CN109784806A - Supply chain control method, system and storage medium - Google Patents
Supply chain control method, system and storage medium Download PDFInfo
- Publication number
- CN109784806A CN109784806A CN201811609450.5A CN201811609450A CN109784806A CN 109784806 A CN109784806 A CN 109784806A CN 201811609450 A CN201811609450 A CN 201811609450A CN 109784806 A CN109784806 A CN 109784806A
- Authority
- CN
- China
- Prior art keywords
- source data
- supplier
- information
- inventory
- model
- 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.)
- Granted
Links
Abstract
The invention discloses a kind of supply chain control method, system and storage mediums, and wherein method includes: to obtain sales forecast data using Sale Forecasting Model and based on sale source data information；Supplier's comprehensive score information is obtained using supplier's assessment models and based on supplier's source data information；Conducive to purchasing forecast model and based on buying source data information, sales forecast data and supplier's comprehensive score information acquisition purchasing forecast result；Finished product and raw materials inventory prediction result are obtained using inventory control model and based on inventory's source data information, purchasing forecast result, sale source data information；Supply chain control method, system and storage medium of the invention, can promote supply chain overall operation efficiency, can have directly directiveness to finished product and raw materials inventory control；The probability that other links are abnormal, and timely early warning can be predicted after some is abnormal event, reduce supply chain operating cost, the operational efficiency of General Promotion enterprise.
Description
Technical field
The present invention relates to field of computer technology more particularly to a kind of supply chain control methods, system and storage medium.
Background technique
The users such as supply chain system Facing to Manufacturing quotient, supplier, dealer, retailer, logistics company, terminal user, from
The links such as sale, buying, supplier, inventory, logistics realize the full chain management of the manufacturing side to consumption terminal, optimize corporate resources
Configuration promotes the efficient collaboration of industrial chain upstream and downstream.Current supply chain management depends on ERP system, to sales data,
Procurement data, inventory data and creation data are managed, and are substantially able to satisfy the day-to-day operations demand of enterprise.But for
Large-scale production enterprise, traditional business management software such as ERP system is in Supply Chain Planner formulation, supplier management and inventory's week
Rate of rotation raising etc. has following weakness: under traditional pushing-type production model, production plan is mainly upper 1 year according to enterprise
The production scale of degree and the business indicator of current year enterprise are formulated, and experience professional more abundant are depended on, without big
The data analysis of amount is as support；With the transformation of market development and production method, " pushing-type+pull-type " becomes supply chain mainstream mould
Formula, sales forecast becomes the core of plan, but the business management softwares such as traditional ERP are unable to satisfy and change demand etc..
Summary of the invention
In view of this, the invention solves a technical problem be to provide a kind of supply chain control method, system and
Storage medium.
According to an aspect of the present invention, a kind of supply chain control method is provided, comprising: sale source data information is obtained,
Sales forecast data are obtained using Sale Forecasting Model and based on the sale source data information；Obtain supplier's source data letter
Breath obtains supplier's comprehensive score information using supplier's assessment models and based on supplier's source data information；It is adopted
Purchase source data information, be conducive to purchasing forecast model and based on the buying source data information, the sales forecast data and
Supplier's comprehensive score information acquisition purchasing forecast result；Inventory's source data information is obtained, simultaneously using inventory control model
Finished product and raw material store are obtained based on inventory's source data information, the purchasing forecast result, the sale source data information
Deposit prediction result.
Optionally, described to obtain sales forecast data using Sale Forecasting Model and based on the sale source data information
It include: to obtain historical sales specified number evidence, and establish historical sales volume data sequence；It will be in the historical sales volume data sequence
Historical sales specified number obtains cumulative data sequence and establishes linear first-order differential side based on this cumulative data sequence according to adding up
Journey；Sliding-model control is carried out to the linear first-order differential equation, and parameter vector is obtained using least square method；Based on described
Linear first-order differential equation and the parameter vector construct to obtain grey forecasting model, as the Sale Forecasting Model；It is based on
The confidence interval of one-variable linear regression prediction model estimation sales volume；Using confidence interval and according to the grey forecasting model into
Row prediction, obtains the sales forecast data.
Optionally, acquisition supplier source data information using supplier's assessment models and is based on the supplier source
The comprehensive score information that data information obtains supplier comprises determining that vendors' evaluating index；It establishes and the evaluation index
Corresponding evaluate collection, and determine according to the evaluation index and the evaluate collection subordinated-degree matrix of the evaluation index；It is logical
It crosses analytic hierarchy process (AHP) and determines the weighted value of each evaluation index based on supplier's source data information, be subordinate to according to described
It spends matrix and the weighted value generates the judge vector of supplier；Synthesis is calculated according to evaluate collection described in the judge vector sum to comment
Valence index determines the comprehensive score of the supplier based on the comprehensive evaluation index and the evaluate collection；Wherein, institute's commentary
Valence index includes: price factor, service ability, delivery cycle, supply of material progress, research and development ability, qualitative factor.
Optionally, described to be conducive to purchasing forecast model and be based on the buying source data information, the sales forecast number
Accordingly and supplier's comprehensive score information acquisition purchasing forecast result includes: based on buying source historical data information, sale
Historical data, supplier's history comprehensive score information and corresponding buying historical information generate training sample；Use deep learning
Method is simultaneously trained preset deep learning model based on the training sample, obtains supplier's assessment models；It will be described
Preset deep learning model modification is supplier's assessment models, by by the buying source data information, the sale
Supplier's assessment models described in volume prediction data and supplier's comprehensive score information input, obtain the purchasing forecast knot
Fruit；Wherein, the buying source data information includes: BOM data, the scrappage of product, practical production capacity, physical holding of stock information, supplies
Answer period, contract information, product supply progress；The purchasing forecast result includes: buying executive mode, buying hour, supply
Quotient's information.
Optionally, it is described using inventory control model and based on inventory's source data information, the purchasing forecast result,
The sale source data information obtains finished product and raw materials inventory prediction result includes: to obtain inventory's source data, sale, buying
Historical data, and obtain storehouse storage space information and finished product and raw materials inventory historical information；By the historical data, described
Storehouse storage space information, the finished product and raw materials inventory historical information are instructed as training data using machine learning algorithm
Get neural network model；Inventory's source data information, the purchasing forecast result, the sale source data information is defeated
Enter to trained neural network model, exports the finished product and raw materials inventory prediction result；Wherein, inventory's source data
It include: on-hand inventory, delivery cycle, in way order, production cycle, consumption of raw materials information；The finished product and raw materials inventory are pre-
Surveying result includes: finished product and raw materials inventory information, the plan of replenishing.
Optionally, using bayesian algorithm, abnormal and other source datas is occurred according to source data and the item between exception occur
Part probability Estimation and prior probability training Bayes classifier；When determining that source data occurs abnormal, pass through what is obtained after training
Bayes classifier carries out risk profile to there is abnormal source data, and other abnormal source datas occurs in prediction；Based on described
Abnormal other source datas acquisition occur correspondingly prevents risk program.Wherein, the source data includes: sale source data, adopts
Purchase source data, supplier's source data, inventory's source data.
According to another aspect of the present invention, a kind of supply chain control system is provided, comprising: sales forecast control module is used
Source data information is sold in obtaining, obtains sales forecast number using Sale Forecasting Model and based on the sale source data information
According to；Supplier's evaluation module using supplier's assessment models and is based on the supplier for obtaining supplier's source data information
Source data information obtains supplier's comprehensive score information；Purchasing forecast module is conducive to buying for obtaining buying source data information
Prediction model is simultaneously based on the buying source data information, the sales forecast data and supplier's comprehensive score information
Obtain purchasing forecast result；Inventory management module using inventory control model and is based on institute for obtaining inventory's source data information
It states inventory's source data information, the purchasing forecast result, the sale source data information and obtains finished product and raw materials inventory prediction
As a result.
Optionally, the sales forecast control module for obtaining historical sales specified number evidence, and establishes historical sales specified number
According to sequence；By the historical sales specified number in the historical sales volume data sequence according to adding up, cumulative data sequence is obtained simultaneously
Linear first-order differential equation is established based on this cumulative data sequence；Sliding-model control is carried out to the linear first-order differential equation,
And parameter vector is obtained using least square method；It constructs to obtain ash based on the linear first-order differential equation and the parameter vector
Color prediction model, as the Sale Forecasting Model；Confidence interval based on one-variable linear regression prediction model estimation sales volume；
It is predicted using confidence interval and according to the grey forecasting model, obtains the sales forecast data.
Optionally, supplier's evaluation module, for determining vendors' evaluating index；It establishes and the evaluation index
Corresponding evaluate collection, and determine according to the evaluation index and the evaluate collection subordinated-degree matrix of the evaluation index；It is logical
It crosses analytic hierarchy process (AHP) and determines the weighted value of each evaluation index based on supplier's source data information, be subordinate to according to described
It spends matrix and the weighted value generates the judge vector of supplier；Synthesis is calculated according to evaluate collection described in the judge vector sum to comment
Valence index determines the comprehensive score of the supplier based on the comprehensive evaluation index and the evaluate collection；Wherein, institute's commentary
Valence index includes: price factor, service ability, delivery cycle, supply of material progress, research and development ability, qualitative factor.
Optionally, the purchasing forecast module, for based on buying source historical data information, sales histories data, supply
Quotient's history comprehensive score information and corresponding buying historical information generate training sample；Using deep learning method and based on described
Training sample is trained preset deep learning model, obtains supplier's assessment models；By the preset deep learning
Model modification is supplier's assessment models, by by the buying source data information, the sales forecast data and institute
Supplier's assessment models described in supplier's comprehensive score information input are stated, the purchasing forecast result is obtained；Wherein, the buying
Source data information include: BOM data, the scrappage of product, practical production capacity, physical holding of stock information, supply cycle, contract information,
Product supply progress；The purchasing forecast result includes: buying executive mode, buying hour, supplier information.
Optionally, the inventory management module for obtaining the historical data of inventory's source data, sale, buying, and obtains
Storehouse storage space information and finished product and raw materials inventory historical information；The historical data, the storehouse memory space are believed
Breath, the finished product and raw materials inventory historical information obtain neural network as training data, using machine learning algorithm training
Model；Inventory's source data information, the purchasing forecast result, the sale source data information are input to trained mind
Through network model, the finished product and raw materials inventory prediction result are exported；Wherein, inventory's source data include: on-hand inventory,
Delivery cycle, in way order, production cycle, consumption of raw materials information；The finished product and raw materials inventory prediction result include: finished product
With raw materials inventory information, the plan of replenishing.
Optionally, there is exception and other according to source data for using bayesian algorithm in supply chain dynamic optimization module
There is the estimation of the conditional probability between exception and prior probability training Bayes classifier in source data；When determine source data occur it is different
Chang Shi carries out risk profile to there is abnormal source data by the Bayes classifier obtained after training, and prediction occurs abnormal
Other source datas；Risk program is correspondingly prevented based on other source datas acquisition for exception occur.Wherein, the source number
According to include: sale source data, buying source data, supplier's source data, inventory's source data.
According to another aspect of the invention, a kind of supply chain control system is provided, comprising: memory；And it is coupled to institute
The processor of memory is stated, the processor is configured to the instruction based on storage in the memory, executes as described above
Method.
In accordance with a further aspect of the present invention, a kind of computer readable storage medium is provided, computer program is stored thereon with
The step of instruction, which realizes method as described above when being executed by one or more processors.
Supply chain control method, system and storage medium of the invention introduces under the mode of traditional SCM
The technologies such as big data, artificial intelligence and machine learning, it is each from requirement forecasting, plan, supplier management and stock control etc.
Link proposes algorithm model, and correlation to each member and relevance impact analysis provide dynamic optimization algorithm model, is promoted
Supply chain overall operation efficiency can have directly directiveness to finished product and raw materials inventory control；Go out from system engineering angle
Hair considers the correlation in supply chain between each link, and it is different can to predict that other links occur after some is abnormal event
Normal probability, and timely early warning reduce supply chain operating cost；The launch period can be shortened, the fortune of General Promotion enterprise
Line efficiency.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention without any creative labor, may be used also for those of ordinary skill in the art
To obtain other drawings based on these drawings.
Fig. 1 is the flow diagram of one embodiment of supply chain control method of the invention；
Fig. 2A is each schematic diagram using link relevance of one embodiment of supply chain control method of the invention；
Fig. 2 B is the process signal predicted sales volume of one embodiment of supply chain control method of the invention
Figure；
Fig. 3 A is the process signal evaluated supplier of one embodiment of supply chain control method of the invention
Figure；
Fig. 3 B is that supplier selects appraisement system schematic diagram；
Fig. 3 C is the schematic diagram of analytic hierarchy process (AHP)；
Fig. 4 is the flow diagram predicted buying of one embodiment of supply chain control method of the invention；
Fig. 5 is the flow diagram predicted inventory of one embodiment of supply chain control method of the invention；
Fig. 6 is the flow diagram of the progress dynamic optimization of one embodiment of supply chain control method of the invention；
Fig. 7 is the composition schematic diagram of one embodiment of supply chain control system of the invention；
Fig. 8 is the composition schematic diagram of another embodiment of supply chain control system of the invention.
Specific embodiment
Carry out the various exemplary embodiments of detailed description of the present invention now with reference to attached drawing.It should also be noted that unless in addition having
Body explanation, the unlimited system of component and the positioned opposite of step, numerical expression and the numerical value otherwise illustrated in these embodiments is originally
The range of invention.
Simultaneously, it should be appreciated that for ease of description, the size of various pieces shown in attached drawing is not according to reality
Proportionate relationship draw.
Be to the description only actually of at least one exemplary embodiment below it is illustrative, never as to the present invention
And its application or any restrictions used.
Technology, method and apparatus known to person of ordinary skill in the relevant may be not discussed in detail, but suitable
In the case of, technology, method and apparatus should be considered as part of specification.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, then in subsequent attached drawing does not need that it is further discussed.
Fig. 1 is the flow diagram of one embodiment of supply chain control method of the invention, as shown in Figure 1:
Step 101, sale source data information is obtained, is sold using Sale Forecasting Model and based on sale source data information
Sell volume prediction data.Sale source data may include trade order, behavioral data, historical data, marketing strategy, user's portrait
Deng, sales forecast data can for per year, season, the sales volume that the moon is unit prediction.
Step 102, supplier's source data information is obtained, using supplier's assessment models and is based on supplier's source data information
Obtain supplier's comprehensive score information.Supplier's source data information may include evaluation information, information on services, progress msg, valence
Lattice, delivery cycle etc..
Step 103, buying source data information is obtained, is conducive to purchasing forecast model and based on buying source data information, sale
Volume prediction data and supplier's comprehensive score information acquisition purchasing forecast result.Purchasing source data can believe for contract, inventory
Breath, delivery cycle etc..Purchasing forecast result can be procurement value, material variety, procurement method etc..
Step 104, inventory's source data information is obtained, using inventory control model and based on inventory's source data information, buying
Prediction result, sale source data information obtain finished product and raw materials inventory prediction result.Inventory's source data information may include existing
In stock, delivery cycle, in way order numbers, monthly quantity consumed, production cycle etc..Finished product and raw materials inventory prediction result packet
Include Replenishment Policy, inventory planning etc..
In one embodiment, plan is that supply chain controls most important link, affects the resource of each link of supply chain
Configuration, is the primary factor of supply chain optimization.Supply Chain Planner includes marketing plan, production plan, supply and demand plan and buying meter
Draw etc., under the new supply chain mode of " pushing-type+pull-type ", marketing plan is the planned source of institute, and is planned dependent on pre-
It surveys.Supply chain control method of the invention can carry out accurately sales forecast by gray level model, in conjunction with each data source etc.
Procurement plan is formulated, realizes that resource is made rational planning for.
, supplier huge for large enterprise's Supplier Number, which selects to lack effective data, and information supports etc. asks
Topic, supply chain control method of the invention are capable of providing flexibly configurable supplier's assessment models, are classified to supplier
Effective management of classification improves the preferred efficiency of supplier, copes with the bursting problem of supply network.Supply chain controlling party of the invention
Method considers that the correlation in supply chain between member, and some basic member are abnormal thing from system engineering angle
After part, the probability that other members are abnormal, and timely early warning, reduce supply chain operating cost.
As shown in Figure 2 A, supply chain control method of the invention for large enterprise supply chain be marketing orientation, buying,
Supplier, inventory, each member of logistics respectively propose to calculate from prediction, plan, supplier's assessment, stock control etc. using link
Method model, and correlation to each member and relevance impact analysis provide dynamic optimization algorithm model, and it is whole to promote supply chain
Operational efficiency.
Prediction class model is divided into Sale Forecasting Model and purchasing forecast model, supports to the efficient integrated of multi-source heterogeneous data
With processing.A variety of data acquisition modes such as supporting industry terminal, batch, streaming, log, support Various types of data ETL (extract,
Conversion, load) process, support multiple-task scheduling mode, to meet different data processing needs, and can be according to enterprise
Demand Quick Extended.
Gray zone Sale Forecasting Model is established in sales forecast for product, will affect sale factor (such as time because
Element) it is included in gray system, it handles sales volume as ash colo(u)r specification and brings into prediction model and make inferences and prove, and from just
Really it is worth real-time big data analysis system and the realization of supply chain related tool that inclusive and section radius angle verifies the model
Technical solution validity.
The gray zone sales forecast of interval number form be can use as a result, considering in actual scene due to different shaped
The scrappage of number product is different, and same material makes for the loss difference in the consumption error or production of product type not of the same race
With the improvement BOM data structure of range format, and by sales forecast be converted into purchasing forecast process Real-time inventory restraint condition,
Practical capacity constraints, remaining capacity constraints, plan production capacity, occupation of capital limitation are converted into the constraint condition with interval number, thus
Sales forecast is changed into interval number optimization problem to the association conversion process of purchasing forecast.
By the angle from section possibility degree and inverted constraint, the optimization to the uncertain transmitting of interval number is realized, and pass through
Predict that the angle of stability and forecasting accuracy verifies conversion of the section sales forecast to purchasing forecast.It is finally excellent by not knowing
On the basis of the gray zone interaction prediction of change, using fiducial inference method, requirement forecasting situation and demand history are comprehensively considered
Information is recorded, the method for inventory control under the demand input condition of section is used.Supply chain control method of the invention, utilizes association
Prediction result verifies the effective of the method for inventory control, and then verifies from sales forecast to purchasing forecast, arrives storage controlling again
The validity and feasibility of interaction prediction model.
In one embodiment, sales forecast data are obtained using Sale Forecasting Model and based on sale source data information
It can be there are many method.Fig. 2 B is the stream predicted sales volume of one embodiment of supply chain control method of the invention
Journey schematic diagram, as shown in Figure 2 B:
Step 201, historical sales specified number evidence is obtained, and establishes historical sales volume data sequence.
Step 202, the historical sales specified number in historical sales volume data sequence is obtained into cumulative data sequence according to adding up
It arranges and is based on this cumulative data sequence and establish linear first-order differential equation.
Step 203, to linear first-order differential equation carry out sliding-model control, and using least square method obtain parameter to
Amount.
Step 204, it constructs to obtain grey forecasting model based on linear first-order differential equation and parameter vector, it is pre- as sale
Survey model.
Step 205, the confidence interval based on one-variable linear regression prediction model estimation sales volume, by combining unitary linear
Regressive prediction model and grey forecasting model are combined prediction, obtain sales forecast data.It is pre- in conjunction with one-variable linear regression
Surveying model and being combined prediction with grey forecasting model can be existing a variety of methods.
Sale Forecasting Model can be using multiple linear regression model, G (1, N) gray model, three kinds of BP neural network calculations
Method model.After three prediction model training terminate, system can check training result mean square error (MSE) automatically, work as MSE
It is worth smaller, then prediction model accuracy is higher, and prediction effect is better, recommends optimal algorithm automatically.
For example, Sale Forecasting Model uses grey forecasting model.Gray prediction is a kind of
The method that system is predicted.Gray prediction is associated point by the different degree of development trend between identification system factor
Analysis, and generation processing is carried out to initial data and carrys out the rule that searching system changes, the data sequence for having stronger regularity is generated, so
After establish corresponding Differential Equation Model, to predict the situation of things future developing trend.It is observed anti-with even time interval
It should predict a series of quantitative values construction grey forecasting model of characteristics of objects, the characteristic quantity at the prediction following a certain moment, or reach
The time of a certain characteristic quantity.One-variable linear regression prediction refers to that the scatter plot of two pairs of variable datas shows trends of straight line
When, using least square method, find empirical equation between the two, i.e. one-variable linear regression prediction model.According to independent variable
Variation, to estimate the prediction technique of dependent variable variation.
Requirement to data source can be reduced using Grey System Model algorithm, and realized on the basis of precision of prediction
Quantization to fluctuating error range.In enterprise, it can be used for the data source of sales forecast typically from historical form or ERP
Historical data, data source property is more single, and the purchase quantity of certain high value materials, the frequency are often very low, causes data volume
Deficient, data modeling difficulty awkward situation.Therefore, to manufacturing enterprise sales forecast and purchasing forecast in, using gray scale system
Model of uniting is a kind of optimal selection.
Using time series buying historical data as single argument, GM (1,1) model is established based on Grey Prediction Algorithm.GM(1,
1) model really goes matched curve to obtain predicted value to the end with univariate differential equation of first order.One is established based on interval estimation
First linear regression curves prediction model, the result obtained based on one-variable linear regression curve prediction model are set as confidence interval；
Foundation obtains the combination forecasting method that gray model is combined with one-variable linear regression, carries out significance test, if received,
Obtain the confidence interval under Interval Grey interval prediction model.
In one embodiment, supplier's source data information is obtained, using supplier's assessment models and is based on supplier source
The comprehensive score information that data information obtains supplier can be there are many method.Fig. 3 A is supply chain control method of the invention
The flow diagram that supplier is evaluated of one embodiment, as shown in Figure 3A:
Step 301, vendors' evaluating index is determined.Evaluation index can be there are many index.
Step 302, evaluate collection corresponding with evaluation index is established, and determines that evaluation refers to according to evaluation index and evaluate collection
Target subordinated-degree matrix.
Step 303, the weighted value of each evaluation index, root are determined by analytic hierarchy process (AHP) and based on supplier's source data information
The judge vector of supplier is generated according to subordinated-degree matrix and weighted value.
Step 304, according to vector sum evaluate collection calculating comprehensive evaluation index is judged, comprehensive evaluation index and evaluation are based on
Collect the comprehensive score for determining supplier；Wherein, evaluation index include: price factor, service ability, delivery cycle, supply of material progress,
Research and development ability, qualitative factor etc..
Analytic hierarchy process (AHP), abbreviation AHP refer to element related with decision resolving into the levels such as target, criterion, scheme,
The decision-making technique of qualitative and quantitative analysis is carried out on basis herein.Supplier's assessment is carried out to first have to determine evaluation index body
System.The principle for constructing parameter system is as follows: most simple property: i.e. in the case where being able to satisfy assessment requirement and given demand substantially, to the greatest extent
Amount is assessed with less key index.Measurability: i.e. selection is easy the index quantitatively calculated and is easy accurately really as far as possible
Fixed key index, it is subjective random to reduce.Objectivity: i.e. each index can more accurately reflect the items of evaluated system
Energy, feature and property.Completeness: i.e. each index more should be able to comprehensively reflect the full content of evaluated system.Independence: i.e.
Each index in index system should be as independent as possible, reduces the degree of overlapping of index intension, in order to determine index weights.
Obtain more realistic weight.Constructing parameter system is actually to construct the set of factors U=for judging object
{ u1, u2 ..., um }, each factor in set of factors is from the relevant parameter that can really reflect power of suppliers.For example,
If using a certain type supplier as research object, it is assumed that consider that content includes qualitative factor, price factor, production capacity, research and development
Ability, service ability etc..The vendors' evaluating index system of building is as shown in 3B figure.User can be according to itself enterprises characteristics
Customized vendors' evaluating index system optimizes.
After constructing vendors' evaluating index system, not yet determine each evaluation index parameter for evaluation object
Influence degree.Analytic hierarchy process (AHP) aim at obtain parameter system in the bottom (solution layer) relative to top (destination layer)
Weights of importance, as shown in Figure 3 C.The step of analytic hierarchy process (AHP) is as follows: analytic hierarchy process (AHP) is opposite to each factor in each level
Importance is judged that these judge the matrix by way of introducing suitable scale and constituting numerical value, i.e. judgment matrix.Judgement
Matrix is the essential information of analytic hierarchy process (AHP), and carries out the important evidence of relative Link Importance calculating.It can use existing more
Kind method development of judgment matrix, Judgement Matricies have very strong subjectivity, it is therefore necessary to be carried out by the expert in industry
Judgement avoids subjective judgement fault from influencing assessment result bring as far as possible.
For example, select assessment indicator system parameter system shown in figure to judge supplier, third layer parameter needle
To the resulting jdgement matrix of the second layer parameter as shown in table one and following table two, the second layer parameter is commented for the first layer parameter is resulting
Matrix is sentenced as shown in following table three.
| Service ability | The rate of complaints? | Problem resolving ability? |
| The rate of complaints? | 1 | 1/3 |
| Problem resolving ability? | 3 | 1 |
One judgment matrix example --- service ability of table
Two judgment matrix example --- supplier evaluation of table
Three judgment matrix example --- price factor of table
Since when practical problem solves, the judgment matrix of construction not necessarily has consistency, it is therefore desirable to carry out consistent
Property examine.Consistency refer to expert in judge index importance, it is harmonious between each judgement, do not occur conflicting knot
Fruit.When judgment matrix does not have crash consistency, the characteristic root corresponding to judgment matrix can also change.Therefore, can lead to
The variation for crossing judgment matrix characteristic root carrys out the degree of consistency of test and judge.Coincident indicator CI is introduced as measurement judgment matrix
Deviate the index of consistency, is defined as:
Wherein, λmaxFor the maximum value of judgment matrix characteristic root, n is the order of judgment matrix.The maximum feature of judgment matrix
Root λmaxCalculating formula are as follows:
Wherein, (AW)iIndicate i-th of element of vector AW.CI value is bigger, shows that judgment matrix deviates crash consistency
Degree is bigger；CI value is smaller, shows that the consistency of criterion matrix is better.When judgment matrix has crash consistency, CI=0.
Due to the judgment matrix for different orders, the uniform error of people's judgement is different.Therefore, measuring different order judgment matrixs is
It is no that there is satisfied consistency, need to introduce the Aver-age Random Consistency Index RI of judgment matrix.For 1~9 rank judgment matrix,
The value of RI is listed in the following table respectively.
| n | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 |
| RI | 0.00 | 0.00 | 0.58 | 0.90 | 1.12 | 1.24 | 1.32 | 1.41 | 1.45 |
The value table of four-RI of table
For 1,2 rank matrixes, RI is formal, because 1,2 rank judgment matrixs always have crash consistency.Work as order
When greater than 2, the ratio between coincident indicator CI and same order average homogeneity index RI of judgment matrix are known as random consistency ration, note
For CR.WhenWhen, that is, think that sentencing RI breaks matrix with satisfied consistency.Otherwise it just needs to adjust judgment matrix,
Until there is satisfied consistency until it.It is successively successively calculated along recursive hierarchy structure, finally calculates bottom factor phase
For the relative importance of top factor, i.e. total hierarchial sorting.For the decision problem of 3 levels, the 3rd layer of note to the 2nd layer,
2nd layer is respectively W to the 1st layer of weight vectors3-2And W2-1, then the 3rd layer is W to the 1st layer of weight vectors3-1=W3-2*W2-1。
Similarly, n-th layer can be acquired to the 1st layer of weight vectors.For example, the 3rd layer parameter joins the 1st layer in the parameter system shown in
Several weights is as shown in table 11, and total weight vectors are [0.14,0.41,0.21,0.20,0.05].Following table is total hierarchial sorting power
Weight example.
Table five-total hierarchial sorting weight table
In one embodiment, supplier is assessed in conjunction with analytic hierarchy process (AHP) using fuzzy comprehensive evaluation method
Step includes: building parameter system；Establish subordinated-degree matrix；Parameters weighting is determined by analytic hierarchy process (AHP)；Determine opinion rating point
It is worth vector；Calculate Comprehensis pertaining vector；Calculate comprehensive grading value.Supplier's assessment is carried out to first have to determine that evaluation refers to recommendation
Mark system.
Constructing parameter system is actually to construct the set of factors U={ u1, u2 ..., u m } for judging object, in set of factors
Each factor is from the relevant parameter that can really reflect power of suppliers.It establishes subordinated-degree matrix and establishes evaluation rank collection V
={ v1, u2 ..., vm } is evaluated for each factor in set of factors U={ u1, u2 ..., u m }, obtains jdgement matrix:
For example, being { excellent, good, in, poor, bad } for the evaluation rank collection that certain parameter system is established.Pass through several relevant peoples
Member judges each parameter, and statistics obtains the frequency that each opinion rating occurs, as shown in following table six.
The frequency table that six-opinion rating of table occurs
Such data can be obtained from SAP system, can be for statistical analysis to relevant parameter according to big data algorithm,
Objective results are directly given, chose mode by expert's subjective judgement in the past to change.
In one embodiment, be conducive to purchasing forecast model and based on buying source data information, sales forecast data with
And supplier's comprehensive score information acquisition purchasing forecast result can be there are many method.Fig. 4 is supply chain controlling party of the invention
The flow diagram that buying is predicted of one embodiment of method, as shown in Figure 4:
Step 401, based on buying source historical data information, sales histories data, supplier's history comprehensive score information and
Corresponding buying historical information generates training sample.
Step 402, preset deep learning model is trained using deep learning method and based on training sample, is obtained
Obtain supplier's assessment models.
It step 403, is supplier's assessment models by preset deep learning model modification, by the way that source data letter will be purchased
Breath, sales forecast data and comprehensive score information input supplier, supplier assessment models obtain purchasing forecast result.
Purchasing source data information includes: BOM (Bill of Material, bill of materials) data, the scrappage of product, reality
Border production capacity, physical holding of stock information, supply cycle, contract information, product supply progress etc.；Purchasing forecast result includes: that buying is held
Line mode, buying hour, supplier information etc..
There are many deep learning models, such as deep learning model includes: convolutional neural networks CNN, DBN, circulation nerve
Network RNN, autocoder, production confrontation network G AN etc..Preset deep learning model includes three layers of neuron models,
Three layers of neuron models include input layer model, middle layer neuron models and output layer neuron model, every layer of mind
Input of the output as next layer of neuron models through meta-model, the neuron and buying source data of input layer model
Information, sales forecast data and supplier's comprehensive score information are corresponding, the neuron of output layer neuron model and buying
Prediction result is corresponding.Three layers of neuron models can be the sub-network knot of multiple neural net layers with full connection structure
Structure, middle layer neuron models are full articulamentum.
In one embodiment, can according to sales forecast result etc. obtain purchasing forecast as a result, according to accurate BOM,
Sales forecast is expanded to production materials procurement by practical production capacity, physical holding of stock etc..In purchasing forecast model, optimization aim is set
The neat set rate for being set to sales order improves.Therefore, it needs to introduce accurate BOM data in the constraint condition of purchasing forecast model
And scrappage (the production process proportion of goods damageds) setting of products of different specifications etc..
The data basis that order produces neat set rate is BOM, and BOM is formed as the material of production in purchasing forecast model
In play important role, BOM is known that every kind of product when what procedure needs how many material.BOM data is enterprise
The important factor of industry purchase quantity operation, and the material quantity provided based on BOM is all standard number, enterprise produces due to process
The coefficient of losses of the limitation of technique and employee's level, the different materials of identical product is different, and same material is in not identical product
Coefficient of losses it is also different, furthermore the data structure of BOM is complicated, and complicated BOM includes multilayer dose inventory, in every layer of bill of materials
Material it is not unique, this result in sales forecast result by BOM be converted into material procurement prediction result when be doped with
A large amount of unascertained informations from BOM, production and inventory, while multilayer BOM result is unfavorable for the operation of interval number.Therefore it closes
Reason BOM data structure is reconstructed will directly influence the accuracy of purchasing forecast, i.e., the neat set rate that final order is completed.
In one embodiment, using inventory control model and based on inventory's source data information, purchasing forecast result, sale
Source data information obtains finished product and raw materials inventory prediction result can be there are many method.Fig. 5 is that supply chain of the invention controls
The flow diagram that inventory is predicted of one embodiment of method, as shown in Figure 5:
Step 501, obtain inventory's source data, the historical data of sale, buying, and obtain storehouse storage space information and at
Product and raw materials inventory historical information.
Step 502, using historical data, storehouse storage space information, finished product and raw materials inventory historical information as training
Data obtain neural network model using machine learning algorithm training.
Step 503, inventory's source data information, purchasing forecast result, sale source data information are input to trained mind
Through network model, finished product and raw materials inventory prediction result are exported.
Inventory's source data includes: on-hand inventory, delivery cycle, in way order, production cycle, consumption of raw materials information etc.；At
Product and raw materials inventory prediction result include: finished product and raw materials inventory information, the plan of replenishing etc..
Inventory control model can be for neural network model etc., and machine learning algorithm can be gone point using the rule that study obtains
Analysis prediction unknown data.Using historical data, storehouse storage space information, finished product and raw materials inventory historical information as training number
According to, using machine learning algorithm training obtain neural network model.By inventory's source data information, purchasing forecast result, sale source
Data information is input to trained neural network model, exports finished product and raw materials inventory prediction result.Neural network model
Can there are many, such as CNN, RNN, GAN etc..
Fig. 6 is the flow diagram of the progress dynamic optimization of one embodiment of supply chain control method of the invention, such as
Shown in Fig. 6:
Step 601, using bayesian algorithm, abnormal and other source datas is occurred according to source data and the item between exception occur
Part probability Estimation and prior probability training Bayes classifier.
Bayes classifier is bayes predictive model, i.e. supply chain dynamic optimization model.Bayes predictive model is fortune
A kind of prediction carried out with Bayesian statistics.Bayesian statistics makes full use of not merely with model information and data information
Prior information.By the method for proof analysis, the prediction result of bayes predictive model and common regressive prediction model is carried out
Compare, the results showed that bayes predictive model has apparent superiority.
Step 602, abnormal to occurring by the Bayes classifier obtained after training when determining that source data occurs abnormal
Source data carry out risk profile, there are other abnormal source datas in prediction.
Step 603, risk program is correspondingly prevented based on other source datas acquisition for exception occur.Prevent risk program can
With to send alarm or provide emergency plan etc..Source data includes: sale source data, buying source data, supplier's source data, library
Deposit source data etc..
Under the conditions of some certain can occur for the supply chain dynamic optimization model based on Bayes to link a certain in supply chain
When part thing, the probability of happening of other links is obtained.For example, in supplier's link, since certain supplier's supply of material progress occurs
Risk, can be seller's seven sale 10 days, can quickly obtain the influence to other links by bayesian algorithm.I.e. when determining supplier
There is exception in supply of material progress in source data, passes through the Bayes classifier obtained after training to the supplier's source number for exception occur
Supply of material progress in carries out risk profile, and the delivery cycle etc. in the abnormal buying source data of prediction appearance is likely to occur different
Often, risk program is correspondingly prevented based on acquisitions such as the delivery cycles occurred in abnormal buying source data, can be supplied to send
The alarm of goods cycle delay provides another supplier etc..
Use bayesian algorithm generate supply chain dynamic optimization model and prediction there are other abnormal source datas can be with
Are as follows: determine the characteristic attribute (various source datas) of supply chain dynamic model；Characteristic attribute data are divided into training sample and test
Template；The prior probability P (xi) and P (yi) of characteristic attribute event x and y are calculated classification；All strokes are calculated to each characteristic attribute
The conditional probability divided；To calculating P of all categories (x | yi) P (yi)；Using P (x | yi) P (yi) maximal term as x generic.
If x={ a1, a2..., amIt is an item to be sorted, and each a is a characteristic attribute of x.There is category set C
={ y1, y2..., yn}.Calculate P (y1| x): P (y2| x) ..., P (yn|x)。
If P (yk| x)=max { P (y1| x), P (y2| x) ..., P (yn| x) }, then x ∈ yk。
Each conditional probability is calculated with the following method: finding the item set to be sorted classified known to one, this collection
Conjunction is called training sample set；Statistics obtains the conditional probability estimation of each characteristic attribute under of all categories.I.e.
P(a1|y1), P (a2|y1) ..., P (am|y1)；P(a1|y2), P (a2|y2) ..., P (am|y2)；...；P(a1|
yn), P (a2|yn) ..., P (am|yn)
If each characteristic attribute is conditional sampling, following derivation is had according to Bayes' theorem:
Because denominator is constant for all categories, as long as because molecule maximization all may be used by we.Again because of each feature
Attribute is conditional sampling, so having:
In one embodiment, as shown in fig. 7, the present invention provides a kind of supply chain control system 70, comprising: sales forecast
Control module 71, supplier's evaluation module 72, purchasing forecast module 73, inventory management module 74 and supply chain dynamic optimization module
75.Sales forecast control module 71 obtains sale source data information, using Sale Forecasting Model and based on sale source data information
Obtain sales forecast data.Supplier's evaluation module 72 obtains supplier's source data information, simultaneously using supplier's assessment models
Supplier's comprehensive score information is obtained based on supplier's source data information.
Purchasing forecast module 73 obtains buying source data information, is conducive to purchasing forecast model and based on buying source data letter
Breath, sales forecast data and supplier's comprehensive score information acquisition purchasing forecast result.Inventory management module 74 obtains library
Source data information is deposited, using inventory control model and based on inventory's source data information, purchasing forecast result, sale source data information
Obtain finished product and raw materials inventory prediction result.
In one embodiment, sales forecast control module 71 obtains historical sales specified number evidence, and establishes historical sales volume
Data sequence.Sales forecast control module 71 according to adding up, obtains the historical sales specified number in historical sales volume data sequence
Linear first-order differential equation is established to cumulative data sequence and based on this cumulative data sequence.Sales forecast control module 71 is to one
Rank linear differential equation carries out sliding-model control, and obtains parameter vector using least square method.Sales forecast control module 71
It constructs to obtain grey forecasting model based on linear first-order differential equation and parameter vector, as Sale Forecasting Model.Sales forecast
Confidence interval of the control module 71 based on one-variable linear regression prediction model estimation sales volume.Sales forecast control module 71 uses
Confidence interval is simultaneously predicted according to grey forecasting model, and sales forecast data are obtained.
Supplier's evaluation module 72 determines vendors' evaluating index.Supplier's evaluation module 72 is established and evaluation index phase
Corresponding evaluate collection, and determine according to evaluation index and evaluate collection the subordinated-degree matrix of evaluation index.Supplier's evaluation module 72
The weighted value that each evaluation index is determined by analytic hierarchy process (AHP) and based on supplier's source data information, according to subordinated-degree matrix and power
The judge vector of weight values generation supplier.Supplier's evaluation module 72 refers to according to vector sum evaluate collection calculating overall merit is judged
Number, the comprehensive score of supplier is determined based on comprehensive evaluation index and evaluate collection；Wherein, evaluation index include: price factor,
Service ability, delivery cycle, supply of material progress, research and development ability, qualitative factor etc..
Purchasing forecast module 73 is based on buying source historical data information, sales histories data, supplier's history comprehensive score
Information and corresponding buying historical information generate training sample.Purchasing forecast module 73 is using deep learning method and based on training
Sample is trained preset deep learning model, obtains supplier's assessment models.Purchasing forecast module 73 is by preset depth
Degree learning model is updated to supplier's assessment models, comprehensive by that will purchase source data information, sales forecast data and supplier
It closes score information and inputs supplier's assessment models, obtain purchasing forecast result；Wherein, buying source data information includes: BOM number
According to, the scrappage of product, practical production capacity, physical holding of stock information, supply cycle, contract information, product supply progress etc.；Buying is pre-
Surveying result includes: buying executive mode, buying hour, supplier information etc..
Inventory management module 74 obtains inventory's source data, the historical data of sale, buying, and obtains storehouse memory space letter
Breath and finished product and raw materials inventory historical information.Inventory management module 74 by historical data, storehouse storage space information, finished product and
Raw materials inventory historical information obtains neural network model as training data, using machine learning algorithm training.Stock control
Inventory's source data information, purchasing forecast result, sale source data information are input to trained neural network model by module 74,
Export finished product and raw materials inventory prediction result；Wherein, inventory's source data include: on-hand inventory, delivery cycle, way order,
Production cycle, consumption of raw materials information etc.；Finished product and raw materials inventory prediction result include: finished product and raw materials inventory information, mend
Goods plan etc..
Supply chain dynamic optimization module 75 uses bayesian algorithm, abnormal and other source datas occurs according to source data and occurs
Conditional probability estimation and prior probability training Bayes classifier between exception.Supply chain dynamic optimization module 75 is when the source of determination
When data occur abnormal, risk profile is carried out to there is abnormal source data by the Bayes classifier obtained after training, in advance
Measure existing other abnormal source datas.Supply chain dynamic optimization module 75 is obtained correspondingly based on there are other abnormal source datas
Prevent risk program.Wherein, source data includes: sale source data, buying source data, supplier's source data, inventory's source data etc..
Fig. 8 is the module diagram according to another embodiment of supply chain control system disclosed by the invention.Such as Fig. 8 institute
Show, which may include memory 81, processor 82, communication interface 83 and bus 84.Memory 81 for storing instruction, is located
Reason device 82 is coupled to memory 81, and processor 82 is configured as realizing above-mentioned supply based on the instruction execution that memory 81 stores
Chain control method.
Memory 81 can be high speed RAM memory, nonvolatile memory (NoN-volatile memory) etc., deposit
Reservoir 81 is also possible to memory array.Memory 81 is also possible to by piecemeal, and block can be combined into virtually by certain rule
Volume.Processor 82 can be central processor CPU or application-specific integrated circuit ASIC (Application Specific
Integrated Circuit), or be arranged to implement the one or more of supply chain control method disclosed by the invention
Integrated circuit.
In one embodiment, the present invention provides a kind of computer readable storage medium, and computer readable storage medium is deposited
Computer instruction is contained, the supply chain control method in as above any one embodiment is realized when instruction is executed by processor.
Supply chain control method, system and storage medium provided by the above embodiment, in the mould of traditional SCM
Under formula, the technologies such as big data, artificial intelligence and machine learning are introduced, from requirement forecasting, plan, supplier management and inventory
Each links such as management propose algorithm model, and correlation to each member and relevance impact analysis provide dynamic optimization algorithm mould
Type promotes supply chain overall operation efficiency, can have directly directiveness to finished product and raw materials inventory control；From system engineering
Angle is set out, and is considered the correlation in supply chain between each link, can be predicted other links after some is abnormal event
The probability being abnormal, and timely early warning reduce supply chain operating cost；The launch period can be shortened, General Promotion enterprise
The operational efficiency of industry.
Method and system of the invention may be achieved in many ways.For example, can by software, hardware, firmware or
Software, hardware, firmware any combination realize method and system of the invention.The said sequence of the step of for method is only
In order to be illustrated, the step of method of the invention, is not limited to sequence described in detail above, especially says unless otherwise
It is bright.In addition, in some embodiments, also the present invention can be embodied as to record program in the recording medium, these programs include
For realizing machine readable instructions according to the method for the present invention.Thus, the present invention also covers storage for executing according to this hair
The recording medium of the program of bright method.
Description of the invention is given for the purpose of illustration and description, and is not exhaustively or will be of the invention
It is limited to disclosed form.Many modifications and variations are obvious for the ordinary skill in the art.It selects and retouches
It states embodiment and is to more preferably illustrate the principle of the present invention and practical application, and those skilled in the art is enable to manage
The solution present invention is to design various embodiments suitable for specific applications with various modifications.
Claims (10)
1. a kind of supply chain control method characterized by comprising
Sale source data information is obtained, obtains sales forecast number using Sale Forecasting Model and based on sale source data information
According to；
Supplier's source data information is obtained, is supplied using supplier's assessment models and based on supplier's source data information
Quotient's comprehensive score information；
Buying source data information is obtained, it is conducive to purchasing forecast model and pre- based on the buying source data information, the sales volume
Measured data and supplier's comprehensive score information acquisition purchasing forecast result；
Inventory's source data information is obtained, using inventory control model and is based on inventory's source data information, the purchasing forecast
As a result, the sale source data information obtains finished product and raw materials inventory prediction result.
2. the method as described in claim 1, which is characterized in that described using Sale Forecasting Model and based on sale source number
Include: according to information acquisition sales forecast data
Historical sales specified number evidence is obtained, and establishes historical sales volume data sequence；
By the historical sales specified number in the historical sales volume data sequence according to adding up, obtains cumulative data sequence and be based on
This cumulative data sequence establishes linear first-order differential equation；
Sliding-model control is carried out to the linear first-order differential equation, and parameter vector is obtained using least square method；
It constructs to obtain grey forecasting model based on the linear first-order differential equation and the parameter vector, it is pre- as the sale
Survey model；
It is using confidence interval and pre- according to the grey based on the confidence interval of one-variable linear regression prediction model estimation sales volume
It surveys model to be predicted, obtains the sales forecast data.
3. method according to claim 2, which is characterized in that acquisition supplier source data information is commented using supplier
Estimate model and the comprehensive score information for obtaining supplier based on supplier's source data information includes:
Determine vendors' evaluating index；
Evaluate collection corresponding with the evaluation index is established, and institute's commentary is determined according to the evaluation index and the evaluate collection
The subordinated-degree matrix of valence index；
The weighted value that each evaluation index is determined by analytic hierarchy process (AHP) and based on supplier's source data information, according to institute
It states subordinated-degree matrix and the weighted value generates the judge vector of supplier；
Comprehensive evaluation index is calculated according to evaluate collection described in the judge vector sum, based on the comprehensive evaluation index and described
Evaluate collection determines the comprehensive score of the supplier；
Wherein, the evaluation index include: price factor, service ability, delivery cycle, supply of material progress, research and development ability, quality because
Element.
4. method as claimed in claim 3, which is characterized in that described to be conducive to purchasing forecast model and be based on buying source number
It is believed that breath, the sales forecast data and supplier's comprehensive score information acquisition purchasing forecast result include:
It is gone through based on buying source historical data information, sales histories data, supplier's history comprehensive score information and corresponding buying
History information generates training sample；
Preset deep learning model is trained using deep learning method and based on the training sample, obtains supplier
Assessment models；
It is supplier's assessment models by the preset deep learning model modification, by believing the buying source data
It ceases, supplier's assessment models described in the sales forecast data and supplier's comprehensive score information input, described in acquisition
Purchasing forecast result；
Wherein, the buying source data information includes: BOM data, the scrappage of product, practical production capacity, physical holding of stock information, supplies
Answer period, contract information, product supply progress；The purchasing forecast result includes: buying executive mode, buying hour, supply
Quotient's information.
5. method as claimed in claim 4, which is characterized in that described using inventory control model and based on inventory source number
It is believed that breath, the purchasing forecast result, the sale source data information obtain finished product and raw materials inventory prediction result includes:
Inventory's source data, the historical data of sale, buying are obtained, and obtains storehouse storage space information and finished product and raw material store
Deposit historical information；
Using the historical data, the storehouse storage space information, the finished product and raw materials inventory historical information as training
Data obtain neural network model using machine learning algorithm training；
Inventory's source data information, the purchasing forecast result, the sale source data information are input to trained mind
Through network model, the finished product and raw materials inventory prediction result are exported；
Wherein, inventory's source data includes: on-hand inventory, delivery cycle, in way order, production cycle, consumption of raw materials information；
The finished product and raw materials inventory prediction result include: finished product and raw materials inventory information, the plan of replenishing.
6. method as claimed in claim 5, which is characterized in that further include:
Using bayesian algorithm, according to source data occur abnormal and other source datas occur the estimation of the conditional probability between exception and
Prior probability trains Bayes classifier；
When determining that source data occurs abnormal, carried out by the Bayes classifier obtained after training to there is abnormal source data
There are other abnormal source datas in risk profile, prediction；
Risk program is correspondingly prevented based on other source datas acquisition for exception occur.
Wherein, the source data includes: sale source data, buying source data, supplier's source data, inventory's source data.
7. a kind of supply chain control system characterized by comprising
Sales forecast control module using Sale Forecasting Model and is based on the sale source for obtaining sale source data information
Data information obtains sales forecast data；
Supplier's evaluation module using supplier's assessment models and is based on the supply for obtaining supplier's source data information
Quotient's source data information obtains supplier's comprehensive score information；
Purchasing forecast module, for obtaining buying source data information, being conducive to purchasing forecast model and being based on the buying source data
Information, the sales forecast data and supplier's comprehensive score information acquisition purchasing forecast result；
Inventory management module using inventory control model and is based on inventory's source data for obtaining inventory's source data information
Information, the purchasing forecast result, the sale source data information obtain finished product and raw materials inventory prediction result.
8. system as claimed in claim 7, which is characterized in that
The sales forecast control module for obtaining historical sales specified number evidence, and establishes historical sales volume data sequence；By institute
The historical sales specified number in historical sales volume data sequence is stated according to adding up, obtains cumulative data sequence and based on this cumulative number
Linear first-order differential equation is established according to sequence；Sliding-model control is carried out to the linear first-order differential equation, and using minimum two
Multiplication obtains parameter vector；It constructs to obtain grey forecasting model based on the linear first-order differential equation and the parameter vector,
As the Sale Forecasting Model；Confidence interval based on one-variable linear regression prediction model estimation sales volume；Use confidence area
Between and predicted according to the grey forecasting model, obtain the sales forecast data.
9. a kind of supply chain control system characterized by comprising
Memory；And it is coupled to the processor of the memory, the processor is configured to based on the storage is stored in
Instruction in device executes such as method described in any one of claims 1 to 6.
10. a kind of computer readable storage medium, is stored thereon with computer program instructions, which is handled by one or more
The step of method described in claim 1 to 6 any one is realized when device executes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811609450.5A CN109784806B (en) | 2018-12-27 | 2018-12-27 | Supply chain control method, system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811609450.5A CN109784806B (en) | 2018-12-27 | 2018-12-27 | Supply chain control method, system and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109784806A true CN109784806A (en) | 2019-05-21 |
| CN109784806B CN109784806B (en) | 2023-09-19 |
Family
ID=66498572
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811609450.5A Active CN109784806B (en) | 2018-12-27 | 2018-12-27 | Supply chain control method, system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109784806B (en) |
Cited By (46)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110222900A (en) * | 2019-06-12 | 2019-09-10 | 行小膳科技(杭州)有限公司 | A kind of quinoa polygamy side meal replacement powder raw materials inventory procurement management system |
| CN110363468A (en) * | 2019-06-18 | 2019-10-22 | 阿里巴巴集团控股有限公司 | Determination method, apparatus, server and the readable storage medium storing program for executing of purchase order |
| CN110414688A (en) * | 2019-07-29 | 2019-11-05 | 卓尔智联(武汉)研究院有限公司 | Information analysis method, device, server and storage medium |
| CN110442642A (en) * | 2019-06-19 | 2019-11-12 | 北京航天智造科技发展有限公司 | Data processing method, device and the storage medium of distributed data base |
| CN110472863A (en) * | 2019-08-12 | 2019-11-19 | 北京联想金服科技有限公司 | A kind of early warning index evaluation method, device and storage medium |
| CN110659946A (en) * | 2019-10-09 | 2020-01-07 | 成都九洲电子信息系统股份有限公司 | Product purchase quantity analysis method |
| CN110826928A (en) * | 2019-11-12 | 2020-02-21 | 山东怡之家智能科技有限公司 | ERP inventory optimization analysis method and system based on big data |
| CN110930179A (en) * | 2019-10-18 | 2020-03-27 | 深圳市云积分科技有限公司 | Task evaluation method, system, device and computer readable storage medium |
| CN111340660A (en) * | 2019-07-01 | 2020-06-26 | 黑龙江省华熵助晟网络科技有限公司 | Online learning auxiliary system and method |
| CN111352945A (en) * | 2020-02-28 | 2020-06-30 | 杭州网易再顾科技有限公司 | Inventory supply chain management system, method, device, equipment and medium |
| CN111445133A (en) * | 2020-03-26 | 2020-07-24 | 珠海随变科技有限公司 | Material management method and device, computer equipment and storage medium |
| CN111598660A (en) * | 2020-05-14 | 2020-08-28 | 杭州乐顺科技有限公司 | Computer screening device and method for screening suppliers and storage medium |
| CN111639784A (en) * | 2020-04-20 | 2020-09-08 | 华为技术有限公司 | Inventory management method and related device |
| CN112053107A (en) * | 2020-07-16 | 2020-12-08 | 南京简睿捷软件开发有限公司 | Stock dimension's scheduling result evaluation device |
| CN112184075A (en) * | 2020-10-29 | 2021-01-05 | 西南交通大学 | Sustainable supply chain risk analysis method |
| CN112396374A (en) * | 2020-11-17 | 2021-02-23 | 山东财经大学 | Inventory optimization management system and method for dairy product supply chain system under uncertain environment |
| CN112580989A (en) * | 2020-12-23 | 2021-03-30 | 南京绿投科技有限公司 | Cloud platform data management system and management method based on industrial big data |
| CN112651534A (en) * | 2019-10-10 | 2021-04-13 | 顺丰科技有限公司 | Method, device and storage medium for predicting resource supply chain demand |
| CN112734282A (en) * | 2021-01-21 | 2021-04-30 | 网思科技股份有限公司 | Supply chain management method, system, storage medium and electronic device |
| CN112784173A (en) * | 2021-02-26 | 2021-05-11 | 电子科技大学 | Recommendation system scoring prediction method based on self-attention confrontation neural network |
| CN112884496A (en) * | 2021-05-06 | 2021-06-01 | 达而观数据(成都)有限公司 | Method, device and computer storage medium for calculating enterprise credit factor score |
| CN112884404A (en) * | 2021-02-08 | 2021-06-01 | 中国科学技术大学 | Intelligent supply chain inventory transfer optimization and transaction early warning system |
| CN112988854A (en) * | 2021-05-20 | 2021-06-18 | 创新奇智(成都)科技有限公司 | Complaint data mining method and device, electronic equipment and storage medium |
| CN113128975A (en) * | 2021-04-30 | 2021-07-16 | 北京思诺博信息技术有限公司 | Supply chain cooperative processing method based on digital service |
| CN113191814A (en) * | 2021-05-14 | 2021-07-30 | 扬州互江船舶科技有限公司 | Method and system for automatically inquiring price and purchasing |
| CN113610657A (en) * | 2021-10-10 | 2021-11-05 | 江苏四方精密钢管有限公司 | Method and system for popularizing and selling steel pipe products |
| CN113627662A (en) * | 2021-08-03 | 2021-11-09 | 杭州拼便宜网络科技有限公司 | Inventory data prediction method, device, equipment and storage medium |
| CN113742315A (en) * | 2021-08-17 | 2021-12-03 | 广州工业智能研究院 | Manufacturing big data processing platform and method |
| CN114186181A (en) * | 2022-02-16 | 2022-03-15 | 国家能源集团物资有限公司西南配送中心 | Multi-level redundancy collection control method for spare part supply |
| CN114462895A (en) * | 2022-04-12 | 2022-05-10 | 青岛华正信息技术股份有限公司 | Digital transformation management method and system for enterprises |
| CN114581159A (en) * | 2022-05-04 | 2022-06-03 | 爱迪森(北京)生物科技有限公司 | Warehouse prediction method and system based on big data analysis and readable storage medium |
| CN115099726A (en) * | 2022-08-25 | 2022-09-23 | 南通飞隼信息科技有限公司 | Intelligent management and control method and system based on full life cycle of textile product |
| CN115293826A (en) * | 2022-10-09 | 2022-11-04 | 南京卓博威信息科技有限公司 | Intelligent supply chain marketing system and evaluation method |
| CN115375352A (en) * | 2022-08-09 | 2022-11-22 | 木链网财务服务有限公司 | Supply chain financial data monitoring service management system based on thing networking |
| US11526845B2 (en) | 2020-04-07 | 2022-12-13 | Coupang Corp. | Systems and methods for automated outbound profile generation |
| CN115829611A (en) * | 2022-12-05 | 2023-03-21 | 杭州登卓科技有限公司 | Performance management method and system based on data processing |
| CN116562760A (en) * | 2023-05-09 | 2023-08-08 | 杭州君方科技有限公司 | Textile chemical fiber supply chain supervision method and system thereof |
| CN116629577A (en) * | 2023-06-20 | 2023-08-22 | 深圳市携客互联科技有限公司 | Intelligent supply chain management system based on big data |
| CN116993102A (en) * | 2023-08-10 | 2023-11-03 | 苏州中耀科技有限公司 | MIM forming process |
| CN117114583A (en) * | 2023-10-24 | 2023-11-24 | 电能易购(北京)科技有限公司 | Supply chain management system based on cloud service platform |
| CN117236663A (en) * | 2023-11-14 | 2023-12-15 | 深圳前海橙色魔方信息技术有限公司 | Computer data analysis method and system based on artificial intelligence |
| CN117252400A (en) * | 2023-11-16 | 2023-12-19 | 天津马上好车信息技术股份有限公司 | Coordination management method, system and application of automobile supply chain |
| CN117557073A (en) * | 2024-01-11 | 2024-02-13 | 云南建投物流有限公司 | Full life cycle provider service management method and system |
| CN117635358A (en) * | 2024-01-25 | 2024-03-01 | 山东师范大学 | Financial management method and system based on big data |
| CN117787816A (en) * | 2024-02-28 | 2024-03-29 | 山东中翰软件有限公司 | Material data quality detection method and system for industrial enterprises |
| CN116993102B (en) * | 2023-08-10 | 2024-04-26 | 苏州中耀科技有限公司 | MIM forming process |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005063280A (en) * | 2003-08-19 | 2005-03-10 | Nri & Ncc Co Ltd | Supply chain evaluation system and program |
| CN103617477A (en) * | 2013-10-31 | 2014-03-05 | 淘金信息科技（苏州）有限公司 | An enterprise management system |
| CN106502885A (en) * | 2016-10-11 | 2017-03-15 | 广西电网有限责任公司电力科学研究院 | A kind of intelligent electric meter Software Quality Evaluation System based on AHP |
| CN108764974A (en) * | 2018-05-11 | 2018-11-06 | 国网电子商务有限公司 | A kind of procurement of commodities amount prediction technique and device based on deep learning |
-
2018
- 2018-12-27 CN CN201811609450.5A patent/CN109784806B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005063280A (en) * | 2003-08-19 | 2005-03-10 | Nri & Ncc Co Ltd | Supply chain evaluation system and program |
| CN103617477A (en) * | 2013-10-31 | 2014-03-05 | 淘金信息科技（苏州）有限公司 | An enterprise management system |
| CN106502885A (en) * | 2016-10-11 | 2017-03-15 | 广西电网有限责任公司电力科学研究院 | A kind of intelligent electric meter Software Quality Evaluation System based on AHP |
| CN108764974A (en) * | 2018-05-11 | 2018-11-06 | 国网电子商务有限公司 | A kind of procurement of commodities amount prediction technique and device based on deep learning |
Non-Patent Citations (2)
| Title |
|---|
| 宋琛;: "无锡DY电器公司库存管理优化方法研究", no. 02, pages 128 - 132 * |
| 薛文军: "半导体元器件产品销售与采购关联预测模型的设计与实现", no. 3, pages 150 - 126 * |
Cited By (63)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110222900A (en) * | 2019-06-12 | 2019-09-10 | 行小膳科技(杭州)有限公司 | A kind of quinoa polygamy side meal replacement powder raw materials inventory procurement management system |
| CN110363468A (en) * | 2019-06-18 | 2019-10-22 | 阿里巴巴集团控股有限公司 | Determination method, apparatus, server and the readable storage medium storing program for executing of purchase order |
| CN110363468B (en) * | 2019-06-18 | 2023-09-26 | 创新先进技术有限公司 | Method and device for determining purchase order, server and readable storage medium |
| CN110442642B (en) * | 2019-06-19 | 2021-11-23 | 北京航天智造科技发展有限公司 | Data processing method and device for distributed database and storage medium |
| CN110442642A (en) * | 2019-06-19 | 2019-11-12 | 北京航天智造科技发展有限公司 | Data processing method, device and the storage medium of distributed data base |
| CN111340660B (en) * | 2019-07-01 | 2023-09-01 | 黑龙江省华熵助晟网络科技有限公司 | Online learning auxiliary system and method |
| CN111340660A (en) * | 2019-07-01 | 2020-06-26 | 黑龙江省华熵助晟网络科技有限公司 | Online learning auxiliary system and method |
| CN110414688A (en) * | 2019-07-29 | 2019-11-05 | 卓尔智联(武汉)研究院有限公司 | Information analysis method, device, server and storage medium |
| CN110472863B (en) * | 2019-08-12 | 2020-09-25 | 北京联想金服科技有限公司 | Early warning index evaluation method and device and storage medium |
| CN110472863A (en) * | 2019-08-12 | 2019-11-19 | 北京联想金服科技有限公司 | A kind of early warning index evaluation method, device and storage medium |
| CN110659946B (en) * | 2019-10-09 | 2023-07-21 | 成都九洲电子信息系统股份有限公司 | Product purchase quantity analysis method |
| CN110659946A (en) * | 2019-10-09 | 2020-01-07 | 成都九洲电子信息系统股份有限公司 | Product purchase quantity analysis method |
| CN112651534A (en) * | 2019-10-10 | 2021-04-13 | 顺丰科技有限公司 | Method, device and storage medium for predicting resource supply chain demand |
| CN110930179A (en) * | 2019-10-18 | 2020-03-27 | 深圳市云积分科技有限公司 | Task evaluation method, system, device and computer readable storage medium |
| CN110826928A (en) * | 2019-11-12 | 2020-02-21 | 山东怡之家智能科技有限公司 | ERP inventory optimization analysis method and system based on big data |
| CN111352945A (en) * | 2020-02-28 | 2020-06-30 | 杭州网易再顾科技有限公司 | Inventory supply chain management system, method, device, equipment and medium |
| CN111445133B (en) * | 2020-03-26 | 2021-04-27 | 珠海必要工业科技股份有限公司 | Material management method and device, computer equipment and storage medium |
| CN111445133A (en) * | 2020-03-26 | 2020-07-24 | 珠海随变科技有限公司 | Material management method and device, computer equipment and storage medium |
| US11526845B2 (en) | 2020-04-07 | 2022-12-13 | Coupang Corp. | Systems and methods for automated outbound profile generation |
| CN111639784A (en) * | 2020-04-20 | 2020-09-08 | 华为技术有限公司 | Inventory management method and related device |
| CN111639784B (en) * | 2020-04-20 | 2023-04-18 | 华为技术有限公司 | Inventory management method and related device |
| CN111598660A (en) * | 2020-05-14 | 2020-08-28 | 杭州乐顺科技有限公司 | Computer screening device and method for screening suppliers and storage medium |
| CN112053107A (en) * | 2020-07-16 | 2020-12-08 | 南京简睿捷软件开发有限公司 | Stock dimension's scheduling result evaluation device |
| CN112184075A (en) * | 2020-10-29 | 2021-01-05 | 西南交通大学 | Sustainable supply chain risk analysis method |
| CN112184075B (en) * | 2020-10-29 | 2022-04-22 | 西南交通大学 | Sustainable supply chain risk analysis method |
| CN112396374A (en) * | 2020-11-17 | 2021-02-23 | 山东财经大学 | Inventory optimization management system and method for dairy product supply chain system under uncertain environment |
| CN112580989A (en) * | 2020-12-23 | 2021-03-30 | 南京绿投科技有限公司 | Cloud platform data management system and management method based on industrial big data |
| CN112734282A (en) * | 2021-01-21 | 2021-04-30 | 网思科技股份有限公司 | Supply chain management method, system, storage medium and electronic device |
| CN112884404B (en) * | 2021-02-08 | 2023-09-05 | 中国科学技术大学 | Intelligent supply chain inventory transit optimization and abnormal movement early warning system |
| CN112884404A (en) * | 2021-02-08 | 2021-06-01 | 中国科学技术大学 | Intelligent supply chain inventory transfer optimization and transaction early warning system |
| CN112784173A (en) * | 2021-02-26 | 2021-05-11 | 电子科技大学 | Recommendation system scoring prediction method based on self-attention confrontation neural network |
| CN113128975A (en) * | 2021-04-30 | 2021-07-16 | 北京思诺博信息技术有限公司 | Supply chain cooperative processing method based on digital service |
| CN112884496A (en) * | 2021-05-06 | 2021-06-01 | 达而观数据(成都)有限公司 | Method, device and computer storage medium for calculating enterprise credit factor score |
| CN113191814A (en) * | 2021-05-14 | 2021-07-30 | 扬州互江船舶科技有限公司 | Method and system for automatically inquiring price and purchasing |
| CN112988854A (en) * | 2021-05-20 | 2021-06-18 | 创新奇智(成都)科技有限公司 | Complaint data mining method and device, electronic equipment and storage medium |
| CN113627662A (en) * | 2021-08-03 | 2021-11-09 | 杭州拼便宜网络科技有限公司 | Inventory data prediction method, device, equipment and storage medium |
| CN113742315A (en) * | 2021-08-17 | 2021-12-03 | 广州工业智能研究院 | Manufacturing big data processing platform and method |
| CN113610657A (en) * | 2021-10-10 | 2021-11-05 | 江苏四方精密钢管有限公司 | Method and system for popularizing and selling steel pipe products |
| CN114186181A (en) * | 2022-02-16 | 2022-03-15 | 国家能源集团物资有限公司西南配送中心 | Multi-level redundancy collection control method for spare part supply |
| CN114462895A (en) * | 2022-04-12 | 2022-05-10 | 青岛华正信息技术股份有限公司 | Digital transformation management method and system for enterprises |
| CN114581159B (en) * | 2022-05-04 | 2022-08-12 | 爱迪森(北京)生物科技有限公司 | Warehouse prediction method and system based on big data analysis and readable storage medium |
| CN114581159A (en) * | 2022-05-04 | 2022-06-03 | 爱迪森(北京)生物科技有限公司 | Warehouse prediction method and system based on big data analysis and readable storage medium |
| CN115375352A (en) * | 2022-08-09 | 2022-11-22 | 木链网财务服务有限公司 | Supply chain financial data monitoring service management system based on thing networking |
| CN115375352B (en) * | 2022-08-09 | 2023-09-22 | 木链网财务服务有限公司 | Supply chain financial data monitoring service management system based on Internet of things |
| CN115099726A (en) * | 2022-08-25 | 2022-09-23 | 南通飞隼信息科技有限公司 | Intelligent management and control method and system based on full life cycle of textile product |
| CN115293826A (en) * | 2022-10-09 | 2022-11-04 | 南京卓博威信息科技有限公司 | Intelligent supply chain marketing system and evaluation method |
| CN115829611A (en) * | 2022-12-05 | 2023-03-21 | 杭州登卓科技有限公司 | Performance management method and system based on data processing |
| CN116562760A (en) * | 2023-05-09 | 2023-08-08 | 杭州君方科技有限公司 | Textile chemical fiber supply chain supervision method and system thereof |
| CN116562760B (en) * | 2023-05-09 | 2024-04-26 | 杭州君方科技有限公司 | Textile chemical fiber supply chain supervision method and system thereof |
| CN116629577A (en) * | 2023-06-20 | 2023-08-22 | 深圳市携客互联科技有限公司 | Intelligent supply chain management system based on big data |
| CN116993102B (en) * | 2023-08-10 | 2024-04-26 | 苏州中耀科技有限公司 | MIM forming process |
| CN116993102A (en) * | 2023-08-10 | 2023-11-03 | 苏州中耀科技有限公司 | MIM forming process |
| CN117114583A (en) * | 2023-10-24 | 2023-11-24 | 电能易购(北京)科技有限公司 | Supply chain management system based on cloud service platform |
| CN117114583B (en) * | 2023-10-24 | 2024-01-23 | 电能易购(北京)科技有限公司 | Supply chain management system based on cloud service platform |
| CN117236663A (en) * | 2023-11-14 | 2023-12-15 | 深圳前海橙色魔方信息技术有限公司 | Computer data analysis method and system based on artificial intelligence |
| CN117236663B (en) * | 2023-11-14 | 2024-03-05 | 深圳前海橙色魔方信息技术有限公司 | Computer data analysis method and system based on artificial intelligence |
| CN117252400A (en) * | 2023-11-16 | 2023-12-19 | 天津马上好车信息技术股份有限公司 | Coordination management method, system and application of automobile supply chain |
| CN117252400B (en) * | 2023-11-16 | 2024-02-23 | 天津马上好车信息技术股份有限公司 | Coordination management method, system and application of automobile supply chain |
| CN117557073A (en) * | 2024-01-11 | 2024-02-13 | 云南建投物流有限公司 | Full life cycle provider service management method and system |
| CN117557073B (en) * | 2024-01-11 | 2024-04-02 | 云南建投物流有限公司 | Full life cycle provider service management method and system |
| CN117635358B (en) * | 2024-01-25 | 2024-04-16 | 山东师范大学 | Financial management method and system based on big data |
| CN117635358A (en) * | 2024-01-25 | 2024-03-01 | 山东师范大学 | Financial management method and system based on big data |
| CN117787816A (en) * | 2024-02-28 | 2024-03-29 | 山东中翰软件有限公司 | Material data quality detection method and system for industrial enterprises |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109784806B (en) | 2023-09-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109784806A (en) | Supply chain control method, system and storage medium | |
| Lima-Junior et al. | Combining SCOR® model and fuzzy TOPSIS for supplier evaluation and management | |
| Kleijnen et al. | Performance metrics in supply chain management | |
| Chou et al. | A decision support system for supplier selection based on a strategy-aligned fuzzy SMART approach | |
| Khaleie et al. | Supplier selection using a novel intuitionist fuzzy clustering approach | |
| Yadavalli et al. | An integrated optimization model for selection of sustainable suppliers based on customers’ expectations | |
| Yang et al. | Big data market optimization pricing model based on data quality | |
| Fulzele et al. | Performance measurement of sustainable freight transportation: a consensus model and FERA approach | |
| CN101840534A (en) | Integrated supply chain performance index evaluation method | |
| CN101840535A (en) | Integrated supply chain performance indicator evaluation method based on improved grey correlation analysis method | |
| Öztayşi et al. | Supply chain performance measurement using a SCOR based fuzzy VIKOR approach | |
| Manucharyan | Multi-criteria decision making for supplier selection: A literature critique | |
| Tadayonrad et al. | A new key performance indicator model for demand forecasting in inventory management considering supply chain reliability and seasonality | |
| Lesmana et al. | Productivity analysis in assembly department using objective matrix (OMAX) method in labor intensive manufacturing | |
| Naik et al. | Machine Learning based Food Sales Prediction using Random Forest Regression | |
| Pang | Multi-criteria supplier evaluation using fuzzy AHP | |
| Liu et al. | Application of fuzzy ordered weighted geometric averaging (FOWGA) operator for project delivery system decision-making | |
| Chiadamrong et al. | An integrated approach with SEM, fuzzy-QFD and MLP for supply chain management strategy development | |
| Silva et al. | Early warning method for the commodity prices based on artificial neural networks: SMEs case | |
| Amirjabbari | An application of a cost minimization model in determining safety stock level and location | |
| Shil et al. | A survey on existing vendor selection techniques | |
| Fridley | Improving online demand forecast using novel features in website data: a case study at Zara | |
| Sarı | Responsive Demand Management in the Era of Digitization | |
| Kolner | Applying machine learning on the data of a controltower in a retail distribution landscape | |
| Milovanović et al. | SELECTION OF SUPPLIERS IN THE SUPPLY CHAIN |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |