CN109784806B - Supply chain control method, system and storage medium - Google Patents
Supply chain control method, system and storage medium Download PDFInfo
- Publication number
- CN109784806B CN109784806B CN201811609450.5A CN201811609450A CN109784806B CN 109784806 B CN109784806 B CN 109784806B CN 201811609450 A CN201811609450 A CN 201811609450A CN 109784806 B CN109784806 B CN 109784806B
- Authority
- CN
- China
- Prior art keywords
- information
- source data
- sales
- prediction
- 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.)
- Active
Links
Abstract
The invention discloses a supply chain control method, a system and a storage medium, wherein the method comprises the following steps: obtaining sales forecast data based on sales source data information using a sales forecast model; obtaining supplier comprehensive scoring information based on the supplier source data information by using the supplier assessment model; facilitating a purchase forecast model and obtaining a purchase forecast result based on purchase source data information, sales forecast data and comprehensive scoring information of suppliers; obtaining stock forecast results of finished products and raw materials by utilizing the stock management model and based on stock source data information, purchasing forecast results and sales source data information; the supply chain control method, the system and the storage medium can improve the overall operation efficiency of the supply chain and have direct guidance on the inventory control of finished products and raw materials; after an abnormal event occurs, the probability of the occurrence of the abnormality of other links can be predicted, early warning is timely carried out, the running cost of a supply chain is reduced, and the running efficiency of enterprises is comprehensively improved.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a supply chain control method, a supply chain control system, and a storage medium.
Background
The supply chain system is oriented to users such as manufacturers, suppliers, distributors, retailers, logistics companies, end users and the like, and realizes full chain management from production end to consumption end from links such as sales, purchasing, suppliers, inventory, logistics and the like, optimizes enterprise resource allocation and promotes efficient collaboration of upstream and downstream of an industrial chain. The current supply chain management mainly depends on an ERP system to manage sales data, purchasing data, inventory data and production data, and can basically meet the daily operation requirements of enterprises. However, for large-scale production enterprises, conventional enterprise management software such as ERP systems has the following weaknesses in terms of supply chain planning, supplier management, inventory turnover rate improvement, and the like: under the traditional push type production mode, a production plan is mainly formulated according to the production scale of the last year of an enterprise and the operation index of the enterprise of the year, depends on professionals with relatively abundant experience, and does not have a large amount of data analysis as a support; along with the market development and the production mode transition, the push-pull type becomes a main stream mode of a supply chain, sales prediction becomes a core part of planning, but the traditional enterprise management software such as ERP and the like cannot meet the changing requirements and the like.
Disclosure of Invention
In view of the above, it is an object of the present invention to provide a supply chain control method, system and storage medium.
According to one aspect of the present invention, there is provided a supply chain control method including: obtaining sales source data information, and obtaining sales prediction data based on the sales source data information by using a sales prediction model; obtaining supplier source data information, utilizing a supplier assessment model and obtaining supplier comprehensive scoring information based on the supplier source data information; obtaining purchase source data information, facilitating a purchase prediction model and obtaining a purchase prediction result based on the purchase source data information, the sales prediction data and the supplier comprehensive score information; inventory source data information is obtained, and inventory management models are utilized to obtain inventory forecast results of finished products and raw materials based on the inventory source data information, the purchase forecast results and the sales source data information.
Optionally, the obtaining sales prediction data using a sales prediction model and based on the sales source data information includes: obtaining historical sales data and establishing a historical sales data sequence; accumulating the historical sales line data in the historical sales line data sequence to obtain an accumulated data sequence, and establishing a first-order linear differential equation based on the accumulated data sequence; discretizing the first-order linear differential equation, and obtaining a parameter vector by adopting a least square method; constructing a gray prediction model based on the first-order linear differential equation and the parameter vector, and taking the gray prediction model as the sales prediction model; estimating a confidence interval of sales based on the unitary linear regression prediction model; and predicting according to the gray prediction model by using a confidence interval to obtain sales prediction data.
Optionally, the obtaining the supplier source data information, using a supplier assessment model and obtaining the comprehensive score information of the supplier based on the supplier source data information includes: determining an evaluation index of a provider; establishing an evaluation set corresponding to the evaluation index, and determining a membership matrix of the evaluation index according to the evaluation index and the evaluation set; determining the weight value of each evaluation index based on the supplier source data information by using an analytic hierarchy process, and generating a judgment vector of a supplier according to the membership matrix and the weight value; calculating a comprehensive evaluation index according to the evaluation vector and the evaluation set, and determining a comprehensive score of the provider based on the comprehensive evaluation index and the evaluation set; wherein the evaluation index includes: price factors, service capabilities, supply periods, supply schedules, research and development capabilities, and quality factors.
Optionally, the facilitating the purchase forecast model and obtaining the purchase forecast result based on the purchase source data information, the sales forecast data, and the vendor comprehensive score information includes: generating a training sample based on the purchase source historical data information, the sales historical data, the provider historical comprehensive scoring information and the corresponding purchase historical information; training a preset deep learning model by using a deep learning method based on the training sample to obtain a supplier evaluation model; updating the preset deep learning model into the supplier evaluation model, and obtaining the purchase prediction result by inputting the purchase source data information, the sales prediction data and the supplier comprehensive score information into the supplier evaluation model; wherein, the purchase source data information includes: BOM data, rejection rate of products, actual productivity, actual inventory information, supply period, contract information and product supply progress; the purchase forecast result comprises: purchasing execution mode, purchasing time and supplier information.
Optionally, the obtaining the finished product and raw material inventory forecast results using an inventory management model and based on the inventory source data information, the procurement forecast results, and the sales source data information includes: acquiring inventory source data, historical data of sales and purchase, and acquiring warehouse storage space information and finished product and raw material inventory historical information; taking the historical data, the storehouse storage space information and the finished product and raw material inventory historical information as training data, and training by using a machine learning algorithm to obtain a neural network model; inputting the stock source data information, the purchasing prediction result and the sales source data information into a trained neural network model, and outputting the stock prediction result of the finished product and the raw material; wherein the stock source data comprises: stock, supply period, on-the-way order, production period, raw material consumption information; the product and raw material inventory forecasting results include: finished product and raw material inventory information, replenishment program.
Optionally, a Bayesian algorithm is adopted, and a Bayesian classifier is trained according to conditional probability estimation and prior probability between occurrence of anomalies of source data and occurrence of anomalies of other source data; when the source data is determined to be abnormal, performing risk prediction on the source data with the abnormality through a Bayesian classifier obtained after training, and predicting other source data with the abnormality; and obtaining a corresponding risk prevention scheme based on the other source data with the abnormality. Wherein the source data comprises: sales source data, procurement source data, supplier source data, inventory source data.
According to another aspect of the present invention, there is provided a supply chain control system comprising: the sales prediction control module is used for obtaining sales source data information, and obtaining sales amount prediction data based on the sales source data information by utilizing a sales prediction model; the supplier evaluation module is used for obtaining supplier source data information, utilizing a supplier evaluation model and obtaining supplier comprehensive scoring information based on the supplier source data information; the purchase prediction module is used for obtaining purchase source data information, facilitating a purchase prediction model and obtaining a purchase prediction result based on the purchase source data information, the sales prediction data and the comprehensive score information of the suppliers; the inventory management module is used for obtaining inventory source data information, utilizing an inventory management model and obtaining finished product and raw material inventory prediction results based on the inventory source data information, the purchase prediction results and the sales source data information.
Optionally, the sales prediction control module is configured to obtain historical sales data and establish a historical sales data sequence; accumulating the historical sales line data in the historical sales line data sequence to obtain an accumulated data sequence, and establishing a first-order linear differential equation based on the accumulated data sequence; discretizing the first-order linear differential equation, and obtaining a parameter vector by adopting a least square method; constructing a gray prediction model based on the first-order linear differential equation and the parameter vector, and taking the gray prediction model as the sales prediction model; estimating a confidence interval of sales based on the unitary linear regression prediction model; and predicting according to the gray prediction model by using a confidence interval to obtain sales prediction data.
Optionally, the provider assessment module is configured to determine an assessment index of a provider; establishing an evaluation set corresponding to the evaluation index, and determining a membership matrix of the evaluation index according to the evaluation index and the evaluation set; determining the weight value of each evaluation index based on the supplier source data information by using an analytic hierarchy process, and generating a judgment vector of a supplier according to the membership matrix and the weight value; calculating a comprehensive evaluation index according to the evaluation vector and the evaluation set, and determining a comprehensive score of the provider based on the comprehensive evaluation index and the evaluation set; wherein the evaluation index includes: price factors, service capabilities, supply periods, supply schedules, research and development capabilities, and quality factors.
Optionally, the purchase prediction module is configured to generate a training sample based on the purchase source historical data information, the sales historical data, the provider historical comprehensive score information and the corresponding purchase historical information; training a preset deep learning model by using a deep learning method based on the training sample to obtain a supplier evaluation model; updating the preset deep learning model into the supplier evaluation model, and obtaining the purchase prediction result by inputting the purchase source data information, the sales prediction data and the supplier comprehensive score information into the supplier evaluation model; wherein, the purchase source data information includes: BOM data, rejection rate of products, actual productivity, actual inventory information, supply period, contract information and product supply progress; the purchase forecast result comprises: purchasing execution mode, purchasing time and supplier information.
Optionally, the inventory management module is used for acquiring inventory source data, sales and purchasing history data, and acquiring warehouse storage space information and finished product and raw material inventory history information; taking the historical data, the storehouse storage space information and the finished product and raw material inventory historical information as training data, and training by using a machine learning algorithm to obtain a neural network model; inputting the stock source data information, the purchasing prediction result and the sales source data information into a trained neural network model, and outputting the stock prediction result of the finished product and the raw material; wherein the stock source data comprises: stock, supply period, on-the-way order, production period, raw material consumption information; the product and raw material inventory forecasting results include: finished product and raw material inventory information, replenishment program.
Optionally, the supply chain dynamic optimization module is used for training the Bayesian classifier according to the conditional probability estimation and the prior probability between the occurrence of the abnormality of the source data and the occurrence of the abnormality of other source data by adopting a Bayesian algorithm; when the source data is determined to be abnormal, performing risk prediction on the source data with the abnormality through a Bayesian classifier obtained after training, and predicting other source data with the abnormality; and obtaining a corresponding risk prevention scheme based on the other source data with the abnormality. Wherein the source data comprises: sales source data, procurement source data, supplier source data, inventory source data.
According to yet another aspect of the present invention, there is provided a supply chain control system including: a memory; and a processor coupled to the memory, the processor configured to perform the method as described above based on instructions stored in the memory.
According to a further aspect of the present invention there is provided a computer readable storage medium having stored thereon computer program instructions which when executed by one or more processors perform the steps of the method as described above.
According to the supply chain control method, system and storage medium, under the mode of traditional supply chain management, big data, artificial intelligence, machine learning and other technologies are introduced, algorithm models are provided from links such as demand prediction, planning, supplier management, inventory management and the like, dynamic optimization algorithm models are provided for correlation and correlation influence analysis of each member, the overall operation efficiency of the supply chain is improved, and the method has direct guidance on finished product and raw material inventory control; from the system engineering perspective, the relativity among links in the supply chain is considered, the abnormal probability of other links can be predicted after an abnormal event occurs, early warning is timely carried out, and the running cost of the supply chain is reduced; the product marketing period can be shortened, and the operation efficiency of enterprises is comprehensively improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
FIG. 1 is a flow chart of one embodiment of a supply chain control method of the present invention;
FIG. 2A is a diagram illustrating the relevance of various application links of one embodiment of a supply chain control method of the present invention;
FIG. 2B is a flow chart of predicting sales according to an embodiment of the supply chain control method of the present invention;
FIG. 3A is a flow chart of a supplier evaluation according to one embodiment of the supply chain control method of the present invention;
FIG. 3B is a schematic diagram of a vendor selection evaluation system;
FIG. 3C is a schematic diagram of an analytic hierarchy process;
FIG. 4 is a flow chart of predicting purchases in accordance with one embodiment of the supply chain control method of the present invention;
FIG. 5 is a schematic flow chart diagram of inventory forecasting in accordance with one embodiment of the supply chain control method of the present invention;
FIG. 6 is a flow chart illustrating dynamic optimization of one embodiment of a supply chain control method of the present invention;
FIG. 7 is a schematic diagram of the composition of one embodiment of a supply chain control system of the present invention;
FIG. 8 is a schematic diagram of the components of another embodiment of the supply chain control system of the present invention.
Detailed Description
Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the components and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless it is specifically stated otherwise.
Meanwhile, it should be understood that the sizes of the respective parts shown in the drawings are not drawn in actual scale for convenience of description.
The following description of at least one exemplary embodiment is merely exemplary in nature and is in no way intended to limit the invention, its application, or uses.
Techniques, methods, and apparatus known to one of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, the techniques, methods, and apparatus should be considered part of the specification.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further discussion thereof is necessary in subsequent figures.
FIG. 1 is a flow chart of an embodiment of a supply chain control method according to the present invention, as shown in FIG. 1:
step 101, obtaining sales source data information, and obtaining sales prediction data based on the sales source data information by using a sales prediction model. The sales source data may include trade orders, behavioral data, historical data, marketing strategies, user portraits, etc., and the sales prediction data may be sales predicted in units of years, quarters, months.
