Supply chain management method and system for cloud warehousing

Abstract

The application relates to the technical field of cloud warehouse management, in particular to a supply chain management method and system for cloud warehouse management, which discloses a corresponding warehouse scene building module, determines various entity warehouses aimed at by cloud warehouse management, and builds a warehouse supply chain simulation scene corresponding to each entity warehouse; a warehouse supply chain management process generation module regularly generates a warehouse supply chain management process, acquires inventory management prediction data and supply chain order prediction data corresponding to each entity warehouse; and a management recommendation landing plan generation module generates management recommendation landing plans of each entity warehouse in sequence according to the warehouse supply chain management process. The application intelligently senses the change demand degree of the management recommendation landing plans of each entity warehouse in the cloud warehouse, intelligently identifies the entity warehouses that need to generate new management recommendation landing plans, and solves the problem of blindness of resource allocation in cloud warehouse management.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of cloud warehouse management, more particularly, it relates to a supply chain management method and system for cloud warehouse. BACKGROUND

[0002] In recent years, with the rapid development of cloud computing and big data technology, cloud warehouse management mode has gradually become an important direction in the field of supply chain management. Traditional cloud warehouse management systems mostly use static resource configuration and passive response mechanism, rely on manual experience for inventory scheduling and order processing, and are difficult to cope with dynamic changes in supply chain demand. Especially in the multi-entity warehouse collaborative scene, due to the lack of in-depth analysis of the personalized operation needs of the warehouse, there are often problems such as uneven resource allocation, inventory backlog or shortage, order response delay, etc., resulting in low overall efficiency of the supply chain.

[0003] In the prior art, some schemes try to optimize warehouse management through data acquisition and visualization technology, but there are still significant defects: the adaptability of the scheme is insufficient: most systems use a "one-size-fits-all" management strategy, and do not adapt the personalized scheme to the operation characteristics (such as geographical location, category characteristics, logistics network) of different entity warehouses, resulting in resource waste; the dynamic optimization capability is missing: there is a lack of multi-dimensional evaluation mechanism for the landing effect of the management scheme, which cannot actively identify the scheme failure risk and trigger the optimization process in time.

[0004] In view of the above problems, the present application provides a supply chain management method and system for cloud warehouse, to realize the transformation from "experience-driven" to "data intelligent-driven". SUMMARY

[0005] In view of the deficiencies in the prior art, the purpose of the present application is to provide a supply chain management method and system for cloud warehouse.

[0006] To achieve the above purpose, the present application provides the following technical scheme:

[0007] The supply chain management method for cloud warehouse is as follows:

[0008] Step 1: Determine each entity warehouse to which the cloud warehouse is directed;

[0009] Step 2: Build a warehouse supply chain simulation scene corresponding to each entity warehouse;

[0010] Step 3: Generate a warehouse supply chain management process regularly;

[0011] Step 4: Generate a management recommendation landing scheme for each entity warehouse.

[0012] Further, the supply chain management system for cloud warehouse comprises

[0013] The corresponding warehouse scenario building module determines each entity warehouse corresponding to the cloud warehouse, and builds a warehouse supply chain simulation scenario corresponding to each entity warehouse;

[0014] The warehouse supply chain management process generation module generates a warehouse supply chain management process regularly, and obtains inventory management prediction data and supply chain order prediction data corresponding to each entity warehouse;

[0015] The management recommendation landing plan generation module generates management recommendation landing plans for each entity warehouse in turn according to the warehouse supply chain management process.

[0016] Further, the warehouse supply chain management process is generated regularly as follows: regularly obtaining supply chain management scheme change values of each entity warehouse, sorting all entity warehouses in turn from large to small according to the numerical values of the supply chain management scheme change values, and determining the warehouse supply chain management process according to the sorting.

[0017] Further, the supply chain management scheme change value of the entity warehouse is regularly obtained as follows: selecting an entity warehouse, obtaining management recommendation landing plans of the entity warehouse in the previous continuous p periods, obtaining scheme landing difference values of the management recommendation landing plans of each adjacent two periods, and calculating the supply chain management scheme change value of the entity warehouse by summing all scheme landing difference values and taking the average.

[0018] Further, the scheme landing difference value of the management recommendation landing plans of the adjacent two periods is obtained as follows: the adjacent two periods of management recommendation landing plans are marked as management recommendation landing plan M and management recommendation landing plan N respectively, the strategy parameters of the management recommendation landing plan M and the strategy parameters of the management recommendation landing plan N are obtained, the strategy parameters of the management recommendation landing plan M and the strategy parameters of the management recommendation landing plan N are synchronously imported into the scheme landing comparison model, and the scheme landing comparison model exports the scheme landing difference value.

[0019] Further, the inventory management prediction data and the supply chain order prediction data corresponding to an entity warehouse are regularly generated as follows: selecting an entity warehouse, regularly collecting inventory management data and supply chain order data corresponding to the entity warehouse, and collecting inventory management data and supply chain order data corresponding to the entity warehouse in the previous continuous i periods, combining i+1 inventory management data into a time series set in a time series manner, combining i+1 supply chain order data into a time series set in a time series manner, importing the time series set corresponding to the inventory management data into an inventory management data prediction model corresponding to the entity warehouse, and exporting inventory management prediction data from the inventory management data prediction model. The time series set corresponding to the supply chain order data is imported into a supply chain order data prediction model corresponding to the entity warehouse, and supply chain order prediction data is exported from the supply chain order data prediction model.

[0020] Further, the management recommended landing plan generation steps of the entity warehouse are as follows: selecting an entity warehouse, importing the inventory management prediction data and supply chain order prediction data corresponding to the entity warehouse into the warehouse supply chain simulation scene, controlling the warehouse supply chain simulation scene to perform multiple simulations, generating a warehouse supply chain management scheme each time, obtaining the scheme landing evaluation value of each warehouse supply chain management scheme, setting a scheme landing evaluation threshold, marking the corresponding warehouse supply chain management scheme as a management feasible scheme when the scheme landing evaluation value of the warehouse supply chain management scheme is greater than or equal to the scheme landing evaluation threshold, further obtaining the comprehensive data fluctuation landing value of each management feasible scheme, and marking the management feasible scheme with the maximum comprehensive data fluctuation landing value as the management recommended landing plan.

[0021] Further, the warehouse supply chain management scheme landing evaluation value generation steps are as follows: the warehouse supply chain simulation scene is simulated based on a warehouse supply chain management scheme, all supply chain order processing in the warehouse supply chain simulation scene is completed, each supply chain management index of the warehouse supply chain simulation scene is collected, each supply chain management index is combined into a supply chain management index set in a set manner, the supply chain management index set is imported into the scheme landing evaluation model, and the scheme landing evaluation model exports a scheme landing evaluation value.

[0022] Further, the management feasible scheme comprehensive data fluctuation landing value obtaining steps are as follows: obtaining the inventory management prediction data and supply chain order prediction data corresponding to the entity warehouse, determining each refined data contained in the inventory management prediction data and the supply chain order prediction data, determining the data fluctuation range of each refined data, and then randomly generating multiple inventory management prediction fluctuation data and multiple supply chain order prediction fluctuation data, randomly combining the multiple inventory management prediction fluctuation data and the multiple supply chain order prediction fluctuation data to generate multiple random data groups, obtaining the scheme landing evaluation value of each random data group, calculating the average random landing evaluation value by summing and averaging all random data group scheme landing evaluation values, comparing the scheme landing evaluation values of all random data groups two by two, calculating the absolute difference value of the scheme landing evaluation values of the two compared random data groups, calculating the random landing evaluation turbulence value, calculating the average random landing evaluation turbulence value by summing and averaging all random landing evaluation turbulence values, and calculating the comprehensive data fluctuation landing value of the management feasible scheme by ratio calculation of the average random landing evaluation value and the average random landing evaluation turbulence value.

