WO2024032397A1

WO2024032397A1 - Inventory replenishment recommendation method and apparatus, and electronic device

Info

Publication number: WO2024032397A1
Application number: PCT/CN2023/110044
Authority: WO
Inventors: 荣华琪
Original assignee: 深圳市库宝软件有限公司
Priority date: 2022-08-08
Filing date: 2023-07-28
Publication date: 2024-02-15
Also published as: CN115409441A

Abstract

The present invention relates to the field of inventory management systems. Disclosed are an inventory replenishment recommendation method and apparatus, and an electronic device. In the present method, at least one replenishment model corresponding to a service is determined; a replenishment list corresponding to the at least one replenishment model is generated according to the replenishment model; a replenishment income corresponding to the replenishment list is predicted according to the replenishment list; and a target replenishment list is determined from the replenishment list according to the replenishment income, the target replenishment list being used to guide a user to execute a replenishment action for a business. According to the inventory replenishment recommendation method and apparatus and the electronic device provided in the present invention, a replenishment list can be obtained only by calling a preset replenishment model, reducing a professional replenishment knowledge threshold for personnel, and further predicting the replenishment income of the replenishment list. By means of prediction and visual data analysis of a prediction result, a future trend after replenishment may be visually foreseen, thereby improving the degree of information support to a decision maker, and helping a user determine a proper replenishment list.

Description

Recommended methods, devices and electronic equipment for inventory replenishment

This application claims priority to CN202210943392.

Technical field

The present invention relates to the field of inventory management systems, and in particular to an inventory replenishment recommendation method, device and electronic equipment.

Background technique

Inventory is a cost before it is shipped out for sale. In addition to occupying physical space itself, slow-moving products will also occupy the storage space of best-selling products. The biggest goal of inventory management is to minimize inventory and ensure safety stock for sales.

At present, the judgment on how to replenish goods is usually based on the experience value of replenishment personnel. However, the warehouse revenue indicators and consumption speed after replenishment cannot be well predicted, making it impossible to provide customers with guidance after replenishment. Therefore, providing a complete, highly integrated, highly automated replenishment recommendation solution is of great significance for inventory management.

Application content

The inventory replenishment recommendation method, device and electronic equipment provided by the embodiment of the present invention can provide guidance for warehousing inventory management, thereby solving the problem of insufficient inventory and excessive warehousing caused by existing Internet of Things trading companies when there is a difference between warehousing and actual sales. , liquidation and other technical issues.

In order to solve the above technical problems, one technical solution adopted by the embodiment of the present invention is to provide an inventory replenishment recommendation method, which includes: determining at least one replenishment model corresponding to the business; and generating the at least one replenishment model according to the replenishment model. The replenishment list corresponding to the cargo model; predicting the replenishment revenue corresponding to the replenishment list according to the replenishment list; determining the target replenishment list from the replenishment list based on the replenishment revenue, and the target replenishment list The list is used to guide users to perform replenishment actions for the business.

Optionally, determining at least one replenishment model corresponding to the business includes: recommending at least one replenishment model corresponding to the business from the model library; or, based on the user data corresponding to the business, recommending at least one replenishment model corresponding to the business from the model library. A replenishment model with a preset ranking is selected from the replenishment model and provided to the user, so that the user determines at least one replenishment model corresponding to the business from the replenishment model with the preset ranking.

Optionally, generating a replenishment list corresponding to the at least one replenishment model according to the replenishment model includes: obtaining parameter information associated with the replenishment model, and controlling the parameter information to be in an editable state, so The parameter information in the editable state is used to enable the user to modify the parameter information; when receiving the user's instruction to determine the replenishment model and the parameter information, based on the parameter information, run the replenishment model Function code block to generate the replenishment list corresponding to the replenishment model.

Optionally, determining at least one replenishment model corresponding to the business includes: obtaining the SKU variety corresponding to the business; obtaining historical outbound order data and historical warehouse inventory data corresponding to the SKU variety; Obtain the historical consumption speed curve of the SKU variety from the order data and the historical warehousing inventory data; determine the prediction algorithm corresponding to the SKU variety; and obtain the replenishment model based on the historical consumption speed curve and the prediction algorithm training.

Optionally, generating a replenishment list corresponding to the at least one replenishment model according to the replenishment model includes: inputting a parameter N to the replenishment model to obtain a consumption speed curve corresponding to N, N is the minimum number of days that the current replenishment can support normal outbound operations; the replenishment list corresponding to N is obtained according to the consumption speed curve corresponding to N and the replenishment model prediction.

Optionally, predicting the replenishment revenue corresponding to the replenishment list based on the replenishment list includes: obtaining the replenishment revenue corresponding to the replenishment list based on the consumption speed curve and the replenishment list.

Optionally, the prediction algorithm for determining the SKU variety specifically includes: obtaining the SKU variety, the SKU variety includes at least one of long-tail products, regular products, new products, and popular products, and selecting the obtained SKU variety. The prediction algorithm corresponding to the SKU variety.

Optionally, obtaining the replenishment revenue corresponding to the replenishment list according to the consumption speed curve and the replenishment list includes: obtaining the replenishment date and replenishment quantity of the SKU variety according to the replenishment list; The consumption speed curve obtains the SKU varieties consumed within the preset time period and the consumption quantity corresponding to the SKU variety; according to the consumption quantity corresponding to the SKU variety and the The replenishment date and the replenishment quantity are used to calculate the hit rate of the SKU variety in the replenishment list.

In order to solve the above technical problems, another technical solution adopted by the embodiment of the present invention is to provide an inventory replenishment recommendation device, including: a replenishment model determination module, used to determine at least one replenishment model corresponding to the business; a replenishment list The acquisition module is used to generate a replenishment list corresponding to the at least one replenishment model according to the replenishment model; the prediction analysis module is used to predict the replenishment revenue corresponding to the replenishment list according to the replenishment list; replenishment A goods list recommendation module is used to determine a target replenishment list from the replenishment list according to the replenishment revenue, and the target replenishment list is used to guide the user to perform replenishment actions for the business.

In order to solve the above technical problems, another technical solution adopted by the embodiments of the present invention is to provide an electronic device, including: at least one processor, and a memory connected to the at least one processor, wherein the memory stores Instructions executable by the at least one processor, the instructions being executed by the at least one processor, so that the at least one processor can perform the inventory replenishment recommendation method as described above.

Different from the situation in the related art, the replenishment recommendation method, device and electronic device provided by the embodiment of the present invention determine at least one replenishment model corresponding to the business; and generate a replenishment list corresponding to at least one replenishment model based on the replenishment model. ; Predict the replenishment revenue corresponding to the replenishment list based on the replenishment list; determine the target replenishment list from the replenishment list based on the replenishment revenue, and the target replenishment list is used to guide users to perform replenishment actions for the business . On the one hand, the replenishment list can be obtained by simply calling the preset replenishment model, which lowers the threshold for professional replenishment knowledge for business personnel; on the other hand, the replenishment revenue of the replenishment list is also predicted. Through prediction and The visual data analysis of prediction results can intuitively predict the future trend after replenishment, thereby improving the information support of decision-makers, helping users determine the appropriate replenishment list, and effectively reducing the risk of insufficient inventory, excessive warehousing, and liquidation. probability of the problem occurring.

Description of drawings

One or more embodiments are illustrated through the corresponding drawings. These exemplary illustrations do not constitute limitations to the embodiments. Elements with the same reference numerals in the drawings represent similar elements, unless otherwise specified. It is stated that the figures in the accompanying drawings do not constitute limitations on scale.

Figure 1 is a flow chart of an inventory replenishment recommendation method provided by an embodiment of the present invention;

Figure 2 is a flow chart of a method for obtaining the replenishment list provided by an embodiment of the present invention;

Figure 3 is a flow chart of a method for obtaining the replenishment model provided by an embodiment of the present invention;

Figure 4 is a flow chart of a method for obtaining the replenishment list provided by another embodiment of the present invention;

Figure 5 is a flow chart of a method for obtaining the replenishment revenue provided by an embodiment of the present invention;

Figure 6 is a schematic structural diagram of an inventory replenishment recommendation device provided by an embodiment of the present invention;

FIG. 7 is a schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention.

Detailed ways

In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention and are not intended to limit the present invention.

It should be noted that, if there is no conflict, various features in the embodiments of the present invention can be combined with each other, and they are all within the protection scope of the present invention. In addition, although the functional modules are divided in the device schematic diagram and the logical sequence is shown in the flow chart, in some cases, the module division in the device schematic diagram or the order in the flow chart can be performed. The steps shown or described. Unless otherwise defined, all technical and scientific terms used in this specification have the same meanings commonly understood by those skilled in the technical field belonging to the present invention. The terms used in the description of the present invention are only for the purpose of describing specific embodiments and are not used to limit the present invention.

Please refer to Figure 1, which is a flow chart of an inventory replenishment recommendation method provided by an embodiment of the present invention. The method may include the following steps:

S11. Determine at least one replenishment model corresponding to the business.

The inventory replenishment recommendation method provided by the embodiment of the present invention provides inventory management guidance for different businesses. The business includes inventory matters related to various industries, such as clothing industry inventory management, auto parts inventory management, etc. As you know, inventory replenishment refers to the process of replenishing products in the right quantity at the right time based on current demand and expected sales. Usually we will guide inventory replenishment based on the replenishment model. During inventory replenishment, the replenishment model can balance the ordering cost and inventory cost, so that the order can meet the estimated market demand and minimize the cost. The replenishment models include traditional replenishment models, such as EOQ (Economic Order Quantity) model, newsboy model, periodic inventory model, demand-driven replenishment model, etc. The replenishment model also includes a model obtained by combining historical data with statistical modeling, data mining technology and machine learning. For example, combined with historical data, the genetic algorithm is used to calculate the optimal safety stock replenishment model. Based on the replenishment model, the current optimal safety stock days can be obtained, and the optimal replenishment plan suitable for the current situation can be derived.

In the embodiment of the present invention, the replenishment model corresponding to the business can be determined based on the traditional replenishment model, or the replenishment model of the business can be obtained using data mining technology and machine learning based on the historical data corresponding to the business. Model. One or more replenishment models corresponding to the business may be determined. When determining the replenishment model, the system can provide a model display interface, and the user can select one or more replenishment models that match the current business based on the model displayed on the interface, or the system can actively recommend one or more replenishment models to the user. Model.

S12. Generate a replenishment list corresponding to the at least one replenishment model according to the replenishment model.

The replenishment list refers to a data sheet including the replenishment date, replenishment product name, replenishment product category, replenishment product quantity, replenishment cycle days and other information. When there are multiple replenishment models, the corresponding replenishment list is obtained according to each replenishment model.

Since the replenishment model is a combination of different parameters through formulas, a replenishment model can correspond to multiple parameters. The parameter type can be fixed, but the parameter values can be different, resulting in different results of the replenishment model modeled by the formula. When the replenishment model is a traditional business replenishment model, generating a replenishment list based on the replenishment model may include obtaining parameters corresponding to the replenishment model, determining the parameters, and then calling the function code corresponding to the replenishment model. block to run the function code block containing the parameters to generate the replenishment list. When the replenishment model is determined based on historical data corresponding to the business and combined with a machine learning algorithm, generating a replenishment list based on the replenishment model may include determining specific parameter values corresponding to the business based on the parameters of the replenishment model, and converting the specific parameters into Values are input into the replenishment model, which outputs a replenishment list. For example, factors that affect the quantity of replenished products include replenishment cycle days, delivery cycle days, average daily sales, inventory count, etc. These influencing factors can be used as parameters of the replenishment model, and machine learning is used based on the historical data corresponding to the parameters. The algorithm trains to obtain the replenishment model. When it is necessary to obtain the replenishment list, obtain the specific parameter values corresponding to the above parameters and enter the trained replenishment model to obtain the replenishment product quantity, and then combine the replenishment product quantity with the replenishment date , replenishment product names, etc. constitute the replenishment list.

S13. Predict the replenishment revenue corresponding to the replenishment list based on the replenishment list.

In the embodiment of the present invention, the replenishment revenue refers to how many days of warehouse outflow can be covered after replenishing goods according to the replenishment list, and what is the daily consumption trend. Restock via the Revenue can evaluate whether the replenishment plan corresponding to the replenishment list is excellent and meets the needs of users.

SKU (Stock Keeping Unit) is the smallest unit available for maintaining inventory control. For example, an SKU in textiles usually represents specifications, colors, and styles. SKU can be the number corresponding to the product when it is stored in the warehouse. SKU can distinguish the different attributes of different products, thus providing convenience for product procurement, sales, logistics management, warehousing management, etc.

Among them, factors related to the replenishment revenue include: single SKU consumption speed, number of SKU storage pieces, SKU storage distribution, business order structure change trend, business order SKU distribution change trend, business order SKU consumption change trend, replenishment SKU Number of pieces, replenishment SKU distribution, replenishment SKU mixing degree distribution, etc. Therefore, the inventory consumption rate can be predicted based on the replenishment list, and then the replenishment revenue can be predicted based on the predicted inventory consumption rate and the replenishment list. Specifically, the prediction of the replenishment revenue is to predict how many days of consumption the inventory can cover, or to predict Change trend of average outbound efficiency. Among them, the trend information of the inventory consumption speed can be obtained based on the number of SKU storage pieces and SKU storage distribution, as well as the SKU distribution change trend of business orders and the SKU consumption change trend of business orders.

The above is mainly to determine the replenishment revenue by predicting the inventory consumption rate and the replenishment list. It should be noted that the replenishment revenue can also be determined through other methods, such as based on the historical replenishment list and the historical replenishment list. The corresponding inventory consumption data is combined with the machine learning algorithm to train a replenishment revenue prediction model. The relevant parameters of the current replenishment list are input into the replenishment revenue prediction model, thereby obtaining the replenishment revenue corresponding to the current replenishment list. .

S14. Determine a target replenishment list from the replenishment list according to the replenishment revenue. The target replenishment list is used to guide the user to perform replenishment actions for the business.

Through the above steps S11 to S13, at least one replenishment list and the replenishment revenue corresponding to the replenishment list can be obtained. The replenishment list and the replenishment revenue can be visually presented to the user, for example, they can be reported in the form of predictive analysis. The method is provided to the user so that the user can see the income and prediction results after using the replenishment list, so as to determine whether the replenishment list is the target replenishment list. The target replenishment list is finally provided to the user for business Replenishment data list. The replenishment list can also be uploaded to the cloud server to be stored in the database of the server. The stored replenishment list can be used as reference data or historical data for the replenishment list of the same or similar business in the subsequent process. When the replenishment list includes multiple replenishment lists, it can be predicted that each replenishment list corresponds to Replenishment revenue: determine one or several target replenishment lists from multiple replenishment lists to the user based on the replenishment revenue.

The inventory replenishment recommendation method provided by the embodiment of the present invention can determine at least one replenishment model according to the business, and generate a replenishment list corresponding to the replenishment model, thereby lowering the threshold of professional replenishment knowledge for business personnel; it can also determine the replenishment model according to the replenishment model. The replenishment list mentioned in the goods revenue evaluation provides data analysis after replenishment, thereby improving the information support for decision-makers and helping decision-makers determine the most appropriate replenishment list, which has good guiding significance. Generally speaking, the inventory replenishment recommendation method provided by the embodiment of the present invention can effectively reduce the probability of occurrence of problems such as insufficient inventory, excessive storage, and liquidation, and improve the user experience.

The inventory replenishment recommendation method provided by the embodiment of the present invention will be described below with reference to specific application scenarios. For example, in e-commerce system warehousing management, when inventory replenishment is required, the replenishment model can be determined based on the industry's general model, and then based on the determined replenishment model, the parameters of the replenishment model can be adjusted based on the user's own business experience. Adjust or not adjust to get the replenishment list. Specifically, determining at least one replenishment model corresponding to the business includes: recommending at least one replenishment model corresponding to the business from the model library; or, based on the user data corresponding to the business, recommending at least one replenishment model corresponding to the business from the model library. Select a preset ranked replenishment model and provide it to the user, so that the user can determine at least one replenishment model corresponding to the business from the preset ranked replenishment models. The model library includes traditional models in the industry, such as EOQ model, newsboy model, periodic inventory model, etc. You can select the traditional model that has been used most frequently in this type of business based on the business and recommend this traditional model to users. You can also select the traditional model that is currently popular in the industry, such as a model that is used more frequently and has a higher level of discussion.

As shown in Figure 2, S12: Generate a replenishment list corresponding to the at least one replenishment model according to the replenishment model, which specifically includes:

S121. Obtain the parameter information associated with the replenishment model, and control the parameter information to be in an editable state. The parameter information in the editable state is used to enable the user to modify the parameter information;

S123. When receiving the user's instruction to determine the replenishment model and the parameter information, run the function code block of the replenishment model based on the parameter information to generate replenishment corresponding to the replenishment model. Checklist.

The parameter information changes with different models and strategies. For example, if the business selects the periodic (s, S) model, then the platform will first display the default parameters in the parameter value cell corresponding to the parameter information. numerical value. For example, the supplier lead time is 10 days, the inventory cycle is 20 days, the safety stock is 100,000, the replenishment point is 80,000, etc., among which "10 days", "20 days", "100,000", "80,000", etc. are all Parameter information. The business party can accept the default parameter information, or double-click the cell to directly modify the parameter information. For example, the business party double-clicks the cell to modify the inventory cycle to 60 days. After the business party confirms the use of the model and confirms all parameter information, the platform starts the function code block of the built-in periodic (s, S) model to generate the replenishment list, which includes the replenishment date. , the name of the SKU that should be replenished, the number of pieces of this SKU that should be replenished, etc.

In some embodiments, the replenishment model can also be determined based on historical data in combination with a machine learning algorithm, and then the replenishment list can be predicted based on the determined replenishment model. Specifically, as shown in Figure 3, S11. Determine at least one replenishment model corresponding to the business, which specifically includes:

S111. Obtain the SKU variety corresponding to the business;

S112. Obtain the historical outbound order data and historical warehousing inventory data corresponding to the SKU variety;

S113. Obtain the historical consumption speed curve of the SKU variety according to the historical outbound order data and the historical warehousing inventory data;

S114. Determine the prediction algorithm corresponding to the SKU variety;

S115. Train and obtain the replenishment model based on the historical consumption speed curve and the prediction algorithm.

Among them, the SKU variety refers to the product combination subdivision under the category. For example, daily necessities are a category, and the SKU varieties below it can be shampoo, shower gel, etc., and vegetables are a category, and the SKU variety below it can be cucumber. , cabbage, pepper, etc. The historical outbound order data includes detailed data such as the outbound time of the SKU variety, the number of outbound pieces, the number of SKU varieties, storage methods, and the number of used boxes. The historical warehousing inventory data corresponds to the historical outbound order data, including SKU varieties in the warehouse, number of pieces in the warehouse, storage method, number of boxes, etc. The historical consumption rate of a certain SKU variety can be calculated based on the historical outbound order data and the historical warehousing inventory data. The historical consumption rate can be based on the outbound probability of the SKU variety within the unit time or the preset time period. Indicated by the number of items in stock, etc. The greater the probability of stocking out, the greater the consumption speed of the SKU variety, or the number of items in stock within the preset time is getting smaller and smaller, the greater the consumption speed of the SKU variety. Optionally, obtain the number of pieces of the SKU variety or the number of SKU varieties consumed per day or hourly through data statistics, thereby determining the historical consumption rate of the SKU variety. You can also count the number of pieces consumed per SKU per day or hourly to determine the historical consumption rate of the SKU variety. The obtained historical consumption speed value and time together form the historical consumption speed curve, that is, the historical consumption speed curve includes how much and what types of products are consumed in what time period. The historical consumption speed curve of the SKU variety can be used as part of the predictive analysis report to provide decision makers.

Due to the complexity and diversity of customer services, a single prediction algorithm may not be able to meet user needs. Therefore, in this embodiment, different prediction algorithms may be enabled based on parameter information determined by the user. Wherein, determining the prediction algorithm corresponding to the SKU variety specifically includes obtaining the SKU variety, the SKU variety includes at least one of long-tail products, regular products, new products and hot products, and selecting the prediction corresponding to the obtained SKU variety. algorithm. For example, when forecasting long-tail products, you can choose the ARIMA model (Autoregressive Integrated Moving Average model, the prediction object changes over time); when forecasting regular products, you can choose the LightGBM algorithm; when predicting new products, you can choose the LightGBM algorithm or LSTM (Long Short-Term Memory, Long short-term memory network) algorithm; when predicting explosive products, you can choose the Stacking algorithm or the Meta Learning algorithm.

After determining the prediction algorithm, the parameters in the prediction algorithm need to be obtained to determine the final replenishment model. Specifically, according to the historical consumption speed curve, a large number of historical consumption speed values and the times corresponding to the historical consumption speed values can be obtained. These data are used as training sets and test sets. The training set is used for training and is used to generate the prediction algorithm. The data set and test set are used to test the data set of the learned model or algorithm, and then combine the set considerations or factor weights to determine the optimal data set from the learned model or algorithm data set, thereby determining The final model is the replenishment model. Among them, you can also perform data preprocessing on the data of the training set and the test set, and determine the feature vectors. Training and testing can be carried out based on different algorithms. Different considerations and factor weights in the algorithms are also different. The specific training process and testing The process will not be described in detail here.

After the above-mentioned replenishment model is obtained according to the above-mentioned steps S111 to S115, as shown in Figure 4, S12. Generate a replenishment list corresponding to the at least one replenishment model according to the replenishment model, which specifically includes:

S122. Input parameter N to the replenishment model to obtain the consumption speed curve corresponding to N, where N is the minimum number of days that the current replenishment can support normal outbound operations;

S124. Obtain the replenishment list corresponding to the N according to the consumption speed curve corresponding to the N and the replenishment model prediction.

The N can be determined by the decision-maker according to specific application conditions, or can be customized by the system. According to the consumption speed curve of N days and the replenishment model, the replenishment demand curve of N days is predicted. The replenishment demand curve includes predicting the consumption changes of the replenished goods in the future preset time, and how soon the replenished goods will be available. Exhausted use and predicted replenishment of goods affect the AVG order outbound efficiency curve. These curve information can be presented in the predictive analysis report, and the predictive analysis report is provided to the decision-maker. The replenishment list is generated according to the replenishment demand curve. The replenishment list includes SKU varieties, order numbers, replenishment time, replenishment cycle, transportation mode, transportation cycle, etc.

The embodiment of the present invention mainly obtains the replenishment list through the above two methods, that is, based on the general model in the industry, and combined with the user adjusting or not adjusting the parameters of the model based on business experience, thereby obtaining the replenishment list; and Based on historical data, the consumption speed curve is obtained, and then the replenishment list is obtained through machine learning model or algorithm prediction. It should be noted that in addition to the two methods introduced above to obtain the replenishment list, the replenishment list can also be obtained through other methods, such as obtaining the first replenishment list according to a general model, historical data and machine learning algorithms Obtain the second replenishment list, and then comprehensively evaluate the first replenishment list and the second replenishment list in combination with user experience, thereby obtaining the final replenishment list.

After obtaining the replenishment list, the embodiment of the present invention predicts the replenishment revenue corresponding to the replenishment list based on the consumption speed. Specifically, the replenishment profit corresponding to the replenishment list is obtained according to the consumption speed curve and the replenishment list. goods income. As shown in Figure 5, obtaining the replenishment revenue corresponding to the replenishment list based on the consumption speed curve and the replenishment list includes:

S131. Obtain the replenishment date and replenishment quantity of the SKU variety according to the replenishment list;

S132. Obtain the SKU varieties consumed within the preset time period and the consumption quantity corresponding to the SKU varieties according to the consumption speed curve;

S133. Calculate the hit rate of the SKU variety in the replenishment list based on the consumption quantity corresponding to the SKU variety, the replenishment date, and the replenishment quantity.

Among them, whether the consumed products are in stock (that is, existing before replenishment) or in the consumed replenishment list, the replenishment income can be obtained by determining the hit rate of the products consumed in the replenishment list, and at the same time , after the warehouse replenishes goods according to the replenishment list, the structure of the entire inventory also changes It is easy to improve the hit rate, which means that the replenished goods can be quickly shipped out of the warehouse or avoid being shipped in time. This is the meaning of replenishment revenue. Therefore, the embodiment of the present invention can effectively improve the outbound efficiency and inventory management effect through the evaluation of replenishment revenue.

Please refer to Figure 6. Figure 6 is a schematic structural diagram of an inventory replenishment recommendation device provided by an embodiment of the present invention. The inventory replenishment recommendation device 100 includes: a replenishment model determination module 101, a replenishment list acquisition module 102, and predictive analysis. Module 103 and replenishment list recommendation module 104.

The replenishment model determination module 101 is used to determine at least one replenishment model corresponding to the business; the replenishment list acquisition module 102 is used to generate the replenishment model corresponding to the at least one replenishment model according to the replenishment model. list; the predictive analysis module 103 is used to predict the replenishment revenue corresponding to the replenishment list according to the replenishment list; the replenishment list recommendation module 104 is used to calculate the replenishment revenue from the replenishment list based on the replenishment list. A target replenishment list is determined, and the target replenishment list is used to guide the user to perform replenishment actions for the business.

Wherein, the replenishment model determination module 101 is specifically configured to recommend at least one replenishment model corresponding to the business from the model library; or, select a preset from the model library according to the user data corresponding to the business. The ranked replenishment models are provided to the user, so that the user can determine at least one replenishment model corresponding to the business from the preset ranked replenishment models. The replenishment list acquisition module 102 is specifically used to obtain parameter information associated with the replenishment model, and control the parameter information to be in an editable state. The parameter information in the editable state is used to enable the user to modify the parameter information. ; Upon receiving the user's instruction to determine the replenishment model and the parameter information, based on the parameter information, run the function code block of the replenishment model to generate a replenishment list corresponding to the replenishment model .

In some embodiments, the replenishment module determination module 101 is specifically configured to: obtain the SKU variety corresponding to the business; obtain historical outbound order data and historical warehousing inventory data corresponding to the SKU variety; Obtain the historical consumption speed curve of the SKU variety from the warehouse order data and the historical warehousing inventory data; determine the prediction algorithm corresponding to the SKU variety; and obtain the replenishment model based on the historical consumption speed curve and the prediction algorithm training. . Wherein, determining the prediction algorithm corresponding to the SKU variety specifically includes: obtaining the SKU variety, the SKU variety includes at least one of long-tail products, conventional products, new products and hot products, and selecting the SKU corresponding to the obtained SKU variety. Prediction algorithm. Wherein, the replenishment list acquisition module 102 is specifically used to: input parameter N into the replenishment model to obtain the consumption speed curve corresponding to N, The N is the minimum number of days that the current replenishment can support normal outbound operations; the replenishment list corresponding to the N is obtained according to the consumption speed curve corresponding to the N and the replenishment model prediction.

The prediction analysis module 103 is specifically used to: obtain the replenishment date and replenishment quantity of the SKU variety according to the replenishment list; obtain the SKU varieties consumed within the preset time period and the corresponding SKU varieties according to the consumption speed curve. the consumption quantity; calculate the hit rate of the SKU variety in the replenishment list based on the consumption quantity corresponding to the SKU variety, the replenishment date, and the replenishment quantity.

It should be noted that the above-mentioned inventory replenishment recommendation device 100 can execute the inventory replenishment recommendation method provided by the embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method, which are not described in detail in the embodiment of the inventory replenishment recommendation device. For technical details, please refer to the inventory replenishment recommendation method provided by the embodiment of the present invention.

Please refer to FIG. 7 , which is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. The electronic device 200 is used to execute the above inventory replenishment recommendation method. The electronic device 200 includes:

One or more processors 201 and memory 202. In Figure 7, one processor 201 is taken as an example. The processor 201 and the memory 202 may be connected through a bus or other means. In FIG. 7 , the connection through a bus is taken as an example.

As a non-volatile computer-readable storage medium, the memory 202 can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as those corresponding to the inventory replenishment recommendation method in the embodiment of the present invention. Program instructions/modules (for example, the replenishment model determination module 101, the replenishment list acquisition module 102, the predictive analysis module 103 and the replenishment list recommendation module 104 shown in Figure 6). The processor 201 executes various functional applications and data processing of the server by running non-volatile software programs, instructions and modules stored in the memory 202, that is, implementing the inventory replenishment recommendation method of the above method embodiment.

The memory 202 may include a storage program area and a storage data area, where the storage program area may store an operating system and an application program required for at least one function; the storage data area may store data created according to the use of the inventory replenishment recommendation device, etc. In addition, the memory 202 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, memory 202 optionally includes memory located remotely relative to processor 201, and these remote memories may to connect to the inventory replenishment recommendation device via the network. Examples of the above-mentioned networks include but are not limited to the Internet, intranets, local area networks, mobile communication networks and combinations thereof.

The one or more modules are stored in the memory 202. When executed by the one or more processors 201, the inventory replenishment recommendation method in any of the above method embodiments is executed. For example, the above-described figure is executed. 1 to each method step in Figure 5, and implement the functions of the module in Figure 6.

The above-mentioned products can execute the methods provided by the embodiments of the present invention, and have corresponding functional modules and beneficial effects for executing the methods. For technical details that are not described in detail in this embodiment, please refer to the method provided by the embodiment of the present invention.

Electronic devices provided by embodiments of the present invention exist in various forms, including but not limited to: mobile communication devices, such as smart phones, functional mobile phones, etc.; ultra-mobile personal computer devices, which belong to the category of personal computers and have computing and The processing function generally also has mobile Internet features; the server is a device that provides computing services. The server is composed of a processor, a hard disk, a memory, a system bus, etc.; and other electronic devices with data interaction functions.

Through the above description of the embodiments, those of ordinary skill in the art can clearly understand that each embodiment can be implemented by means of software plus a general hardware platform, and of course, it can also be implemented by hardware. Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a computer-readable storage medium, and the program can be stored in a computer-readable storage medium. When executed, the process may include the processes of the above method embodiments. Wherein, the storage medium can be a magnetic disk, an optical disk, a read-only memory (Read-Only Memory, ROM) or a random access memory (Random Access Memory, RAM), etc.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention, but not to limit it; under the idea of the present invention, the technical features of the above embodiments or different embodiments can also be combined. The steps may be performed in any order, and there are many other variations of the different aspects of the invention as described above, which are not provided in detail for the sake of brevity; although the invention has been described in detail with reference to the foregoing embodiments, one of ordinary skill in the art Skilled persons should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent substitutions for some of the technical features; and these modifications or substitutions do not deviate from the essence of the corresponding technical solutions from the implementation of the present application. Example scope of technical solutions.

Claims

A recommended method for inventory replenishment, which is characterized by including:

Determine at least one replenishment model corresponding to the business;

Generate a replenishment list corresponding to the at least one replenishment model according to the replenishment model;

Predict the replenishment revenue corresponding to the replenishment list based on the replenishment list;

A target replenishment list is determined from the replenishment list according to the replenishment revenue, and the target replenishment list is used to guide the user to perform replenishment actions for the business.
The inventory replenishment recommendation method according to claim 1, wherein the determining at least one replenishment model corresponding to the business includes:

Recommend at least one replenishment model corresponding to the business from the model library; or,

Select a preset ranked replenishment model from the model library according to the user data corresponding to the business and provide it to the user, so that the user can determine at least one replenishment model corresponding to the business from the preset ranked replenishment model. Cargo model.
The inventory replenishment recommendation method according to claim 2, wherein generating a replenishment list corresponding to the at least one replenishment model according to the replenishment model includes:

Obtain parameter information associated with the replenishment model, and control the parameter information to be in an editable state. The parameter information in the editable state is used to enable the user to modify the parameter information;

When a user's instruction to determine the replenishment model and the parameter information is received, the function code block of the replenishment model is run based on the parameter information to generate a replenishment list corresponding to the replenishment model.
The inventory replenishment recommendation method according to claim 1, wherein the determining at least one replenishment model corresponding to the business includes:

Obtain the SKU variety corresponding to the business;

Obtain the historical outbound order data and historical warehousing inventory data corresponding to the SKU variety;

Obtain the historical consumption speed curve of the SKU variety according to the historical outbound order data and the historical warehousing inventory data;

Determine the prediction algorithm corresponding to the SKU variety;

The replenishment model is obtained by training based on the historical consumption speed curve and the prediction algorithm.
The inventory replenishment recommendation method according to claim 4, wherein generating a replenishment list corresponding to the at least one replenishment model according to the replenishment model includes:

Input parameter N to the replenishment model to obtain the consumption speed curve corresponding to N, where N is the minimum number of days that the current replenishment can support normal outbound operations;

The replenishment list corresponding to the N is obtained according to the consumption speed curve corresponding to the N and the replenishment model prediction.
The inventory replenishment recommendation method according to claim 3 or 5, wherein predicting the replenishment revenue corresponding to the replenishment list based on the replenishment list includes:

The replenishment revenue corresponding to the replenishment list is obtained according to the consumption speed curve and the replenishment list.
The inventory replenishment recommendation method according to claim 4, wherein the prediction algorithm for determining the SKU variety specifically includes:

Obtain SKU varieties, which include at least one of long-tail products, conventional products, new products, and popular products, and select a prediction algorithm corresponding to the obtained SKU varieties.
The inventory replenishment recommendation method according to claim 6, wherein obtaining the replenishment revenue corresponding to the replenishment list based on the consumption speed curve and the replenishment list includes:

Obtain the replenishment date and replenishment quantity of the SKU variety according to the replenishment list;

Obtain the SKU varieties consumed within the preset time period and the consumption quantity corresponding to the SKU varieties according to the consumption speed curve;

The hit rate of the SKU variety in the replenishment list is calculated based on the consumption quantity corresponding to the SKU variety, the replenishment date, and the replenishment quantity.
An inventory replenishment recommendation device, characterized by including:

The replenishment model determination module is used to determine at least one replenishment model corresponding to the business;

A replenishment list acquisition module, configured to generate a replenishment list corresponding to the at least one replenishment model according to the replenishment model;

A predictive analysis module, used to predict the replenishment revenue corresponding to the replenishment list based on the replenishment list;

A replenishment list recommendation module is used to determine a target replenishment list from the replenishment list according to the replenishment revenue, and the target replenishment list is used to guide the user to perform replenishment actions for the business.
An electronic device, characterized by comprising: at least one processor, and a memory connected to the at least one processor, wherein the memory stores instructions that can be executed by the at least one processor, and the instructions Executed by the at least one processor, so that the at least one processor can execute the inventory replenishment recommendation method according to any one of claims 1 to 8.