CN112396365B - Stock item prediction method, device, computer equipment and storage medium - Google Patents
Stock item prediction method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN112396365B CN112396365B CN201910748524.1A CN201910748524A CN112396365B CN 112396365 B CN112396365 B CN 112396365B CN 201910748524 A CN201910748524 A CN 201910748524A CN 112396365 B CN112396365 B CN 112396365B
- Authority
- CN
- China
- Prior art keywords
- order
- sales
- constraint condition
- stock
- orders
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000012545 processing Methods 0.000 claims abstract description 124
- 239000011159 matrix material Substances 0.000 claims description 107
- 230000006870 function Effects 0.000 claims description 81
- 238000006243 chemical reaction Methods 0.000 claims description 24
- 238000010276 construction Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 5
- 238000007726 management method Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 239000003086 colorant Substances 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
- G06Q10/0875—Itemisation or classification of parts, supplies or services, e.g. bill of materials
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0605—Supply or demand aggregation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
- G06Q30/0635—Processing of requisition or of purchase orders
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a stock single product prediction method, a device, computer equipment and a storage medium, and relates to the technical field of data processing. The stock item prediction method comprises the following steps: acquiring historical order data of a merchant from a target warehouse in a first time period; carrying out statistical processing on the historical order data to obtain a statistical processing result of the historical shipment data of the target warehouse; and predicting the stock list of the goods which are delivered from the target warehouse by the merchant in a second time period in the future according to the statistical processing result, and outputting the stock list. According to the embodiment of the invention, the stock orders in the target warehouse are predicted in the future by the statistical processing result of the historical order data of the target warehouse, so that the stock orders meeting the warehouse requirements are determined, the efficiency, the accuracy and the flexibility of determining the stock orders can be improved, and the management cost is reduced.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a method and apparatus for predicting a stock form, a computer device, and a storage medium.
Background
In the internet era, many users have been on-line through the internet when picking goods. In general, the types of commodities sold by merchants are often hundreds or thousands, and sales of each commodity is not only high or low, but also can be obviously different in different regions. In each warehouse, if all the single products sold by the merchant (one single product corresponds to one SKU (Stock Keeping Unit), and SKUs are the smallest available unit for keeping inventory control, such as a mobile phone, and different colors, colors and configurations correspond to different SKUs) are kept in inventory, problems of rising of transportation cost, stock backlog and the like are caused, and difficulty is increased in management. The existing method for determining the stock items for each warehouse is to select the stock items according to experience or sequentially select the stock items from high to low according to the sales volume ratio, the method for determining the stock items for the warehouse is often not optimal, the adjustment is not flexible enough, the efficiency, the accuracy and the flexibility for determining the stock items for the warehouse are reduced, and the management cost is increased.
Disclosure of Invention
The embodiment of the invention provides a method, a device, computer equipment and a storage medium for predicting inventory items, which can improve the efficiency, accuracy and flexibility of determining inventory items, reduce management cost and solve the problems of low efficiency, low accuracy, poor flexibility and high cost in the prior art when inventory items are determined for a warehouse.
The embodiment of the invention provides a stock item prediction method, which comprises the following steps:
Acquiring historical order data of a merchant from a target warehouse in a first time period;
carrying out statistical processing on the historical order data to obtain a statistical processing result of the historical shipment data of the target warehouse;
And predicting the stock list of the goods which are delivered from the target warehouse by the merchant in a second time period in the future according to the statistical processing result, and outputting the stock list.
Further, the statistical processing of the historical order data to obtain a statistical processing result of the historical shipment data of the target warehouse includes:
counting the total number of orders in the historical order data and the total sales of all the single products in the historical order data;
Counting sales of various single products in each order in the historical order data;
Determining the existence state of each item in each order in the historical order data;
Processing sales of the single items in each order and the existence state of the single items in each order to obtain an order single item processing result;
the statistical processing results comprise the total number of orders, the total sales of all the single products and the processing results of the orders.
Further, the processing the sales amount of each individual item in each order and the existence state of each individual item in each order to obtain an order individual item processing result includes:
Performing matrix conversion on sales of each individual item in each order to obtain a sales matrix;
performing binary conversion on the existence state of each order in each order to obtain a binary matrix;
the order form processing result comprises the sales volume matrix and the binary matrix.
Further, according to the statistical processing result, predicting the inventory items of the merchant, which are delivered from the target warehouse in a second time period in the future, and outputting an inventory item list, including:
Acquiring a preset order meeting rate and sales meeting rate;
And predicting the stock list of the goods which are delivered from the target warehouse by the merchant in a second time period in the future according to the statistical processing result, the preset order meeting rate and the preset sales meeting rate, and outputting the stock list.
Further, before the step of predicting the inventory items of the merchant, which are delivered from the target warehouse in the second time period in the future, according to the statistical processing result, and outputting the inventory item list, the inventory item prediction method further includes:
Constructing a stock single product prediction model;
Predicting the stock list of the goods delivered from the target warehouse by the merchant in a second time period in the future according to the statistical processing result, and outputting the stock list of the goods, wherein the method comprises the following steps: and inputting the statistical processing result into the stock item prediction model, predicting the stock items which are delivered from the target warehouse by the merchant in a second time period in the future, and outputting a stock item list.
Further, the constructing the stock item prediction model includes:
Setting order meeting rate, sales meeting rate and binarization variable;
Setting the predicted stock order minimization as an objective function;
constructing constraint conditions of the objective function according to the relation among the order satisfaction rate, sales satisfaction rate and binarization variables;
and constructing the stock single product prediction model according to the constraint condition of the objective function.
Further, the stock item prediction model includes sales matrix parameters, binary matrix parameters, order total number parameters, and total sales parameters of all items, and the constructing constraint conditions of the objective function according to the relation among the order satisfaction rate, sales satisfaction rate, and binarization variables includes:
Setting the relation between the sales matrix parameters and the binarization variables as a first constraint condition of the objective function;
setting the relation between the binary matrix parameters and the binarization variables as a second constraint condition of the objective function;
setting the relation among the sales matrix parameters, the sales satisfaction rate and the total sales parameters of all the single products as a third constraint condition of the objective function;
and setting the relation among the binary matrix parameters, the order satisfaction rate and the order total number parameters as a fourth constraint condition of the objective function.
The embodiment of the invention also provides a stock item prediction device, which comprises:
an order acquisition unit for acquiring historical order data of a merchant from a target warehouse in a first time period;
The statistical processing unit is used for carrying out statistical processing on the historical order data to obtain a statistical processing result of the historical shipment data of the target warehouse;
and the prediction unit is used for predicting the inventory items which are delivered from the target warehouse by the merchant in a second time period in the future according to the statistical processing result and outputting an inventory item list.
Further, the statistical processing unit includes:
The order sales volume statistics unit is used for counting the total number of orders in the historical order data and the total sales volume of all the orders in the historical order data;
the sales statistics unit is used for counting sales of various single products in each order in the historical order data;
The single item state determining unit is used for determining the existence state of each single item in each order in the historical order data;
the order item processing unit is used for processing sales of each item in each order and the existence state of each item in each order to obtain an order item processing result;
the statistical processing results comprise the total number of orders, the total sales of all the single products and the processing results of the orders.
Further, the order item processing unit includes:
the sales matrix determining unit is used for performing matrix conversion on sales of each single product in each order to obtain a sales matrix;
The binary matrix determining unit is used for carrying out binary conversion on the existence state of each single product in each order to obtain a binary matrix;
the order form processing result comprises the sales volume matrix and the binary matrix.
Further, the prediction unit includes:
the first satisfaction rate acquisition unit is used for acquiring preset order satisfaction rate and sales satisfaction rate;
And the first order predicting unit is used for predicting the stock order which is delivered from the target warehouse by the merchant in a second time period in the future according to the statistical processing result and the preset order satisfaction rate and sales satisfaction rate, and outputting a stock order list.
Further, the stock item predicting device further includes:
the construction unit is used for constructing a stock single product prediction model;
The prediction unit is further configured to: and inputting the statistical processing result into the stock item prediction model, predicting the stock items which are delivered from the target warehouse by the merchant in a second time period in the future, and outputting a stock item list.
Further, the construction unit includes:
The parameter variable setting unit is used for setting an order meeting rate, a sales meeting rate and a binarization variable;
An objective function setting unit for setting the predicted quantity of stock orders to be minimized as an objective function;
The constraint condition setting unit is used for constructing constraint conditions of the objective function according to the relation among the order meeting rate, the sales meeting rate and the binarization variable;
And the model construction unit is used for constructing the stock single product prediction model according to the constraint condition of the objective function.
Further, the constraint condition setting unit includes:
A first condition setting unit, configured to set a relationship between the sales matrix parameter and the binarized variable as a first constraint condition of the objective function;
A second condition setting unit, configured to set a relationship between the binary matrix parameter and the binarized variable as a second constraint condition of the objective function;
a third condition setting unit, configured to set a relationship among the sales matrix parameter, the sales satisfaction rate, and the total sales parameter of all the individual products, as a third constraint condition of the objective function;
And a fourth condition setting unit, configured to set a relationship among the binary matrix parameter, the order satisfaction rate, and the order total parameter as a fourth constraint condition of the objective function.
The embodiment of the invention also provides a computer device, which comprises: one or more processors; a memory; and one or more applications, wherein the processor is coupled to the memory, the one or more applications being stored in the memory and configured to perform the stock form prediction method of any one of the above by the processor.
The embodiment of the invention also provides a computer readable storage medium, on which a computer program is stored, the computer program being loaded by a processor to execute the stock item prediction method of any one of the above.
According to the embodiment of the invention, the historical order data of the target warehouse shipment is obtained, the historical order data is subjected to statistical processing to obtain a statistical processing result, the stock orders shipped in the target warehouse in the future are predicted according to the statistical processing result, and a stock order list is output. The stock orders meeting the warehouse requirements are determined by predicting the stock orders in the target warehouse in the future according to the statistical processing result of the historical order data of the target warehouse shipment, so that the efficiency, accuracy and flexibility of determining the stock orders can be improved, and the management cost is reduced.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a stock form prediction method provided by an embodiment of the present invention;
FIG. 2 is a schematic sub-flowchart of a stock form prediction method according to an embodiment of the present invention;
FIG. 3 is a flow chart of a stock form prediction method according to another embodiment of the present invention;
FIG. 4 is a schematic sub-flowchart of a stock form prediction method according to another embodiment of the present invention;
FIG. 5 is a schematic block diagram of an inventory item prediction device provided by an embodiment of the present invention;
FIG. 6 is a schematic block diagram of an inventory item prediction device provided by another embodiment of the invention;
fig. 7 is a schematic block diagram of a computer device provided by an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to fall within the scope of the invention.
In the description of the present invention, it should be understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more of the described features. In the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise. In addition, the terms "first" and "second" are used to distinguish a plurality of elements from one another. For example, a first constraint may be referred to as a second constraint, and similarly, a second constraint may be referred to as a first constraint, without departing from the scope of the present invention. The first constraint and the second constraint are both constraints, but they are not the same constraint.
In the present invention, the term "exemplary" is used to mean "serving as an example, instance, or illustration. Any embodiment described as "exemplary" in this disclosure is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is presented to enable any person skilled in the art to make and use the invention. In the following description, details are set forth for purposes of explanation. It will be apparent to one of ordinary skill in the art that the present invention may be practiced without these specific details. In other instances, well-known structures and processes have not been described in detail so as not to obscure the description of the invention with unnecessary detail. Thus, the present invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.
The embodiment of the invention provides a stock item prediction method, a device, computer equipment and a storage medium. The stock single product prediction method is operated in equipment, and the equipment can be a server or a terminal, such as a mobile phone, a Pad, a desktop computer and the like. The following will describe in detail.
Fig. 1 is a schematic flow chart of a method for predicting an inventory item according to an embodiment of the present invention, where the specific flow chart of the method for predicting an inventory item is as follows:
at 101, historical order data for a merchant to be shipped from a target warehouse during a first time period is obtained.
The historical order data of the merchant, which is delivered from the target warehouse in the first time period, can be stored locally, can be stored in a database, can be stored in other equipment, and the like, and the historical order data of the merchant, which is delivered from the target warehouse in the first time period, can be directly obtained from the local, can be obtained from the database, can be obtained from other equipment by sending an obtaining request.
The merchant can be an off-line merchant or an on-line merchant. For example, when a customer buys a bill, the online merchant can input and store order data to form order data; after the online merchant, such as an e-commerce merchant, places an order, order data is stored in a database of an e-commerce platform. The merchant may be one merchant or a plurality of merchants. For example, if one merchant corresponds to a plurality of electronic stores, and the plurality of electronic stores share a warehouse, then the historical order data of the merchant for delivering from the target warehouse is obtained, which may be the historical order data of one electronic store for delivering from the warehouse, or the historical order data of all electronic stores for delivering from the warehouse. For example, a plurality of merchants correspond to a plurality of electronic stores, and products sold by the plurality of electronic stores are different, and the plurality of electronic stores share one warehouse, then the historical order data of the merchant for delivering from the target warehouse is acquired, which may be the historical order data of the electronic stores of one merchant for delivering from the public warehouse, or the historical order data of the electronic stores of the plurality of merchants for delivering from the public warehouse. For another example, one merchant corresponds to a plurality of warehouses, and one warehouse among the plurality of warehouses is taken as a target warehouse. For example, where the plurality of warehouses are located in different locations, such as one in city A and one in city B, historical order data for a merchant from a target warehouse is obtained, including obtaining historical order data for the merchant from a city A warehouse or obtaining historical order data for the merchant from a city B warehouse.
The first time period may be half a year, one quarter, multiple quarters, etc. For example, if an inventory item is to be predicted for a target warehouse in the second quarter, historical order data of the target warehouse in the second quarter of the last year, historical order data of the target warehouse in the first quarter of the year, or historical order data of the target warehouse in a plurality of previous quarters may be obtained.
The historical order data of the orders sent from the target warehouse in the first time period comprises all orders sent from the target warehouse in the first time period, and each order comprises the single product and the corresponding quantity of each single product. Wherein, a single item corresponds to a SKU (Stock Keeping Unit, stock unit), which is the smallest available unit for keeping inventory control, such as a mobile phone, and different types, colors, and configurations are different SKUs.
Table 1 is an example of historical order data, where order numbers include order1, order2, and order numbers include s1, s2, s3. In an order with order number order1, the number (sales) of the single products s1 is 2, and the number (sales) of the single products s2 is 2; in the order with order number order2, the number of items s2 (sales) is 1, and the number of items s3 (sales) is 1. It should be noted that the data in table 1 are merely exemplary to facilitate understanding of the solution of the present invention, and do not constitute limitation of the historical order data. In practice, more orders for each order, a greater number of orders for each order, etc., may be included in the historical order data, and more data, such as date, shipping time, etc., may be included in each order.
Table 1 historical order data example
Order number | Single product number | Quantity (sales) |
order1 | s1 | 2 |
order1 | s2 | 2 |
order2 | s2 | 1 |
order2 | s3 | 1 |
And 102, carrying out statistical processing on the historical order data to obtain a statistical processing result of the historical shipment data of the target warehouse.
The statistical processing method comprises statistics, inquiry, data conversion and the like.
In one embodiment, as shown in FIG. 2, step 102 comprises the steps of:
the total number of orders in the historical order data, and the total sales of all orders in the historical order data, are counted 201.
Wherein, the statistics of the total number of orders in the historical order data comprises: and eliminating the same order numbers in the historical order data, and accumulating and counting the rest order numbers to obtain the total number of orders in the historical order data. For example, the total number of orders in the historical order data in Table 1 is 2.
Counting the total sales of all the single products in the historical order data, including: and carrying out addition operation on the sales volume corresponding to each single item in each order to obtain the total sales volume of all single items in the historical order data. For example, in table 1, the total sales of all the individual items in the obtained historical order data is 6 by adding the number corresponding to the number field.
202, The sales of the individual items in each order in the historical order data are counted.
Sales of individual items in each order refer to the corresponding sales of each item in each order. Specifically, the step of counting sales of individual items in each order in the historical order data includes: and acquiring data in each order, and counting sales of each individual item in each order according to the data in each order. Or obtaining an order number from the historical order data; inquiring whether the same order number exists or not; if the same order number exists, acquiring data corresponding to all the same order numbers, and taking the data corresponding to all the same order numbers as data of one order; and counting sales of all the single products in the order until all the order numbers are acquired. Wherein, sales corresponding to the single product which does not exist in the order are set to 0. For example, in table 1, after order number order1 in the first piece of data is acquired, whether order number or order1 of the second piece of data is acquired is queried, and then the data in the two orders 1 are used as data of an order, and sales of each individual item in the order are counted, wherein in the order, the sales of s1 is 2, the sales of s2 is 2, and the sales of s3 is 0, so that all order numbers are acquired.
203, Determining the existence status of each item in each order in the historical order data.
The presence status of individual items in each order refers to the status of whether individual items are present in each order. Specifically, the step of determining the presence status of each item in each order in the historical order data includes: acquiring data in each order, and judging whether each item exists in the order according to the data in each order; and determining the existence state of each item in each order according to the judgment result. If the judgment result is that a certain item exists, the certain item is determined to exist in the order, and if the judgment result is that the certain item does not exist, the certain item is determined to not exist in the order. For example, in order1 in table 1, the single products s1 and s2 are present, and the single product s3 is absent.
204, Processing sales of the individual items in each order and the existence state of the individual items in each order to obtain an order item processing result.
The statistical processing result of the historical shipment data of the target warehouse comprises the following steps: total number of orders, total sales of all orders, order processing results.
Note that the total sales for all orders refers to the total sales for all orders.
Specifically, the step of processing sales of each individual item in each order and existence state of each individual item in each order to obtain an order individual item processing result includes: performing matrix conversion on sales of each individual item in each order to obtain a sales matrix; performing binary conversion on the existence state of each order in each order to obtain a binary matrix; the order form processing result comprises the sales volume matrix and the binary matrix. The sales matrix is specifically an order sales matrix, and the binary matrix is specifically an order binary matrix.
The method for obtaining the sales matrix comprises the following steps of: obtaining one order in all orders, converting sales of each individual item in the order into one row or one column of a matrix, obtaining the next order, converting sales of each individual item in the next order into the next row or the next column of the matrix, and taking the obtained matrix as a sales matrix until all orders are counted. For example, for sales of individual products in order1, after matrix conversion, a corresponding row or column in the sales matrix is: 2,2,0.
Table 2 is an example sales matrix. The sales matrix is obtained by matrix conversion based on the data in table 1.
Table 2 sales matrix example
Sales matrix | s1 | s2 | s3 |
order1 | 2 | 2 | 0 |
order2 | 0 | 1 | 1 |
The method for obtaining the binary matrix comprises the following steps of: acquiring one order in all orders, carrying out binary conversion on the existence state of each item in the order, and taking the result of binary conversion on the existence state of each item in the order as one row or one column of a matrix; acquiring a next order, performing binary conversion on the existence state of each item in the next order, taking the result of binary conversion on the existence state of each item in the next order as the next row or the next column of the matrix until all orders perform binary conversion, and taking the obtained matrix as a binary matrix. The step of binary conversion of the existence state of each item in the order comprises the following steps: if a certain item exists in the order, setting the existence state of the certain item in the order to be 1, otherwise, setting the existence state of the certain item in the order to be 0 until the existence state of each item in the order is set. For example, in table 1, in an order with order number order1, the existence state of s1 is 1, the existence state of s2 is 1, the existence state of s3 is 0, and after matrix conversion, the corresponding row or column in the binary matrix is: 1,1,0. Other characters or numerals may be used to indicate the presence status of each item in the order, for example, 1 and 2 indicate the presence or absence of an item, etc.
Table 3 is an example of a binary matrix. The binary matrix is obtained by binary conversion based on the data in table 1.
Table 3 binary matrix example
Binary matrix | s1 | s2 | s3 |
order1 | 1 | 1 | 0 |
order2 | 0 | 1 | 1 |
In one embodiment, the step 102 further includes 205.
And 205, taking the total number of orders, the total sales of all the orders and the order processing result in the historical order data as the statistical processing result of the historical shipment data of the target warehouse.
Thus, the statistical processing results of the historical shipment data of the target warehouse include: total number of orders, total sales of all orders, order processing results (including sales matrix, binary matrix).
It should be noted that the sequence of steps 202 and 203 is not specifically limited, and 202 may be executed first, 203 may be executed first, or steps 202 and 203 may be executed synchronously; the sequence of steps 201, 204 is not specifically limited, and steps 202, 203, 204 may be performed first, then 201 may be performed first, or steps 203, 202, 204 may be performed first, then 201 may be performed, or steps 202, 203, 204 (203, 202, 204) may be performed in synchronization with step 201.
In other embodiments, the statistical processing results of the historical shipment data of the target warehouse may also include other data.
And 103, predicting the stock list of the goods which are delivered from the target warehouse by the merchant in a second time period in the future according to the statistical processing result, and outputting the stock list.
It should be noted that, in the embodiment of the present invention, the future stock orders are predicted according to the historical order data, which is based on the situation that the sales amount of each order is not much different in the first preset time period and the second preset time period.
The first time period and the second time period may be the same or different, for example, the first time period may be half a year, the second time period may be half a year, or a quarter, etc.
In one embodiment, step 103 includes: acquiring a preset order meeting rate and sales meeting rate; and predicting the stock list of the goods delivered from the target warehouse by the merchant in a second time period in the future according to the statistical processing result and the preset order meeting rate and sales meeting rate, and outputting the stock list.
The order meeting rate refers to the number of orders which can be met divided by the total number of orders, and if all the orders in one order have corresponding quantity of stock in the target warehouse, determining that the order is met; the sales satisfaction rate refers to the total sales corresponding to the orders that can be satisfied divided by the total sales corresponding to all orders. For example, with the data in table 1, if only the single item s1 and the single item s2 are present in a certain target warehouse, and the number of the single items s1 is 2, and the number of the single items s2 is 2, the order1 is satisfied, and the order1 cannot be satisfied, and therefore, the order satisfaction rate is 1/2=0.5, and the sales satisfaction rate is (2+2)/(2+2+1) =2/3. Note that 0< order satisfaction rate < =1, and 0< sales order satisfaction rate < =1.
In one embodiment, the prediction of inventory items may be performed by an inventory item prediction model.
Specifically, step 103 includes: and inputting the statistical processing result into a stock item prediction model, predicting the stock item which is delivered from the target warehouse by the merchant in a second time period in the future, and outputting a stock item list.
In one embodiment, step 103 includes: acquiring a preset order meeting rate and sales meeting rate; and inputting the statistical processing result, the preset order meeting rate and the preset sales meeting rate into a stock item preset model to predict stock items which are delivered from the target warehouse by the merchant in a second time period in the future and output a stock item list.
Wherein, it can be understood that the order satisfaction rate and sales satisfaction rate are also designed in the stock item prediction model. The preset order satisfaction rate and sales volume satisfaction rate may be preset, and may be the same as or different from the order satisfaction rate and sales volume satisfaction rate in the stock item prediction model. It can be understood that if the order satisfaction rate and the sales satisfaction rate in the stock item prediction model are directly used, the preset order satisfaction rate and sales satisfaction rate do not need to be acquired. And if the order meeting rate and the sales meeting rate in the stock item prediction model are required to be modified, acquiring the preset order meeting rate and sales meeting rate. It is understood that the order satisfaction rate and the sales satisfaction rate in the stock item prediction model do not necessarily satisfy the needs of the user, and therefore, the order satisfaction rate and the sales satisfaction rate need to be reset and the preset order satisfaction rate and sales satisfaction rate need to be obtained. Namely, the method and the device for obtaining the preset order meeting rate and sales meeting rate are provided in the embodiment of the invention, so that the order meeting rate and sales meeting rate in the stock item prediction model are modified, the practicability of the stock item prediction model is improved, and the user experience is improved.
In one embodiment, the inventory single measurement model includes a mixed integer linear programming model. Some or all of the decision variables in the linear programming model are required to be integers, and the linear programming model is called a mixed integer linear programming model.
According to the embodiment of the invention, the historical order data of the delivery in the target warehouse is subjected to statistical processing, and the stock orders of the target warehouse are predicted according to the statistical processing result, so that the stock orders meeting the requirements of the target warehouse are determined, the efficiency, the accuracy and the flexibility of determining the stock orders can be improved, and the management cost is reduced.
In one embodiment, the prediction of the inventory items is performed by an inventory item prediction model that includes a mixed integer linear programming model. Fig. 3 is a schematic flow chart of a stock form prediction method according to an embodiment of the present invention. The method comprises the following specific processes:
301, constructing a mixed integer linear programming model.
And constructing a mixed integer linear programming model by setting parameters and constructing an objective function and a constraint condition of the objective function. Wherein the objective function and the constraint condition of the objective function can comprise the set parameters.
In one embodiment, as shown in FIG. 4, step 301 includes the steps of:
401 defining a set of mixed integer linear programming models, and setting parameters of the mixed integer linear programming models.
It should be noted that if other inventory item prediction models are used, other sets and/or parameters may be included. This embodiment is described by taking a mixed integer linear programming model as an example to facilitate understanding of the scheme in the embodiment of the present invention.
The set definition involved in the mixed integer linear programming model is shown in table 4. Corresponding to Table 1, order1 and order2 are included in the I set; the J set comprises s1, s2 and s3.
Table 4 sets involved in mixed integer linear programming model
The parameters related to the mixed integer linear programming model comprise sales matrix parameters a, binary matrix parameters b, order total parameters M, total sales parameters S of all single products and the like. The parameters involved in the mixed integer linear programming model are shown in table 5.
Table 5 parameters related to mixed integer linear programming model
402, Order satisfaction rate, sales satisfaction rate, and binarized variable are set.
It should be noted that the order satisfaction rate and sales satisfaction rate are also parameters in some embodiments as in the mixed integer linear programming model, and thus are also present in table 5. The order satisfaction rate and the sales volume satisfaction rate in the mixed integer linear programming model can be set to specific values, so that if the order satisfaction rate and the sales volume satisfaction rate set in the mixed integer linear programming model need to be modified, the preset order satisfaction rate and sales volume satisfaction rate need to be obtained when stock order prediction is carried out. In other embodiments, the order satisfaction rate and sales satisfaction rate in the mixed integer linear programming model may exist in the form of parameters, such that a predetermined order satisfaction rate and sales satisfaction rate need to be obtained when inventory item predictions are made. Wherein the order satisfaction rate corresponds to a service level and the sales satisfaction rate corresponds to a sales level. In the embodiment of the invention, the service level, namely the order meeting rate, is firstly required, and the sales meeting rate is further required. This is because there may be a plurality of possible solutions in the case where the order satisfaction rate is satisfied, and a more preferable possible solution can be obtained from the plurality of possible solutions, together with the constraint of the sales satisfaction rate.
For example, for the data in Table 1, there are two orders order1 and order2. If only the order satisfaction rate is set, it is assumed that the order satisfaction rate is 50%, then only either order1 or order2 is satisfied. If order1 is satisfied, the sales satisfaction rate is (2+2)/(2+2+1+1) =2/3; if order2 is satisfied, the sales satisfaction rate is (1+1)/(2+2+1+1) =1/3. If only the order satisfaction rate is met, two feasible solutions exist, and sales satisfaction rates corresponding to the feasible solutions are different, such as 2/3 and 1/3 calculated. For merchants, the more products are sold, the better, so sales satisfaction rates are further introduced to allow the merchant to obtain a better viable solution from a plurality of viable solutions. If the sales satisfaction rate is set to be 50%, a more preferable possible solution is that order1 is satisfied, and the orders s1 and s2 are selected.
Wherein, the binary variables of the set mixed integer linear programming model are shown in table 6.
Table 6 binarized variables for mixed integer linear programming model
403, Setting the predicted stock order minimization as an objective function.
Wherein, the predicted stock item quantity minimization is set as an objective function, namely, the predicted stock SKU quantity minimization is also understood as the stock item class quantity minimization. The set objective function is shown in table 7.
404, Constructing constraint conditions of the objective function according to the relation among the order satisfaction rate, sales satisfaction rate and binarized variables.
Wherein step 404 comprises: and constructing constraint conditions of the objective function according to the set parameters, the order satisfaction rate, the sales satisfaction rate and the relation between the binarized variables. Specifically, constructing constraint conditions of the objective function according to the set parameters, the order satisfaction rate, the sales satisfaction rate and the relation between the binarized variables, wherein the constraint conditions comprise: setting a relation between sales matrix parameters and binarization variables as a first constraint condition of an objective function; setting a relation between the binary matrix parameters and the binarization variables as a second constraint condition of the objective function; setting a relation among sales matrix parameters, sales satisfaction rates and total sales parameters of all single products as a third constraint condition of an objective function; and setting the relation among the binary matrix parameters, the order satisfaction rate and the order total number parameters as a fourth constraint condition of the objective function.
Specifically, a relation between sales matrix parameters and binarized variables is set, and the relation is used as a first constraint condition of an objective function, and the relation comprises the following steps: the relation among the sales matrix parameter a, the binarized variable x j and the binarized variable xi i is set as a first constraint condition of the objective function.
Specifically, setting a relation between a binary matrix parameter and a binarized variable as a second constraint condition of an objective function, including: the relation among the binary matrix parameter b, the binarized variable x j and the binarized variable xi i is set as a second constraint condition of the objective function.
Specifically, a relation among sales matrix parameters, sales satisfaction rates and total sales parameters of all single products is set, and the relation is used as a third constraint condition of an objective function, wherein the third constraint condition comprises the following steps: and setting a relation among the sales matrix parameter a, the sales satisfaction rate beta and the total sales parameter S of all the single products as a third constraint condition of the objective function. For example, it will be appreciated that this third constraint means that the total sales for each individual item of the order being fulfilled is set to be greater than or equal to the sales fulfillment rate multiplied by the total sales for all individual items.
Specifically, a relation among a binary matrix parameter, an order satisfaction rate and an order total number parameter is set, and the relation is used as a fourth constraint condition of an objective function, and the relation comprises the following steps: and setting a relation among the binary matrix parameter b, the order satisfaction rate alpha and the order total number parameter M as a fourth constraint condition of the objective function. For example, it will be appreciated that this fourth constraint means that the number of orders that are set to be satisfied is equal to or greater than the order satisfaction rate times the total number of orders.
TABLE 7 target function and constraint of target function
The specific settings of the objective function and the first constraint, the second constraint, the third constraint, and the fourth constraint of the objective function are shown in table 7. Although not shown in table 7, it is understood that the values of i and j both belong to integers.
Constraint conditions (1), constraint conditions (2), constraint conditions (3) and constraint conditions (4) correspond to the first constraint condition, the second constraint condition, the third constraint condition and the fourth constraint condition respectively. Wherein, the formulas in the third constraint condition and the fourth constraint condition are easy to understand, and for the formulas in the first preset condition and the second constraint condition, it can be understood that for each order, the formulas in the first constraint condition and the second constraint condition are all established.
For example, for order1 in table 1, the formula to the left of the first constraint is a (order 1-s 1) x (s 1) +a (order 1-s 2) x (s 2) +a (order 1-s 3) x (s 3), where a (order 1-s 1), a (order 1-s 2), a (order 1-s 3) correspond to the first row of data in the sales matrix, are 2,0, respectively, so the formula to the left is 2*x (s 1) +2*x (s 2) +0*x (s 3); the formula in the first constraint is to the right (a (order 1-s 1) +a (order 1-s 2) +a (order 1-s 3)) × ζ order1=4*ξorder1. Assuming order1 is satisfied, ζ order1 =1, equation 2*x (s 1) +2*x (s 2) > =4. Thus, if order1 is satisfied, then order s1 and order s2 are selected for the equation 2*x (s 1) +2*x (s 2) > =4 to be satisfied. Similarly, for order2, the formula constraint in the first constraint is also satisfied. The formula constraint in the second preset condition is similar to the formula constraint in the first constraint condition, and will not be described in detail herein.
And 405, constructing a mixed integer linear programming model according to the target function and the constraint condition.
A mixed integer linear programming model is constructed from the target functions and constraints of the target functions in table 7, i.e. the mixed integer linear programming model includes the target functions and constraints of the target functions in table 7.
It should be noted that, in this embodiment, the execution order of the step 401 and the step 402 is not limited, and the step 402 may be executed first, then the step 401 may be executed, or the step 401 and the step 402 may be executed simultaneously.
This embodiment further defines the procedure specifically for constructing the mixed integer linear programming model.
302, Historical order data for a merchant to be shipped from a target warehouse during a first time period is obtained.
And 303, carrying out statistical processing on the historical order data to obtain a statistical processing result of the historical shipment data of the target warehouse.
The specific flow of the statistical process is shown in step 102 in the embodiment of fig. 1. The statistical processing result comprises sales matrix, binary matrix, total number of orders, total sales of all single products and the like.
Steps 302-303 in this embodiment correspond to steps 101-102 in the embodiment of fig. 1, and refer specifically to the description in the embodiment of fig. 1, and are not repeated here.
And 304, inputting the statistical processing result into a mixed integer linear programming model, predicting the stock list of the target warehouse in a second time period of the future, and outputting the stock list.
Specifically, the statistical processing result is input into a mixed integer linear programming model, and a mathematical programming solver is used for solving the mixed integer linear programming model, so that an optimal solution meeting the order satisfaction rate and the sales satisfaction rate can be obtained.
For example, for the data in table 1, the order satisfaction rate=1/2, the sales satisfaction rate=1/2, the number of stock orders finally solved is 2, the stock order list includes s1, s2, and the order satisfied is order1.
In one embodiment, step 304 includes: acquiring a preset order meeting rate and sales meeting rate; and inputting the statistical processing result, the preset order meeting rate and sales meeting rate into a mixed integer linear programming model, predicting the stock orders which are delivered from the target warehouse by the merchant in a second time period in the future, and outputting a stock order list. According to the embodiment, the preset order satisfaction rate and sales volume satisfaction rate are further obtained, the order satisfaction rate and sales volume satisfaction rate in the mixed integer linear programming model are replaced according to the obtained order satisfaction rate and sales volume satisfaction rate, namely, the order satisfaction rate and sales volume satisfaction rate in the mixed integer linear programming model are modified, the practicability of the mixed integer linear programming model is improved, and the user experience is improved.
According to the embodiment, the inventory list is predicted according to the constructed mixed integer linear programming model, constraint of order satisfaction rate and sales satisfaction rate is related in the constructed mixed integer linear programming model, so that the mixed integer linear programming model can obtain the optimal feasible solution from a plurality of feasible solutions when solving, and the optimal inventory list is obtained, namely the minimum inventory quantity (namely the inventory category quantity) is predicted. The method can predict the single products stored and transported in the target warehouse under the condition of not influencing the service level, improves the efficiency, accuracy and flexibility of determining the single products stored in the target warehouse, greatly reduces the quantity of the single products stored in the target warehouse and reduces the management cost.
In order to better implement the stock item prediction method in the embodiment of the invention, the embodiment of the invention also provides a stock item prediction device based on the stock item prediction method. The stock single product prediction device is integrated in equipment, and the equipment can be a server or a terminal, such as a mobile phone, a Pad, a desktop computer and the like.
Fig. 5 is a schematic block diagram of an inventory item predicting device provided by an embodiment of the present invention, which includes an order acquisition unit 501, a statistical processing unit 502, and a predicting unit 503.
An order acquisition unit 501 is configured to acquire historical order data for a merchant that is shipped from a target warehouse during a first period of time.
And the statistics processing unit 502 is used for performing statistics processing on the historical order data to obtain a statistics processing result of the historical shipment data of the target warehouse.
The statistics processing unit 502 includes an order sales statistics unit, a single product state determining unit, and an order processing unit. The order sales statistics unit is used for counting the total number of orders in the historical order data and the total sales of all the orders in the historical order data. And the single item sales statistics unit is used for counting sales of various single items in each order in the historical order data. And the single item state determining unit is used for determining the existence state of each single item in each order in the historical order data. And the order item processing unit is used for processing sales of each item in each order and the existence state of each item in each order to obtain an order item processing result, wherein the statistical processing result comprises the total number of orders, the total sales of all items and the order item processing result. In an embodiment, the statistics processing unit 502 further comprises: and the result determining unit is used for taking the total number of orders in the historical order data, the total sales of all the orders and the order processing result as the statistical processing result of the historical shipment data of the target warehouse. The order and order processing unit comprises a sales matrix determining unit and a binary matrix determining unit. The sales matrix determining unit is used for performing matrix conversion on sales of each single product in each order to obtain a sales matrix. The binary matrix determining unit is used for carrying out binary conversion on the existence state of each single product in each order to obtain a binary matrix. The order form processing result comprises a sales matrix and a binary matrix.
And the prediction unit 503 is used for predicting the stock list of the goods delivered from the target warehouse in the second time period in the future by the merchant according to the statistical processing result and outputting the stock list.
In an embodiment, the prediction unit 503 includes a first satisfaction rate obtaining unit and a first single-product prediction unit. The first satisfaction rate acquisition unit is used for acquiring a preset order satisfaction rate and sales satisfaction rate. The first item predicting unit is used for predicting the inventory items which are delivered from the target warehouse in a second time period in the future according to the statistical processing result, the preset order meeting rate and the preset sales meeting rate and outputting an inventory item list.
In one embodiment, the prediction of inventory items may be performed by an inventory item prediction model. The prediction unit 503 specifically is configured to: and inputting the statistical processing result into a stock item prediction model, predicting the stock item which is delivered from the target warehouse by the merchant in a second time period in the future, and outputting a stock item list.
In one embodiment, the prediction of inventory items may be performed by an inventory item prediction model. The prediction unit 503 includes: the second satisfaction rate acquisition unit and the second single product prediction unit. The second satisfaction rate acquisition unit is used for acquiring preset order satisfaction rates and sales satisfaction rates. The second item predicting unit is used for inputting the statistical processing result, the preset order meeting rate and the preset sales meeting rate into the inventory item preset model so as to predict inventory items which are delivered from the target warehouse by the merchant in a second time period in the future and output an inventory item list.
In one embodiment, the prediction of the inventory items is performed by an inventory item prediction model that includes a mixed integer linear programming model. As shown in fig. 6, a schematic block diagram of an inventory item predicting device provided by an embodiment of the present invention includes a construction unit 601, an order acquisition unit 602, a statistical processing unit 603, and a predicting unit 604.
And a construction unit 601, configured to construct a mixed integer linear programming model.
In an embodiment, the construction unit 601 includes: parameter variable setting unit, objective function setting unit, constraint condition setting unit, model building unit. The parameter variable setting unit is used for defining a set related to the mixed integer linear programming model and setting parameters related to the mixed integer linear programming model. The parameter variable setting unit is also used for setting the order meeting rate, the sales meeting rate and the binarization variable. And an objective function setting unit for setting the predicted quantity of stock orders to be minimized as an objective function. And the constraint condition setting unit is used for constructing the constraint condition of the objective function according to the relation among the order meeting rate, the sales meeting rate and the binarized variable. And the model construction unit is used for constructing a mixed integer linear programming model according to the objective function and the constraint condition. The constraint condition setting unit comprises a first condition setting unit, a second condition setting unit, a third condition setting unit and a fourth condition setting unit. The first condition setting unit is used for setting the relation between the sales matrix parameters and the binarized variables as a first constraint condition of the objective function. And the second condition setting unit is used for setting the relation between the binary matrix parameters and the binarized variables as a second constraint condition of the objective function. And the third condition setting unit is used for setting the relation among the sales matrix parameters, the sales satisfaction rate and the total sales parameters of all the single products as a third constraint condition of the objective function. And the fourth condition setting unit is used for setting the relation among the binary matrix parameters, the order satisfaction rate and the order total number parameters as a fourth constraint condition of the objective function.
An order acquisition unit 602 for acquiring historical order data for a merchant for shipment from a target warehouse during a first period of time.
The statistical processing unit 603 is configured to perform statistical processing on the historical order data, so as to obtain a statistical processing result of the historical shipment data of the target warehouse. The statistical processing unit 603 is the same as the statistical processing unit 502 in the above embodiment, and please refer to the description of the statistical processing unit 502 in the above embodiment specifically, which is not repeated here.
And the prediction unit 604 is used for inputting the statistical processing result into the mixed integer linear programming model, predicting the stock orders which are delivered from the target warehouse by the merchant in the second time period in the future, and outputting a stock order list.
In an embodiment, the prediction unit 604 includes a third satisfaction rate acquisition unit and a third single-product prediction unit. The third satisfaction rate acquisition unit is used for acquiring preset order satisfaction rates and sales satisfaction rates. And the third item predicting unit is used for inputting the statistical processing result, the preset order meeting rate and sales meeting rate into the mixed integer linear programming model, predicting the inventory items which are delivered from the target warehouse by the merchant in the second time period in the future, and outputting an inventory item list.
It should be noted that, as those skilled in the art can clearly understand the specific implementation process of the foregoing apparatus and each unit, reference may be made to the corresponding description in the foregoing method embodiment, and for convenience and brevity of description, no further description is provided herein.
The embodiment of the invention also provides a computer device which integrates any of the stock list predicting devices provided by the embodiment of the invention, and the computer device comprises:
one or more processors;
A memory; and
One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the processor to perform the steps in the stock form prediction method described in any of the embodiments above.
The embodiment of the invention also provides computer equipment which integrates any stock single product prediction device provided by the embodiment of the invention. As shown in fig. 7, a schematic structural diagram of a computer device according to an embodiment of the present invention is shown, specifically:
The computer device may include one or more processors 701 of a processing core, memory 702 of one or more computer readable storage media, power supply 703, and input unit 704, among other components. It will be appreciated by those skilled in the art that the computer device structure shown in the figures is not limiting of the computer device and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components. Wherein:
The processor 701 is a control center of the computer device, connects various parts of the entire computer device using various interfaces and lines, and performs various functions of the computer device and processes data by running or executing software programs and/or modules stored in the memory 702, and calling data stored in the memory 702, thereby performing overall monitoring of the computer device. Optionally, processor 701 may include one or more processing cores; preferably, the processor 701 may integrate an application processor and a modem processor, wherein the application processor primarily handles operating systems, user interfaces, applications, etc., and the modem processor primarily handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 701.
The memory 702 may be used to store software programs and modules, and the processor 701 executes various functional applications and data processing by executing the software programs and modules stored in the memory 702. The memory 702 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data created according to the use of the computer device, etc. In addition, the memory 702 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 702 may also include a memory controller to provide access to the memory 702 by the processor 701.
The computer device further comprises a power supply 703 for powering the various components, preferably the power supply 703 is logically connected to the processor 701 by a power management system, whereby the functions of managing charging, discharging, and power consumption are performed by the power management system. The power supply 703 may also include one or more of any component, such as a direct current or alternating current power supply, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, etc.
The computer device may further comprise an input unit 704, which input unit 704 may be used for receiving input numerical or character information and generating keyboard, mouse, joystick, optical or trackball signal inputs in connection with user settings and function control.
Although not shown, the computer device may further include a display unit or the like, which is not described herein. In particular, in this embodiment, the processor 701 in the computer device loads executable files corresponding to the processes of one or more application programs into the memory 702 according to the following instructions, and the processor 701 executes the application programs stored in the memory 702, so as to implement various functions, as follows:
Acquiring historical order data of a merchant from a target warehouse in a first time period;
carrying out statistical processing on the historical order data to obtain a statistical processing result of the historical shipment data of the target warehouse;
And predicting the stock list of the goods which are delivered from the target warehouse by the merchant in a second time period in the future according to the statistical processing result, and outputting the stock list.
The computer device can realize the steps in any embodiment of the stock item prediction method provided by the embodiment of the invention, so that the beneficial effects which can be realized by any stock item prediction method provided by the embodiment of the invention can be realized, and detailed reference is made to the previous embodiment, and details are not repeated here.
Those of ordinary skill in the art will appreciate that all or a portion of the steps of the various methods of the above embodiments may be performed by instructions, or by instructions controlling associated hardware, which may be stored in a computer-readable storage medium and loaded and executed by a processor.
To this end, an embodiment of the present invention provides a storage medium, which may include: read Only Memory (ROM), random access Memory (RAM, random Access Memory), magnetic or optical disk, and the like. On which a computer program is stored, which is loaded by a processor to perform the steps of any of the stock form prediction methods provided by the embodiments of the present invention. For example, the loading of the computer program by the processor may perform the steps of:
Acquiring historical order data of a merchant from a target warehouse in a first time period;
carrying out statistical processing on the historical order data to obtain a statistical processing result of the historical shipment data of the target warehouse;
And predicting the stock list of the goods which are delivered from the target warehouse by the merchant in a second time period in the future according to the statistical processing result, and outputting the stock list.
In the foregoing embodiments, the descriptions of the embodiments are focused on, and the portions of one embodiment that are not described in detail in the foregoing embodiments may be referred to in the foregoing detailed description of other embodiments, which are not described herein again.
In the implementation, each unit or structure may be implemented as an independent entity, or may be implemented as the same entity or several entities in any combination, and the implementation of each unit or structure may be referred to the foregoing method embodiments and will not be repeated herein.
The specific implementation of each operation above may be referred to the previous embodiments, and will not be described herein.
The above description of the method, the device, the computer equipment and the storage medium for predicting the inventory bill provided by the embodiment of the invention applies specific examples to describe the principle and the implementation of the invention, and the description of the above embodiment is only used for helping to understand the method and the core idea of the invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in light of the ideas of the present invention, the present description should not be construed as limiting the present invention.
Claims (7)
1. A stock form prediction method, comprising:
Acquiring historical order data of a merchant from a target warehouse in a first time period;
carrying out statistical processing on the historical order data to obtain a statistical processing result of the historical shipment data of the target warehouse;
predicting the stock list of the goods delivered from the target warehouse by the merchant in a second time period in the future according to the statistical processing result, and outputting the stock list;
and predicting the stock list of the goods delivered from the target warehouse by the merchant in a second time period in the future according to the statistical processing result, and outputting the stock list of the goods, wherein the method comprises the following steps:
acquiring a preset order meeting rate and sales volume meeting rate, wherein the sales volume meeting rate refers to the total sales volume corresponding to the orders which can be met divided by the total sales volume corresponding to all the orders, and the order meeting rate refers to the number of the orders which can be met divided by the total number of the orders;
Inputting the statistical processing result, the preset order meeting rate and sales meeting rate into a pre-constructed stock item prediction model, predicting the stock items which are delivered from the target warehouse by the merchant in a second time period in the future, and outputting a stock item list; the inventory item list comprises predicted inventory item numbers, the inventory item prediction model comprises sales matrix parameters, binary matrix parameters, order total parameters and total sales parameters of all items, and constraint conditions of an objective function of the inventory item prediction model comprise a first constraint condition, a second constraint condition, a third constraint condition and a fourth constraint condition;
The construction of the stock item prediction model comprises the following steps: setting order meeting rate, sales meeting rate and binarization variable; setting the predicted stock order minimization as an objective function; constructing constraint conditions of the objective function according to the relation among the order satisfaction rate, sales satisfaction rate and binarization variables; constructing the stock single product prediction model according to the constraint condition of the objective function;
The objective function is:
Wherein I e I, which refers to the collection of orders I; j e J, J refers to the collection of singles J; x j refers to whether the jth order is selected to the inventory order list, if so, x j = 1, otherwise, x j = 0;
The construction of the first constraint condition comprises the following steps: setting the relation between the sales matrix parameters and the binarization variables as a first constraint condition of the objective function; the first constraint condition is used for constraining the relation between two binarization variables so as to ensure that all the single products corresponding to the order are selected when the order is satisfied; the first constraint condition is:
Wherein a ij refers to the number of the jth items contained in the ith order, I e I, J e J; ζ i refers to whether the ith order was successful, if so, ζ i =1, otherwise, ζ i =0;
the construction of the second constraint condition comprises the following steps: setting the relation between the binary matrix parameters and the binarization variables as a second constraint condition of the objective function; the second constraint condition is used for constraining the relation between two binarization variables, and ensuring that all the single products corresponding to the order are selected when the order is satisfied; the second constraint condition is:
Wherein b ij refers to whether the ith order contains the jth order, if yes, it is 1, if not, it is 0, I e I, J e J;
The construction of the third constraint condition comprises the following steps: setting the relation among the sales matrix parameters, the sales satisfaction rate and the total sales parameters of all the single products as a third constraint condition of the objective function; wherein the third constraint condition is used for that the total sales of all single products in the satisfied order is not less than the sales satisfaction rate multiplied by the total sales of all single products; the third constraint condition is:
wherein beta is sales volume satisfaction rate, S is total sales volume of all orders;
The construction of the fourth constraint condition comprises the following steps: setting the relation among the binary matrix parameters, the order satisfaction rate and the order total number parameters as a fourth constraint condition of the objective function; wherein the fourth constraint condition is used for the number of the satisfied orders to be not less than the order satisfaction rate multiplied by the total number of orders; the fourth constraint is:
Wherein alpha is the order satisfaction rate, and M is the total number of orders.
2. The stock item predicting method as set forth in claim 1, wherein said statistically processing said historical order data to obtain a statistical processing result of said historical shipment data of said target warehouse comprises:
counting the total number of orders in the historical order data and the total sales of all the single products in the historical order data;
Counting sales of various single products in each order in the historical order data;
Determining the existence state of each item in each order in the historical order data;
Processing sales of the single items in each order and the existence state of the single items in each order to obtain an order single item processing result;
the statistical processing results comprise the total number of orders, the total sales of all the single products and the processing results of the orders.
3. The stock item predicting method as set forth in claim 2, wherein the processing the sales amount of the items in each order and the existence state of the items in each order to obtain the order item processing result includes:
Performing matrix conversion on sales of each individual item in each order to obtain a sales matrix;
performing binary conversion on the existence state of each order in each order to obtain a binary matrix;
the order form processing result comprises the sales volume matrix and the binary matrix.
4. The stock item predicting method as set forth in claim 3, wherein the step of performing a binary conversion on the presence status of each item in each order to obtain a binary matrix comprises:
performing binary conversion on the existence state of each item in each order, and taking the result of binary conversion on the existence state of each item in each order as one row or one column of a matrix;
the obtained matrix is used as a binary matrix.
5. An inventory item prediction apparatus, comprising:
an order acquisition unit for acquiring historical order data of a merchant from a target warehouse in a first time period;
The statistical processing unit is used for carrying out statistical processing on the historical order data to obtain a statistical processing result of the historical shipment data of the target warehouse;
the prediction unit is used for predicting the inventory items which are delivered from the target warehouse by the merchant in a second time period in the future according to the statistical processing result and outputting an inventory item list;
Wherein, the prediction unit specifically includes:
The second satisfaction rate acquisition unit is used for acquiring a preset order satisfaction rate and sales volume satisfaction rate, wherein the sales volume satisfaction rate refers to the total sales volume corresponding to the orders capable of being satisfied divided by the total sales volume corresponding to all the orders, and the order satisfaction rate is the number of the orders capable of being satisfied divided by the total number of the orders;
The second single product prediction unit is used for inputting the statistical processing result, the preset order meeting rate and sales meeting rate into a pre-constructed stock single product prediction model so as to predict stock single products which are delivered from a target warehouse by a merchant in a second time period in the future and output a stock single product list; the inventory item list comprises predicted inventory item numbers, the inventory item prediction model comprises sales matrix parameters, binary matrix parameters, order total parameters and total sales parameters of all items, and constraint conditions of an objective function of the inventory item prediction model comprise a first constraint condition, a second constraint condition, a third constraint condition and a fourth constraint condition; the construction of the stock item prediction model comprises the following steps: setting order meeting rate, sales meeting rate and binarization variable; setting the predicted stock order minimization as an objective function; constructing constraint conditions of the objective function according to the relation among the order satisfaction rate, sales satisfaction rate and binarization variables; constructing the stock single product prediction model according to the constraint condition of the objective function; the construction of the first constraint condition comprises the following steps: setting the relation between the sales matrix parameters and the binarization variables as a first constraint condition of the objective function; the first constraint condition is used for constraining the relation between two binarization variables so as to ensure that all the single products corresponding to the order are selected when the order is satisfied; the construction of the second constraint condition comprises the following steps: setting the relation between the binary matrix parameters and the binarization variables as a second constraint condition of the objective function; the second constraint condition is used for constraining the relation between two binarization variables, and ensuring that all the single products corresponding to the order are selected when the order is satisfied; the construction of the third constraint condition comprises the following steps: setting the relation among the sales matrix parameters, the sales satisfaction rate and the total sales parameters of all the single products as a third constraint condition of the objective function; wherein the third constraint condition is used for that the total sales of all single products in the satisfied order is not less than the sales satisfaction rate multiplied by the total sales of all single products; the construction of the fourth constraint condition comprises the following steps: setting the relation among the binary matrix parameters, the order satisfaction rate and the order total number parameters as a fourth constraint condition of the objective function; wherein the fourth constraint condition is used for the number of the satisfied orders to be not less than the order satisfaction rate multiplied by the total number of orders;
Wherein the objective function is:
Wherein I e I, which refers to the collection of orders I; j e J, J refers to the collection of singles J; x j refers to whether the jth order is selected to the inventory order list, if so, x j = 1, otherwise, x j = 0;
the first constraint condition is:
Wherein a ij refers to the number of the jth items contained in the ith order, I e I, J e J; ζ i refers to whether the ith order was successful, if so, ζ i =1, otherwise, ζ i =0;
The second constraint condition is:
Wherein b ij refers to whether the ith order contains the jth order, if yes, it is 1, if not, it is 0, I e I, J e J;
the third constraint condition is:
wherein beta is sales volume satisfaction rate, S is total sales volume of all orders;
The fourth constraint is:
Wherein alpha is the order satisfaction rate, and M is the total number of orders.
6. A computer device, the computer device comprising:
one or more processors; a memory; and one or more applications, wherein the processor is coupled to the memory, the one or more applications being stored in the memory and configured to be executed by the processor to implement the stock form prediction method of any one of claims 1 to 4.
7. A storage medium having stored thereon a computer program to be loaded by a processor to perform the steps in the stock item prediction method of any one of claims 1 to 4.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910748524.1A CN112396365B (en) | 2019-08-14 | 2019-08-14 | Stock item prediction method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910748524.1A CN112396365B (en) | 2019-08-14 | 2019-08-14 | Stock item prediction method, device, computer equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112396365A CN112396365A (en) | 2021-02-23 |
CN112396365B true CN112396365B (en) | 2024-07-02 |
Family
ID=74601451
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910748524.1A Active CN112396365B (en) | 2019-08-14 | 2019-08-14 | Stock item prediction method, device, computer equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112396365B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113128932B (en) * | 2021-04-16 | 2024-04-16 | 北京京东振世信息技术有限公司 | Warehouse stock processing method and device, storage medium and electronic equipment |
CN113537874A (en) * | 2021-05-14 | 2021-10-22 | 深圳市富能新能源科技有限公司 | Storage management method, system, terminal equipment and computer storage medium |
CN113627662B (en) * | 2021-08-03 | 2024-05-28 | 杭州拼便宜网络科技有限公司 | Inventory data prediction method, apparatus, device and storage medium |
CN114997471A (en) * | 2022-05-12 | 2022-09-02 | 北京沃东天骏信息技术有限公司 | Information generation method and device, electronic equipment and computer readable medium |
CN115034523B (en) * | 2022-08-10 | 2022-11-01 | 深圳市感恩网络科技有限公司 | Enterprise ERP (enterprise resource planning) comprehensive management system and method based on big data |
CN115660733A (en) * | 2022-11-04 | 2023-01-31 | 鹏展万国电子商务(深圳)有限公司 | Sales prediction system and method based on artificial intelligence |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109840730A (en) * | 2017-11-29 | 2019-06-04 | 北京京东尚科信息技术有限公司 | Method and device for data prediction |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5630070A (en) * | 1993-08-16 | 1997-05-13 | International Business Machines Corporation | Optimization of manufacturing resource planning |
WO2010004587A2 (en) * | 2008-07-11 | 2010-01-14 | Gorur Narayana Srinivasa Prasa | A computer implemented decision support method and system |
CN109978428A (en) * | 2017-12-28 | 2019-07-05 | 北京京东尚科信息技术有限公司 | Data estimation method and apparatus and computer readable storage medium |
-
2019
- 2019-08-14 CN CN201910748524.1A patent/CN112396365B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109840730A (en) * | 2017-11-29 | 2019-06-04 | 北京京东尚科信息技术有限公司 | Method and device for data prediction |
Also Published As
Publication number | Publication date |
---|---|
CN112396365A (en) | 2021-02-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112396365B (en) | Stock item prediction method, device, computer equipment and storage medium | |
CN110390501B (en) | Data processing method and system, computer system and computer readable medium | |
CN110633820B (en) | Warehouse address recommendation method and device and computer readable storage medium | |
CN110472899B (en) | Method and device for distributing articles out of warehouse | |
Hemmati et al. | Vendor managed inventory with consignment stock for supply chain with stock-and price-dependent demand | |
Pourakbar et al. | End‐of‐life inventory decisions for consumer electronics service parts | |
Pasandideh et al. | A genetic algorithm approach to optimize a multi-products EPQ model with discrete delivery orders and constrained space | |
US20150112750A1 (en) | Supply network optimization method and system for multiple objectives | |
CN111401619A (en) | Purchase order processing method and device, electronic equipment and storage medium | |
Ahmadi et al. | A centralized stochastic inventory control model for perishable products considering age-dependent purchase price and lead time | |
CN113762885B (en) | Method, apparatus, device, storage medium and program product for determining replenishment quantity | |
CN113191713A (en) | Warehouse out-of-stock transferring method, device, equipment and storage medium | |
CN111242531A (en) | Raw material management and control method and device and electronic equipment | |
CN112053168A (en) | Material monitoring method and device, electronic equipment and storage medium | |
CN113793081A (en) | Storage monitoring method and device, computer readable medium and electronic equipment | |
Puka et al. | Decision rules-based method for dynamic adjustment of Min–Max ordering levels | |
CN112330235A (en) | Data processing method and device for inventory management, electronic equipment and medium | |
CN111242532A (en) | Purchasing management method and device and electronic equipment | |
CN111062669A (en) | Service processing method, device, storage medium and server | |
US20160300173A1 (en) | Oscillation detection and reduction in supply chain | |
CN115482051A (en) | Commodity management method, device and equipment based on ERP system and readable storage medium | |
Lam et al. | Responsive pick face replenishment strategy for stock allocation to fulfil e-commerce order | |
CN112581014A (en) | Statistical method, device, equipment and storage medium for material preparation degree | |
CN114444990A (en) | Product selection method for supply chain network front-end bin | |
Duc et al. | Inventory Positioning in Supply Chain Network: A Service-Oriented Approach |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant |