Intelligent inventory early warning and dynamic replenishment strategy integration method and system

Abstract

The invention relates to an intelligent inventory early warning and dynamic replenishment strategy integration method, and relates to the field of data processing specially suitable for administrative, commercial, financial, management, supervision or prediction purposes. The method comprises the steps that an intelligent prediction model is adopted to intelligently predict the total sales amount of each part corresponding to various retail commodities in sale in a current time segment of a set distribution site according to various basic data screened in a targeted mode; and formulating an inventory early warning mechanism and a dynamic replenishment strategy of the current time segment for the set distribution site based on the intelligent prediction result. The invention also relates to an intelligent inventory early warning and dynamic replenishment strategy integration system. According to the invention, the artificial intelligence model of a customized structure can be constructed to intelligently predict and serve the sales volume data of various retail commodities in the distribution site of each block in the future time segment, and then a corresponding inventory early warning mechanism and a dynamic replenishment strategy are formulated, so that the commodity sales efficiency and the platform operation cost are both considered.

Description

Technical Field

[0001] The present invention relates to the field of data processing specifically suitable for administrative, commercial, financial, management, supervisory or forecasting purposes, and in particular to an integrated method and system for intelligent inventory early warning and dynamic replenishment strategy. Background Art

[0002] With the rapid development of electronic finance and e-commerce, the use of electronic sales models to implement online sales of various retail goods has become a development trend in retail sales. More and more physical retail stores have been gradually replaced by online sales platforms, such as online sales apps. These online sales platforms are usually fixed areas in the city, such as multiple blocks, and set up the same distribution station to provide supply services for online orders of retail goods from residents in multiple blocks, thereby reducing the operating costs of physical stores and taking into account the economic interests of both residents and online sales platform operators as purchasing users.

[0003] For example, the Chinese invention patent publication CN111125140A proposes an automatic inventory replenishment system based on the daily sales coefficient, the system includes an inventory dynamic adjustment module, the signal output end of the inventory dynamic adjustment module is electrically connected to a computer, the signal output end of the computer is electrically connected to a dynamic replenishment module, a replenishment switch module, an inventory quantity calculation module, an inventory depth calculation module, a safety inventory calculation module, and a safety inventory and inventory comparison module. Through the inventory dynamic adjustment module, the inventory quantity of the goods on the product page can be calculated more accurately, so that the obtained inventory dynamic parameters are accurately presented on the product page, the accuracy of the product inventory value is improved, and the value that needs to be replenished is more accurately provided to the staff, so that the staff can replenish the goods in advance, avoiding the loss of the store caused by the failure to replenish in time.

[0004] For example, the Chinese invention patent publication CN118171991A proposes an item inventory control method, device, electronic device and storage medium, the method comprising: determining the total item satisfaction rate including each item category; determining at least one item category to be replenished according to the total item satisfaction rate and / or the replenishment point quantity corresponding to each item category; determining the to-be-replenished quantity of the current item category to be replenished according to the historical out-of-sale data of the current item category to be replenished; determining the target replenishment quantity of each item category to be replenished according to the target inventory quantity, to-be-replenished quantity and existing inventory quantity of each item category to be replenished. This technical solution solves the problem that the corresponding service cannot be provided to the user due to the untimely replenishment of the item category, realizes the timely determination of the to-be-replenished quantity of the corresponding item category, and determines the target replenishment quantity based on the to-be-replenished quantity and the corresponding target inventory quantity, thereby achieving the technical effect of dynamic and effective replenishment according to the item shipment information.

[0005] It can be seen that the inventory status analysis and replenishment strategy formulation involved in the above-mentioned prior art, when mentioned in a timely manner, only refers to the timely calculation and analysis of the current inventory and sales volume of various sales commodities. Obviously, the results of such calculation and analysis are all lagged data, and it is impossible to accurately obtain the sales data corresponding to each sales commodity in the future time segment. Naturally, it is impossible to determine whether the inventory data corresponding to each sales commodity of the online sales platform can keep up with their respective sales data based on the sales data corresponding to each sales commodity in the future time segment. As a result, the inventory early warning mechanism and dynamic replenishment strategy of the online sales platform cannot be effectively and reliably implemented due to the lack of reliable basic data, which easily leads to a sales dilemma of insufficient or excessive supply of a certain type of sales commodity. Summary of the invention

[0006] In order to solve the technical defects in the prior art, the present invention provides an integrated method and system of intelligent inventory warning and dynamic replenishment strategy, which can build an artificial intelligence model with a customized structure for the same distribution site that serves various blocks at the same time, and based on the comprehensive and sufficient basic data screened in a targeted manner, intelligently predict the sales data corresponding to various retail commodities of the distribution site in the current time segment, that is, a future time segment, and then formulate corresponding inventory warning mechanism and dynamic replenishment strategy, thereby completing the organic integration of the inventory warning mechanism based on the intelligent prediction results and the dynamic replenishment strategy, thereby avoiding the sales dilemma of insufficient or excessive supply of a certain type of sales commodity, improving the operating efficiency of the online sales platform, and reducing the operating cost of the online sales platform.

[0007] According to a first aspect of the present invention, a method for integrating intelligent inventory warning and dynamic replenishment strategy is provided, the method comprising: Obtain the number of retail product categories on sale, the maximum storage capacity, the number of blocks in each block managed, the cumulative value of each permanent population corresponding to each block managed, and the geographical area occupied by each block managed at the set distribution site, and output them as multiple configuration information of the set distribution site; Obtain the retail commodity sales data corresponding to each past time segment before the current time segment of the set distribution site, and obtain the retail commodity sales data corresponding to the past simultaneous time segment of the set distribution site at the same time segment position as the current time segment on the previous day; Performing multiple training operations on the feedforward neural network to obtain the feedforward neural network after the multiple training operations are completed, and outputting the feedforward neural network after the multiple training operations as an intelligent prediction model; An intelligent prediction model is used to intelligently predict the total sales volume of various retail commodities on sale at the set distribution station in the current time segment according to the duration of each time segment, multiple configuration information of the set distribution station, the sales data of each retail commodity corresponding to each past time segment before the current time segment of the set distribution station, and the sales data of a single retail commodity corresponding to the set distribution station in the same past segment; When there is a type of commodity on sale whose total sales volume is less than the total inventory volume in each of the total sales volume corresponding to each of the various retail commodities on sale predicted by the intelligent forecast, the commodity on sale is used as an inventory warning type; When there is a type of retail commodity on sale whose total sales volume is less than the total inventory volume among the total sales volume corresponding to each of the various retail commodities on sale intelligently predicted, the type of retail commodity on sale will be used as a dynamic replenishment type, and the dynamic replenishment type will be replenished based on the difference between the total sales volume and the total inventory volume corresponding to the dynamic replenishment type.