Step 102, obtaining supplier source data information, utilizing a supplier assessment model and obtaining supplier comprehensive scoring information based on the supplier source data information. The provider source data information may include rating information, service information, progress information, price, supply period, etc.
And step 103, obtaining purchase source data information, facilitating a purchase prediction model and obtaining a purchase prediction result based on the purchase source data information, sales prediction data and comprehensive scoring information of the suppliers. The purchase source data may be contracts, inventory information, supply periods, and the like. The purchase forecast result can be purchase amount, material type, purchase mode, etc.
Step 104, obtaining stock source data information, and obtaining stock forecast results of finished products and raw materials by utilizing the stock management model and based on the stock source data information, the purchase forecast results and the sales source data information. The stock source data information may include stock-on-hand, supply period, amount of orders in transit, amount consumed per month, production period, etc. The product and raw material inventory forecast results include restocking strategies, inventory plans, and the like.
In one embodiment, planning is the most important link of the supply chain control, affecting the resource allocation of the links of the supply chain, and is the primary factor in supply chain optimization. Supply chain plans include sales plans, production plans, supply and demand plans, procurement plans, etc., which are sources of all plans in the new supply chain model of "push + pull", with the plans being predictive dependent. The supply chain control method can accurately predict sales through the gray model, and then makes a purchasing plan by combining various data sources and the like, so that reasonable planning of resources is realized.
Aiming at the problems of huge number of suppliers of large enterprises, lack of effective data and information for supporting the suppliers, and the like, the supply chain control method can provide a flexible and configurable supplier assessment model, effectively manage the suppliers in a classified manner, improve the optimization efficiency of the suppliers and deal with the sudden problem of a supply network. The supply chain control method considers the relativity among members in the supply chain from the system engineering perspective and the probability of abnormality of other members after the occurrence of an abnormal event of a certain member basically, and gives early warning in time, thereby reducing the running cost of the supply chain.
As shown in FIG. 2A, the supply chain control method of the invention aims at the supply chain of a large enterprise to be oriented to each member of sales, purchasing, suppliers, inventory and logistics, provides an algorithm model from each application link of prediction, planning, supplier assessment, inventory management and the like, and provides a dynamic optimization algorithm model for the correlation and correlation influence analysis of each member, thereby improving the overall operation efficiency of the supply chain.
The prediction model is divided into a sales prediction model and a purchasing prediction model, and supports efficient integration and processing of multi-source heterogeneous data. The method supports multiple data acquisition modes such as industrial terminals, batches, streams, logs and the like, supports ETL (extraction, conversion and loading) processes of various data, supports multiple task scheduling modes, meets different data processing requirements, and can be rapidly expanded according to the requirements of enterprises.
A gray interval sales prediction model is established for sales prediction of products, factors (such as time factors) influencing sales are brought into a gray system, sales are treated as gray quantities and brought into the prediction model for reasoning and demonstration, and the real-time big data analysis system of the model and the related tools of a supply chain are verified from the angles of correct value inclusion and interval radius to realize the effectiveness of a technical scheme.
The gray interval sales prediction result in the interval number form can be utilized, and the fact that the rejection rate of products of different types is different in an actual scene is considered, the consumption errors of the same material for different types of products or the consumption in production is different is considered, the improved BOM data structure in the interval form is utilized, sales prediction is converted into real-time inventory constraint conditions, actual capacity constraint, residual capacity constraint, planned capacity and fund occupation constraint of a purchasing prediction process, and the constraint conditions of the number of zones are converted, so that the associated conversion process from sales prediction to purchasing prediction is converted into the interval number optimization problem.
The optimization of the uncertain transfer of the number of intervals is realized from the angles of interval possibility and reverse constraint, and the conversion from the interval sales prediction to the purchasing prediction is verified from the angles of prediction stability and prediction accuracy. And finally, comprehensively considering the demand prediction situation and the demand history record information by using a confidence reasoning method on the basis of the uncertain and optimized gray interval correlation prediction, and using an inventory control method under the interval demand input situation. The supply chain control method of the invention uses the associated prediction result to verify the effectiveness of the inventory control method, thereby further verifying the effectiveness and feasibility of the associated prediction model from sales prediction to purchase prediction and then to inventory control.
In one embodiment, there are a number of ways to obtain sales prediction data using a sales prediction model and based on sales source data information. FIG. 2B is a flow chart of predicting sales according to an embodiment of the supply chain control method of the present invention, as shown in FIG. 2B:
step 201, obtaining historical sales data and establishing a historical sales data sequence.
Step 202, accumulating the historical sales line data in the historical sales line data sequence to obtain an accumulated data sequence, and establishing a first-order linear differential equation based on the accumulated data sequence.
And 203, discretizing the first-order linear differential equation, and obtaining a parameter vector by adopting a least square method.
And 204, constructing a gray prediction model based on the first-order linear differential equation and the parameter vector, and taking the gray prediction model as a sales prediction model.
And 205, estimating a confidence interval of sales based on the unitary linear regression prediction model, and obtaining sales prediction data by combining the unitary linear regression prediction model and the gray prediction model for prediction. The combination prediction by combining the unitary linear regression prediction model and the gray prediction model can be an existing multiple method.
The sales prediction model can adopt three algorithm models, namely a multiple linear regression model, a G (1, N) gray model and a BP neural network. After the training of the three prediction models is finished, the system can automatically check the Mean Square Error (MSE) of the training result, and when the MSE value is smaller, the accuracy of the prediction models is higher, the prediction effect is better, and the optimal algorithm is automatically recommended.
For example, the sales prediction model employs a gray prediction model. Grey prediction is a method of predicting systems that contain uncertainty. The gray prediction is carried out by identifying the degree of dissimilarity of the development trend among the system factors, namely carrying out association analysis, carrying out generation processing on the original data to find the law of system variation, generating a data sequence with stronger regularity, and then establishing a corresponding differential equation model so as to predict the condition of future development trend of things. It constructs a gray prediction model using a series of quantitative values of the features of the reaction prediction object observed at equal time intervals, predicts the feature quantity at a certain moment in the future, or the time to reach a certain feature quantity. The unitary linear regression prediction refers to finding an empirical formula between two variable data by using a least square method when the scatter diagrams of the two variable data show a linear trend, namely a unitary linear regression prediction model. A prediction method for estimating a change in an independent variable from the change in the independent variable.
The gray system model algorithm is adopted, so that the requirement on a data source can be reduced, and the quantification of the error fluctuation range is realized on the basis of the prediction precision. In enterprises, the data sources for sales prediction are usually from historical forms or ERP historical data, the data source attributes are single, the purchasing quantity and frequency of certain high-value materials are very low, and the embarrassment of data quantity shortage and data modeling difficulty is caused. Therefore, the gray scale system model is the best choice in sales and procurement forecasting for manufacturing enterprises.