[0023] Further, the scheme landing evaluation value of the random data set is obtained as follows: the warehouse supply chain simulation scene is imported with the management feasible scheme, the warehouse inventory management prediction fluctuation data of the random data set and the supply chain order prediction fluctuation data, when all the supply chain orders in the warehouse supply chain simulation scene are processed according to the management feasible scheme, the scheme landing evaluation value of the random data set can be obtained.

[0024] Compared with the prior art, the present application has the following beneficial effects:

[0025] The system and method of the present application builds warehouse supply chain simulation scenes of each entity warehouse in cloud storage, regularly combines time sequence analysis means to predict the warehouse inventory management data and supply chain order data of each entity warehouse, analyzes and adapts the warehouse supply chain management scheme of the predicted data of the entity warehouse in combination with the warehouse supply chain simulation scene, further analyzes a plurality of warehouse supply chain management schemes of the adapted entity warehouse, analyzes various inventory management and supply chain order conditions that the entity warehouse may encounter in the future, selects the warehouse supply chain management scheme with the best landing effect under various conditions, intelligently perceives the change demand degree of the management recommended landing scheme of each entity warehouse in cloud storage through the regularly generated warehouse supply chain management process, intelligently identifies the entity warehouse that needs to generate a new management recommended landing scheme, solves the problem of blind resource allocation in cloud storage management, and realizes the leapfrog upgrade of the supply chain management of cloud storage from 'passive response' to 'active optimization'. BRIEF DESCRIPTION OF DRAWINGS

[0026] Fig. 1 The principle block diagram of the system of the present application is shown in the figure;

[0027] Fig. 2 The generation flowchart of the management recommended landing scheme is shown in the figure;

[0028] Fig. 3 The flowchart of the method of the present application is shown in the figure. DETAILED DESCRIPTION

[0029] Embodiment one, as Figs. 1-2 , a supply chain management system for cloud storage, comprising a corresponding warehouse scene building module, a warehouse supply chain management process generation module and a management recommended landing scheme generation module.

[0030] The corresponding warehouse scene building module determines each entity warehouse to which the cloud storage is directed, and builds a warehouse supply chain simulation scene corresponding to each entity warehouse.

[0031] The building steps of the warehouse supply chain simulation scene corresponding to the entity warehouse are as follows: selecting an entity warehouse, collecting all basic warehouse data of the entity warehouse (the basic warehouse data includes but is not limited to warehouse layout data, equipment parameters, personnel efficiency, etc., the warehouse layout data can be further refined into sorting area area, labeler position, channel width, etc., the equipment parameters can be further refined into labeler processing efficiency, AGV speed, shelf capacity, etc., the personnel efficiency can be further refined into picker / packager processing speed, etc., the data source of the warehouse layout data is CAD drawing, the data source of the equipment parameters is equipment specification + actual measurement, and the data source of the personnel efficiency is operation record analysis), first, a physical model of the entity warehouse is created, and the creation steps include drawing layout and defining resources, drawing layout: importing CAD drawing into the simulation software, dividing storage area, picking area, sorting area, packaging area, and warehouse-out temporary storage area, marking the coordinates of each area (such as picking area start coordinate (10, 10), end coordinate (50, 30)); dragging and dropping "sorting machine", "labeler", "AGV charging pile" and other modules, setting physical size (such as labeler occupying space 2m*1m); defining resources: creating "picker" and "packager" resource pool, setting quantity (such as 20 pickers), working time (8 hours per shift, including 15 minutes rest); setting labeler quantity (such as 2), processing time (1.2 seconds per single), AGV quantity (30), and load capacity (50kg per AGV); modeling the order processing flow, including picking, sorting, packaging and warehouse-out, etc., then calibrating single link and verifying whole link, finally, the warehouse supply chain simulation scene corresponding to the entity warehouse is built, which can simulate the supply chain order processing flow of the entity warehouse, and needs to be updated at any time according to the actual configuration of the entity warehouse (such as updating layout area, number of personnel).

[0032] The warehouse supply chain management process generation module generates a warehouse supply chain management process (all entity warehouses are sorted in a certain order in the warehouse supply chain management process) regularly, and obtains inventory management prediction data and supply chain order prediction data corresponding to each entity warehouse.

[0033] The regular generation steps of the warehouse supply chain management process are as follows: regularly obtaining supply chain management scheme change values of each entity warehouse, sorting all entity warehouses in descending order of the values of the supply chain management scheme change values, and determining the warehouse supply chain management process according to the sorting.

[0034] The regular obtaining steps of the supply chain management scheme change value of the entity warehouse are as follows: selecting an entity warehouse, obtaining the management recommended landing scheme of the entity warehouse in the previous continuous p periods, obtaining the scheme landing difference value of the management recommended landing scheme of each adjacent two periods, summing all scheme landing difference values and taking the average value to calculate, and calculating the supply chain management scheme change value of the entity warehouse.

[0035] The acquisition step of the scheme landing difference value of the management recommendation landing plan of the two adjacent periods is as follows: the management recommendation landing plans of the two adjacent periods are respectively marked as management recommendation landing plan M and management recommendation landing plan N, the strategy parameters of the management recommendation landing plan M and the strategy parameters of the management recommendation landing plan N are acquired, the strategy parameters of the management recommendation landing plan M and the strategy parameters of the management recommendation landing plan N are synchronously imported into the scheme landing comparison model, and the scheme landing comparison model exports the scheme landing difference value.

[0036] The building method of the scheme landing comparison model is as follows: a deep learning model is built, a plurality of scheme strategy parameter groups are collected, each scheme strategy parameter group includes the strategy parameters of two management recommendation landing plans, the built deep learning model is trained based on the scheme strategy parameter group as the basic data, in this process, each scheme strategy parameter group is assigned a scheme landing difference value, the value range of the scheme landing difference value is set to 0 to 50, the size of the scheme landing difference value has a clear meaning, the larger the value is, the greater the difference between the strategy parameters of the two management recommendation landing plans in the scheme strategy parameter group is, that is, the management recommendation landing plan of the last period is difficult to apply to the next period, and if it is applied, it may cause a greater management risk, then the plurality of scheme strategy parameter groups are divided into a training set, a verification set and a test set according to a specific proportion, the specific division proportion is determined as 60:20:20, the training set is first used to repeatedly train the deep learning model, in the training process, the performance of the model in the training stage is verified in time by means of the verification set, the parameters of the model are adjusted in time according to the verification result, the structure of the model is optimized, and the model is developed in a more accurate and stable direction, and finally, the scheme landing comparison model is built.

[0037] The periodic generation steps of the inventory management prediction data and the supply chain order prediction data corresponding to one physical warehouse are as follows: selecting one physical warehouse, periodically collecting the inventory management data and the supply chain order data corresponding to the physical warehouse (the periodicity corresponding to the periodicity is adjusted and set according to the management fineness requirement of the cloud warehouse, the inventory management data specifically includes inventory level, inventory turnover rate, replenishment order execution rate, etc., and the supply chain order data specifically includes order response time, order quantity, on-time delivery rate, wrong delivery rate, order cancellation rate, etc.), and collecting the inventory management data and the supply chain order data corresponding to the previous i periods of the physical warehouse, combining i+1 inventory management data in time series as a time series set, combining i+1 supply chain order data in time series as a time series set, importing the time series set corresponding to the inventory management data into the inventory management data prediction model corresponding to the physical warehouse, and the inventory management data prediction model exports the inventory management prediction data, and importing the time series set corresponding to the supply chain order data into the supply chain order data prediction model corresponding to the physical warehouse, and the supply chain order data prediction model exports the supply chain order prediction data.

[0038] Each physical warehouse includes an inventory management data prediction model and a supply chain order data prediction model, and the inventory management data prediction model and the supply chain order data prediction model are built based on an LSTM model. Hereinafter, No. 1 physical warehouse is randomly defined, and the brief building steps of the inventory management data prediction model and the supply chain order data prediction model corresponding to No. 1 physical warehouse are disclosed.

[0039] The building steps of the inventory management data prediction model corresponding to No. 1 physical warehouse are as follows: building an LSTM model, collecting a plurality of time series sets corresponding to the inventory management data of No. 1 physical warehouse, using the plurality of time series sets corresponding to the inventory management data as basic data, and training the built LSTM model, in which process, each time series set corresponding to the inventory management data is assigned an inventory management prediction data, the inventory management prediction data is to predict the inventory management data of No. 1 physical warehouse in the next period, then the plurality of time series sets corresponding to the inventory management data are divided into a training set, a validation set and a test set according to a specific ratio, and the specific division ratio is determined as 60:20:20, the training set (60%): for model parameter learning; the validation set (20%): to evaluate the model performance during the training process, to assist in adjusting the hyperparameters (such as learning rate, number of hidden layer neurons), and to avoid overfitting; the test set (20%): after the model training is completed, the independent data not participating in the training is used to evaluate the prediction accuracy and ensure the generalization ability, finally, the inventory management data prediction model corresponding to No. 1 physical warehouse is built.

[0040] The steps for building the supply chain order data prediction model corresponding to the No. 1 physical warehouse are as follows: building an LSTM model, collecting multiple time series corresponding to the supply chain order data of the No. 1 physical warehouse, using the multiple time series corresponding to the supply chain order data as basic data, training the built LSTM model, in this process, assigning a supply chain order prediction data to each time series corresponding to the supply chain order data, the supply chain order prediction data is to predict the supply chain order data of the No. 1 physical warehouse in the next cycle, then dividing the multiple time series corresponding to the supply chain order data into training set, validation set and test set according to a certain proportion, the specific division proportion is determined as 60%:20%:20%, the training set (60%): used for model parameter learning; the validation set (20%): used to evaluate the model performance during the training process, to assist in adjusting the hyperparameters (such as learning rate, number of hidden layer neurons), to avoid overfitting; the test set (20%): after the model training is completed, the independent data not involved in the training is used to evaluate the prediction accuracy and ensure the generalization ability, finally, the supply chain order data prediction model corresponding to the No. 1 physical warehouse is built.

[0041] The management recommendation landing plan generation module generates the management recommendation landing plan of each physical warehouse in turn according to the warehouse supply chain management process.

[0042] The steps for generating the management recommendation landing plan of the physical warehouse are as follows: selecting a physical warehouse, importing the inventory management prediction data and the supply chain order prediction data corresponding to the physical warehouse into the warehouse supply chain simulation scene, controlling the warehouse supply chain simulation scene to simulate multiple times, generating a warehouse supply chain management scheme each time (there are differences in corresponding strategy parameters between different warehouse supply chain management schemes, such as different safety stock coefficients, different replenishment buffer lead times, different order allocation cost weights, and different order allocation time efficiency weights, the above strategy parameters are adjustable variables, and the differentiated warehouse supply chain management scheme is generated by dynamically modifying these strategy parameters), obtaining the scheme landing evaluation value of each warehouse supply chain management scheme, setting a scheme landing evaluation threshold (which is scientifically set by combining industry benchmarks and cost-benefit analysis), when the scheme landing evaluation value of the warehouse supply chain management scheme is greater than or equal to the scheme landing evaluation threshold, the corresponding warehouse supply chain management scheme is marked as a management feasible scheme (less than the case is not marked), further obtaining the comprehensive data fluctuation landing value of each management feasible scheme, and the management feasible scheme with the maximum comprehensive data fluctuation landing value is marked as the management recommendation landing plan.

[0043] The acquisition steps of the comprehensive data fluctuation landing value of the management feasible solution are as follows: obtaining the inventory management prediction data and the supply chain order prediction data corresponding to the entity warehouse, determining each refined data contained in the inventory management prediction data and the supply chain order prediction data (the inventory management prediction data contains inventory level, inventory turnover rate, replenishment order execution rate and other refined data, and the supply chain order prediction data contains order response time, order quantity, on-time delivery rate, wrong delivery rate and order cancellation rate and other refined data), determining the data fluctuation range of each refined data (the data fluctuation range of each refined data is determined based on historical data statistical analysis, scene extreme value and industry experience parameters, to ensure that the fluctuation range reflects the historical law of the data and covers the possible extreme situation in the future), and then randomly generating a plurality of inventory management prediction fluctuation data and a plurality of supply chain order prediction fluctuation data (each inventory management prediction fluctuation data is different from each other, and each supply chain order prediction fluctuation data is also different from each other, each inventory management prediction fluctuation data is randomly adjusted in the data fluctuation range based on the inventory management prediction data, and the corresponding inventory management prediction fluctuation data is generated after adjustment, and the supply chain order prediction fluctuation data is the same), randomly combining the plurality of inventory management prediction fluctuation data and the plurality of supply chain order prediction fluctuation data to generate a plurality of random data groups (each random data group contains an inventory management prediction fluctuation data and a supply chain order prediction fluctuation data), obtaining the solution landing evaluation value of each random data group, calculating the sum value of the solution landing evaluation values of all random data groups and taking the average value to calculate the average random landing evaluation value, comparing the solution landing evaluation values of all random data groups two by two, calculating the absolute difference value of the solution landing evaluation values of the two random data groups compared, calculating the random landing evaluation fluctuation value, calculating the sum value of all random landing evaluation fluctuation values and taking the average value to calculate the average random landing evaluation fluctuation value, and calculating the ratio of the average random landing evaluation value and the average random landing evaluation fluctuation value to calculate the comprehensive data fluctuation landing value of the management feasible solution.

[0044] The acquisition steps of the solution landing evaluation value of the random data group are as follows: importing the management feasible solution, the inventory management prediction fluctuation data and the supply chain order prediction fluctuation data of the random data group into the warehouse supply chain simulation scene, when all supply chain orders in the warehouse supply chain simulation scene are processed according to the management feasible solution, the solution landing evaluation value of the random data group can be obtained.

[0045] The generation step of the scheme landing evaluation value of the warehouse supply chain management scheme is as follows: the warehouse supply chain simulation scenario is simulated based on a warehouse supply chain management scheme, when all the supply chain order processing in the warehouse supply chain simulation scenario is completed, the warehouse supply chain simulation scenario is collected. Various supply chain management indicators (supply chain management indicators include but are not limited to the following: inventory cost, order satisfaction rate, inventory turnover rate), combine each supply chain management indicator into a supply chain management indicator set in the form of a set, import the supply chain management indicator set into the scheme landing evaluation model, and the scheme landing evaluation model exports a scheme landing evaluation value (i.e. the scheme landing evaluation value of the warehouse supply chain management scheme).

[0046] The building step of the scheme landing evaluation model is as follows: a deep learning model is built, a plurality of supply chain management indicator sets are collected, each supply chain management indicator set belongs to a warehouse supply chain management scheme, the supply chain management indicator set is used as the basic data, and the built deep learning model is trained. In this process, each supply chain management indicator set is assigned a scheme landing evaluation value, the value range of the scheme landing evaluation value is set to 0-100, and the size of the scheme landing evaluation value has a clear meaning. The larger the value is, the better the comprehensive performance of the warehouse supply chain management scheme corresponding to the supply chain management indicator set in the cost, efficiency and service dimensions, and the more suitable it is for actual landing implementation. Then, the plurality of supply chain management indicator sets are divided into training set, validation set and test set according to a certain proportion, and the specific division proportion is determined as 70:15:15. First, the training set is used to repeatedly train the deep learning model, and in the training process, the validation set is used to verify the performance of the model in the training stage in time, and the parameters of the model are adjusted in time according to the verification result, and the structure of the model is optimized, so that it develops in a more accurate and stable direction. Finally, the scheme landing evaluation model is built.

[0047] The system builds warehouse supply chain simulation scenarios for each entity warehouse in cloud storage, regularly predicts inventory management data and supply chain order data for each entity warehouse by combining time series analysis means, analyzes and adapts warehouse supply chain management schemes for entity warehouse predicted data in combination with warehouse supply chain simulation scenarios, and further analyzes a plurality of warehouse supply chain management schemes for the entity warehouse. Analyze the various inventory management and supply chain order situations that the entity warehouse may encounter, select the warehouse supply chain management scheme with the best landing effect under various situations, and intelligently perceive the change demand degree of the management recommended landing scheme of each entity warehouse in cloud storage through the regularly generated warehouse supply chain management process.

[0048] Embodiment two, as Fig. 3 , a supply chain management method for cloud storage, the steps are as follows:

[0049] Step one: determine each entity warehouse targeted by cloud warehousing;

[0050] Step two: build a warehouse supply chain simulation scenario corresponding to each entity warehouse;

[0051] Step three: generate a warehouse supply chain management process regularly;

[0052] Step four: generate management recommendation landing plans for each entity warehouse.

[0053] The above method intelligently identifies the entity warehouse that needs to generate a new management recommendation landing plan, solves the problem of blind resource allocation in cloud warehousing management, and realizes the leapfrog upgrade of cloud warehousing supply chain management from "passive response" to "active optimization".

[0054] The above formulas are all dimensionless values, and the preset parameters in the formulas are set by a person skilled in the art according to the actual situation.

[0055] Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0056] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and unit described above can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0057] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units or components shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0058] The above merely provides the specific implementation of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can easily think of the changes or replacements within the technical range disclosed by the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A supply chain management approach for cloud warehousing, characterized in that, The steps are as follows: Step one: determine the respective entity warehouses targeted by cloud storage; Step two: build a warehouse supply chain simulation scenario corresponding to each entity warehouse; Step three: generate warehouse supply chain management processes regularly; Step four: generate management recommendation landing plans for each entity warehouse; The steps for generating the management recommendation landing plans for the entity warehouse are as follows: select an entity warehouse, import the inventory management prediction data and supply chain order prediction data corresponding to the entity warehouse into the warehouse supply chain simulation scenario, control the warehouse supply chain simulation scenario to perform multiple simulations, generate a warehouse supply chain management scheme for each simulation, obtain the scheme landing evaluation value of each warehouse supply chain management scheme, set a scheme landing evaluation threshold, when the scheme landing evaluation value of the warehouse supply chain management scheme is greater than or equal to the scheme landing evaluation threshold, mark the corresponding warehouse supply chain management scheme as a management feasible scheme, further obtain the comprehensive data fluctuation landing value of each management feasible scheme, and mark the management feasible scheme with the maximum comprehensive data fluctuation landing value as the management recommendation landing plan; The steps for generating the scheme landing evaluation value of the warehouse supply chain management scheme are as follows: the warehouse supply chain simulation scenario is simulated based on a warehouse supply chain management scheme, when all supply chain orders in the warehouse supply chain simulation scenario are processed, the various supply chain management indicators of the warehouse supply chain simulation scenario are collected, the various supply chain management indicators are combined into a supply chain management indicator set in the form of a set, the supply chain management indicator set is imported into the scheme landing evaluation model, and the scheme landing evaluation model outputs a scheme landing evaluation value; The steps for obtaining the comprehensive data fluctuation landing value of the management feasible scheme are as follows: obtain the inventory management prediction data and supply chain order prediction data corresponding to the entity warehouse, determine the various detailed data contained in the inventory management prediction data and supply chain order prediction data, determine the data fluctuation range of each detailed data, and then randomly generate multiple inventory management prediction fluctuation data and multiple supply chain order prediction fluctuation data, randomly combine the multiple inventory management prediction fluctuation data and the multiple supply chain order prediction fluctuation data to generate multiple random data groups, obtain the scheme landing evaluation value of each random data group, calculate the average of the sum of the scheme landing evaluation values of all random data groups to obtain the average random landing evaluation value, compare the scheme landing evaluation values of all random data groups in pairs, calculate the absolute difference value of the scheme landing evaluation values of the two random data groups compared, calculate the random landing evaluation turbulence value, calculate the average of the sum of all random landing evaluation turbulence values to obtain the average random landing evaluation turbulence value, and calculate the ratio of the average random landing evaluation value to the average random landing evaluation turbulence value to obtain the comprehensive data fluctuation landing value of the management feasible scheme.

2. The supply chain management system for cloud warehousing, applied to the supply chain management method for cloud warehousing in claim 1, characterized in that, The steps for generating the management recommendation landing plans for the entity warehouse are as follows: The corresponding warehouse scenario building module determines the respective entity warehouses targeted by cloud storage, and builds a warehouse supply chain simulation scenario corresponding to each entity warehouse; The warehouse supply chain management process generation module generates a warehouse supply chain management process periodically, and obtains inventory management prediction data and supply chain order prediction data corresponding to each entity warehouse. The management recommendation landing plan generation module generates management recommendation landing plans for each entity warehouse in turn according to the warehouse supply chain management process.

3. The supply chain management system for cloud warehousing as claimed in claim 2 wherein, The periodic generation of the warehouse supply chain management process is as follows: periodically obtaining supply chain management scheme change values of each entity warehouse, sorting all entity warehouses in turn from large to small according to the numerical values of the supply chain management scheme change values, and determining the warehouse supply chain management process according to the sorting.

4. The supply chain management system for cloud warehousing as claimed in claim 3 wherein, The periodic obtaining of the supply chain management scheme change value of the entity warehouse is as follows: selecting an entity warehouse, obtaining management recommendation landing plans of the entity warehouse in the previous p consecutive periods, obtaining scheme landing difference values of the management recommendation landing plans of each adjacent two periods, and calculating the supply chain management scheme change value of the entity warehouse by summing all scheme landing difference values and taking the average.

5. The supply chain management system for cloud warehousing as claimed in claim 4 wherein, The obtaining of the scheme landing difference value of the management recommendation landing plans of the adjacent two periods is as follows: the adjacent two periods of management recommendation landing plans are marked as management recommendation landing plan M and management recommendation landing plan N respectively, the strategy parameters of the management recommendation landing plan M and the strategy parameters of the management recommendation landing plan N are obtained, the strategy parameters of the management recommendation landing plan M and the strategy parameters of the management recommendation landing plan N are synchronously imported into the scheme landing comparison model, and the scheme landing comparison model exports the scheme landing difference value.

6. The supply chain management system for cloud warehousing as claimed in claim 2 wherein, The periodic generation of the inventory management prediction data and the supply chain order prediction data corresponding to an entity warehouse is as follows: selecting an entity warehouse, periodically collecting inventory management data and supply chain order data corresponding to the entity warehouse, collecting inventory management data and supply chain order data corresponding to the entity warehouse in the previous i consecutive periods, combining i+1 inventory management data into a time series set in a time series manner, combining i+1 supply chain order data into a time series set in a time series manner, importing the time series set corresponding to the inventory management data into an inventory management data prediction model corresponding to the entity warehouse, and exporting inventory management prediction data from the inventory management data prediction model.

7. The supply chain management system for cloud warehousing as claimed in claim 2 wherein, The obtaining of the scheme landing evaluation value of the random data set is as follows: importing the management feasible scheme, the inventory management prediction fluctuation data and the supply chain order prediction fluctuation data of the random data set into the warehouse supply chain simulation scene, and obtaining the scheme landing evaluation value of the random data set when all supply chain orders in the warehouse supply chain simulation scene are processed according to the management feasible scheme.

Images