[0008] According to a second aspect of the present invention, there is provided an integrated system of intelligent inventory warning and dynamic replenishment strategy, the system comprising: The first capture mechanism is used to obtain the number of retail product categories on sale, the maximum storage capacity, the number of blocks in each block managed, the cumulative value of each permanent population corresponding to each block managed, and the geographical area occupied by each block managed, and output it as multiple configuration information of the set distribution site; The second capture mechanism is used to obtain the retail commodity sales data corresponding to each past time segment before the current time segment of the set distribution site, and to obtain the retail commodity sales data corresponding to the past simultaneous time segment of the set distribution site at the same time segment position as the current time segment on the previous day; An object forming mechanism is used to perform multiple training operations on the feedforward neural network to obtain the feedforward neural network after the multiple training operations are completed, and output the feedforward neural network after the multiple training operations as an intelligent prediction model; A prediction execution mechanism, connected to the first capture mechanism, the second capture mechanism and the object formation mechanism respectively, for using an intelligent prediction model to intelligently predict the total sales volume of each retail commodity on sale at the set distribution site in the current time segment according to the duration of each time segment, multiple configuration information of the set distribution site, the sales data of each retail commodity corresponding to each past time segment before the current time segment of the set distribution site, and the acquisition of the sales data of a single retail commodity corresponding to the set distribution site in the same past segment; An inventory warning mechanism, connected to the forecast execution mechanism, is used to use the on-sale commodity category as an inventory warning category when there is a category of on-sale commodity whose total sales volume is less than the total inventory volume in each of the total sales volume corresponding to each of the various retail commodities on sale in the intelligent forecast; The dynamic replenishment mechanism is connected to the forecast execution mechanism and is used to use the sales commodity category as a dynamic replenishment category when there is a sales commodity category whose total sales volume is less than the total inventory volume among the total sales volume corresponding to each of the various retail commodities on sale in the intelligent forecast, and replenish the dynamic replenishment category based on the difference between the total sales volume and the total inventory volume corresponding to the dynamic replenishment category.

[0009] It can be seen that the present invention has at least the following key invention features: First: for the set distribution site that is responsible for the supply of retail goods in each block at the same time, a customized intelligent prediction model is constructed for the intelligent prediction of the sales quantity of each corresponding to various retail goods on sale in the current time segment of the set distribution site, that is, a future time segment. The intelligent prediction model is a feedforward neural network that has completed multiple training operations, and the number of training operations is monotonically positively correlated with the number of types of retail goods on sale at the set distribution site, so that intelligent prediction models with different structures are designed for different distribution sites, ensuring the effectiveness and stability of the intelligent prediction results; Second: for the intelligent prediction of the sales quantity of each corresponding to each retail commodity on sale in the current time segment of the distribution site, various basic data are selected in a targeted manner. The basic data include the number of retail commodity types on sale at the distribution site, the maximum storage capacity, the number of blocks managed in each block, the cumulative value of each permanent population corresponding to each block managed, and the geographical area occupied by each block managed, as well as the sales data of each retail commodity corresponding to each past time segment before the current time segment of the distribution site, and the acquisition of the sales data of a single retail commodity corresponding to the same time segment position as the current time segment of the distribution site on the previous day. The full and comprehensive selection of the above basic data further ensures the effectiveness and stability of the intelligent prediction results; Third: In each training operation performed on the feedforward neural network, the total sales volume of each retail commodity sold at the known set distribution site in a certain past time segment is used as the output content of the feedforward neural network, the duration of each time segment, multiple configuration information of the set distribution site, the sales data of each retail commodity corresponding to each past time segment before the set distribution site, and the sales data of a single retail commodity corresponding to the past simultaneous segment of the set distribution site in the past time segment are used as the input content of the feedforward neural network to perform this training operation, thereby ensuring the training effect of each training operation of the feedforward neural network; Fourth place: when there are types of sales commodities whose total sales volume is less than the total inventory volume among the total sales volume corresponding to the various retail commodities on sale in the current time segment of the set distribution site in the intelligent prediction, the types of sales commodities on sale are used as inventory warning types for warning, and when there are types of sales commodities whose total sales volume is less than the total inventory volume among the total sales volume corresponding to the various retail commodities on sale in the current time segment of the set distribution site in the intelligent prediction, the types of sales commodities on sale are used as dynamic replenishment types, and the dynamic replenishment types are replenished based on the difference between the total sales volume and the total inventory volume corresponding to the dynamic replenishment types, wherein the number of commodities replenished for the dynamic replenishment types is equal to the difference between the total sales volume and the total inventory volume corresponding to the dynamic replenishment types, thereby completing the inventory warning and dynamic replenishment of various retail commodities on sale based on the intelligent prediction results, completing the organic integration of the inventory warning mechanism based on the intelligent prediction results and the dynamic replenishment strategy, and improving the intelligence level and automation level of the set distribution site management. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The embodiments of the present invention will be described below with reference to the accompanying drawings, wherein: Figure 1 It is a technical flow chart of the integrated method and system of intelligent inventory warning and dynamic replenishment strategy according to the present invention.

[0011] Figure 2 The figure is a flowchart of the steps of the method for integrating intelligent inventory warning and dynamic replenishment strategy according to Embodiment 1 of the present invention.

[0012] Figure 3 The figure is a flowchart of the steps of the method for integrating intelligent inventory warning and dynamic replenishment strategy according to Embodiment 2 of the present invention.

[0013] Figure 4 The figure is a flowchart of the steps of the method for integrating intelligent inventory warning and dynamic replenishment strategy according to Embodiment 3 of the present invention.

[0014] Figure 51 is an internal structure diagram of an integrated system of intelligent inventory warning and dynamic replenishment strategy according to Embodiment 4 of the present invention.

[0015] Figure 6 This is an internal structure diagram of an integrated system of intelligent inventory warning and dynamic replenishment strategy according to Example 5 of the present invention.

[0016] Figure 7 1 is an internal structure diagram of an integrated system of intelligent inventory warning and dynamic replenishment strategy according to Example 6 of the present invention. DETAILED DESCRIPTION

[0017] like Figure 1 As shown, a technical flow chart of the integrated method and system of intelligent inventory warning and dynamic replenishment strategy according to the present invention is given.

[0018] like Figure 1 As shown, the specific technical process of the present invention is as follows: The first technical process: for the distribution stations that are responsible for the supply of retail goods in each block at the same time, a customized intelligent prediction model is built for the intelligent prediction of the sales quantity of various retail goods on sale in the current time segment, i.e., a future time segment, at the distribution stations; exist Figure 1 In the process, each block feeds back the sales order information to the designated distribution station, and the designated distribution station feeds back to the intelligent prediction model, so as to formulate the inventory warning mechanism and dynamic replenishment strategy for the designated distribution station in the future time segment; and in Figure 1 In the embodiment, the first technical process, the second technical process and the third technical process are carried out at the intelligent prediction model, and the fourth technical process is carried out at the online sales platform above the intelligent prediction model, such as the online sales APP; Specifically, the structural customization of the intelligent prediction model is mainly reflected in the following aspects: First: the intelligent prediction model is a feedforward neural network after completing multiple training operations; Secondly: the number of training operations of the feedforward neural network is monotonically positively correlated with the number of retail product categories on sale at the set distribution site, so that intelligent prediction models with different structures are designed for different distribution sites, ensuring the effectiveness and stability of the intelligent prediction results; Finally: in each training operation performed on the feedforward neural network, the total sales volume of each retail commodity sold at the known set distribution site in a certain past time segment is used as the output content of the feedforward neural network, the duration of each time segment, multiple configuration information of the set distribution site, the sales data of each retail commodity corresponding to each past time segment before the set distribution site, and the sales data of a single retail commodity corresponding to the past simultaneous segment of the set distribution site in the past time segment are used as the input content of the feedforward neural network to perform this training operation, thereby ensuring the training effect of each training operation of the feedforward neural network; The second technical process: targeted screening of various basic data for intelligent prediction of the sales quantity of various retail commodities on sale in the current time segment of the distribution site; Specifically, the basic data include the number of retail product categories on sale at the distribution site, the maximum storage capacity, the number of blocks in each block managed, the cumulative value of each permanent population corresponding to each block managed, and the geographical area occupied by each block managed; Specifically, the basic data also include the sales data of each retail commodity corresponding to each past time segment before the current time segment of the set distribution site, and the sales data of a single retail commodity corresponding to the past simultaneous time segment of the set distribution site at the same time segment position as the current time segment on the previous day; In this way, the full and comprehensive screening of the above basic data further ensures the effectiveness and stability of the intelligent prediction results; The third technical process: the intelligent prediction model customized by the first technical process is used to intelligently predict the total sales volume of various retail products on sale in the current time segment of the distribution site based on the basic data fully and comprehensively selected by the second technical process; Specifically, since the distribution stations are set to serve each block, the total sales volume of each retail commodity on sale at the current time segment of the distribution stations intelligently predicted reflects the demand quantity of each retail commodity on sale in the orders placed by residents in each block as sales users at the same online sales platform in the current time segment; Here, since the current time segment starts at the current moment, in fact, the current time segment belongs to a future time segment; Fourth technical process: Based on the intelligent prediction results of the third technical process, the inventory warning mechanism and dynamic replenishment strategy of the current time segment are customized for the set distribution site, thereby completing the organic integration of the inventory warning mechanism based on the intelligent prediction results and the dynamic replenishment strategy; Specifically, when there is a type of selling commodity whose total sales volume is less than the total inventory volume among the total sales volume corresponding to each of the various retail commodities on sale in the current time segment of the set distribution site in the intelligent prediction, the type of selling commodity on sale is used as an inventory warning type for warning; Specifically, when there is a type of selling commodity whose total sales volume is less than the total inventory volume among the total sales volume corresponding to various retail commodities on sale in the current time segment of the set distribution site in the intelligent prediction, the selling commodity type is used as a dynamic replenishment type, and the dynamic replenishment type is replenished based on the difference between the total sales volume and the total inventory volume corresponding to the dynamic replenishment type, wherein the quantity of commodities replenished for the dynamic replenishment type is equal to the difference between the total sales volume and the total inventory volume corresponding to the dynamic replenishment type; In this way, inventory warning and dynamic replenishment of various retail products on sale can be completed based on the intelligent prediction results, thereby improving the intelligence and automation level of the management of distribution sites.

