CN113469597A

CN113469597A - Intelligent supply chain system and server platform

Info

Publication number: CN113469597A
Application number: CN202010241378.6A
Authority: CN
Inventors: 戴芸; 左滨; 黎杰臻; 赖素红
Original assignee: Hitachi Ltd
Current assignee: Hitachi Ltd
Priority date: 2020-03-31
Filing date: 2020-03-31
Publication date: 2021-10-01
Also published as: JP2021163485A; JP7105336B2

Abstract

The invention provides an intelligent supply chain system and a server platform. An intelligent supply chain system for managing supply chains of a plurality of commodities, comprising: a commodity classification device for classifying a plurality of commodities based on the history data; a sales prediction device that predicts sales for each of a plurality of types of commodities based on historical data and the classification result of the commodity classification device for the plurality of types of commodities; and the intelligent replenishment device is used for applying an automatic replenishment model to generate a replenishment decision based on the prediction result of the sales prediction device. Therefore, three important blocks of commodity classification, sales prediction and intelligent replenishment can be effectively fused, so that the service becomes accurate, the supply chain becomes transparent, flexible and agile, and all functions are more cooperated.

Description

Intelligent supply chain system and server platform

Technical Field

The invention relates to an intelligent supply chain system and a server platform, in particular to a layout mode of an intelligent supply chain.

Background

In recent years, there is a strong need for effective management of the supply chain between manufacturers, suppliers, and sales stores. Specifically, in supply chain management, the commodities need to be scientifically classified and located, and then corresponding selling and inventory strategies are adopted for different classes of commodities. Secondly, more accurate sales prediction is needed to be used as a driver of the commodity quantity, a demand plan taking the sales prediction as a core can support the planning of each link, and the operation cost can be reduced by several times when the prediction accuracy is improved by 1%. And finally, applying the automatic replenishment model to a specific scene to optimize an inventory structure so as to continuously keep the inventory at a healthy level, positioning all SKUs (stock keeping units) meeting the replenishment condition under the condition of warehousing, obtaining a recommendation of replenishment quantity according to the replenishment task running model, and finally generating a replenishment decision to be delivered to production.

However, the prior art does not provide a supply chain management scheme that satisfies the above requirements, and an intelligent supply chain layout method that can satisfy the above requirements is urgently needed.

Disclosure of Invention

The invention aims to solve the technical problems in the prior art, and aims to provide an intelligent supply chain system and a server platform which can effectively integrate three important blocks of commodity classification, sales prediction and intelligent replenishment, so that the service becomes accurate, the supply chain becomes transparent, flexible and agile, and all functions are more cooperative.

One embodiment of the present invention provides an intelligent supply chain system for managing supply chains of a plurality of types of commodities, including: a commodity classification device for classifying a plurality of commodities based on the history data; a sales prediction device that predicts sales for each of a plurality of types of commodities based on historical data and the classification result of the commodity classification device for the plurality of types of commodities; and the intelligent replenishment device is used for applying an automatic replenishment model to generate a replenishment decision based on the prediction result of the sales prediction device.

Therefore, three important blocks of commodity classification, sales prediction and intelligent replenishment can be effectively fused, so that the service becomes accurate, the supply chain becomes transparent, flexible and agile, and all functions are more cooperated.

In the above-described smart supply chain system, the commodity classification device may classify a plurality of commodities to obtain a preliminary classification result by using an ABC classification result based on sales data as history data and a latest sales time interval as two dimensions, calculate a commodity characteristic analysis index for each commodity based on the history data, and further subdivide the preliminary classification result into a plurality of dimensions using the calculated commodity characteristic analysis index as a final classification result, the commodity characteristic analysis index including at least one of a sales frequency, a variation coefficient, a variation width, a customer concentration ratio, a sales tempo, and a distribution interval.

Thus, the commodity requiring the confirmation of the demand prediction result by the salesperson can be extracted based on the segmentation result, and the accuracy of the demand prediction can be improved by effectively combining the business experience of the salesperson.

In the above-described intelligent supply chain system, the sales predicting device may predict, for each product subdivided by the product classifying device into products for which a demand prediction result needs to be confirmed, an amount of sales corresponding to at least one prediction time for each product, using any one of a point prediction method, a section prediction method, and a mixed prediction method combining the point prediction method and the section prediction method, with respect to the at least one prediction time to be predicted.

Thus, by using the most suitable prediction method in combination with factors such as the classification result of the product and the time to be predicted, a more accurate prediction result corresponding to the required prediction time can be obtained.

In the above-described intelligent supply chain system, the intelligent replenishment device may generate a replenishment plan using any one of a replenishment model based on point prediction, a mixed replenishment model based on point prediction and section prediction, and a replenishment model based on section prediction, based on the prediction result of the sales prediction device and the product characteristic analysis index calculated by the product classification device.

Therefore, according to the characteristics of different commodities, different replenishment periods and other factors, the replenishment plan is generated by using the most suitable replenishment model, and a replenishment decision which meets the requirements better can be provided.

In the intelligent supply chain system, the sales predicting device may include: a point prediction unit that performs point prediction based on the long-and-short-term memory network; and a section prediction unit that performs probability density section prediction; the intelligent supply chain system further comprises: and a model selecting unit that selects, in the sales predicting device, whether to perform sales prediction by the point predicting unit, the section predicting unit, or both the point predicting unit and the section predicting unit, based on at least one of an application target, a prediction time, and a classification result of the product classifying device.

Thus, the sales prediction can be performed by selecting an optimal prediction method according to the application (for example, sales store, supplier, and manufacturer), the prediction time (for example, 1 day, 1 week, 1 month, 1 year), the classification result, and the like.

In the above-described intelligent supply chain system, the intelligent replenishment device may include: a point prediction replenishment unit that generates a replenishment plan of a fixed amount or an irregular amount using a replenishment model based on point prediction; a mixed replenishment part for generating a regular and quantitative replenishment plan by using a mixed replenishment model based on the point prediction and the section prediction; and a section prediction replenishment section that generates an irregular replenishment plan by using a replenishment model based on section prediction, wherein the model selection section selects which one of the point prediction replenishment section, the mixed replenishment section, and the section prediction replenishment section generates a replenishment plan in the intelligent replenishment device based on at least one of an application target, a prediction time, a classification result of the product classification device, and a prediction result of the sales prediction device.

Thus, the replenishment plan can be generated by selecting the most appropriate replenishment model according to the application (for example, sales store, supplier, and manufacturer), the prediction time (for example, 1 day, 1 week, 1 month, 1 year), the classification result, the prediction result, and the like.