And establishing a GM (1, 1) model based on a gray prediction algorithm by taking the time series purchase history data as a univariate. The GM (1, 1) model is actually a single-variable first-order differential equation to fit the curve to obtain the final predicted value. Establishing a unified linear regression curve prediction model based on interval estimation, and setting a result obtained based on the unified linear regression curve prediction model as a confidence interval; and (3) establishing a combined prediction method for combining the gray model and the unitary linear regression, and performing significance test, if the combined prediction method is accepted, obtaining a confidence interval under the interval gray interval prediction model.
In one embodiment, there are a number of ways to obtain vendor source data information, utilizing a vendor assessment model, and obtaining vendor's composite score information based on the vendor source data information. FIG. 3A is a schematic flow chart of the supply chain control method according to an embodiment of the present invention for evaluating suppliers, as shown in FIG. 3A:
In step 301, an evaluation index of the provider is determined. The evaluation index may have various indexes.
Step 302, an evaluation set corresponding to the evaluation index is established, and a membership matrix of the evaluation index is determined according to the evaluation index and the evaluation set.
And 303, determining the weight value of each evaluation index based on the supplier source data information by a analytic hierarchy process, and generating a supplier judgment vector according to the membership matrix and the weight value.
Step 304, calculating a comprehensive evaluation index according to the evaluation vector and the evaluation set, and determining the comprehensive score of the supplier based on the comprehensive evaluation index and the evaluation set; wherein, the evaluation index includes: price factors, service capabilities, supply periods, supply schedules, research and development capabilities, quality factors, and the like.
The analytic hierarchy process, AHP for short, refers to a decision making process of decomposing elements related to decision making into layers of targets, criteria, schemes, etc., and performing qualitative and quantitative analysis on the basis of the decomposition. The provider assessment is performed by first determining an assessment index system. The principle of constructing the parameter system is that the parameter system is simplified, namely, the parameter system is evaluated with fewer key indexes as possible under the condition that the evaluation requirement and the given requirement can be basically met. And the scalability is to select the index easy to quantitatively calculate and the key index easy to accurately determine as much as possible so as to reduce subjective randomness. Objectivity, namely, each index can reflect each performance, characteristic and property of the system to be evaluated more truly. The completeness, i.e. each index should reflect the whole content of the evaluated system more comprehensively. The independence, namely, each index in the index system should be as independent as possible, so as to reduce the overlapping degree of the index connotation and facilitate the determination of the index weight.
A more realistic weight is obtained. The build parameter system is actually a factor set u= { U1, U2, & gt, um } that builds a judgment object, and each factor in the factor set comes from a related parameter that can truly reflect the capability of the provider. For example, if a certain type of provider is the subject of study, it is assumed that the content includes quality factors, price factors, productivity, research and development capabilities, service capabilities, and the like. The evaluation index system of the constructed suppliers is shown in figure 3B. The user can customize the evaluation index system of the provider to optimize according to the characteristics of the enterprise.
After the evaluation index system of the supplier is constructed, the influence degree of each evaluation index parameter on the evaluation object is not determined yet. The objective of the analytic hierarchy process is to obtain importance weights of the lowest layer (scheme layer) relative to the highest layer (target layer) in the parameter system, as shown in fig. 3C. The analytic hierarchy process comprises the steps of judging the relative importance of each factor in each hierarchy by the analytic hierarchy process, and constructing a matrix in the form of numerical values, namely judging the matrix by introducing proper scales. The judgment matrix is basic information of an analytic hierarchy process and is also an important basis for carrying out relative importance calculation. The conventional methods can be used for constructing the judgment matrix, and the construction of the judgment matrix has strong subjectivity, so that the judgment must be carried out by experts in the industry, and the influence of subjective judgment errors on the evaluation result is avoided as much as possible.
For example, the parameter system shown in the provider selection evaluation index system diagram is evaluated, the evaluation matrix obtained by the third layer parameter for the second layer parameter is shown in table one and table two below, and the evaluation matrix obtained by the second layer parameter for the first layer parameter is shown in table three below.
| Service capability | Is the complaint rate? | Question resolution capability? |
| Is the complaint rate? | 1 | 1/3 |
| Question resolution capability? | 3 | 1 |
Table one judgment matrix example—service capability
Table two judgment matrix example-vendor evaluation
List three judgment matrix example-price factor
Since the constructed judgment matrix does not necessarily have consistency when solving the actual problem, consistency check is required. The consistency refers to that when an expert judges the importance of the index, all the judgments are coordinated and consistent, and the contradictory results do not appear. When the judgment matrix does not have complete consistency, the feature root corresponding to the judgment matrix also changes. Thus, the consistency of the judgment can be checked by judging the change of the characteristic root of the matrix. Introducing a consistency index CI as an index for measuring the deviation consistency of the judgment matrix, and defining as follows:
wherein lambda is max To determine the maximum value of the matrix feature root, n is the order of the determination matrix. Judging the maximum characteristic root lambda of the matrix max The calculation formula of (2) is as follows:
wherein, (AW) i Representing the ith element of vector AW. The larger the CI value, the greater the degree to which the judgment matrix deviates from perfect consistency; the smaller the CI value, the better the consistency of the criterion matrix. When the judgment matrix has complete consistency, ci=0. Since the consistency errors of human judgment are different for judgment matrices of different orders. Therefore, it is necessary to introduce an average random uniformity index RI of the judgment matrix to measure whether the judgment matrix of different orders has satisfactory uniformity. For the 1-9 th order judgment matrix, the RI values are 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 |
Table four-RI value table
For 1, 2-order matrices, RI is only formally due toThe judgment matrix of 1 and 2 steps always has complete consistency. When the order is greater than 2, the ratio of the consistency index CI of the judgment matrix to the average consistency index RI of the same order is called a random consistency ratio and is marked as CR. When (when)And when the RI judgment matrix is judged to have satisfactory consistency. Otherwise, the decision matrix needs to be adjusted until it has satisfactory consistency. And sequentially calculating layer by layer along the hierarchical structure, and finally calculating the relative importance of the bottommost layer factors relative to the highest layer factors, namely the total hierarchical ordering. For the decision problem of 3 layers, the weight vectors of the layer 3 to the layer 2 and the layer 2 to the layer 1 are recorded as W respectively 3-2 And W is 2-1 Then the weight vector of the layer 3 to the layer 1 is W 3-1 ＝W 3-2 *W 2-1 . Similarly, the weight vector of the n-th layer to the 1-th layer can be obtained. For example, in the illustrated parameter system, the layer 3 parameters are weighted against the layer 1 parameters as shown in Table five, with a total weight vector of [0.14,0.41,0.21,0.20,0.05 ]]. The following table is an example of the total rank weights of the hierarchy.