[0019] The key points of the present invention are: an intelligent prediction model with a customized structure for intelligent prediction of the sales quantities of various retail commodities on sale corresponding to future time segments for a distribution station that is responsible for supplying retail commodities to each block at the same time, a number of basic data targetedly screened for intelligent prediction, a targeted design of each training mechanism of a feedforward neural network, and an organic integration of an inventory warning mechanism and a dynamic replenishment strategy for retail commodities on sale based on intelligent prediction results.

[0020] The integrated method and system of intelligent inventory warning and dynamic replenishment strategy of the present invention will be specifically described below by way of embodiments.

[0021] Example 1 Figure 2 The figure is a flowchart of the steps of the method for integrating intelligent inventory warning and dynamic replenishment strategy according to Embodiment 1 of the present invention.

[0022] like Figure 2 As shown, the integration method of the intelligent inventory warning and dynamic replenishment strategy includes the following steps: Step S201: Obtain the number of retail product categories on sale, the maximum storage capacity, the number of blocks in each block managed, the cumulative value of each permanent population corresponding to each block managed, and the geographical area occupied by each block managed, and output them as multiple configuration information of the set distribution site; Specifically, the number of types of retail goods on sale, the maximum storage capacity, the number of blocks of each block managed, the cumulative values ​​of each permanent population corresponding to each block managed, and the geographical area jointly occupied by each block managed at the set distribution site are obtained, and output as multiple configuration information of the set distribution site includes: using multiple information parsing components to respectively obtain the number of types of retail goods on sale, the maximum storage capacity, the number of blocks of each block managed, the cumulative values ​​of each permanent population corresponding to each block managed, and the geographical area jointly occupied by each block managed; Step S202: Acquire the sales data of each retail commodity corresponding to each past time segment before the current time segment of the set distribution site, and acquire the sales data of a single retail commodity corresponding to the past simultaneous time segment of the set distribution site at the same time segment position as the current time segment on the previous day; For example, obtaining the retail commodity sales data corresponding to each past time segment before the current time segment of the set distribution site and obtaining the retail commodity sales data corresponding to the past simultaneous segment at the same time segment position as the current time segment of the previous day of the set distribution site includes: the current time segment is from 11:00 a.m. to 11:30 a.m., then the past time segments before the current time segment are 10:30 a.m. to 11:00 a.m., 10:00 a.m. to 10:30 a.m., 9:30 a.m. to 10:00 a.m., 9:00 a.m. to 9:30 a.m., 8:30 a.m. to 9:00 a.m., 8:00 a.m. to 8:30 a.m., 7:30 a.m. to 8:00 a.m., and 7:00 a.m. to 7:30 a.m., a total of 8 past time segments, and the past simultaneous segment is from 11:00 a.m. to 11:30 a.m. of the previous day; Step S203: performing multiple training operations on the feedforward neural network to obtain the feedforward neural network after the multiple training operations are completed, and outputting the feedforward neural network after the multiple training operations as an intelligent prediction model; For example, performing multiple training operations on a feedforward neural network to obtain a feedforward neural network after the multiple training operations, and outputting the feedforward neural network after the multiple training operations as an intelligent prediction model includes: using a numerical simulation mode to implement a processing process of performing multiple training operations on the feedforward neural network to obtain a feedforward neural network after the multiple training operations, and outputting the feedforward neural network after the multiple training operations as an intelligent prediction model; Step S204: using an intelligent prediction model to intelligently predict the total sales volume of each retail commodity on sale at the set distribution site in the current time segment according to the duration of each time segment, multiple configuration information of the set distribution site, the sales data of each retail commodity corresponding to each past time segment before the current time segment of the set distribution site, and the sales data of a single retail commodity corresponding to the set distribution site in the same past segment; Step S205: when there is a type of retail commodity on sale whose total sales volume is less than the total inventory volume among the total sales volumes corresponding to the various retail commodities on sale intelligently predicted, the type of retail commodity on sale is used as an inventory warning type; Step S206: when there is a category of retail goods on sale whose total sales volume is less than the total inventory volume among the total sales volume corresponding to each of the retail goods on sale intelligently predicted, the category of retail goods on sale is used as a dynamic replenishment category, and the dynamic replenishment category is replenished based on the difference between the total sales volume and the total inventory volume corresponding to the dynamic replenishment category; The step of performing a plurality of training operations on the feedforward neural network to obtain the feedforward neural network after the plurality of training operations are completed, and outputting the feedforward neural network after the plurality of training operations as the intelligent prediction model comprises: the number of training operations completed by the feedforward neural network is monotonically positively correlated with the number of types of retail products on sale at the set distribution site; For example, the number of training operations completed by the feedforward neural network is monotonically positively correlated with the number of retail item types on sale at the distribution site, including: setting the number of retail item types on sale at the distribution site to 200, the number of training operations completed by the feedforward neural network is 100 times; setting the number of retail item types on sale at the distribution site to 300, the number of training operations completed by the feedforward neural network is 150 times; setting the number of retail item types on sale at the distribution site to 400, the number of training operations completed by the feedforward neural network is 200 times, and so on; Among them, obtaining the retail commodity sales data corresponding to each past time segment before the current time segment of the set distribution station and obtaining the retail commodity sales data corresponding to the past simultaneous time segment of the set distribution station at the same time segment position as the current time segment on the previous day includes: the number of time segments of each past time segment before the current time segment is proportional to the number of blocks of each block managed by the set distribution station; For example, the number of time segments of each past time segment before the current time segment is proportional to the number of blocks of each block managed by the distribution station, including: setting the number of blocks of each block managed by the distribution station to 3, the number of time segments of each past time segment before the current time segment is 6, setting the number of blocks of each block managed by the distribution station to 4, the number of time segments of each past time segment before the current time segment is 8, setting the number of blocks of each block managed by the distribution station to 5, the number of time segments of each past time segment before the current time segment is 10, and so on; Among them, obtaining the retail commodity sales data corresponding to each past time segment before the current time segment of the set distribution site and obtaining the retail commodity sales data corresponding to the past simultaneous segment at the same time segment position as the current time segment on the previous day also includes: the position occupied by the past simultaneous segment on the time axis of the previous day is the same as the position occupied by the current time segment on the time axis of the current day, and the current time segment is a time segment starting from the current time; Among them, obtaining the sales data of each retail commodity corresponding to each past time segment before the current time segment of the set distribution site and obtaining the sales data of a single retail commodity corresponding to the past simultaneous time segment of the set distribution site at the same time segment position as the current time segment on the previous day also includes: the duration of each time segment is equal, and the sales data of a single retail commodity corresponding to each time segment of the set distribution site is the total sales volume of each retail commodity on sale at the set distribution site in the said time segment; And wherein, performing multiple training operations on the feedforward neural network to obtain the feedforward neural network after completing the multiple training operations, and outputting the feedforward neural network after completing the multiple training operations as an intelligent prediction model also includes: in each training operation performed on the feedforward neural network, using the total sales volume corresponding to each retail commodity on sale at a known set distribution site in a past time segment as the output content of the feedforward neural network, using the duration of each time segment, multiple configuration information of the set distribution site, the sales data of each retail commodity corresponding to each past time segment before the set distribution site, and the sales data of a single retail commodity corresponding to the past simultaneous segment of the set distribution site in the past time segment as the input content of the feedforward neural network to perform this training operation.

[0023] Example 2 Figure 3 The figure is a flowchart of the steps of the method for integrating intelligent inventory warning and dynamic replenishment strategy according to Embodiment 2 of the present invention.

[0024] like Figure 3As shown, when there is a type of selling commodity whose total sales volume is less than the total inventory volume in the total sales volume corresponding to each of the various retail commodities on sale in the intelligent forecast, after the type of selling commodity is used as the inventory warning type, that is, after step S205, the integration method of the intelligent inventory warning and dynamic replenishment strategy further includes: Step S301: receiving each inventory warning type, and using a giant screen display mechanism to complete the on-site display of each inventory warning type; Specifically, it is also possible to choose to use an optical alarm mechanism or an acoustic alarm mechanism to perform on-site warning operations for each inventory warning type.

[0025] Example 3 Figure 4 The figure is a flowchart of the steps of the method for integrating intelligent inventory warning and dynamic replenishment strategy according to Embodiment 3 of the present invention.

[0026] like Figure 4 As shown, after performing multiple training operations on the feedforward neural network to obtain the feedforward neural network after the multiple training operations, and outputting the feedforward neural network after the multiple training operations as the intelligent prediction model, that is, after step S203, the integration method of the intelligent inventory warning and dynamic replenishment strategy also includes: Step S401: using a data storage chip to receive various model parameters of the intelligent prediction model, and completing model storage of the intelligent prediction model by storing various model parameters of the intelligent prediction model; For example, using a data storage chip to receive various model parameters of the intelligent prediction model, and completing the model storage of the intelligent prediction model by storing the various model parameters of the intelligent prediction model includes: the data storage chip can be selected as a CF storage chip, a TF storage chip or an MMC storage chip.

[0027] In any of the above embodiments 1-3, optionally, in the method for integrating the intelligent inventory warning and the dynamic replenishment strategy: When there is a type of on-sale commodity whose total sales volume is less than the total inventory volume among the total sales volumes corresponding to the various retail commodities on sale in the intelligent prediction, the type of on-sale commodity is used as a dynamic replenishment type, and the dynamic replenishment type is replenished based on the difference between the total sales volume and the total inventory volume corresponding to the dynamic replenishment type, including: the number of commodities replenished for the dynamic replenishment type is equal to the difference between the total sales volume and the total inventory volume corresponding to the dynamic replenishment type; For example, the number of commodities replenished for the dynamic replenishment category is equal to the difference between the total sales volume and the total inventory volume corresponding to the dynamic replenishment category, including: when it is determined that the garbage bag in the current time segment is the dynamic replenishment category, the total sales volume of the garbage bag in the current time segment is predicted to be 50 pieces, and the inventory volume of the garbage bag at the current moment is 35 pieces, then the number of commodities replenished for the garbage bag is equal to the difference between the total sales volume and the total inventory volume corresponding to the garbage bag, that is, the number of commodities replenished for the garbage bag in the current time segment is 15 pieces; In each training operation performed on the feedforward neural network, the total sales amount of each retail commodity sold at the known set distribution site in a certain past time segment is used as the output content of the feedforward neural network, and the duration of each time segment, multiple configuration information of the set distribution site, the sales data of each retail commodity corresponding to each past time segment before the set distribution site, and the single retail commodity sales data corresponding to the past simultaneous segment of the set distribution site in the past time segment are used as the input content of the feedforward neural network. The execution of this training operation includes: the position occupied by the past simultaneous segment of the past time segment on the time axis of the day before the past day of the past time segment is the same as the position occupied by the past time segment on the time axis of the past day of the past time segment; Among them, the intelligent prediction model is used to intelligently predict the total sales volume of various retail commodities on sale at the set distribution station in the current time segment according to the duration of each time segment, multiple configuration information of the distribution station, sales data of each retail commodity corresponding to each past time segment before the current time segment of the distribution station, and the sales data of a single retail commodity corresponding to the set distribution station in the past simultaneous segments. The method includes: performing numerical normalization processing on the duration of each time segment, multiple configuration information of the distribution station, sales data of each retail commodity corresponding to each past time segment before the current time segment of the distribution station, and the sales data of a single retail commodity corresponding to the set distribution station in the past simultaneous segments, and then synchronously inputting them into the intelligent prediction model; Among them, the intelligent prediction model is used to intelligently predict the total sales volume of various retail commodities on sale at the set distribution station in the current time segment according to the duration of each time segment, multiple configuration information of the set distribution station, the sales data of each retail commodity corresponding to each past time segment before the current time segment of the set distribution station, and the sales data of a single retail commodity corresponding to the set distribution station in the past simultaneous segments, and the intelligent prediction also includes: the total sales volume of various retail commodities on sale at the set distribution station in the current time segment obtained by intelligent prediction is a normalized representation of the numerical value; The number of training operations completed by the feedforward neural network and the number of retail product types on sale at the set distribution site are monotonically positively correlated, including: using a numerical mapping function to represent a numerical mapping relationship of the number of training operations completed by the feedforward neural network and the number of retail product types on sale at the set distribution site; The method of using a numerical mapping function to represent the numerical mapping relationship of the monotonically positive correlation between the number of training operations completed by the feedforward neural network and the number of retail product types on sale at the distribution site includes: in the numerical mapping function, setting the retail product types on sale at the distribution site as the input content of the numerical mapping function; Specifically, the numerical mapping function is used to represent the numerical mapping relationship of the number of training operations completed by the feedforward neural network and the number of retail product categories on sale at the set distribution site, which is monotonically positively correlated, and further includes: the MATLAB toolbox can be selected to complete the test and simulation of the operation process of the numerical mapping function; And wherein, the numerical mapping relationship in which a numerical mapping function is used to represent the monotonically positive correlation between the number of training operations completed by the feedforward neural network and the number of retail product types on sale at the set distribution site also includes: in the numerical mapping function, the number of training operations completed by the feedforward neural network corresponding to the retail product types on sale at the set distribution site is the output content of the numerical mapping function.

[0028] Example 4 Figure 5 1 is an internal structure diagram of an integrated system of intelligent inventory warning and dynamic replenishment strategy according to Embodiment 4 of the present invention.

[0029] like Figure 5 As shown, the integrated system of intelligent inventory warning and dynamic replenishment strategy includes the following components: The first capture mechanism is used to obtain the number of retail product categories on sale, the maximum storage capacity, the number of blocks in each block managed, the cumulative value of each permanent population corresponding to each block managed, and the geographical area occupied by each block managed, and output it as multiple configuration information of the set distribution site; Specifically, the number of types of retail goods on sale, the maximum storage capacity, the number of blocks of each block managed, the cumulative values ​​of each permanent population corresponding to each block managed, and the geographical area jointly occupied by each block managed at the set distribution site are obtained, and output as multiple configuration information of the set distribution site includes: using multiple information parsing components to respectively obtain the number of types of retail goods on sale, the maximum storage capacity, the number of blocks of each block managed, the cumulative values ​​of each permanent population corresponding to each block managed, and the geographical area jointly occupied by each block managed; The second capture mechanism is used to obtain the retail commodity sales data corresponding to each past time segment before the current time segment of the set distribution site, and to obtain the retail commodity sales data corresponding to the past simultaneous time segment of the set distribution site at the same time segment position as the current time segment on the previous day; For example, obtaining the retail commodity sales data corresponding to each past time segment before the current time segment of the set distribution site and obtaining the retail commodity sales data corresponding to the past simultaneous segment at the same time segment position as the current time segment of the previous day of the set distribution site includes: the current time segment is from 11:00 a.m. to 11:30 a.m., then the past time segments before the current time segment are 10:30 a.m. to 11:00 a.m., 10:00 a.m. to 10:30 a.m., 9:30 a.m. to 10:00 a.m., 9:00 a.m. to 9:30 a.m., 8:30 a.m. to 9:00 a.m., 8:00 a.m. to 8:30 a.m., 7:30 a.m. to 8:00 a.m., and 7:00 a.m. to 7:30 a.m., a total of 8 past time segments, and the past simultaneous segment is from 11:00 a.m. to 11:30 a.m. of the previous day; An object forming mechanism is used to perform multiple training operations on the feedforward neural network to obtain the feedforward neural network after the multiple training operations are completed, and output the feedforward neural network after the multiple training operations as an intelligent prediction model; For example, performing multiple training operations on a feedforward neural network to obtain a feedforward neural network after the multiple training operations, and outputting the feedforward neural network after the multiple training operations as an intelligent prediction model includes: using a numerical simulation mode to implement a processing process of performing multiple training operations on the feedforward neural network to obtain a feedforward neural network after the multiple training operations, and outputting the feedforward neural network after the multiple training operations as an intelligent prediction model; A prediction execution mechanism, connected to the first capture mechanism, the second capture mechanism and the object formation mechanism respectively, for using an intelligent prediction model to intelligently predict the total sales volume of each retail commodity on sale at the set distribution site in the current time segment according to the duration of each time segment, multiple configuration information of the set distribution site, the sales data of each retail commodity corresponding to each past time segment before the current time segment of the set distribution site, and the acquisition of the sales data of a single retail commodity corresponding to the set distribution site in the same past segment; An inventory warning mechanism, connected to the forecast execution mechanism, is used to use the on-sale commodity category as an inventory warning category when there is a category of on-sale commodity whose total sales volume is less than the total inventory volume in each of the total sales volume corresponding to each of the various retail commodities on sale in the intelligent forecast; A dynamic replenishment mechanism, connected to the forecast execution mechanism, is used to, when there is a category of on-sale goods whose total sales volume is less than the total inventory volume among the total sales volume corresponding to each of the various retail goods on sale intelligently predicted, use the category of on-sale goods as a dynamic replenishment category, and replenish the dynamic replenishment category based on the difference between the total sales volume and the total inventory volume corresponding to the dynamic replenishment category; The step of performing a plurality of training operations on the feedforward neural network to obtain the feedforward neural network after the plurality of training operations are completed, and outputting the feedforward neural network after the plurality of training operations as the intelligent prediction model comprises: the number of training operations completed by the feedforward neural network is monotonically positively correlated with the number of types of retail products on sale at the set distribution site; For example, the number of training operations completed by the feedforward neural network is monotonically positively correlated with the number of retail item types on sale at the distribution site, including: setting the number of retail item types on sale at the distribution site to 200, the number of training operations completed by the feedforward neural network is 100 times; setting the number of retail item types on sale at the distribution site to 300, the number of training operations completed by the feedforward neural network is 150 times; setting the number of retail item types on sale at the distribution site to 400, the number of training operations completed by the feedforward neural network is 200 times, and so on; Among them, obtaining the retail commodity sales data corresponding to each past time segment before the current time segment of the set distribution station and obtaining the retail commodity sales data corresponding to the past simultaneous time segment of the set distribution station at the same time segment position as the current time segment on the previous day includes: the number of time segments of each past time segment before the current time segment is proportional to the number of blocks of each block managed by the set distribution station; For example, the number of time segments of each past time segment before the current time segment is proportional to the number of blocks of each block managed by the distribution station, including: setting the number of blocks of each block managed by the distribution station to 3, the number of time segments of each past time segment before the current time segment is 6, setting the number of blocks of each block managed by the distribution station to 4, the number of time segments of each past time segment before the current time segment is 8, setting the number of blocks of each block managed by the distribution station to 5, the number of time segments of each past time segment before the current time segment is 10, and so on; Among them, obtaining the retail commodity sales data corresponding to each past time segment before the current time segment of the set distribution site and obtaining the retail commodity sales data corresponding to the past simultaneous segment at the same time segment position as the current time segment on the previous day also includes: the position occupied by the past simultaneous segment on the time axis of the previous day is the same as the position occupied by the current time segment on the time axis of the current day, and the current time segment is a time segment starting from the current time; Among them, obtaining the sales data of each retail commodity corresponding to each past time segment before the current time segment of the set distribution site and obtaining the sales data of a single retail commodity corresponding to the past simultaneous time segment of the set distribution site at the same time segment position as the current time segment on the previous day also includes: the duration of each time segment is equal, and the sales data of a single retail commodity corresponding to each time segment of the set distribution site is the total sales volume of each retail commodity on sale at the set distribution site in the said time segment; And wherein, performing multiple training operations on the feedforward neural network to obtain the feedforward neural network after completing the multiple training operations, and outputting the feedforward neural network after completing the multiple training operations as an intelligent prediction model also includes: in each training operation performed on the feedforward neural network, using the total sales volume corresponding to each retail commodity on sale at a known set distribution site in a past time segment as the output content of the feedforward neural network, using the duration of each time segment, multiple configuration information of the set distribution site, the sales data of each retail commodity corresponding to each past time segment before the set distribution site, and the sales data of a single retail commodity corresponding to the past simultaneous segment of the set distribution site in the past time segment as the input content of the feedforward neural network to perform this training operation.

[0030] Example 5 Figure 6 This is an internal structure diagram of an integrated system of intelligent inventory warning and dynamic replenishment strategy according to Example 5 of the present invention.

[0031] like Figure 6 As shown, the integrated system of intelligent inventory warning and dynamic replenishment strategy also includes: A giant screen display mechanism, connected to the inventory warning mechanism, is used to receive each inventory warning type and complete the on-site display of each inventory warning type; Specifically, it is also possible to choose to use an optical alarm mechanism or an acoustic alarm mechanism to perform on-site warning operations for each inventory warning type.

[0032] Example 6 Figure 71 is an internal structure diagram of an integrated system of intelligent inventory warning and dynamic replenishment strategy according to Example 6 of the present invention.

[0033] like Figure 7 As shown, the integrated system of intelligent inventory warning and dynamic replenishment strategy also includes: A model storage mechanism, connected to the object building mechanism, used for various model parameters of the intelligent prediction model, and completing the model storage of the intelligent prediction model by storing various model parameters of the intelligent prediction model; For example, a model storage mechanism is connected to the object assembly mechanism, is used for various model parameters of the intelligent prediction model, and completes the model storage of the intelligent prediction model by storing the various model parameters of the intelligent prediction model, including: the model storage mechanism can be selected as a CF storage chip, a TF storage chip or an MMC storage chip.

[0034] And in any of the above embodiments 4-6, optionally, in the integrated system of the intelligent inventory warning and dynamic replenishment strategy: When there is a type of on-sale commodity whose total sales volume is less than the total inventory volume among the total sales volumes corresponding to the various retail commodities on sale in the intelligent prediction, the type of on-sale commodity is used as a dynamic replenishment type, and the dynamic replenishment type is replenished based on the difference between the total sales volume and the total inventory volume corresponding to the dynamic replenishment type, including: the number of commodities replenished for the dynamic replenishment type is equal to the difference between the total sales volume and the total inventory volume corresponding to the dynamic replenishment type; For example, the number of commodities replenished for the dynamic replenishment category is equal to the difference between the total sales volume and the total inventory volume corresponding to the dynamic replenishment category, including: when it is determined that the garbage bag in the current time segment is the dynamic replenishment category, the total sales volume of the garbage bag in the current time segment is predicted to be 50 pieces, and the inventory volume of the garbage bag at the current moment is 35 pieces, then the number of commodities replenished for the garbage bag is equal to the difference between the total sales volume and the total inventory volume corresponding to the garbage bag, that is, the number of commodities replenished for the garbage bag in the current time segment is 15 pieces; In each training operation performed on the feedforward neural network, the total sales amount of each retail commodity sold at the known set distribution site in a certain past time segment is used as the output content of the feedforward neural network, and the duration of each time segment, multiple configuration information of the set distribution site, the sales data of each retail commodity corresponding to each past time segment before the set distribution site, and the single retail commodity sales data corresponding to the past simultaneous segment of the set distribution site in the past time segment are used as the input content of the feedforward neural network. The execution of this training operation includes: the position occupied by the past simultaneous segment of the past time segment on the time axis of the day before the past day of the past time segment is the same as the position occupied by the past time segment on the time axis of the past day of the past time segment; Among them, the intelligent prediction model is used to intelligently predict the total sales volume of various retail commodities on sale at the set distribution station in the current time segment according to the duration of each time segment, multiple configuration information of the distribution station, sales data of each retail commodity corresponding to each past time segment before the current time segment of the distribution station, and the sales data of a single retail commodity corresponding to the set distribution station in the past simultaneous segments. The method includes: performing numerical normalization processing on the duration of each time segment, multiple configuration information of the distribution station, sales data of each retail commodity corresponding to each past time segment before the current time segment of the distribution station, and the sales data of a single retail commodity corresponding to the set distribution station in the past simultaneous segments, and then synchronously inputting them into the intelligent prediction model; Among them, the intelligent prediction model is used to intelligently predict the total sales volume of various retail commodities on sale at the set distribution station in the current time segment according to the duration of each time segment, multiple configuration information of the set distribution station, the sales data of each retail commodity corresponding to each past time segment before the current time segment of the set distribution station, and the sales data of a single retail commodity corresponding to the set distribution station in the past simultaneous segments, and the intelligent prediction also includes: the total sales volume of various retail commodities on sale at the set distribution station in the current time segment obtained by intelligent prediction is a normalized representation of the numerical value; The number of training operations completed by the feedforward neural network and the number of retail product types on sale at the set distribution site are monotonically positively correlated, including: using a numerical mapping function to represent a numerical mapping relationship of the number of training operations completed by the feedforward neural network and the number of retail product types on sale at the set distribution site; The method of using a numerical mapping function to represent the numerical mapping relationship of the monotonically positive correlation between the number of training operations completed by the feedforward neural network and the number of retail product types on sale at the distribution site includes: in the numerical mapping function, setting the retail product types on sale at the distribution site as the input content of the numerical mapping function; Specifically, the numerical mapping function is used to represent the numerical mapping relationship of the number of training operations completed by the feedforward neural network and the number of retail product categories on sale at the set distribution site, which is monotonically positively correlated, and further includes: the MATLAB toolbox can be selected to complete the test and simulation of the operation process of the numerical mapping function; And wherein, the numerical mapping relationship in which a numerical mapping function is used to represent the monotonically positive correlation between the number of training operations completed by the feedforward neural network and the number of retail product types on sale at the set distribution site also includes: in the numerical mapping function, the number of training operations completed by the feedforward neural network corresponding to the retail product types on sale at the set distribution site is the output content of the numerical mapping function.

[0035] In addition, in the integrated method and system of intelligent inventory warning and dynamic replenishment strategy according to the present invention: The duration of each time segment, multiple configuration information of the distribution site, the sales data of each retail commodity corresponding to each past time segment of the distribution site before the current time segment, and the single retail commodity sales data corresponding to the distribution site in the past simultaneous segments are respectively subjected to numerical normalization processing and then synchronously input into the intelligent prediction model, including: using a numerical processing component to complete the numerical normalization processing of the duration of each time segment, multiple configuration information of the distribution site, the sales data of each retail commodity corresponding to each past time segment of the distribution site before the current time segment, and the single retail commodity sales data corresponding to the distribution site in the past simultaneous segments; For example, the numerical processing component is used to complete the numerical normalization processing of the duration of each time segment, setting multiple configuration information of the distribution site, setting the retail commodity sales data corresponding to each past time segment of the distribution site before the current time segment, and obtaining the single retail commodity sales data corresponding to the set distribution site in the past simultaneous segment, including: the numerical processing component is a CPLD device designed by VHDL language; And wherein, the duration of each time segment, the multiple configuration information of the distribution site, the sales data of each retail commodity corresponding to each past time segment before the current time segment of the distribution site, and the single retail commodity sales data corresponding to the previous simultaneous segments of the distribution site are respectively subjected to numerical normalization processing and then synchronously input into the intelligent prediction model, further comprising: using a synchronous control component connected to the numerical processing component to complete the synchronous input of the duration of each time segment after the numerical normalization processing is respectively performed, the multiple configuration information of the distribution site is set, the sales data of each retail commodity corresponding to each past time segment before the current time segment of the distribution site, and the single retail commodity sales data corresponding to the previous simultaneous segments of the distribution site to the intelligent prediction model; And by way of example, a synchronous control component connected to a numerical processing component is used to complete the duration of each time segment after numerical normalization processing is performed respectively, set multiple configuration information of the distribution site, set the sales data of each retail commodity corresponding to each past time segment before the current time segment of the distribution site, and obtain the sales data of a single retail commodity corresponding to the set distribution site in the same past segment to the synchronous input of the intelligent prediction model, including: the numerical normalization processing is a hexadecimal numerical conversion processing.

[0036] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0037] In the description of this specification, the description with reference to the terms "one embodiment", "certain embodiments", "illustrative embodiments", "examples", "specific examples" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiments or examples are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0038] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in the field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. An integrated method of intelligent inventory warning and dynamic replenishment strategy, characterized in that: The method comprises: Obtain the number of retail product categories on sale, the maximum storage capacity, the number of blocks in each block managed, the cumulative value of each permanent population corresponding to each block managed, and the geographical area occupied by each block managed at the set distribution site, and output them as multiple configuration information of the set distribution site; Obtain the retail commodity sales data corresponding to each past time segment before the current time segment of the set distribution site, and obtain the retail commodity sales data corresponding to the past simultaneous time segment of the set distribution site at the same time segment position as the current time segment on the previous day; Performing multiple training operations on the feedforward neural network to obtain the feedforward neural network after the multiple training operations are completed, and outputting the feedforward neural network after the multiple training operations as an intelligent prediction model; An intelligent prediction model is used to intelligently predict the total sales volume of various retail commodities on sale at the set distribution station in the current time segment according to the duration of each time segment, multiple configuration information of the set distribution station, the sales data of each retail commodity corresponding to each past time segment before the current time segment of the set distribution station, and the sales data of a single retail commodity corresponding to the set distribution station in the same past segment; When there is a type of commodity on sale whose total sales volume is less than the total inventory volume in each of the total sales volume corresponding to each of the various retail commodities on sale predicted by the intelligent forecast, the commodity on sale is used as an inventory warning type; When there is a type of retail commodity on sale whose total sales volume is less than the total inventory volume among the total sales volume corresponding to each of the various retail commodities on sale intelligently predicted, the type of retail commodity on sale will be used as a dynamic replenishment type, and the dynamic replenishment type will be replenished based on the difference between the total sales volume and the total inventory volume corresponding to the dynamic replenishment type.

2. The method for integrating intelligent inventory warning and dynamic replenishment strategy according to claim 1, characterized in that: Performing multiple training operations on the feedforward neural network to obtain the feedforward neural network after the multiple training operations, and outputting the feedforward neural network after the multiple training operations as the intelligent prediction model includes: the number of training operations completed by the feedforward neural network is monotonically positively correlated with the number of retail product categories on sale at the set distribution site; Among them, obtaining the retail commodity sales data corresponding to each past time segment before the current time segment of the set distribution station and obtaining the retail commodity sales data corresponding to the past simultaneous time segment of the set distribution station at the same time segment position as the current time segment on the previous day includes: the number of time segments of each past time segment before the current time segment is proportional to the number of blocks of each block managed by the set distribution station; Among them, obtaining the retail commodity sales data corresponding to each past time segment before the current time segment of the set distribution site and obtaining the retail commodity sales data corresponding to the past simultaneous segment at the same time segment position as the current time segment on the previous day also includes: the position occupied by the past simultaneous segment on the time axis of the previous day is the same as the position occupied by the current time segment on the time axis of the current day, and the current time segment is a time segment starting from the current time; Among them, obtaining the sales data of each retail commodity corresponding to each past time segment before the current time segment of the set distribution site and obtaining the sales data of a single retail commodity corresponding to the past simultaneous time segment of the set distribution site at the same time segment position as the current time segment on the previous day also includes: the duration of each time segment is equal, and the sales data of a single retail commodity corresponding to each time segment of the set distribution site is the total sales volume of each retail commodity on sale at the set distribution site in the said time segment; Among them, performing multiple training operations on the feedforward neural network to obtain the feedforward neural network after completing the multiple training operations, and outputting the feedforward neural network after completing the multiple training operations as an intelligent prediction model also includes: in each training operation performed on the feedforward neural network, using the total sales volume corresponding to each retail commodity on sale at a known set distribution site in a past time segment as the output content of the feedforward neural network, using the duration of each time segment, multiple configuration information of the set distribution site, the sales data of each retail commodity corresponding to each past time segment before the set distribution site, and the sales data of a single retail commodity corresponding to the past simultaneous segment of the set distribution site in the past time segment as the input content of the feedforward neural network to perform this training operation.

3. The integrated method of intelligent inventory warning and dynamic replenishment strategy according to claim 2, characterized in that: When there is a type of on-sale commodity whose total sales volume is less than the total inventory volume in each of the total sales volume corresponding to each of the various retail commodities on sale in the intelligent prediction, after the type of on-sale commodity is used as an inventory warning type, the method further includes: Receive each inventory warning type and use a giant screen display mechanism to complete the on-site display of each inventory warning type.

4. The method for integrating intelligent inventory warning and dynamic replenishment strategy according to claim 2, characterized in that: After performing multiple training operations on the feedforward neural network to obtain the feedforward neural network after the multiple training operations are completed, and outputting the feedforward neural network after the multiple training operations as the intelligent prediction model, the method further includes: A data storage chip is used to receive various model parameters of the intelligent prediction model, and the model storage of the intelligent prediction model is completed by storing various model parameters of the intelligent prediction model.

5. The method for integrating intelligent inventory warning and dynamic replenishment strategy according to any one of claims 2 to 4, characterized in that: When there is a type of on-sale commodity whose total sales volume is less than the total inventory volume among the total sales volumes corresponding to the various retail commodities on sale in the intelligent prediction, the type of on-sale commodity is used as a dynamic replenishment type, and the dynamic replenishment type is replenished based on the difference between the total sales volume and the total inventory volume corresponding to the dynamic replenishment type, including: the number of commodities replenished for the dynamic replenishment type is equal to the difference between the total sales volume and the total inventory volume corresponding to the dynamic replenishment type; In each training operation performed on the feedforward neural network, the total sales amount of each retail commodity sold at the known set distribution site in a certain past time segment is used as the output content of the feedforward neural network, and the duration of each time segment, multiple configuration information of the set distribution site, the sales data of each retail commodity corresponding to each past time segment before the set distribution site, and the single retail commodity sales data corresponding to the past simultaneous segment of the set distribution site in the past time segment are used as the input content of the feedforward neural network. The execution of this training operation includes: the position occupied by the past simultaneous segment of the past time segment on the time axis of the day before the past day of the past time segment is the same as the position occupied by the past time segment on the time axis of the past day of the past time segment; Among them, the intelligent prediction model is used to intelligently predict the total sales volume of various retail commodities on sale at the set distribution station in the current time segment according to the duration of each time segment, multiple configuration information of the distribution station, sales data of each retail commodity corresponding to each past time segment before the current time segment of the distribution station, and the sales data of a single retail commodity corresponding to the set distribution station in the past simultaneous segments. The method includes: performing numerical normalization processing on the duration of each time segment, multiple configuration information of the distribution station, sales data of each retail commodity corresponding to each past time segment before the current time segment of the distribution station, and the sales data of a single retail commodity corresponding to the set distribution station in the past simultaneous segments, and then synchronously inputting them into the intelligent prediction model; Among them, the intelligent prediction model is used to intelligently predict the total sales volume of various retail commodities on sale at the set distribution station in the current time segment according to the duration of each time segment, multiple configuration information of the set distribution station, the sales data of each retail commodity corresponding to each past time segment before the current time segment of the set distribution station, and the sales data of a single retail commodity corresponding to the set distribution station in the past simultaneous segments, and the intelligent prediction also includes: the total sales volume of various retail commodities on sale at the set distribution station in the current time segment obtained by intelligent prediction is a normalized representation of the numerical value; The number of training operations completed by the feedforward neural network and the number of retail product types on sale at the set distribution site are monotonically positively correlated, including: using a numerical mapping function to represent a numerical mapping relationship of the number of training operations completed by the feedforward neural network and the number of retail product types on sale at the set distribution site; The method of using a numerical mapping function to represent the numerical mapping relationship of the monotonically positive correlation between the number of training operations completed by the feedforward neural network and the number of retail product types on sale at the distribution site includes: in the numerical mapping function, setting the retail product types on sale at the distribution site as the input content of the numerical mapping function; Among them, the use of a numerical mapping function to represent the numerical mapping relationship in which the number of training operations completed by the feedforward neural network and the number of retail product types on sale at the set distribution site are monotonically positively correlated also includes: in the numerical mapping function, the number of training operations completed by the feedforward neural network corresponding to the retail product types on sale at the set distribution site is the output content of the numerical mapping function.

6. An integrated system of intelligent inventory warning and dynamic replenishment strategy, characterized in that: The system comprises: The first capture mechanism is used to obtain the number of retail product categories on sale, the maximum storage capacity, the number of blocks in each block managed, the cumulative value of each permanent population corresponding to each block managed, and the geographical area occupied by each block managed, and output it as multiple configuration information of the set distribution site; The second capture mechanism is used to obtain the retail commodity sales data corresponding to each past time segment before the current time segment of the set distribution site, and to obtain the retail commodity sales data corresponding to the past simultaneous time segment of the set distribution site at the same time segment position as the current time segment on the previous day; An object forming mechanism is used to perform multiple training operations on the feedforward neural network to obtain the feedforward neural network after the multiple training operations are completed, and output the feedforward neural network after the multiple training operations as an intelligent prediction model; A prediction execution mechanism, connected to the first capture mechanism, the second capture mechanism and the object formation mechanism respectively, for using an intelligent prediction model to intelligently predict the total sales volume of each retail commodity on sale at the set distribution site in the current time segment according to the duration of each time segment, multiple configuration information of the set distribution site, the sales data of each retail commodity corresponding to each past time segment before the current time segment of the set distribution site, and the acquisition of the sales data of a single retail commodity corresponding to the set distribution site in the same past segment; An inventory warning mechanism, connected to the forecast execution mechanism, is used to use the on-sale commodity category as an inventory warning category when there is a category of on-sale commodity whose total sales volume is less than the total inventory volume in each of the total sales volume corresponding to each of the various retail commodities on sale in the intelligent forecast; The dynamic replenishment mechanism is connected to the forecast execution mechanism and is used to use the sales commodity category as a dynamic replenishment category when there is a sales commodity category whose total sales volume is less than the total inventory volume among the total sales volume corresponding to each of the various retail commodities on sale in the intelligent forecast, and replenish the dynamic replenishment category based on the difference between the total sales volume and the total inventory volume corresponding to the dynamic replenishment category.

7. The method for integrating intelligent inventory warning and dynamic replenishment strategy according to claim 6, characterized in that: Performing multiple training operations on the feedforward neural network to obtain the feedforward neural network after the multiple training operations, and outputting the feedforward neural network after the multiple training operations as the intelligent prediction model includes: the number of training operations completed by the feedforward neural network is monotonically positively correlated with the number of retail product categories on sale at the set distribution site; Among them, obtaining the retail commodity sales data corresponding to each past time segment before the current time segment of the set distribution station and obtaining the retail commodity sales data corresponding to the past simultaneous time segment of the set distribution station at the same time segment position as the current time segment on the previous day includes: the number of time segments of each past time segment before the current time segment is proportional to the number of blocks of each block managed by the set distribution station; Among them, obtaining the retail commodity sales data corresponding to each past time segment before the current time segment of the set distribution site and obtaining the retail commodity sales data corresponding to the past simultaneous segment at the same time segment position as the current time segment on the previous day also includes: the position occupied by the past simultaneous segment on the time axis of the previous day is the same as the position occupied by the current time segment on the time axis of the current day, and the current time segment is a time segment starting from the current time; Among them, obtaining the sales data of each retail commodity corresponding to each past time segment before the current time segment of the set distribution site and obtaining the sales data of a single retail commodity corresponding to the past simultaneous time segment of the set distribution site at the same time segment position as the current time segment on the previous day also includes: the duration of each time segment is equal, and the sales data of a single retail commodity corresponding to each time segment of the set distribution site is the total sales volume of each retail commodity on sale at the set distribution site in the said time segment; Among them, performing multiple training operations on the feedforward neural network to obtain the feedforward neural network after completing the multiple training operations, and outputting the feedforward neural network after completing the multiple training operations as an intelligent prediction model also includes: in each training operation performed on the feedforward neural network, using the total sales volume corresponding to each retail commodity on sale at a known set distribution site in a past time segment as the output content of the feedforward neural network, using the duration of each time segment, multiple configuration information of the set distribution site, the sales data of each retail commodity corresponding to each past time segment before the set distribution site, and the sales data of a single retail commodity corresponding to the past simultaneous segment of the set distribution site in the past time segment as the input content of the feedforward neural network to perform this training operation.

8. The integrated system of intelligent inventory warning and dynamic replenishment strategy according to claim 7, characterized in that: The system further comprises: The giant screen display mechanism is connected to the inventory warning mechanism, and is used to receive each inventory warning type and complete the on-site display of each inventory warning type.

9. The integrated system of intelligent inventory warning and dynamic replenishment strategy according to claim 7, characterized in that: The system further comprises: The model storage mechanism is connected to the object assembly mechanism and is used for various model parameters of the intelligent prediction model. The model storage of the intelligent prediction model is completed by storing various model parameters of the intelligent prediction model.

10. The integrated system of intelligent inventory warning and dynamic replenishment strategy according to any one of claims 7 to 9, characterized in that: When there is a type of on-sale commodity whose total sales volume is less than the total inventory volume among the total sales volumes corresponding to the various retail commodities on sale in the intelligent prediction, the type of on-sale commodity is used as a dynamic replenishment type, and the dynamic replenishment type is replenished based on the difference between the total sales volume and the total inventory volume corresponding to the dynamic replenishment type, including: the number of commodities replenished for the dynamic replenishment type is equal to the difference between the total sales volume and the total inventory volume corresponding to the dynamic replenishment type; In each training operation performed on the feedforward neural network, the total sales amount of each retail commodity sold at the known set distribution site in a certain past time segment is used as the output content of the feedforward neural network, and the duration of each time segment, multiple configuration information of the set distribution site, the sales data of each retail commodity corresponding to each past time segment before the set distribution site, and the single retail commodity sales data corresponding to the past simultaneous segment of the set distribution site in the past time segment are used as the input content of the feedforward neural network. The execution of this training operation includes: the position occupied by the past simultaneous segment of the past time segment on the time axis of the day before the past day of the past time segment is the same as the position occupied by the past time segment on the time axis of the past day of the past time segment; Among them, the intelligent prediction model is used to intelligently predict the total sales volume of various retail commodities on sale at the set distribution station in the current time segment according to the duration of each time segment, multiple configuration information of the distribution station, sales data of each retail commodity corresponding to each past time segment before the current time segment of the distribution station, and the sales data of a single retail commodity corresponding to the set distribution station in the past simultaneous segments. The method includes: performing numerical normalization processing on the duration of each time segment, multiple configuration information of the distribution station, sales data of each retail commodity corresponding to each past time segment before the current time segment of the distribution station, and the sales data of a single retail commodity corresponding to the set distribution station in the past simultaneous segments, and then synchronously inputting them into the intelligent prediction model; Among them, the intelligent prediction model is used to intelligently predict the total sales volume of various retail commodities on sale at the set distribution station in the current time segment according to the duration of each time segment, multiple configuration information of the set distribution station, the sales data of each retail commodity corresponding to each past time segment before the current time segment of the set distribution station, and the sales data of a single retail commodity corresponding to the set distribution station in the past simultaneous segments, and the intelligent prediction also includes: the total sales volume of various retail commodities on sale at the set distribution station in the current time segment obtained by intelligent prediction is a normalized representation of the numerical value; The number of training operations completed by the feedforward neural network and the number of retail product types on sale at the set distribution site are monotonically positively correlated, including: using a numerical mapping function to represent a numerical mapping relationship of the number of training operations completed by the feedforward neural network and the number of retail product types on sale at the set distribution site; The method of using a numerical mapping function to represent the numerical mapping relationship of the monotonically positive correlation between the number of training operations completed by the feedforward neural network and the number of retail product types on sale at the distribution site includes: in the numerical mapping function, setting the retail product types on sale at the distribution site as the input content of the numerical mapping function; Among them, the use of a numerical mapping function to represent the numerical mapping relationship in which the number of training operations completed by the feedforward neural network and the number of retail product types on sale at the set distribution site are monotonically positively correlated also includes: in the numerical mapping function, the number of training operations completed by the feedforward neural network corresponding to the retail product types on sale at the set distribution site is the output content of the numerical mapping function.

Images