In the above-described intelligent supply chain system, when the application target is a sales store, the model selection unit may select a point prediction model in which the point prediction unit performs sales prediction in the sales prediction device for each product to which a demand prediction result needs to be confirmed, the point prediction model being a long-and-short-term memory network corresponding to at least one prediction time, the sales amount corresponding to the at least one prediction time is predicted for each product, the model selection unit may select a replenishment plan to be generated by the point prediction replenishment unit in the intelligent replenishment device, and the replenishment plan may be generated in a regular or irregular manner by using the replenishment model based on the point prediction.

Thus, the intelligent supply chain system can be effectively applied to the sales stores.

In the above-described intelligent supply chain system, when the application target is a supplier, the model selecting unit may select, for each product to be subdivided by the product classification device into products for which a demand prediction result needs to be confirmed, a point prediction model in which a point prediction unit and a section prediction unit both perform sales prediction in the sales prediction device, build a long-and-short-term memory network corresponding to at least one of a plurality of prediction times, and a probability density section prediction model corresponding to at least one of the other of the plurality of prediction times, predict sales amounts corresponding to the plurality of prediction times for each product, and further select, by the model selecting unit, a replenishment plan to be generated by the hybrid replenishment unit in the intelligent replenishment device, and use the hybrid replenishment model based on the point prediction and the section prediction, and generating a regular and quantitative replenishment plan.

Thus, the intelligent supply chain system can be effectively applied to suppliers.

In the above-described intelligent supply chain system, when the application target is a manufacturer, the model selecting unit may select a product to be classified by the product classifying unit for each product for which a demand prediction result needs to be confirmed, the section predicting unit may predict sales in the sales predicting device, build a probability density section prediction model corresponding to at least one prediction time, predict a sales amount corresponding to the at least one prediction time for each product, the model selecting unit may select a replenishment plan to be generated by the section prediction replenishment unit in the intelligent replenishment device, and generate an irregular replenishment plan using the replenishment model based on the section prediction.

Therefore, the intelligent supply chain system can be effectively applied to manufacturers.

An embodiment of the present invention provides a server platform that manages supply chains of a plurality of types of commodities, including a processor, a memory, and an interface, and capable of performing data communication with a client device via the interface, wherein the processor executes a program stored in the memory to perform: a commodity classification process for classifying a plurality of commodities based on historical data; a sales prediction process of performing sales prediction for each commodity based on historical data and a classification result of the commodity classification process for a plurality of commodities; and intelligent replenishment processing, wherein an automatic replenishment model is applied based on a prediction result of the sales prediction processing to generate a replenishment decision, and the replenishment decision is sent to the client device through the interface.

The above-described embodiments and effects of the intelligent supply chain system according to the present invention can be realized by the server platform, the method executed by the intelligent supply chain system, the program for causing the computer to execute the method, or the recording medium storing the program.

Drawings

Fig. 1 is a conceptual diagram illustrating an application object to which the smart supply chain system according to the first embodiment of the present invention can be applied.

Fig. 2 is a functional block diagram of an intelligent supply chain system according to a first embodiment of the present invention.

Fig. 3 is a block diagram showing an example of a hardware configuration of the intelligent supply chain system according to the first embodiment of the present invention.

Fig. 4 is a block diagram showing another example of the hardware configuration of the intelligent supply chain system according to the first embodiment of the present invention.

FIG. 5 is a flowchart illustrating a method performed by the intelligent supply chain system according to the first embodiment of the present invention.

Fig. 6 is a functional block diagram of an intelligent supply chain system according to a second embodiment of the present invention.

Fig. 7 is a table showing an example of a model selection reference table to be referred to by the model selection unit according to the second embodiment of the present invention.

Fig. 8 is a flowchart showing an application example (specific example 1) in the case where the intelligent supply chain system of the present invention is applied to a sales store.

Fig. 9 is a flowchart showing an application example (specific example 2) in the case where the intelligent supply chain system of the present invention is applied to a supplier.

FIG. 10 is a flowchart showing an application example (specific example 3) in the case where the intelligent supply chain system of the present invention is applied to a manufacturer.

Description of reference numerals:

100. 100': a smart supply chain system; 10: a commodity sorting device; 20: a sales prediction device; 21: a point prediction unit; 22: an interval prediction unit; 30: an intelligent replenishment device; 31: a point prediction replenishment section; 32: a mixed replenishment part; 33: an interval prediction replenishment unit; 40: a model selection unit; 110. 110A, 110B: a processor; 120. 120A, 120B: a memory; 130. 130A, 130B: an interface; 140: an input device; 150: a display unit; 160. 160A, 160B: a bus; 100A: a server platform; 100B: a client device; 200: a database.

Detailed Description

The present invention will be described in more detail below with reference to the accompanying drawings, embodiments, and specific examples. The following description is only an example for the convenience of understanding the present invention and is not intended to limit the scope of the present invention. In the embodiments, the components of the apparatus and the system may be changed, deleted, or added according to the actual situation, and the steps of the method may be changed, deleted, added, or changed in order according to the actual situation.

(first embodiment)

First, an application object to which the intelligent supply chain system 100 of the present embodiment can be applied will be described. Fig. 1 is a conceptual diagram illustrating an application object to which the smart supply chain system according to the first embodiment of the present invention can be applied. The application objects of the intelligent supply chain system 100 include at least one of a sales store, a supplier and a manufacturer, wherein the relationship between the sales store, the supplier and the manufacturer is shown in fig. 1, and the arrows indicate the flow of goods. Three sales stores, namely, a sales store 1, a sales store 2, and a sales store 3, three manufacturers, namely, a supplier 1, a supplier 2, and a manufacturer 1, a manufacturer 2, and a manufacturer 3, are shown here, but the number and relationship of the sales stores, the suppliers, and the manufacturers are not limited thereto, and a large number of sales stores, suppliers, manufacturers, and more complicated relationships may actually exist.

The sales stores need to monitor sales volume of each commodity, so as to make sales and inventory strategies. Since a supplier takes goods from different manufacturers and supplies the taken goods to a plurality of sales stores, it is necessary to order the manufacturers and arrange a delivery plan for the sales stores at the next stage. The manufacturer produces goods to be supplied to a plurality of different suppliers, so that the suppliers supply the goods to the sales stores, the life cycle of each kind of goods is different, and the demand of the goods in the future needs to be predicted to guide the future production plan.

In response to at least one of the above needs, the present embodiment provides a smart supply chain system 100. Fig. 2 is a functional block diagram of the intelligent supply chain system 100 according to the first embodiment of the present invention. As shown in fig. 2, the intelligent supply chain system 100 includes a product sorting device 10, a sales predicting device 20, and an intelligent replenishment device 30, and manages supply chains of a plurality of products as shown in fig. 1, for example. Each device may be implemented as a functional module by executing an application program stored in a memory by a processor, or may be implemented as a hardware configuration independent of each other. Two specific examples will be described below with respect to specific embodiments.

As shown in fig. 2, the product sorting apparatus 10 sorts a plurality of products based on history data. For example, the product classification apparatus 10 additionally considers the temporal characteristics of the product in addition to the conventional ABC classification method. For example, a latest sales time interval is added as an analysis dimension, and a plurality of kinds of commodities are classified as an R-ABC classification method with ABC classification results based on sales data as history data and the latest sales time interval as two dimensions. Therefore, the ABC classification is further refined, and more valuable commodities can be selected from the traditional ABC classification.

Here, the history data includes the delivery time, the month/week number, the destination warehouse number, the commodity number, the delivery amount, and the like. For example, when the application object is a sales store, the history data includes a sales time, a month/week number, a commodity number, a sales volume, and the like. The historical data may also include other data as desired. In addition, since "ex-warehouse" for a certain customer is equivalent to "sales" for a supplier/manufacturer, the "ex-warehouse" in the supplier/manufacturer and "sales" in a sales store are collectively expressed as "sales" in this specification. For example, "sales time" includes not only sales time in a sales store but also ex-warehouse time in a supplier/manufacturer, "sales amount" includes not only sales amount in a sales store but also ex-warehouse amount in a supplier/manufacturer.

Further, in order to further clarify the sales characteristics of the products, the product classification device 10 may calculate a product characteristic analysis index for each product based on the history data. The article characteristic analysis index includes, for example, at least one of the following: demand probability, sales frequency, variation coefficient, variation amplitude, customer concentration, sales tempo, distribution interval and the like. Thus, based on the classification result (preliminary classification result) of the improved R-ABC classification method, multidimensional subdivision is performed using the calculated characteristic analysis indexes of each product, as a final classification result. Further, based on the result of the division, a commodity requiring confirmation of the result of the demand prediction by the salesperson is extracted. Therefore, the accuracy of demand forecast can be improved by effectively combining the business experience of the salesperson.

The sales prediction apparatus 20 predicts sales for each product based on the history data and the classification result of the product classification apparatus 10 for a plurality of types of products. For example, the sales predicting device 20 predicts sales for each product for a predetermined time (for example, 1 day, 1 week, 1 month, 1 year, etc.) for the product extracted by the product sorting device 10, for example, for which the demand predicting result needs to be confirmed, based on the sorting result of the product sorting device 10.

Specifically, the sales prediction apparatus 20 may construct a long/short term memory network point prediction model corresponding to a prediction time (for example, 1 day, 1 week, or 1 year) by using, for example, point prediction based on a long/short term memory network, perform data collection, data processing, model construction, model evaluation, and model deployment, and output a prediction result corresponding to the prediction time. Alternatively, the sales prediction apparatus 20 may construct a probability density section prediction model corresponding to a prediction time (for example, 1 month) by using probability density section prediction by deep learning (for example, deep ar method), perform data collection, data processing, model construction, and prediction result processing, and output a prediction result corresponding to the prediction time.

Further, the sales prediction apparatus 20 may build a plurality of prediction models corresponding to the respective prediction times among the plurality of prediction times by using a hybrid prediction combining the point prediction and the section prediction, and output prediction results corresponding to the respective prediction times. For example, the sales prediction apparatus 20 may build a long-term memory network point prediction model corresponding to 1 day, a probability density interval prediction model corresponding to 1 month, and a long-term memory network point prediction model corresponding to 1 year, and output prediction results corresponding to 1 day, 1 month, and 1 year, respectively. By combining the classification result of the product, the time to be predicted, and other factors, a more accurate prediction result corresponding to the required prediction time can be obtained by using the most appropriate prediction method.

The intelligent replenishment device 30 applies an automatic replenishment model based on the prediction result of the sales prediction device 20 and the commodity characteristic evaluation index to generate a replenishment decision. For example, the intelligent replenishment device 30 creates different replenishment strategies for the characteristics of different products, and creates a "regular and irregular", a "regular and regular", and an "irregular and irregular" replenishment plan.

Specifically, the intelligent replenishment device 30 can generate a "regular and irregular" or "irregular and irregular" replenishment plan using a replenishment model based on point prediction. Alternatively, the intelligent replenishment device 30 may generate a "regular and quantitative" replenishment plan using a mixed replenishment model based on the point prediction and the section prediction. Alternatively, the intelligent replenishment device 30 may generate a "non-regular and non-regular" replenishment plan using a replenishment model based on section prediction. In this way, a replenishment plan is generated by using the most appropriate replenishment model according to factors such as the characteristics of different commodities and different replenishment periods, and a replenishment decision more satisfying the demand can be provided.

Fig. 2 shows an example in which the intelligent supply chain system 100 is connected to an external database 200, and history data is acquired from the external database 200. However, the present embodiment is not limited thereto, and the database 200 may be stored in a built-in storage device of the smart supply chain system 100. In addition, the connection between the intelligent supply chain system 100 and the external database 200 may be various wired or wireless connections, which is not limited herein.

According to the intelligent supply chain system 100 of the embodiment, supply chain management is not only supply chain, but also depends on big data and information systems, three important blocks of commodity classification, sales prediction and intelligent replenishment are effectively integrated, internal and external data elements are integrated, and all systems coordinate and act together under the guidance of information, so that service energy is condensed to the maximum extent, and service capacity is released orderly. Therefore, the service can be accurate, the supply chain is transparent, flexible and agile, and the functions are more coordinated.

Two specific examples of the hardware configuration of the intelligent supply chain system 100 according to the present embodiment will be described below. Fig. 3 is a block diagram showing an example of a hardware configuration of the intelligent supply chain system 100 according to the first embodiment of the present invention. As shown in fig. 3, the intelligent supply chain system 100 implements the functional modules shown in fig. 2 through a computer system having a processor 110, a memory 120, an interface 130, an input device 140, and a display portion 150. The processor 110, the memory 120, the interface 130, the input device 140, and the display unit 150 are connected to each other via a bus 160.

Specifically, the processor 110 is, for example, a CPU, a microprocessor, or the like, and executes an application program stored in the memory 120 to realize the functions of each device of the smart supply chain system 100. The interface 130 is, for example, a communication interface, and is capable of data communication with the database 200. The input device 140 is an input device such as a keyboard, a mouse, a microphone, etc. for a user to input an instruction. The display unit 150 is, for example, a liquid crystal display, and can display a screen related to the processing procedure and the result of the smart supply chain system 100.

The intelligent supply chain system 100 based on the hardware configuration of this example can be installed in, for example, a sales store, a supplier, and a manufacturer as application targets, and used by the sales store, the supplier, and the manufacturer as users.

Fig. 4 is a block diagram showing another example of the hardware configuration of the intelligent supply chain system 100 according to the first embodiment of the present invention. As shown in FIG. 4, the intelligent supply chain system 100 includes a server platform 100A and a client device 100B that are capable of data communication with each other. The server platform 100A has a processor 110A, a memory 120A, and an interface 130A connected to each other via a bus 160A, and the client device 100B has a processor 110B, a memory 120B, an interface 130B, an input device 140, and a display section 150 connected to each other via a bus 160B.

Specifically, the processor 110A of the server platform 100A is, for example, a CPU, a microprocessor, or the like, and executes an application program stored in the memory 120A to realize the functions of each device of the intelligent supply chain system 100. The interface 130A of the server platform 100A is, for example, a communication interface, and is capable of data communication with the interface 130B of the client device 100B and/or the database 200.

The processor 110B of the client device 100B is, for example, a CPU, a microprocessor, or the like, and executes an application program stored in the memory 120B to implement the function of a user interface. The input device 140 is an input device such as a keyboard, a mouse, a microphone, etc. for a user to input an instruction. The display unit 150 is, for example, a liquid crystal display, and can display a screen related to the processing procedure and the result of the smart supply chain system 100.

In the intelligent supply chain system 100 based on the hardware configuration of this example, the server platform 100A may be provided at a service provider, and the client device 100B may be provided at a sales store, a vendor, or a manufacturer, which is an application target. Thus, the service provider provides the aforementioned functions of the intelligent supply chain system 100 to the sales store, the supplier, and the manufacturer as the user.

The following describes a method performed by the intelligent supply chain system 100 of the present embodiment. Fig. 5 is a flowchart illustrating a method executed by the intelligent supply chain system 100 according to the first embodiment of the present invention. Here, an example of the method executed by the intelligent supply chain system 100 according to the present embodiment is specifically described, but the method executed by the intelligent supply chain system 100 according to the present embodiment is not limited to the following example.

As shown in fig. 5, in step S1, the article sorting apparatus 100 sorts the articles so as to adopt corresponding sales and stock policies for different categories of articles. Specifically, based on the R-ABC classification method, the products are subdivided in combination with each product characteristic analysis index, and the products requiring the confirmation of the demand prediction result by the salesperson are selected from the subdivided products.

In step S2, the sales predicting apparatus 20 performs sales prediction to make a demand plan. As described above, the sales prediction apparatus 20 uses, for example, the point prediction by the long and short term memory network or the probability density interval prediction by the DeepAR algorithm for the commodity for which the demand prediction result needs to be confirmed based on the classification result in step S1.

In step S3, the intelligent replenishment device 30 applies the automatic replenishment model to a specific scenario to generate a replenishment decision. As described above, the intelligent replenishment device 30 may use a replenishment model based on point prediction, a mixed replenishment model based on point prediction and section prediction, or a replenishment model based on section prediction, in accordance with the prediction method and the prediction result in step S2.

(second embodiment)

The second embodiment of the present invention will be specifically described below. Fig. 6 is a functional block diagram of an intelligent supply chain system 100' according to a second embodiment of the present invention. As shown in fig. 6, the intelligent supply chain system 100' of the present embodiment is the intelligent supply chain system 100 of the first embodiment, in which the functions of the sales predicting device 20 and the intelligent replenishment device 30 are changed, and a model selecting unit 40 is added. The following is a detailed description.

As shown in fig. 6, the sales prediction apparatus 20 includes a point prediction unit 21 and a section prediction unit 22. The point prediction unit 21 performs point prediction based on the long/short term memory network, and the section prediction unit 22 performs probability density section prediction. The intelligent replenishment device 30 includes a spot prediction replenishment part 31, a mixed replenishment part 32, and a section prediction replenishment part 33. The point forecast replenishment unit 31 generates a regular or irregular replenishment plan using a replenishment model based on point forecast, the mixed replenishment unit 32 generates a regular or quantitative replenishment plan using a mixed replenishment model based on point forecast and section forecast, and the section forecast replenishment unit 33 generates an irregular replenishment plan using a replenishment model based on section forecast.

Furthermore, the intelligent supply chain system 100' further includes a model selecting unit 40. The model selection unit 40 may be implemented by hardware separate from the product sorting apparatus 10, the sales prediction apparatus 20, and the intelligent replenishment device 30, or may be implemented by hardware similar to any one of the product sorting apparatus 10, the sales prediction apparatus 20, and the intelligent replenishment device 30. Further, the present embodiment may be applied to the hardware configuration shown in fig. 3, or may be applied to the hardware configuration shown in fig. 4.

The model selecting unit 40 selects whether the sales predicting unit 21 predicts sales in the sales predicting apparatus 20, the section predicting unit 22 predicts sales, or both the sales predicting unit 21 and the section predicting unit 22 predict sales in the sales predicting apparatus 20, based on at least one of an application object (for example, a sales store, a supplier, a manufacturer, etc.), a prediction time (for example, 1 day, 1 week, 1 month, 1 year, etc.), and a classification result of the product classifying apparatus 10. For example, the time required for prediction can be determined based on whether the application target is a sales store, a supplier, or a manufacturer, and the point prediction unit 21 can select point prediction based on the long-term memory network or the section prediction unit 22 can select probability density section prediction, so that the sales prediction can be performed by selecting the most appropriate prediction method based on the application target, the prediction time, the classification result, and the like.

Further, the model selection unit 40 selects which of the spot predictive replenishment unit 31, the mixed replenishment unit 32, and the section predictive replenishment unit 33 generates a replenishment plan in the intelligent replenishment device 30 based on at least one of the application target, the prediction time, the classification result of the product classification device 10, and the prediction result of the sales prediction device 20. For example, the replenishment plan can be generated by selecting the most appropriate replenishment model based on whether the application target is a sales store, a supplier, or a manufacturer, and the prediction model and the prediction result selected by the sales prediction apparatus 20.

The model selection unit 40 may perform the selection based on a model selection reference table stored in advance, for example. However, the selection method of the model selection unit 40 is not limited to this, and the selection result may be directly input from the outside, or the result selected based on the model selection reference table may be modified by an external input, or a selection plan may be generated by applying machine learning to the previous selection result. Fig. 7 is a table showing an example of a model selection reference table to be referred to by the model selection unit 40 according to the second embodiment of the present invention, and the following description will be made in detail.

As shown in fig. 7, in the case that the application target of the intelligent supply chain system 100' is a sales store, the sales store needs to monitor the sales volume of each commodity so as to make a sales and inventory strategy. Therefore, the product classification device 10 is subdivided into products of each type for which the demand prediction result needs to be confirmed in accordance with the demand of the replenishment plan, and daily prediction and weekly prediction are performed simultaneously for the demand condition of each product. The model selection unit 40 selects the point prediction model for which the point prediction unit 21 performs the daily prediction and the weekly prediction in the sales prediction device 20, generates the corresponding long-and-short-term memory network, and predicts sales amounts corresponding to 1 day and 1 week for each commodity. Further, the model selection unit 40 selects the point prediction replenishment unit 31 to generate a replenishment plan in the intelligent replenishment device 30, and generates a replenishment plan of a fixed amount or an irregular amount using a replenishment model based on the point prediction. Thus, the intelligent supply chain system 100' can be effectively applied to the sales store by determining an appropriate prediction time and prediction model in accordance with the characteristics of the sales store as an application target, and using an appropriate replenishment model.

In addition, as shown in fig. 7, when the application target is a supplier, the supplier takes goods from different manufacturers and supplies the taken goods to a plurality of stores, and therefore, it is necessary to order the suppliers and arrange a delivery plan for the stores at the next stage. Since the supplier contacts both ends of the manufacturer and the shop and needs to know the long-term demand and the short-term demand of the commodity, the commodity classification device 10 is subdivided into each commodity needing to confirm the demand prediction result according to the demand of the replenishment plan, and the demand condition of each commodity is subjected to daily prediction, monthly prediction and annual prediction at the same time. The model selection unit 40 selects a point prediction model in which sales prediction is performed by both the point prediction unit 21 and the section prediction unit 22 in the sales prediction device 20, constructs a point prediction model of a long-and-short memory network corresponding to 1 day and 1 year by the point prediction unit 21, constructs a probability density section prediction model corresponding to 1 month by the section prediction unit 22, and predicts sales amounts corresponding to 1 day, 1 month, and 1 year for each commodity. Further, the model selection unit 40 selects the replenishment plan generated by the hybrid replenishment unit 32 in the intelligent replenishment device 30, and generates a periodic and quantitative replenishment plan by using a hybrid replenishment model based on the point prediction and the section prediction. Thus, the appropriate prediction time and prediction model can be determined in accordance with the characteristics of the supplier as the application target, and the intelligent supply chain system 100' can be effectively applied to the supplier using the appropriate replenishment model.

In addition, as shown in fig. 7, when the application object is a manufacturer, the manufacturer produces a plurality of kinds of products, supplies the products to a plurality of different suppliers, and supplies the products to a sales store by the suppliers. Each commodity has a different life cycle, and the future demand of the commodity needs to be predicted so as to guide the future production plan. Since the number of the commodities produced in each batch is large, and the commodities can be supplied for a long period, the commodity classification device is subdivided into each commodity needing to confirm the demand prediction result, and monthly demand prediction of the commodities is performed. The model selection unit 40 selects the sales prediction performed by the section prediction unit 22 in the sales prediction device 20, constructs a probability density section prediction model corresponding to 1 month, and predicts the sales amount corresponding to 1 month for each commodity. Further, the model selecting unit 40 selects the replenishment plan generated by the section prediction replenishment unit 33 in the intelligent replenishment device 30, and generates an irregular replenishment plan using a replenishment model based on section prediction. Thus, the intelligent supply chain system 100' can be effectively applied to the manufacturer by determining an appropriate prediction time and a prediction model in accordance with the characteristics of the manufacturer as an application target and using an appropriate replenishment model.

The above prediction time is only an example, and other prediction times may be used as appropriate. Alternatively, the prediction time may be specified by the user. That is, the model selection unit 40 may select an appropriate prediction model and replenishment model based on the input application target and prediction time.

(example 1)

One specific example of the present invention is described below. Here, although the present specific example is described as being implemented in the second embodiment, the present specific example can be applied to the first embodiment also when a model to be used for sales prediction and smart replenishment is determined in advance. The specific example may be applied to the hardware configuration shown in fig. 3 or the hardware configuration shown in fig. 4.

This example is used to illustrate the application of the model in a sales outlet. Fig. 8 is a flowchart showing an application example (specific example 1) in the case where the intelligent supply chain system 100' of the present invention is applied to a sales store.

As shown in fig. 8, in step S101, the product classification apparatus 10 classifies the products by the R-ABC classification method.

Specifically, suppose that the sales amounts of the respective commodities in the past three months of a certain sales store are ranked from large to small in total, the percentage of the sales amount of each commodity in the total sales amount is calculated, and then the cumulative percentage is calculated. According to the definition of ABC classification, the cumulative proportion is 0% -80%, and is class A, the cumulative proportion is 80% -90%, and is class B, and the cumulative proportion is 90% -100%, and is class C. Wherein, the proportion here can be adjusted according to the actual conditions.

However, the time characteristic of a commodity is not considered in the conventional ABC analysis method, and for example, although the total sales volume of a certain commodity is 100, the importance of the commodity is different if the 100 sales records include recent sales records or sales records before 2 months. The dimension of the 'nearest sale interval' is added, so that the problem can be well solved. On the basis of ABC classification, commodities are classified into three levels according to the time dimension according to the latest sales interval of each commodity. The number of stages into which the product is divided in the time dimension is not limited to this, and may be set as appropriate according to the actual situation. For example, the classification results based on the R-ABC classification are shown in the last column of Table 1.

Table 1:

further, assuming that the store sales records are as shown in table 2, the following values of the product characteristic analysis indexes are calculated.

Table 2:

shop number	Commodity numbering device	Sale date	Year of year	Moon cake	Week (week)	Customer member number	Number of
								SP01	09	2020/1/3	2020	1	1	C0001	5
SP01	09	2020/1/6	2020	1	2	C0002	20
								SP01	09	2020/1/14	2020	1	3	C0001	6
SP01	09	2020/1/23	2020	1	4	C0001	10
								SP01	09	2020/1/31	2020	1	5	C0002	30
SP01	09	2020/2/7	2020	2	6	C0001	6
								SP01	09	2020/2/16	2020	2	8	C0003	10
SP01	09	2020/2/20	2020	2	8	C0001	8
								SP01	09	2020/2/26	2020	2	9	C0001	5

With respect to demand probabilities, how much probability over a unit period will result in sales performance is calculated. The frequency of sales is determined by counting sales results on a weekly basis and counting the number of weeks in which actual results are present as the frequency. As for the variation coefficient, the magnitude of the demand fluctuation is judged using the variation coefficient. Regarding the fluctuation range, the fluctuation of the total amount of demand in a predetermined period is checked. Regarding customer concentration, it is confirmed whether the sales in a specified period are concentrated on a few customers. Regarding the sales tempo, the time interval from each sales record to the next sales record is counted in units of commodities. The distribution interval is counted in units of the product, and the earliest sale date of the product and the time interval until the current analysis time point are counted, and the longer the interval, the longer the distribution time, and the shorter the interval, the shorter the distribution time.

The characteristics of commercial product 09 are known as follows: the commodity 09 has a large total sales volume, has sales records in the near future, is a current main-sale product, has high sales frequency and small demand variation coefficient, but has a large overall variation range in the unit of month. The client concentration is high, C0002 is the main client, the average selling beat is 7 days, and the selling interval is 67 days. According to the preset rule table, the commodity 09 is judged to be a main sales commodity group, the sales frequency is high, relatively sufficient data samples exist, and the future demand can be predicted in a data analysis and machine learning mode.

Next, in step S102, the model selection unit 40 selects a model to be used for sales prediction and smart replenishment. Specifically, for example, in the case where the model selection unit 40 is applied to a sales store in this specific example, based on the model selection reference table shown in fig. 7, the model selection unit selects the demand situation for each product to perform daily prediction and weekly prediction at the same time, and selects the sales prediction unit 21 to perform sales prediction in the sales prediction device 20, and here, 2 sales prediction models are constructed based on the long-short term memory model. Further, the model selection unit 40 selects the establishment of the regular and irregular replenishment models and the irregular and irregular replenishment models by the point prediction replenishment unit 31 in the intelligent replenishment device 30.

Next, in step S103, the sales prediction apparatus 20 acquires sales history data of each sales store, the attributes of which are shown in table 3.

Table 3:

and then, carrying out data processing, building a long-term memory network model of daily prediction and weekly prediction by using a keras algorithm, carrying out corresponding post-processing on the prediction result according to the difference of prediction subjects, and outputting the prediction result in a proper form such as a webpage, a report form and the like. In this example, a prediction result table is constructed in the database, and the structure and representation thereof are shown in table 4.

Table 4:

next, in step S104, the intelligent replenishment device 30 calculates the maximum stock amount. A periodic non-quantitative replenishment model based on point prediction is applied, the minimum stock quantity in the periodic replenishment mode is calculated based on the prediction result in step S103, and if the current stock quantity is lower than the minimum stock quantity, a replenishment plan is generated to replenish the stock quantity to the calculated maximum stock quantity. Further, an irregular replenishment model based on point prediction is applied, the minimum stock quantity in the irregular replenishment mode is calculated based on the prediction result in step S103, and if the current stock quantity is lower than the minimum stock quantity, a replenishment plan is generated to replenish the stock quantity to the calculated maximum stock quantity.

In this example, assuming that the expected stock period of a business is 2 weeks, the use demand probability and the sales frequency are set, and the stock turnover and the safety factor of each commodity are set as the maximum stock amount according to the rules shown in table 5. The safety coefficient can be adjusted according to actual conditions.

Stock turnover period of each commodity is the demand probability of each commodity 2 (decimal point carry rounding)

The period in the example is 2 months (9 weeks), and the frequency of sales is classified into five grades of high, medium, and low according to the following rules.

Table 5:

frequency of sale	Probability of demand	Period of inventory turnover	Service level	Factor of safety
					8 to 9 (high)	≧0.8	2 weeks	99.90％	3.1
6 to 8 (middle and high)	≧0.6and<0.8	2 weeks	99％	2.33
					3 to 6 (middle)	≧0.4and<0.6	1 week	98％	2
2 to 3 (middle low)	≧0.2and<0.4	1 week	97％	1.88
					0 to 2 (Low)	<0.2	1 week	95％	1.65

The commodity 09 in the example is a high frequency commodity, the inventory turnover period is defined as 2 weeks, and the safety factor is 3.1. Therefore, the maximum inventory of the product 09, is calculated according to the formula:

maximum inventory-forecast of demand in future inventory turnover + safe inventory (SS)

Demand forecast for future two weeks + (3.1 × (standard deviation of demand performance in days for past two weeks √ 14) ((40 +47) + (3.1 × 2.05 × 3.74) ═ 111

Then, using a regular non-quantitative replenishment model, periodically checking the current inventory condition at a fixed time point every week, assuming that the standard replenishment lead period is 3 days, calculating the minimum inventory quantity in the regular replenishment mode by using the following formula:

minimum storage turnover period (week) standard replenishment lead period/7 days (decimal point carry rounding) 3/7 1 (week)

The minimum stock amount is the predicted number of demands in the future minimum stock turnover period + the safe stock amount (SS) — the predicted demand for 1 week in the future + (3.1 × (standard deviation of actual demand performance in days for past 1 week √ 7) ± (40+ 0) ═ 40 { (0) } 40 { (1) } standard deviation of actual demand performance in days for past 1 week

If the current inventory is lower than 40, assuming that the current inventory is 30, producing a replenishment plan, and setting the replenishment quantity to be 111-30-81

Then, using an irregular and non-quantitative replenishment model to check the current inventory condition in real time every day, assuming that the standard replenishment lead period is 3 days, calculating the minimum inventory under the irregular replenishment mode by using the following formula:

the minimum stock amount (the predicted number of demands in the future standard replenishment lead period + the safe stock amount (SS) (+) the predicted demand for 3 days in the future + (3.1 √ 3 √ the standard deviation of the actual demand for the past 3 days) ((5 +10+6) +0 ═ 21 { (2) } 21 { (3.1) } the standard deviation of the actual demand for the past 3 days } the minimum stock amount

If the current inventory is less than 21, the current inventory is assumed to be 18, a replenishment plan is generated, and the replenishment quantity is 111-18-93

(example 2)

This example is used to illustrate the application of the model to the vendor. Fig. 9 is a flowchart showing an application example (specific example 2) in the case where the intelligent supply chain system 100' of the present invention is applied to a supplier.

As shown in fig. 9, in step S201, the product classification apparatus 10 classifies the products by the R-ABC classification method. This step may be the same as in example 1 (step S101 in fig. 8), and a detailed description thereof will be omitted.

Next, in step S202, the model selection unit 40 selects a model to be used for sales prediction and smart replenishment. Specifically, for example, in the case where the model selection reference table shown in fig. 7 is used for the supplier in the present specific example, the model selection unit 40 selects the sales prediction device 20 to simultaneously perform daily prediction, monthly prediction, and yearly prediction for the demand situation of each product, and selects 2 sales prediction models for daily prediction and yearly prediction based on the long-and-short-term memory model and 2 sales prediction models for monthly prediction based on the probability density section prediction model, which are collectively performed by the point prediction unit 21 and the section prediction unit 22. Further, the model selection unit 40 selects the establishment of the regular and quantitative replenishment models by the hybrid replenishment unit 31 in the intelligent replenishment device 30.

Next, in step S203, the sales predicting apparatus 20 acquires the historical data of the suppliers supplying the different stores, and the attributes thereof are as shown in table 6.

Table 6:

and then, data processing is carried out, a long-term and short-term memory network model of daily prediction and annual prediction is built by utilizing a keras algorithm, a probability density interval prediction model of monthly prediction is built by utilizing a Deepar model, corresponding post-processing is carried out on the prediction result according to the difference of prediction subjects, and the prediction result is output in a proper form such as a webpage, a report form and the like. In this example, a prediction result table is constructed in the database, and the structure and the representation are shown in table 1 and table 2, for example.

Table 7:

table 8:

next, in step S204, the intelligent replenishment device 30 generates a replenishment plan based on the prediction result in step S203. For suppliers, it is generally necessary to meet the order of customers as much as possible, but there may be a case where the market feedback is delayed without directly contacting the final market, so that there is a need for a certain risk coping capability for stock, and the cost is controlled to optimize the operation.

For example, for the supplier replenishment scenario, the annual forecast, monthly forecast, and daily forecast data are used to define the service level coefficient as 95%, the current stock quantity is 45, the order lead period is 5 days, the order cost per time is 50 yuan, and the holding cost per commodity is 30 yuan per commodity. The forecast median M is selected for the daily stock quantity and the demand quantity in the period.

(1) Calculate the optimal economic replenishment period based on EOQ, the economic replenishment quantity model, taking the above product 09 as an example:

c_ecost per order in a cycle, C_tD is the storage cost per commodity in the cycle, and D is the demand (predicted median M) in the cycle.

The optimal economic replenishment period is 365/(annual demand forecast/optimal economic replenishment quantity) is 365/(3985/69) is 6

(2) Safety stock preparation

The security stock of the commercial product 09 is (standard deviation of monthly demand/30 × 6) × service level coefficient is (23/30 × 6) × 1.68 ═ 8

(3) Re-replenishment spot customization

The restocking point of the product 09 is 33+8 and 41, respectively, the sales forecast amount in the replenishment lead period and the safety stock

(4) Make-up quantity

The replenishment quantity of the commodity 09 at 2020.3.1 is 2 × the demand forecast in the replenishment lead period + the demand forecast in the replenishment period + the safety stock-the current stock is 2 × 33+ (325/30 × 6) +8-45 ═ 94

Taking the data of the predicted result as an example, the replenishment plan is shown in table 3.

Table 9:

meaning that when the above-mentioned commercial product 09 is in 2020.3.1-2020.4.1 cycle, regular replenishment is performed every 6 days, and if the stock is not full 41 in the replenishment period, replenishment is started, 2020.3.1 is performed for 94 pieces for the first time.

(example 3)

This example is used to illustrate the application of the model to the manufacturer. FIG. 10 is a flowchart showing an example of an application (specific example 3) in the case where the intelligent supply chain system 100' of the present invention is applied to a manufacturer.

As shown in fig. 10, in step S301, the product classification apparatus 10 classifies the products by the R-ABC classification method. This step may be the same as in example 1 (step S101 in fig. 8), and a detailed description thereof will be omitted.

Next, in step S302, the model selection unit 40 selects a model to be used for sales prediction and smart replenishment. Specifically, for example, in the case where the model selection unit 40 is applied to a manufacturer in the present specific example, the model selection reference table shown in fig. 7 selects a sales prediction model in which monthly predictions are made while selecting demand conditions for each product, and the section prediction unit 22 performs sales predictions in the sales prediction device 20, and the monthly predictions are constructed based on the probability density section prediction model. Further, the model selecting unit 40 selects a replenishment model that is created by the section prediction replenishment unit 33 by an irregular amount in the intelligent replenishment device 30.

Next, in step S303, the sales predicting apparatus 20 acquires the sales history data of each product of the manufacturer, the attributes of which are shown in table 10.

Table 10:

and then, carrying out data processing, constructing a probability density interval prediction model of monthly prediction by using a DeepAR model, carrying out corresponding post-processing on a prediction result according to different prediction subjects, and outputting the prediction result in a proper form such as a webpage, a report form and the like. In this example, a prediction result table is constructed in the database, and the structure and example are shown in table 11. The table is used to provide data support for subsequent replenishment strategies.

Table 11:

next, in step S304, the intelligent replenishment device 30 generates a replenishment plan based on the prediction result in step S303. For the manufacturer, in the scenario that a downstream provider needs to supply goods, monthly forecast data is used, for example, a service level coefficient is defined to be 95%, an order lead period is defined to be 5 days, the order cost per time is 50 yuan, and the holding cost per commodity is 10 yuan. The forecast median M is selected for the daily stock quantity and the demand quantity in the period.

Firstly, an optimal replenishment point is established, taking a commodity 02 as an example:

the safety stock of the good 02 is the demand standard deviation of each SKU and the service level coefficient is 3021, 1, 68, 5075

Stock in order lead period of commodity 02, day of order lead period, quantity of stock per day (predicted median M), 5 (10025/22), 2278 (note: 22 working days per month)

Dynamic goods supplement point of product 02 is 7353 for safety stock and stock in advance of order

Next, an optimal economic replenishment quantity is established based on the EOQ model, taking the commodity 02 as an example:

C_eis period ofCost per order, C_tD is the storage cost per commodity in the cycle, and D is the demand (predicted median M) in the cycle.

Taking the data of the predicted result as an example, the replenishment plan is shown in table 12:

table 12:

predicted particle size	Commodity numbering device	Predicting a start date	Predicted end date	Replenishment point	Amount of replenishment
						Monthly forecast	02	2020.3.1	2020.4.1	7353	63
Monthly forecast	04	2020.3.1	2020.4.1	9593	126

Meaning that when item 02 is in the 2020.3.1-2020.4.1 cycle, the supply is started if inventory is not full 7353, and 63 supplies are made each time. When the number of the commodities 04 is in 2020.3.1-2020.4.1 cycles, if the stock is not full 9593, replenishment is started, and 126 commodities are replenished each time.

The embodiments and specific examples of the present invention have been described above with reference to the accompanying drawings. The above-described embodiments and specific examples are merely specific examples of the present invention and are not intended to limit the scope of the present invention. Those skilled in the art can modify the embodiments and specific examples based on the technical idea of the present invention, and various modifications, combinations, and appropriate omissions of the elements can be made, and the embodiments obtained thereby are also included in the scope of the present invention. For example, the above embodiments and specific examples may be combined with each other, and the combined embodiments are also included in the scope of the present invention.

Claims

1. An intelligent supply chain system for managing supply chains of a plurality of kinds of commodities, comprising:

a commodity classification device for classifying a plurality of commodities based on the history data;

a sales prediction device that predicts sales for each of a plurality of types of commodities based on historical data and the classification result of the commodity classification device for the plurality of types of commodities; and

and the intelligent replenishment device is used for applying an automatic replenishment model based on the prediction result of the sales prediction device to generate a replenishment decision.

2. The intelligent supply chain system of claim 1,

the commodity classifying device classifies a plurality of commodities to obtain a preliminary classification result by taking an ABC classification result based on sales data as historical data and a latest sales time interval as two dimensions, calculates commodity characteristic analysis indexes of each commodity based on the historical data, further performs multi-dimensional subdivision by using the calculated commodity characteristic analysis indexes aiming at the preliminary classification result to serve as a final classification result,

the commodity characteristic analysis index includes at least one of a sales frequency, a variation coefficient, a variation width, a customer concentration, a sales tempo, and a distribution interval.

3. The intelligent supply chain system of claim 2,

the sales prediction device predicts, for each commodity subdivided by the commodity classification device into commodities for which a demand prediction result needs to be confirmed, an amount of sales corresponding to at least one prediction time to be predicted for each commodity using any one of point prediction, section prediction, and hybrid prediction combining point prediction and section prediction.

4. The intelligent supply chain system of claim 3,

the intelligent replenishment device generates a replenishment plan by using any one of a replenishment model based on point prediction, a mixed replenishment model based on point prediction and section prediction, and a replenishment model based on section prediction, based on the prediction result of the sales prediction device and the commodity characteristic analysis index calculated by the commodity classification device.

5. The intelligent supply chain system as in any one of claims 1-4,

the sales prediction device is provided with:

a point prediction unit that performs point prediction based on the long-and-short-term memory network; and

an interval prediction unit that performs probability density interval prediction;

the intelligent supply chain system further comprises:

and a model selecting unit that selects, in the sales predicting device, whether to perform sales prediction by the point predicting unit, the section predicting unit, or both the point predicting unit and the section predicting unit, based on at least one of an application target, a prediction time, and a classification result of the product classifying device.

6. The intelligent supply chain system of claim 5,

the intelligent replenishment device is provided with:

a point prediction replenishment unit that generates a replenishment plan of a fixed amount or an irregular amount using a replenishment model based on point prediction;

a mixed replenishment part for generating a regular and quantitative replenishment plan by using a mixed replenishment model based on the point prediction and the section prediction; and

a section prediction replenishment unit for generating an irregular replenishment plan by using a replenishment model based on section prediction,

the model selection unit selects which of the point prediction replenishment unit, the mixed replenishment unit, and the section prediction replenishment unit generates a replenishment plan in the intelligent replenishment device based on at least one of an application target, a prediction time, a classification result of the product classification device, and a prediction result of the sales prediction device.

7. The intelligent supply chain system of claim 6,

in case the application object is a sales outlet,

the model selecting unit selects the point predicting unit to perform sales prediction in the sales predicting device for each commodity to be subdivided into which a demand predicting result is to be confirmed, constructs a point predicting model of a time-lapse memory network corresponding to at least one predicting time, predicts a sales volume corresponding to the at least one predicting time for each commodity,

the model selection unit selects a replenishment plan to be generated by the point prediction replenishment unit in the intelligent replenishment device, and generates a replenishment plan of a fixed amount or an irregular amount using a replenishment model based on point prediction.

8. The intelligent supply chain system of claim 6,

in the case where the application object is a vendor,

the model selecting unit selects a point prediction model of a long-and-short time memory network corresponding to at least one of a plurality of prediction times and a probability density section prediction model corresponding to at least one of the other prediction times in the sales prediction apparatus, and predicts sales volumes corresponding to the prediction times for each commodity,

the model selection unit selects a replenishment plan to be generated by the hybrid replenishment unit in the intelligent replenishment device, and generates a periodic and quantitative replenishment plan by using a hybrid replenishment model based on point prediction and section prediction.

9. The intelligent supply chain system of claim 6,

in case the application object is a manufacturer,

the model selecting unit selects the sales prediction performed by the section predicting unit in the sales predicting device for each commodity to be subdivided into which a demand prediction result needs to be confirmed, constructs a probability density section prediction model corresponding to at least one prediction time, predicts a sales volume corresponding to the at least one prediction time for each commodity,

the model selection unit selects a replenishment plan to be generated by the section prediction replenishment unit in the intelligent replenishment device, and generates an irregular replenishment plan by using a replenishment model based on section prediction.

10. A server platform for managing a supply chain of a plurality of commodities, comprising a processor, a memory and an interface, capable of data communication with a client device via the interface,

the processor executes the program stored in the memory to perform the following processing:

a commodity classification process for classifying a plurality of commodities based on historical data;

a sales prediction process of performing sales prediction for each commodity based on historical data and a classification result of the commodity classification process for a plurality of commodities; and

an intelligent replenishment process for applying an automatic replenishment model based on a prediction result of the sales prediction process to generate a replenishment decision,

the replenishment decision is sent to the client device via the interface.