Table five-level total ranking weight table
In one embodiment, the step of evaluating the supplier using a combination of fuzzy comprehensive evaluation and analytic hierarchy process comprises: constructing a parameter system; establishing a membership matrix; determining parameter weights by an analytic hierarchy process; determining an evaluation grade score vector; calculating a comprehensive membership vector; and calculating the comprehensive grading value. The evaluation index system is first determined for the evaluation and recommendation of suppliers.
The build parameter system is actually a factor set u= { U1, U2, & gt, U m } of the build evaluation object, and each factor in the factor set comes from a related parameter that can truly reflect the capability of the provider. Establishing a membership degree matrix, and establishing a judgment grade set V= { V1, U2, & gt, vm }, and evaluating each factor in a factor set U= { U1, U2, & gt, U m } to obtain a judgment matrix:
for example, the set of evaluation levels established for a certain parameter system is { good, medium, bad, inferior }. And judging each parameter by a plurality of related personnel, and counting to obtain the occurrence frequency of each evaluation grade, wherein the occurrence frequency is shown in a sixth table.
Table six-frequency of occurrence table of evaluation level
The data can be obtained from the SAP system, and the relevant parameters can be statistically analyzed according to a big data algorithm to directly give objective results, so that the previous choosing mode by means of subjective judgment of an expert is changed.
In one embodiment, there are a number of ways to facilitate the purchase forecast model and obtain the purchase forecast results based on the purchase source data information, sales forecast data, and the vendor comprehensive score information. FIG. 4 is a schematic flow chart of predicting purchasing according to one embodiment of the supply chain control method of the present invention, as shown in FIG. 4:
step 401, generating training samples based on purchase source historical data information, sales historical data, provider historical composite score information and corresponding purchase historical information.
Step 402, training a preset deep learning model based on a training sample by using a deep learning method to obtain a provider assessment model.
And step 403, updating the preset deep learning model into a provider assessment model, and obtaining a purchase prediction result by inputting purchase source data information, sales prediction data and provider comprehensive score information into the provider assessment model.
The purchase source data information includes: BOM (Bill of materials) data, rejection rate of products, actual capacity, actual stock information, supply period, contract information, product supply progress and the like; the purchase forecast result comprises: purchasing execution mode, purchasing time, supplier information, etc.
There are various deep learning models, for example, the deep learning model includes: convolutional neural networks CNN, DBN, recurrent neural network RNN, auto-encoder, generative countermeasure network GAN, etc. The preset deep learning model comprises three layers of neuron models, wherein the three layers of neuron models comprise an input layer of neuron model, a middle layer of neuron model and an output layer of neuron model, the output of each layer of neuron model is used as the input of the next layer of neuron model, the neurons of the input layer of neuron model correspond to purchasing source data information, sales prediction data and supplier comprehensive scoring information, and the neurons of the output layer of neuron model correspond to purchasing prediction results. The three-layer neuron model may be a sub-network structure of a plurality of neural network layers having a fully connected structure, and the middle-layer neuron model is a fully connected layer.
In one embodiment, the procurement forecast results may be obtained based on sales forecast results, etc., and the sales forecast may be expanded to produce raw material procurement based on accurate BOM, actual capacity, actual inventory, etc. In the purchase forecast model, the optimization objective is set to increase the rate of the sales order. Therefore, accurate BOM data, rejection rate (loss rate in the production process) setting of products with different specifications and the like need to be introduced into constraint conditions of the purchase prediction model.
The data base of the order production rate is BOM, the BOM plays an important role in the purchase prediction model as the material composition of the product production, and the BOM can know how much material is needed in each product in what process. The BOM data are important factors for the operation of the purchasing quantity of enterprises, the quantity of materials given on the basis of the BOM is standard quantity, the consumption rate of different materials of the same product is different due to the limitation of the working procedure process and the staff level, the consumption rate of different materials of the same product is also different in different products, in addition, the data structure of the BOM is complex, the complex BOM comprises a plurality of layers of bill of materials, the materials in each layer of bill of materials are not unique, and the sales prediction result is doped with a large quantity of uncertainty information from the BOM, production and inventory when being converted into the material purchasing prediction result through the BOM, and meanwhile, the multi-layer BOM result is unfavorable for the operation of the interval number. Therefore, reasonable reconstruction of the BOM data structure directly affects the accuracy of purchase prediction, namely the rate of complete order.
In one embodiment, there are a number of ways to obtain finished and raw material inventory forecasts using an inventory management model and based on inventory source data information, procurement forecast results, sales source data information. FIG. 5 is a schematic flow chart of inventory forecasting in accordance with one embodiment of the supply chain control method of the present invention, as shown in FIG. 5:
Step 501, acquiring inventory source data, historical data of sales and purchase, and acquiring warehouse storage space information and finished product and raw material inventory historical information.
Step 502, using historical data, warehouse storage space information, finished product and raw material inventory historical information as training data, and training by using a machine learning algorithm to obtain a neural network model.
Step 503, inputting the stock source data information, the procurement forecast result and the sales source data information into the trained neural network model, and outputting the stock forecast result of the finished product and the raw material.
The stock source data includes: stock, supply cycle, in-transit order, production cycle, raw material consumption information, etc.; the product and raw material inventory predictions include: inventory information of finished products and raw materials, replenishment plans, etc.
The inventory management model may be a neural network model, etc., and the machine learning algorithm may utilize the rules learned to analyze the predicted unknown data. And training by using the historical data, the storehouse storage space information, the finished product and raw material inventory historical information as training data and utilizing a machine learning algorithm to obtain a neural network model. And inputting the stock source data information, the purchase forecast result and the sales source data information into the trained neural network model, and outputting the stock forecast result of the finished product and the raw material. There are various neural network models, such as CNN, RNN, GAN, etc.
FIG. 6 is a schematic flow chart of dynamic optimization of one embodiment of the supply chain control method of the present invention, as shown in FIG. 6:
and 601, training a Bayesian classifier according to the conditional probability estimation and the prior probability between the occurrence of the abnormality of the source data and the occurrence of the abnormality of other source data by adopting a Bayesian algorithm.
The Bayesian classifier is a Bayesian predictive model, namely a supply chain dynamic optimization model. The Bayesian prediction model is a prediction made by using Bayesian statistics. Bayesian statistics not only utilizes model information and data information, but also fully utilizes prior information. And comparing the Bayesian prediction model with the prediction result of the common regression prediction model by a demonstration analysis method, wherein the result shows that the Bayesian prediction model has obvious superiority.
And 602, when the source data is determined to be abnormal, performing risk prediction on the source data with the abnormality through a Bayesian classifier obtained after training, and predicting other source data with the abnormality.
Step 603, obtaining a corresponding risk prevention scheme based on other source data with anomalies. The risk prevention scheme may be to send an alarm or provide an emergency scheme, etc. The source data includes: sales source data, procurement source data, supplier source data, inventory source data, etc.
The Bayesian-based dynamic optimization model of the supply chain can obtain the occurrence probability of other links when a certain link on the supply chain has a certain occurrence under a certain condition. For example, in the link of suppliers, since the risk of the supply progress of a certain supplier occurs, the delivery is delayed for 10 days, and the influence on other links can be quickly obtained through a Bayesian algorithm. Namely, when determining that the supply progress in the supplier source data is abnormal, performing risk prediction on the supply progress in the abnormal supplier source data through a Bayesian classifier obtained after training, predicting that the supply period and the like in the abnormal purchasing source data are likely to be abnormal, obtaining a corresponding risk prevention scheme based on the supply period and the like in the abnormal purchasing source data, and sending a supply period delay alarm or providing another supplier and the like.
The generation of the supply chain dynamic optimization model by using the Bayesian algorithm and other source data for predicting occurrence of anomalies can be as follows: determining characteristic attributes (various source data) of the supply chain dynamic model; dividing the characteristic attribute data into a training sample and a test sample plate; calculating prior probabilities P (xi) and P (yi) of the feature attribute events x and y for the categories; calculating conditional probabilities of all partitions for each feature attribute; calculating P (x|yi) P (yi) for each class; the maximum term of P (x|yi) P (yi) is taken as the category to which x belongs.
Let x= { a 1 ，a 2 ，...，a m And each a is a characteristic attribute of x. There is a category set c= { y 1 ，y 2 ，...，y n }. Calculation of P (y) 1 |x)：P(y 2 |x)，...，P(y n |x)。
If P (y) k |x)＝max{P(y 1 |x)，P(y 2 |x)，...，P(y n I x), x ε y k 。
The following method is adopted to calculate each conditional probability: finding a set of items to be classified of known classification, which is called a training sample set; and (5) counting to obtain the conditional probability estimation of each characteristic attribute under each category. I.e.
P(a 1 |y 1 )，P(a 2 |y 1 )，...，P(a m |y 1 )；P(a 1 |y 2 )，P(a 2 |y 2 )，...，P(a m |y 2 )；...；P(a 1 |y n )，P(a 2 |y n )，...，P(a m |y n )
If the individual feature attributes are conditional independent, there is the following derivation according to the Bayes theorem:
since the denominator is constant for all classes, we only need to maximize the numerator. Also, since each characteristic attribute is conditional independent, there are:
in one embodiment, as shown in FIG. 7, the present invention provides a supply chain control system 70 comprising: sales forecast control module 71, supplier assessment module 72, procurement forecast module 73, inventory management module 74, and supply chain dynamic optimization module 75. The sales prediction control module 71 obtains sales source data information, utilizes a sales prediction model, and obtains sales prediction data based on the sales source data information. The provider assessment module 72 obtains provider source data information, utilizes a provider assessment model, and obtains provider composite score information based on the provider source data information.
The purchase forecast module 73 obtains purchase source data information, facilitates the purchase forecast model, and obtains a purchase forecast result based on the purchase source data information, sales forecast data, and the vendor composite score information. The inventory management module 74 obtains inventory source data information, utilizes an inventory management model, and obtains finished product and raw material inventory forecasts based on the inventory source data information, the procurement forecast, the sales source data information.
In one embodiment, sales prediction control module 71 obtains historical sales data and establishes a historical sales data sequence. The sales prediction control module 71 accumulates the historical sales volume data in the historical sales volume data sequence to obtain an accumulated data sequence and establishes a first order linear differential equation based on the accumulated data sequence. The sales prediction control module 71 subjects the first-order linear differential equation to discretization processing, and obtains a parameter vector by using a least square method. The sales prediction control module 71 constructs a gray prediction model based on the first-order linear differential equation and the parameter vector as a sales prediction model. The sales prediction control module 71 estimates confidence intervals for sales based on a unitary linear regression prediction model. The sales prediction control module 71 uses the confidence interval and predicts according to the gray prediction model to obtain sales prediction data.
The provider assessment module 72 determines an assessment indicator for the provider. The provider evaluation module 72 establishes an evaluation set corresponding to the evaluation index and determines a membership matrix of the evaluation index based on the evaluation index and the evaluation set. The provider evaluation module 72 determines the weight value of each evaluation index based on the provider source data information by the hierarchical analysis method, and generates a provider evaluation vector according to the membership matrix and the weight value. The provider evaluation module 72 calculates a comprehensive evaluation index from the evaluation vector and the evaluation set, and determines a comprehensive score of the provider based on the comprehensive evaluation index and the evaluation set; wherein, the evaluation index includes: price factors, service capabilities, supply periods, supply schedules, research and development capabilities, quality factors, and the like.
Purchase prediction module 73 generates training samples based on the purchase source history data information, sales history data, provider history composite score information, and corresponding purchase history information. The purchase prediction module 73 uses a deep learning method and trains a preset deep learning model based on training samples to obtain a supplier evaluation model. The purchase prediction module 73 updates the preset deep learning model to a provider assessment model, and obtains a purchase prediction result by inputting purchase source data information, sales prediction data and provider comprehensive score information into the provider assessment model; wherein, the purchase source data information includes: BOM data, rejection rate of products, actual capacity, actual inventory information, supply period, contract information, product supply progress and the like; the purchase forecast result comprises: purchasing execution mode, purchasing time, supplier information, etc.
The inventory management module 74 obtains inventory source data, sales, procurement history data, and inventory storage space information and product and raw material inventory history information. The inventory management module 74 trains the neural network model using machine learning algorithms using the historical data, the warehouse storage space information, and the product and raw material inventory historical information as training data. The inventory management module 74 inputs inventory source data information, procurement forecast results, sales source data information into the trained neural network model, and outputs finished product and raw material inventory forecast results; wherein the stock source data comprises: stock, supply cycle, in-transit order, production cycle, raw material consumption information, etc.; the product and raw material inventory predictions include: inventory information of finished products and raw materials, replenishment plans, etc.
The supply chain dynamic optimization module 75 employs a bayesian algorithm to train a bayesian classifier based on the conditional probability estimates and prior probabilities between anomalies in the source data and anomalies in other source data. When determining that the source data is abnormal, the supply chain dynamic optimization module 75 performs risk prediction on the source data with the abnormality through the Bayesian classifier obtained after training, and predicts other source data with the abnormality. The supply chain dynamic optimization module 75 obtains a corresponding risk prevention scheme based on other source data that is abnormal. Wherein the source data comprises: sales source data, procurement source data, supplier source data, inventory source data, etc.
FIG. 8 is a block diagram of another embodiment of a supply chain control system according to the present disclosure. As shown in fig. 8, the apparatus may include a memory 81, a processor 82, a communication interface 83, and a bus 84. The memory 81 is used for storing instructions, the processor 82 is coupled to the memory 81, and the processor 82 is configured to implement the supply chain control method described above based on the instructions stored by the memory 81.
The memory 81 may be a high-speed RAM memory, a nonvolatile memory (NoN-volatile memory), or the like, or the memory 81 may be a memory array. The memory 81 may also be partitioned and the blocks may be combined into virtual volumes according to certain rules. The processor 82 may be a central processing unit CPU, or an application specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the supply chain control methods of the present disclosure.
In one embodiment, the invention provides a computer readable storage medium storing computer instructions that when executed by a processor implement the supply chain control method of any of the embodiments above.
In the supply chain control method, the system and the storage medium provided by the embodiment, under the mode of traditional supply chain management, big data, artificial intelligence, machine learning and other technologies are introduced, algorithm models are provided from links such as demand prediction, planning, supplier management, inventory management and the like, dynamic optimization algorithm models are provided for correlation and relevance influence analysis of each member, the overall operation efficiency of the supply chain is improved, and the direct guidance on finished product and raw material inventory control can be provided; from the system engineering perspective, the relativity among links in the supply chain is considered, the abnormal probability of other links can be predicted after an abnormal event occurs, early warning is timely carried out, and the running cost of the supply chain is reduced; the product marketing period can be shortened, and the operation efficiency of enterprises is comprehensively improved.
The method and system of the present invention may be implemented in a number of ways. For example, the methods and systems of the present invention may be implemented by software, hardware, firmware, or any combination of software, hardware, firmware. The above-described sequence of steps for the method is for illustration only, and the steps of the method of the present invention are not limited to the sequence specifically described above unless specifically stated otherwise. Furthermore, in some embodiments, the present invention may also be embodied as programs recorded in a recording medium, the programs including machine-readable instructions for implementing the methods according to the present invention. Thus, the present invention also covers a recording medium storing a program for executing the method according to the present invention.
The description of the present invention has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the invention in the form disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, and to enable others of ordinary skill in the art to understand the invention for various embodiments with various modifications as are suited to the particular use contemplated.
Claims (5)
1. A supply chain control method, comprising:
obtaining sales source data information, obtaining sales prediction data using a sales prediction model and based on the sales source data information, comprising:
obtaining historical sales data and establishing a historical sales data sequence; accumulating the historical sales line data in the historical sales line data sequence to obtain an accumulated data sequence, and establishing a first-order linear differential equation based on the accumulated data sequence; discretizing the first-order linear differential equation, and obtaining a parameter vector by adopting a least square method; constructing a gray prediction model based on the first-order linear differential equation and the parameter vector, and taking the gray prediction model as the sales prediction model; estimating a confidence interval of sales based on a unitary linear regression prediction model, and predicting according to the gray prediction model by using the confidence interval to obtain sales prediction data;
obtaining vendor source data information, utilizing a vendor assessment model and obtaining vendor composite score information based on the vendor source data information, comprising:
determining an evaluation index of a provider; establishing an evaluation set corresponding to the evaluation index, and determining a membership matrix of the evaluation index according to the evaluation index and the evaluation set; determining the weight value of each evaluation index based on the supplier source data information by using an analytic hierarchy process, and generating a judgment vector of a supplier according to the membership matrix and the weight value; calculating a comprehensive evaluation index according to the evaluation vector and the evaluation set, and determining a comprehensive score of the provider based on the comprehensive evaluation index and the evaluation set; wherein the evaluation index includes: price factors, service capabilities, supply periods, supply schedules, research and development capabilities, and quality factors;
Obtaining purchase source data information, facilitating a purchase prediction model and obtaining a purchase prediction result based on the purchase source data information, the sales prediction data, and the vendor comprehensive score information, comprising:
generating a training sample based on the purchase source historical data information, the sales historical data, the provider historical comprehensive scoring information and the corresponding purchase historical information; training a preset deep learning model by using a deep learning method based on the training sample to obtain the supplier evaluation model; updating the preset deep learning model into the supplier evaluation model, and obtaining the purchase prediction result by inputting the purchase source data information, the sales prediction data and the supplier comprehensive score information into the supplier evaluation model; wherein, the purchase source data information includes: BOM data, rejection rate of products, actual productivity, actual inventory information, supply period, contract information and product supply progress; the purchase forecast result comprises: purchasing execution mode, purchasing time and supplier information;
obtaining inventory source data information, obtaining finished product and raw material inventory forecast results using an inventory management model and based on the inventory source data information, the procurement forecast results, the sales source data information, comprising:
Acquiring inventory source data, historical data of sales and purchase, and acquiring warehouse storage space information and finished product and raw material inventory historical information;
taking the historical data, the storehouse storage space information and the finished product and raw material inventory historical information as training data, and training by using a machine learning algorithm to obtain a neural network model;
inputting the stock source data information, the purchasing prediction result and the sales source data information into a trained neural network model, and outputting the stock prediction result of the finished product and the raw material;
wherein the stock source data comprises: stock, supply period, on-the-way order, production period, raw material consumption information; the product and raw material inventory forecasting results include: finished product and raw material inventory information, replenishment program.
2. The method as recited in claim 1, further comprising:
a Bayesian algorithm is adopted, and a Bayesian classifier is trained according to conditional probability estimation and prior probability between occurrence of anomalies of source data and occurrence of anomalies of other source data;
when the source data is determined to be abnormal, performing risk prediction on the source data with the abnormality through a Bayesian classifier obtained after training, and predicting other source data with the abnormality;
Acquiring a corresponding risk prevention scheme based on the other source data with the abnormality;
wherein the source data comprises: sales source data, procurement source data, supplier source data, inventory source data.
3. A supply chain control system, comprising:
a sales prediction control module for obtaining sales source data information, obtaining sales prediction data using a sales prediction model and based on the sales source data information, comprising: obtaining historical sales data and establishing a historical sales data sequence; accumulating the historical sales line data in the historical sales line data sequence to obtain an accumulated data sequence, and establishing a first-order linear differential equation based on the accumulated data sequence; discretizing the first-order linear differential equation, and obtaining a parameter vector by adopting a least square method; constructing a gray prediction model based on the first-order linear differential equation and the parameter vector, and taking the gray prediction model as the sales prediction model; estimating a confidence interval of sales based on a unitary linear regression prediction model, and predicting according to the gray prediction model by using the confidence interval to obtain sales prediction data;
A vendor evaluation module for obtaining vendor source data information, utilizing a vendor evaluation model and obtaining vendor composite score information based on the vendor source data information, comprising: determining an evaluation index of a provider; establishing an evaluation set corresponding to the evaluation index, and determining a membership matrix of the evaluation index according to the evaluation index and the evaluation set; determining the weight value of each evaluation index based on the supplier source data information by using an analytic hierarchy process, and generating a judgment vector of a supplier according to the membership matrix and the weight value; calculating a comprehensive evaluation index according to the evaluation vector and the evaluation set, and determining a comprehensive score of the provider based on the comprehensive evaluation index and the evaluation set; wherein the evaluation index includes: price factors, service capabilities, supply periods, supply schedules, research and development capabilities, and quality factors;
the purchase prediction module is used for obtaining purchase source data information, facilitating a purchase prediction model and obtaining a purchase prediction result based on the purchase source data information, the sales prediction data and the comprehensive score information of the suppliers, and comprises the following steps: generating a training sample based on the purchase source historical data information, the sales historical data, the provider historical comprehensive scoring information and the corresponding purchase historical information; training a preset deep learning model by using a deep learning method based on the training sample to obtain the supplier evaluation model; updating the preset deep learning model into the supplier evaluation model, and obtaining the purchase prediction result by inputting the purchase source data information, the sales prediction data and the supplier comprehensive score information into the supplier evaluation model; wherein, the purchase source data information includes: BOM data, rejection rate of products, actual productivity, actual inventory information, supply period, contract information and product supply progress; the purchase forecast result comprises: purchasing execution mode, purchasing time and supplier information;
The inventory management module is used for obtaining inventory source data information, obtaining finished product and raw material inventory prediction results based on the inventory source data information, the purchase prediction results and the sales source data information by utilizing an inventory management model, and comprises the following steps: acquiring inventory source data, historical data of sales and purchase, and acquiring warehouse storage space information and finished product and raw material inventory historical information; taking the historical data, the storehouse storage space information and the finished product and raw material inventory historical information as training data, and training by using a machine learning algorithm to obtain a neural network model; inputting the stock source data information, the purchasing prediction result and the sales source data information into a trained neural network model, and outputting the stock prediction result of the finished product and the raw material; wherein the stock source data comprises: stock, supply period, on-the-way order, production period, raw material consumption information; the product and raw material inventory forecasting results include: finished product and raw material inventory information, replenishment program.
4. A supply chain control system, comprising:
a memory; and a processor coupled to the memory, the processor configured to perform the method of any of claims 1-2 based on instructions stored in the memory.
5. A computer readable storage medium having stored thereon computer program instructions which, when executed by one or more processors, implement the steps of the method of any of claims 1 to 2.
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 CN109784806A (en) | 2019-05-21 |
| CN109784806B true 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) |
Families Citing this family (46)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110222900B (en) * | 2019-06-12 | 2021-08-31 | 中食安泓(广东)健康产业有限公司 | Chenopodium quinoa willd multi-formula meal replacement powder raw material stock purchase management system |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| US10796279B1 (en) | 2020-04-07 | 2020-10-06 | Coupang Corp. | Systems and methods for automated outbound profile generation |
| 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 |
| 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 |
| CN112581066A (en) * | 2020-12-29 | 2021-03-30 | 江苏诺翔网络科技有限公司 | Control system for supplier supply flow in electronic commerce platform |
| 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 |
| CN112784173B (en) * | 2021-02-26 | 2022-06-10 | 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 |
| CN112884496B (en) * | 2021-05-06 | 2021-08-20 | 达而观数据(成都)有限公司 | Method, device and computer storage medium for calculating enterprise credit factor score |
| CN113191814B (en) * | 2021-05-14 | 2022-07-01 | 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 |
| CN113610657B (en) * | 2021-10-10 | 2021-12-24 | 江苏四方精密钢管有限公司 | Method and system for popularizing and selling steel pipe products |
| CN114186181B (en) * | 2022-02-16 | 2022-05-13 | 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 |
| 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 |
| CN115099726B (en) * | 2022-08-25 | 2022-11-15 | 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
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.太原师范学院学报(自然科学版).2012,第11卷(第2期),第128-132页. * |
| 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.中国优秀硕士学位论文全文数据库经济与管理科学辑.2016,(第2期),第J150-126页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109784806A (en) | 2019-05-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109784806B (en) | Supply chain control method, system and storage medium | |
| Khaleie et al. | Supplier selection using a novel intuitionist fuzzy clustering approach | |
| Yerpude et al. | Impact of internet of things (IoT) data on demand forecasting | |
| CN111401808A (en) | Material agreement inventory demand prediction method based on hybrid model | |
| Kumar Sharma et al. | Developing a Bayesian network model for supply chain risk assessment | |
| Chen | An effective fuzzy collaborative forecasting approach for predicting the job cycle time in wafer fabrication | |
| Garmabaki et al. | Maintenance optimization using multi-attribute utility theory | |
| Taghizadeh | Utilizing artificial neural networks to predict demand for weather-sensitive products at retail stores | |
| Daroudi et al. | The minimum latency in location routing fuzzy inventory problem for perishable multi-product materials | |
| Tadayonrad et al. | A new key performance indicator model for demand forecasting in inventory management considering supply chain reliability and seasonality | |
| Ivanov et al. | Demand forecasting | |
| Manucharyan | Multi-criteria decision making for supplier selection: A literature critique | |
| Wang et al. | Modeling of individual customer delivery satisfaction: An AutoML and multi-agent system approach | |
| Naik et al. | Machine Learning based Food Sales Prediction using Random Forest Regression | |
| Klocker et al. | A machine learning approach for automated cost estimation of plastic injection molding parts | |
| Aikhuele et al. | A subjective and objective fuzzy-based analytical hierarchy process model for prioritization of lean product development practices | |
| Wang et al. | A novel auto-weighting deep-learning fuzzy collaborative intelligence approach | |
| Rajak et al. | Designing of fuzzy expert heuristic models with cost management toward coordinating AHP, fuzzy TOPSIS and FIS approaches | |
| Goyal et al. | A fuzzy multi attribute decision making approach for evaluating effectiveness of advanced manufacturing technology–in Indian context | |
| Vaitkus et al. | Electrical spare parts demand forecasting | |
| Thipparat | Application of adaptive neuro fuzzy inference system in supply chain management evaluation | |
| Li et al. | Assessment of product resilience towards the changing customer requirements | |
| Tarish | Optimized computational techniques-based inventory control process in supply chain management | |
| Ziegler et al. | Applications of Neural Networks in Engineer-to-order Environment | |
| Tse et al. | Solving complex logistics problems with multi-artificial intelligent system |
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 |