model;
the decomposition module is used for training to obtain a main production plan and decomposing the main production plan into a plurality of material demand orders according to a bill of material (BOM);
the calculation module is used for inquiring the warehouse system to calculate the net demand;
the prediction module is used for predicting the predicted purchase advance of each material based on the prediction model;
the first determination module is used for determining the actual purchase advance based on the required arrival date according to the predicted purchase advance;
and the second determination module is used for determining the MRP plan of each material based on the actual purchase advance.
6. The material demand plan computing system of claim 1,
the training module is further to:
acquiring historical data and preprocessing the historical data;
extracting data features based on the historical data;
generating a training set and a verification set based on the extracted data features;
setting network parameters and activation functions;
training an initial model based on the training set;
and verifying the trained initial model based on the verification set.
7. The material demand plan computing system of claim 6, wherein the data characteristics include at least one of:
supplier code, material code, purchase price, purchase quantity, historical price first derivative.
8. The computing system of claim 6, wherein the criteria for training the predictive model are:
constructing a loss function according to the training set and the prediction result of the initial prediction model, and iteratively updating the parameters of the model based on the loss function; when the trained model meets the preset condition, finishing the training; wherein the preset condition is that the number of times of convergence or iteration of the loss function reaches a threshold value.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1-4 when executing the computer program.
10. A computer-readable storage medium storing computer instructions, wherein when the computer instructions in the storage medium are read by a computer, the computer performs the method of any one of claims 1-4.
CN202111600569.8A 2021-12-24 2021-12-24 Method, system, equipment and storage medium for calculating material demand plan Pending CN114239989A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111600569.8A CN114239989A (en) 2021-12-24 2021-12-24 Method, system, equipment and storage medium for calculating material demand plan

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111600569.8A CN114239989A (en) 2021-12-24 2021-12-24 Method, system, equipment and storage medium for calculating material demand plan

Publications (1)

Publication Number Publication Date
CN114239989A true CN114239989A (en) 2022-03-25

Family

ID=80762737

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111600569.8A Pending CN114239989A (en) 2021-12-24 2021-12-24 Method, system, equipment and storage medium for calculating material demand plan

Country Status (1)

Country Link
CN (1) CN114239989A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117035339A (en) * 2023-08-18 2023-11-10 天津大学 Method and device for calculating material demand planning problem in enterprise resource planning

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117035339A (en) * 2023-08-18 2023-11-10 天津大学 Method and device for calculating material demand planning problem in enterprise resource planning

Similar Documents

Publication Publication Date Title
Keller et al. Multinational enterprises, international trade, and productivity growth: firm-level evidence from the United States
Boute et al. Dual sourcing and smoothing under nonstationary demand time series: Reshoring with SpeedFactories
CN107563705A (en) Household electrical appliances product safety stock and the system and method ordered goods again are analyzed using big data
CN108733003B (en) Method and system for predicting working hours of rotary part working procedures based on kmeans clustering algorithm
CN108805623B (en) Supply prediction method for fast-selling products
Schuh et al. Methodology for the evaluation of forecast reliability of production planning systems
CN110689190A (en) Power grid load prediction method and device and related equipment
Hur et al. A study on the man-hour prediction system for shipbuilding
CN112381303A (en) Task index data prediction method and system
Dyvak et al. Modeling of dynamics of the company’s share in the solid fuel market
CN113420902A (en) Component prediction model training method, component prediction method and related equipment
CN114239989A (en) Method, system, equipment and storage medium for calculating material demand plan
CN115409563A (en) Multi-factor-influenced agricultural equipment inventory demand prediction method
Mathew et al. Demand forecasting for economic order quantity in inventory management
JP5831363B2 (en) Manufacturing lead time prediction device, manufacturing lead time prediction method, and computer program
CN112330246A (en) Order summarizing method and device, computer equipment and storage medium
CN115081961A (en) Logistics transport capacity intelligent dispatching method based on big data
CN115685912A (en) Manufacturing enterprise production and logistics collaborative optimization scheduling method and system based on big data
CN110033113A (en) The learning method of information processing system and information processing system
Hallman A comparative study on Linear Regression and Neural Networks for estimating order quantities of powder blends
CN115146938A (en) Performance assessment method, device, equipment and storage medium
Huskova et al. Speeding up past stock movement simulation in sporadic demand inventory control
JP2001243401A (en) Order receipt prediction system
CN101714225A (en) Method and device for calculating product cost
Rizki et al. Supply and Demand Analysis by using Comparison of Forecasting Method in Motorcycles Tires Manufacturer

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination