Method, device, electronic device and computer-readable storage medium for determining commodity popularity

Abstract

The embodiment of the present application discloses a method, device, electronic device and computer-readable storage medium for determining the popularity of a product. In the embodiment of the present application, the device for determining the popularity of a product obtains sales information and inventory information of a product in a warehouse within a preset period of time; determines the first sales feature, the second sales feature, the first inventory feature and the second inventory feature of the product based on the sales information and the inventory information; determines the unit sales volume of the product based on the first sales feature and the first inventory feature; and determines the popularity of the product based on the unit sales volume, the second sales feature and the second inventory feature. When predicting the popularity of a product, this solution can automatically predict the popularity of a product based on the sales information and inventory information of the product without relying on management personnel.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device, electronic device and computer-readable storage medium for determining the popularity of a product. Background Art

[0002] Reasonable warehouse management is an important manifestation of warehouse competitiveness. Accurate warehouse management can effectively control and reduce circulation costs and inventory costs. However, the current operation and management of warehouses is extremely dependent on the level of warehouse managers. Relying on the experience of warehouse managers, simple statistical analysis of the sales of goods in the warehouse is performed. Manual analysis lacks reliable and explainable data guidance. Therefore, there is an urgent need for a method that can automatically predict the popularity of goods without relying on the level of managers. Summary of the invention

[0003] The embodiments of the present application provide a method, device, electronic device and computer-readable storage medium for determining the popularity of a product, which can automatically determine the popularity of a product.

[0004] In a first aspect, an embodiment of the present application provides a method for determining the popularity of a product, comprising:

[0005] Obtain sales and inventory information of goods in the warehouse within a preset period of time;

[0006] Determine a first sales feature, a second sales feature, a first inventory feature, and a second inventory feature of the product according to the sales information and the inventory information;

[0007] determining a unit sales volume of the commodity according to the first sales volume feature and the first inventory feature;

[0008] The popularity of the product is determined according to the unit sales volume, the second sales volume feature, and the second inventory feature.

[0009] In some implementations, determining the unit sales volume of the commodity according to the first sales volume feature and the first inventory feature includes:

[0010] Based on the trained first Catboost model, the unit sales volume of the product is determined according to the first sales volume feature and the first inventory feature.

[0011] In some implementations, determining the popularity of the product according to the unit sales volume, the second sales volume feature, and the second inventory feature includes:

[0012] Performing data continuity processing on the number of days that the commodity can be sold in the second inventory feature to obtain a processed second inventory feature;

[0013] Based on a linear weighted product function, the popularity of the product is determined according to the unit sales volume, the second sales volume feature, and the processed second inventory feature.

[0014] In some implementations, determining the popularity of the product according to the unit sales volume, the second sales volume feature, and the second inventory feature includes:

[0015] Dividing the commodity into a first commodity and a second commodity according to a preset ratio;

[0016] For the first commodity, data continuity processing is performed on the number of days the commodity can be sold in the second inventory feature to obtain a processed second inventory feature;

[0017] Based on a linear weighted product function, determining the popularity of the first commodity according to the unit sales volume, the second sales volume feature, and the processed second inventory feature;

[0018] For the second commodity, determining a third sales feature and a third inventory feature according to the sales information and the inventory information;

[0019] Based on the BDP big data platform, a weighted calculation is performed on the third sales feature and the third inventory feature to determine the popularity of the second product.

[0020] In some implementations, before determining the popularity of the product according to the unit sales volume, the second sales volume feature, and the second inventory feature, the method further includes:

[0021] Based on the BDP big data platform, the commodities are filtered according to the sales information to obtain filtered commodities;

[0022] The determining the popularity of the commodity according to the unit sales volume, the second sales volume feature, and the second inventory feature includes:

[0023] The popularity of the filtered products is determined according to the unit sales volume, the second sales volume feature, and the second inventory feature.

[0024] In some implementations, after determining the popularity of the product according to the unit sales volume, the second sales volume feature, and the second inventory feature, the method further includes:

[0025] Based on the trained second Catboost model, the replenishment upper limit of the product is determined according to the popularity of the product, the product sales cycle corresponding to the popularity, the first sales feature, and the first inventory feature.

[0026] In some implementations, after determining the replenishment upper limit of the product according to the popularity of the product, the product sales cycle corresponding to the popularity, the first sales feature, and the first inventory feature, the method further includes:

[0027] A replenishment plan for the commodity is determined according to the unit sales volume and the replenishment upper limit.

[0028] In some implementations, after determining the popularity of the product according to the unit sales volume, the second sales volume feature, and the second inventory feature, the method further includes:

[0029] The commodity space planning of the warehouse is determined according to the popularity of the commodity.

[0030] In a second aspect, the embodiment of the present application further provides a device for determining the popularity of a product, including:

[0031] An acquisition unit, used to acquire sales information and inventory information of commodities in a warehouse within a preset period of time;

[0032] A first determining unit, configured to determine a first sales feature, a second sales feature, a first inventory feature, and a second inventory feature of the commodity according to the sales information and the inventory information;

[0033] a second determining unit, configured to determine a unit sales volume of the commodity according to the first sales volume characteristic and the first inventory characteristic;

[0034] A third determining unit is used to determine the popularity of the product according to the unit sales volume, the second sales volume feature, and the second inventory feature.

[0035] In some implementations, the second determining unit is specifically configured to:

[0036] Based on the trained first Catboost model, the unit sales volume of the product is determined according to the first sales volume feature and the first inventory feature.

[0037] In some implementations, the third determining unit is specifically configured to:

[0038] Performing data continuity processing on the number of days that the commodity can be sold in the second inventory feature to obtain a processed second inventory feature;

[0039] Based on a linear weighted product function, the popularity of the product is determined according to the unit sales volume, the second sales volume feature, and the processed second inventory feature.

[0040] In some implementations, the third determining unit is further specifically configured to:

[0041] Dividing the commodity into a first commodity and a second commodity according to a preset ratio;

[0042] For the first commodity, data continuity processing is performed on the number of days the commodity can be sold in the second inventory feature to obtain a processed second inventory feature;

[0043] Based on a linear weighted product function, determining the popularity of the first commodity according to the unit sales volume, the second sales volume feature, and the processed second inventory feature;

[0044] For the second commodity, determining a third sales feature and a third inventory feature according to the sales information and the inventory information;

[0045] Based on the BDP big data platform, a weighted calculation is performed on the third sales feature and the third inventory feature to determine the popularity of the second product.

[0046] In some embodiments, the device further comprises:

[0047] A filtering unit, used to filter the commodities according to the sales information based on the BDP big data platform to obtain filtered commodities;

[0048] At this time, the third determining unit is specifically used for:

[0049] The popularity of the filtered products is determined according to the unit sales volume, the second sales volume feature, and the second inventory feature.

[0050] In some embodiments, the device further comprises:

[0051] The fourth determining unit is used to determine the replenishment upper limit of the commodity according to the popularity of the commodity, the commodity sales cycle corresponding to the popularity, the first sales feature, and the first inventory feature.

[0052] In some embodiments, the device further comprises:

[0053] A fifth determining unit is used to determine a replenishment plan for the commodity according to the unit sales volume and the replenishment upper limit.

[0054] In some embodiments, the device further comprises:

[0055] The sixth determining unit is used to determine the commodity space planning of the warehouse according to the popularity of the commodity.

[0056] In a third aspect, an embodiment of the present application further provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor calls the computer program in the memory, it executes the steps in any one of the methods for determining the popularity of a commodity provided in the embodiments of the present application.

[0057] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a plurality of instructions, wherein the instructions are suitable for a processor to load to execute the steps in any one of the methods for determining the popularity of a commodity provided in an embodiment of the present application.

[0058] In an embodiment of the present application, a device for determining the popularity of a commodity obtains sales information and inventory information of a commodity in a preset time period in a warehouse; determines a first sales feature, a second sales feature, a first inventory feature, and a second inventory feature of the commodity based on the sales information and the inventory information; determines a unit sales volume of the commodity based on the first sales feature and the first inventory feature; and determines the popularity of the commodity based on the unit sales volume, the second sales feature, and the second inventory feature. This solution can automatically predict the popularity of a commodity based on the sales information and inventory information of the commodity without relying on management personnel when predicting the popularity of the commodity. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0060] Figure 1 This is a schematic diagram of an application scenario of the method for determining the popularity of a product provided in an embodiment of the present application;

[0061] Figure 2 It is a flow chart of a method for determining the popularity of a product provided in an embodiment of the present application;

[0062] Figure 3 is another flow chart of the method for determining the popularity of a product provided in an embodiment of the present application;

[0063] Figure 4 is another flow chart of the method for determining the popularity of a product provided in an embodiment of the present application;

[0064] Figure 5 A schematic diagram of an application scenario for heat calculation provided in an embodiment of the present application;

[0065] Figure 6A schematic diagram of the dynamic adjustment of the upper and lower limits of replenishment provided in an embodiment of the present application;

[0066] Figure 7 It is a structural schematic diagram of a device for determining the popularity of a product provided in an embodiment of the present application;

[0067] Figure 8 is another structural schematic diagram of a device for determining the popularity of a product provided in an embodiment of the present application;

[0068] Fig. 9 It is a structural diagram of a server provided in an embodiment of the present application. DETAILED DESCRIPTION

[0069] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0070] In the following description, the specific embodiments of the present application will be described with reference to the steps and symbols performed by one or more computers, unless otherwise stated. Therefore, these steps and operations will be mentioned several times as being performed by a computer, and the computer execution referred to herein includes the operation of a computer processing unit by an electronic signal representing data in a structured form. This operation converts the data or maintains it at a location in the memory system of the computer, which can be reconfigured or otherwise change the operation of the computer in a manner familiar to testers in the field. The data structure maintained by the data is a physical location in the memory, which has specific characteristics defined by the data format. However, the principles of the present application are described in the above text, which does not represent a limitation, and testers in the field will understand that the various steps and operations described below can also be implemented in hardware.

[0071] The principles of the present application may be operated using many other general or specific purpose computing, communication environments or configurations. Examples of well-known computing systems, environments and configurations suitable for use with the present application may include, but are not limited to, handheld phones, personal computers, servers, multiprocessor systems, microcomputer-based systems, mainframe computers, and distributed computing environments, including any of the above systems or devices.

[0072] The terms "first", "second", and "third" in this application are used to distinguish different objects rather than to describe a specific order. In addition, the terms "include", "have", and any variations thereof are intended to cover non-exclusive inclusions.

[0073] The executor of the method for determining the popularity of a product may be the device for determining the popularity of a product provided in the embodiment of the present application, or an electronic device integrating the device for determining the popularity of a product, wherein the device for determining the popularity of a product may be implemented in hardware or software, the electronic device may be a server or a terminal, and the terminal may be a smart phone, a tablet computer, a PDA, or a laptop computer, etc.

[0074] See also Figure 1 , Figure 1 This is a schematic diagram of an application scenario of the method for determining the popularity of a product in an embodiment of the present application. First, the user can set the sales cycle of each popular product (i.e., the length of time that different popular products can be sold after one replenishment) through the warehouse performance management (WPM) system, and then push the required data to the Mysql database of the data visualization platform (DVP) through the big data platform (BDP). The computing cloud obtains the data in the Mysql database through the interface, calculates the popularity of the product, etc. on the computing cloud platform according to the python algorithm package, and returns the calculation results to the WPM system, so that the user can obtain the calculation results through the WPM system.

[0075] See also Figure 2 , Figure 2 : is a flow chart of a method for determining the popularity of a product provided in an embodiment of the present application. The method for determining the popularity of a product may include:

[0076] 201. Obtain sales information and inventory information of goods in the warehouse within a preset period of time.

[0077] In the embodiment of the present application, the unit of the commodity is a stock keeping unit (sku), and the duration of the preset period can be 3 months. The duration can be set by the user and is not specifically limited here.

[0078] Among them, the sales information in this embodiment can be the outbound order details and the outbound order product details, and the inventory information can be the inventory product details, and the inventory product details include the quantity of the product and the warehousing time of the product.

[0079] 202. Determine a first sales feature, a second sales feature, a first inventory feature, and a second inventory feature of the product according to the sales information and the inventory information.

[0080] In this embodiment, the first sales feature includes: the historical sales value, mean, variance, extreme value, quantile and sales change of the product within a preset time period; the second sales feature includes: the historical sales value, frequency, mean and sales share of the product within the preset time period; the first inventory feature includes: the available inventory of the product; the second inventory feature includes: the available inventory of the product, the number of days the product can be sold and the time the product entered the warehouse.

[0081] 203. Determine the unit sales volume of the product according to the first sales volume characteristic and the first inventory characteristic.

[0082] Specifically, based on the trained first Catboost model, the unit sales volume of the product is determined according to the first sales volume feature and the first inventory feature.

[0083] In this embodiment, when a replenishment plan is subsequently formulated for the goods, it is necessary to combine the unit sales volume. The unit sales volume is the minimum inventory of the goods (that is, the replenishment lower limit mentioned in this application). For example, the sales volume of the goods in one day. When the number of goods in the warehouse is lower than the unit sales volume, replenishment will begin to avoid product shortages due to untimely replenishment.

[0084] 204. Determine the popularity of the product according to the unit sales volume, the second sales volume feature, and the second inventory feature.

[0085] Specifically, determining the popularity of the product according to the unit sales volume, the second sales volume feature, and the second inventory feature includes:

[0086] The data continuity processing is performed on the number of days that the commodity in the second inventory feature can be sold, so as to obtain the processed second inventory feature; then based on the linear weighted product function, the popularity of the commodity is determined according to the unit sales volume, the second sales feature and the processed second inventory feature.

[0087] In some embodiments, before determining the popularity of the product according to the unit sales volume, the second sales volume feature, and the second inventory feature, the method further includes: filtering the product according to the sales volume information based on the BDP big data platform to obtain filtered products;

[0088] At this time, determining the popularity of the product according to the unit sales volume, the second sales volume feature, and the second inventory feature includes: determining the popularity of the filtered product according to the unit sales volume, the second sales volume feature, and the second inventory feature.

[0089] In some embodiments, the popularity of the product is determined based on the unit sales volume, the second sales volume characteristic and the second inventory characteristic, including: dividing the product into a first product and a second product according to a preset ratio; for the first product, performing data continuity processing on the number of days the product can be sold in the second inventory characteristic to obtain a processed second inventory characteristic; based on a linear weighted product function, determining the popularity of the first product based on the unit sales volume, the second sales volume characteristic and the processed second inventory characteristic; for the second product, determining a third sales volume characteristic and a third inventory characteristic based on the sales volume information and the inventory information; based on the BDP big data platform, performing weighted calculation on the third sales volume characteristic and the third inventory characteristic to determine the popularity of the second product.

[0090] In some embodiments, based on the trained second Catboost model, the upper limit of replenishment of the product is determined according to the popularity of the product, the product sales cycle corresponding to the popularity, the first sales feature, and the first inventory feature.

[0091] Among them, the replenishment upper limit is the maximum inventory quantity of the product.

[0092] In this embodiment, it is also necessary to determine a replenishment plan for the product based on the unit sales volume and the replenishment upper limit, that is, when the quantity of the product in the warehouse is lower than the unit sales volume, the replenishment personnel are reminded to replenish the product, wherein the total inventory of the product in the warehouse after replenishment does not exceed the replenishment upper limit.

[0093] In some embodiments, the commodity space planning of the warehouse is also determined according to the popularity of the commodity. Reasonable layout of the warehouse space can reduce the costs caused by frequent changes in storage locations and in-and-out transportation.

[0094] In the embodiment of the present application, the device for determining the popularity of a commodity obtains the sales information and inventory information of the commodity in the warehouse within a preset period of time; determines the first sales feature, the second sales feature, the first inventory feature, and the second inventory feature of the commodity based on the sales information and the inventory information; determines the unit sales volume of the commodity based on the first sales feature and the first inventory feature; and determines the popularity of the commodity based on the unit sales volume, the second sales feature, and the second inventory feature. When predicting the popularity of a commodity, this solution can automatically predict the popularity of the commodity based on the sales information and inventory information of the commodity without relying on management personnel.

[0095] The method for determining the popularity of a product described in the above embodiment will be further described below.

[0096] Please refer to Figure 3 , Figure 3 Another flow chart of the method for determining the popularity of a product provided in an embodiment of the present application. The method for determining the popularity of a product can be applied to a server, such as Figure 3 As shown, the process of the method for determining the popularity of the product can be as follows:

[0097] 301. The server obtains sales information and inventory information of the goods in the warehouse within a preset period of time.

[0098] The sales information in this embodiment can be the details of the outbound delivery order and the details of the goods in the outbound delivery order, and the inventory information can be the details of the inventory goods. The inventory goods details include the quantity of the goods and the time when the goods entered the warehouse. The unit of the goods is sku. The duration of the preset time period can be 3 months, and the duration can be set by the user. There is no specific limitation here.

[0099] In this embodiment, after obtaining the sales information and inventory information of the goods, it is also necessary to preprocess the acquired data. Specifically, the data can be preprocessed through a time order statistics screening module, a SKU statistics screening module, a dimension information filling module, a complete time filling module, a missing value processing module, a promotion marking module, a blank window marking module (lower limit processing) and a time feature processing module.

[0100] 302. The server filters the product based on the sales information based on the BDP big data platform.

[0101] In this embodiment, a portion of the products will be filtered out on the BDP big data platform first, and the popularity level of the filtered products will be set to the lowest popularity level. For example, when the popularity levels include A, B, C and D, the filtered products will be directly classified as D popularity.

[0102] The specific filtering method is:

[0103] The BDP big data platform obtains the sales information of the product within the preset time period, determines the maximum sales value, average sales value and frequency of the product based on the sales information, and then determines whether the maximum sales value, average sales value and frequency meet the requirements (for example, the maximum sales value is greater than the preset sales value, the average sales value is greater than the preset average sales value and the frequency is greater than the preset frequency). If a product meets all the requirements, the product will not be filtered. If it does not meet all the requirements, the product needs to be filtered and the popularity of the product is determined to be the lowest category popularity.

[0104] 303. The server determines a first sales feature, a second sales feature, a first inventory feature, and a second inventory feature of the product according to the sales information and the inventory information.

[0105] In this embodiment, the first sales feature includes: the historical sales value, mean, variance, extreme value, quantile and sales change of the product within a preset time period; the second sales feature includes: the historical sales value, frequency, mean and sales share of the product within the preset time period; the first inventory feature includes: the available inventory of the product; the second inventory feature includes: the available inventory of the product, the number of days the product can be sold and the time the product entered the warehouse.

[0106] 304. The server determines the unit sales volume of the product based on the trained first Catboost model, the first sales volume feature, and the first inventory feature.

[0107] Among them, the unit sales volume is the minimum inventory quantity of the product. When the inventory quantity of the product is lower than the minimum inventory quantity, the staff will be reminded to replenish the product.

[0108] In some embodiments, in addition to determining the unit sales volume of the product based on the first sales feature and the first inventory feature, the trained first Catboost model also determines the unit sales volume of the product based on the unit prediction value of the product, the first sales feature, and the first inventory feature, wherein the unit prediction value is a unit sales volume preliminarily predicted based on the product.

[0109] 305. The server performs data continuity processing on the number of days the commodity can be sold in the second inventory feature to obtain a processed second inventory feature.

[0110] Specifically, the sigmoid function is used to process the data continuity of the number of days that a product can be sold, and the saleable time is converted into probability. The conversion formula is: Here, x is the number of days the product can be sold.

[0111] 306. The server determines the popularity of the product based on a linear weighted product function, according to the unit sales volume, the second sales volume feature, and the processed second inventory feature.

[0112] Specifically, each numerical value in the unit sales volume, the second sales volume feature, and the processed second inventory feature has a corresponding weight. This embodiment performs weighted product calculation on these numerical values ​​according to the corresponding weights, and determines the popularity of the product based on the obtained result.

[0113] Specifically, in some embodiments, after calculating the weighted product results of each commodity, the results are sorted from large to small, and the commodities corresponding to the first 10% of the results are determined as Class A hot commodities, the commodities in the range of the first 10% to 40% are determined as Class B hot commodities, and then the commodities after 40% are determined as Class C hot commodities.

[0114] 307. The server determines the replenishment upper limit of the product based on the trained second Catboost model, according to the popularity of the product, the product sales cycle corresponding to the popularity, the first sales feature, and the first inventory feature.

[0115] The replenishment upper limit quantity is the maximum inventory quantity of the commodity, which corresponds to the unit sales quantity (replenishment lower limit value) mentioned in this embodiment.

[0116] In some embodiments, the trained second Catboost model determines the upper replenishment limit of the product based on the popularity of the product, the product sales cycle corresponding to the popularity, the first sales feature, and the first inventory feature, and also determines the unit sales volume of the product based on the upper limit prediction value of the product, wherein the upper limit prediction value is an upper limit sales volume initially predicted based on the product, wherein the upper limit sales volume may be the total sales volume estimated for the product within the product sales cycle corresponding to the popularity of the product.

[0117] Among them, steps 304 to 307 in this embodiment are implemented based on the python algorithm package.

[0118] 308. The server determines a replenishment plan for the product based on the unit sales volume and the replenishment upper limit.

[0119] Specifically, in a product replenishment plan, when the inventory of a product is lower than the unit sales volume, the staff is reminded to replenish the product, and after replenishment, the total inventory of the product does not exceed the replenishment upper limit of the product.

[0120] At this time, the staff does not need to decide the quantity and time of replenishment based on the on-site situation and experience. Therefore, this solution can also solve the problems of frequent replenishment due to insufficient replenishment quantity and long-term occupation of picking area space due to excessive replenishment quantity.

[0121] 309. The server determines the commodity space planning of the warehouse according to the popularity of the commodity.

[0122] Specifically, the commodity space planning of the warehouse is determined according to the popularity of the commodity, including:

[0123] The shelf space information of the warehouse is obtained, and then the commodity space planning of the warehouse is determined according to the popularity of the commodity and the shelf space information. Specifically, the popular commodities are placed in a location that is easy to be shipped out and stored.

[0124] Therefore, this solution can reasonably plan the storage layout of the goods according to their different conditions, reducing the labor costs caused by frequent changes in storage locations and in-and-out transportation.

[0125] There is no restriction on the order of execution of step 308 and step 309 , that is, step 309 may be executed before step 308 or simultaneously with step 309 .

[0126] In the embodiment of the present application, the device for determining the popularity of a commodity obtains the sales information and inventory information of the commodity in the warehouse within a preset period of time; determines the first sales feature, the second sales feature, the first inventory feature, and the second inventory feature of the commodity based on the sales information and the inventory information; determines the unit sales volume of the commodity based on the first sales feature and the first inventory feature; and determines the popularity of the commodity based on the unit sales volume, the second sales feature, and the second inventory feature. When predicting the popularity of a commodity, this solution can automatically predict the popularity of the commodity based on the sales information and inventory information of the commodity without relying on management personnel.

[0127] Please refer to Figure 4 , Figure 4 Another flow chart of the method for determining the popularity of a product provided in an embodiment of the present application. The method for determining the popularity of a product can be applied to a server. In this embodiment, in order to reduce the amount of calculation of the python algorithm package, the popularity is predicted in combination with the BDP big data platform during the popularity calculation. Figure 4 As shown, the process of the method for determining the popularity of the product can be as follows:

[0128] 401. The server obtains sales information and inventory information of the goods in the warehouse within a preset period of time.

[0129] 402. The server filters the product based on the sales information based on the BDP big data platform.

[0130] 403. The server determines a first sales feature, a second sales feature, a first inventory feature, and a second inventory feature of the product according to the sales information and the inventory information.

[0131] 404. The server determines the unit sales volume of the product based on the trained first Catboost model, the first sales volume feature, and the first inventory feature.

[0132] In this embodiment, steps 401 to 404 are Figure 3 Steps 301 to 304 in the corresponding embodiment are similar and will not be described in detail here.

[0133] 405. The server divides the product into a first product and a second product according to a preset ratio.

[0134] The preset ratio of the first product and the second product may be 7:3, or other ratios may be set according to specific cases. The specific value of the ratio is not limited here.

[0135] 406. For the first commodity, the server performs data continuity processing on the commodity saleable days in the second inventory feature to obtain a processed second inventory feature.

[0136] 407. The server determines the popularity of the first product based on a linear weighted product function according to the unit sales volume, the second sales volume feature, and the processed second inventory feature.

[0137] In this embodiment, steps 406 to 407 are Figure 3 Steps 305 to 306 in the corresponding embodiment are similar and will not be described in detail here.

[0138] 408. For the second product, the server determines a third sales feature and a third inventory feature according to the sales information and the inventory information.

[0139] In this embodiment, the third sales feature includes: the historical sales value and average value of the second commodity within a preset time period, and the third inventory feature includes the available inventory of the second commodity and the warehousing time of the second commodity.

[0140] 409. The server performs weighted calculation on the third sales feature and the third inventory feature based on the BDP big data platform to determine the popularity of the second product.

[0141] In this embodiment, each value in the third sales feature and the third inventory feature is preset with a corresponding weight. This embodiment performs weighted calculation based on the third sales feature, the third inventory feature and the corresponding weight to obtain the popularity of the second product.

[0142] In some embodiments, the specific steps of performing weighted calculation according to the third sales feature, the third inventory feature and the corresponding weight to obtain the popularity of the second product are:

[0143] After weighted calculation based on the third sales feature, the third inventory feature and the corresponding weights, the popularity score of each product is obtained, and then the products are sorted from large to small according to the size of the popularity value, and the top 50 products are determined as Class A popular products, and the products whose scores after sorting account for 60% (that is, the product popularity score accounts for 60% of the total popularity score) are determined as Class A popular products, and the products whose scores after sorting account for 60%-90% are determined as Class B popular products, and the remaining products are determined as Class C popular products.

[0144] Among them, a schematic diagram of an application scenario of the heat calculation in the method for determining the heat of a product in this solution is as follows Figure 5 As shown, in this scenario, the preset time period is 30 days, and the sales information and inventory information are obtained based on historical outbound information, historical inbound information and current inventory information.

[0145] 410. The server determines the replenishment upper limit of the product based on the trained second Catboost model, according to the popularity of the product, the product sales cycle corresponding to the popularity, the first sales feature, and the first inventory feature.

[0146] 411. The server determines a replenishment plan for the product based on the unit sales volume and the replenishment upper limit.

[0147] 412. The server determines the commodity space planning of the warehouse according to the popularity of the commodity.

[0148] In this embodiment, steps 410 to 412 are Figure 3 Steps 307 to 309 in the corresponding embodiment are similar and will not be described in detail here.

[0149] In the embodiment of the present application, the device for determining the popularity of a commodity obtains the sales information and inventory information of the commodity in the warehouse within a preset period of time; determines the first sales feature, the second sales feature, the first inventory feature, and the second inventory feature of the commodity based on the sales information and the inventory information; determines the unit sales volume of the commodity based on the first sales feature and the first inventory feature; and determines the popularity of the commodity based on the unit sales volume, the second sales feature, and the second inventory feature. When predicting the popularity of a commodity, this solution can automatically predict the popularity of the commodity based on the sales information and inventory information of the commodity without relying on management personnel.

[0150] like Figure 6 As shown, Figure 6 A schematic diagram of dynamic adjustment of replenishment upper and lower limits is provided for an embodiment of the present application. In the subsequent replenishment process using the calculation results of the upper and lower limits, the warehouse can adjust the upper and lower limits (replenishment upper limit and replenishment lower limit) according to the utilization rate of the warehouse picking area storage space and the proportion of urgent replenishment tasks, wherein the replenishment lower limit is the unit sales volume, and the replenishment upper limit is the replenishment upper limit quantity, thereby achieving the function of feedback regression adjustment.

[0151] In order to facilitate better implementation of the method for determining the popularity of a product provided in the embodiment of the present application, the embodiment of the present application also provides a device based on the above method for determining the popularity of a product. The meanings of the terms are the same as those in the above method for determining the popularity of a product, and the specific implementation details can refer to the description in the method embodiment.

[0152] See also Figure 7 , Figure 7 A schematic diagram of the structure of a device for determining the popularity of a product provided in an embodiment of the present application, wherein the device 700 for determining the popularity of a product may include an acquisition unit 701, a first determination unit 702, a second determination unit 703, and a third determination unit 704, etc.

[0153] in,

[0154] The acquisition unit 701 is used to acquire the sales information and inventory information of the goods in the warehouse within a preset period of time;

[0155] A first determining unit 702 is used to determine a first sales feature, a second sales feature, a first inventory feature, and a second inventory feature of the commodity according to the sales information and the inventory information;

[0156] A second determining unit 703, configured to determine a unit sales volume of the commodity according to the first sales volume feature and the first inventory feature;

[0157] The third determining unit 704 is used to determine the popularity of the product according to the unit sales volume, the second sales volume feature, and the second inventory feature.

[0158] In some implementations, the second determining unit 703 is specifically configured to:

[0159] Based on the trained first Catboost model, the unit sales volume of the product is determined according to the first sales volume feature and the first inventory feature.

[0160] In some implementations, the third determining unit 704 is specifically configured to:

[0161] Performing data continuity processing on the number of days that the commodity can be sold in the second inventory feature to obtain a processed second inventory feature;

[0162] Based on a linear weighted product function, the popularity of the product is determined according to the unit sales volume, the second sales volume feature, and the processed second inventory feature.

[0163] In some implementations, the third determining unit 704 is further specifically configured to:

[0164] Dividing the commodity into a first commodity and a second commodity according to a preset ratio;

[0165] For the first commodity, data continuity processing is performed on the number of days the commodity can be sold in the second inventory feature to obtain a processed second inventory feature;

[0166] Based on a linear weighted product function, determining the popularity of the first commodity according to the unit sales volume, the second sales volume feature, and the processed second inventory feature;

[0167] For the second commodity, determining a third sales feature and a third inventory feature according to the sales information and the inventory information;

[0168] Based on the BDP big data platform, a weighted calculation is performed on the third sales feature and the third inventory feature to determine the popularity of the second product.

[0169] like Figure 8 As shown, in some embodiments, the device 600 further includes:

[0170] A filtering unit 705 is used to filter the commodities according to the sales information based on the BDP big data platform to obtain filtered commodities;

[0171] At this time, the third determining unit 704 is specifically used to:

[0172] The popularity of the filtered products is determined according to the unit sales volume, the second sales volume feature, and the second inventory feature.

[0173] In some embodiments, the apparatus 700 further comprises:

[0174] The fourth determining unit 706 is used to determine the replenishment upper limit of the commodity according to the popularity of the commodity, the commodity sales cycle corresponding to the popularity, the first sales feature, and the first inventory feature.

[0175] In some embodiments, the apparatus 700 further comprises:

[0176] The fifth determining unit 707 is configured to determine a replenishment plan for the commodity according to the unit sales volume and the replenishment upper limit.

[0177] In some embodiments, the apparatus 700 further comprises:

[0178] The sixth determining unit 708 is configured to determine the commodity space planning of the warehouse according to the popularity of the commodity.

[0179] In the embodiment of the present application, the acquisition unit 701 acquires the sales information and inventory information of the commodity in the warehouse within a preset period of time; the first determination unit 702 determines the first sales feature, the second sales feature, the first inventory feature and the second inventory feature of the commodity according to the sales information and the inventory information; the second determination unit 703 determines the unit sales volume of the commodity according to the first sales feature and the first inventory feature; the third determination unit 704 determines the popularity of the commodity according to the unit sales volume, the second sales feature and the second inventory feature. When predicting the popularity of a commodity, this solution can automatically predict the popularity of the commodity according to the sales information and inventory information of the commodity without relying on management personnel.

[0180] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0181] refer to Fig. 9 The embodiment of the present application provides a server 900, which may include one or more processing core processors 901, one or more computer-readable storage media memories 902, radio frequency (RF) circuits 903, power supplies 904, input units 905, and display units 906. Those skilled in the art will appreciate that Fig. 9 The server structure shown in the figure does not constitute a limitation on the server, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. Among them:

[0182] The processor 901 is the control center of the server, and uses various interfaces and lines to connect various parts of the entire server. By running or executing software programs and / or modules stored in the memory 902, and calling data stored in the memory 902, the processor 901 performs various functions of the server and processes data, thereby monitoring the server as a whole. Optionally, the processor 901 may include one or more processing cores; preferably, the processor 901 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 901.

[0183] The memory 902 may be used to store software programs and modules. The processor 901 executes various functional applications and data processing by running the software programs and modules stored in the memory 902 .

[0184] The RF circuit 903 may be used for receiving and sending signals during the process of sending and receiving information.

[0185] The server also includes a power supply 904 (such as a battery) for supplying power to various components. Preferably, the power supply can be logically connected to the processor 901 through a power management system, so that the power management system can manage charging, discharging, power consumption and other functions.

[0186] The server may further include an input unit 905, which may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0187] The server may also include a display unit 906, which may be used to display information input by a user or information provided to a user and various graphical user interfaces of the server, which may be composed of graphics, text, icons, videos, and any combination thereof. Specifically in this embodiment, the processor 901 in the server will load the executable files corresponding to the processes of one or more applications into the memory 902 according to the following instructions, and the processor 901 will run the applications stored in the memory 902, thereby realizing various functions, as follows:

[0188] Obtain sales and inventory information of goods in the warehouse within a preset period of time;

[0189] Determine a first sales feature, a second sales feature, a first inventory feature, and a second inventory feature of the product according to the sales information and the inventory information;

[0190] determining a unit sales volume of the commodity according to the first sales volume feature and the first inventory feature;

[0191] The popularity of the product is determined according to the unit sales volume, the second sales volume feature, and the second inventory feature.

[0192] In the above embodiments, the description of each embodiment has its own focus. For the parts that are not described in detail in a certain embodiment, please refer to the detailed description of the method for determining the popularity of a product above, and will not be repeated here.

[0193] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0194] To this end, an embodiment of the present application provides a computer-readable storage medium, in which a plurality of instructions are stored, and the instructions can be loaded by a processor to execute the steps in any one of the methods for determining the popularity of a commodity provided in the embodiment of the present application. For example, the instructions can execute the following steps:

[0195] Obtain sales and inventory information of goods in the warehouse within a preset period of time;

[0196] Determine a first sales feature, a second sales feature, a first inventory feature, and a second inventory feature of the product according to the sales information and the inventory information;

[0197] determining a unit sales volume of the commodity according to the first sales volume feature and the first inventory feature;

[0198] The popularity of the product is determined according to the unit sales volume, the second sales volume feature, and the second inventory feature.

[0199] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0200] The computer-readable storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0201] Since the instructions stored in the computer-readable storage medium can execute the steps in any method for determining the popularity of a product provided in the embodiments of the present application, the beneficial effects that can be achieved by any method for determining the popularity of a product provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0202] The above is a detailed introduction to a method, device, electronic device and computer-readable storage medium for determining the popularity of a commodity provided in an embodiment of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for determining the popularity of a product, characterized in that: include: Obtain sales and inventory information of goods in the warehouse within a preset period of time; Determine a first sales feature, a second sales feature, a first inventory feature, and a second inventory feature of the product according to the sales information and the inventory information; determining a unit sales volume of the commodity according to the first sales volume feature and the first inventory feature; determining the popularity of the product according to the unit sales volume, the second sales volume feature, and the second inventory feature; The determining the popularity of the commodity according to the unit sales volume, the second sales volume feature, and the second inventory feature includes: Performing data continuity processing on the number of days that the commodity can be sold in the second inventory feature to obtain a processed second inventory feature; Based on a linear weighted product function, the popularity of the product is determined according to the unit sales volume, the second sales volume feature, and the processed second inventory feature.

2. The method according to claim 1, characterized in that The determining the unit sales volume of the commodity according to the first sales volume characteristic and the first inventory characteristic includes: Based on the trained first Catboost model, the unit sales volume of the product is determined according to the first sales volume feature and the first inventory feature.

3. The method according to claim 1, characterized in that The determining the popularity of the commodity according to the unit sales volume, the second sales volume feature, and the second inventory feature includes: Dividing the commodity into a first commodity and a second commodity according to a preset ratio; For the first commodity, data continuity processing is performed on the number of days the commodity can be sold in the second inventory feature to obtain a processed second inventory feature; Based on a linear weighted product function, determining the popularity of the first commodity according to the unit sales volume, the second sales volume feature, and the processed second inventory feature; For the second commodity, determining a third sales feature and a third inventory feature according to the sales information and the inventory information; Based on the BDP big data platform, a weighted calculation is performed on the third sales feature and the third inventory feature to determine the popularity of the second product.

4. The method according to claim 1, characterized in that: Before determining the popularity of the commodity according to the unit sales volume, the second sales volume feature, and the second inventory feature, the method further includes: Based on the BDP big data platform, the commodities are filtered according to the sales information to obtain filtered commodities; The determining the popularity of the commodity according to the unit sales volume, the second sales volume feature, and the second inventory feature includes: The popularity of the filtered products is determined according to the unit sales volume, the second sales volume feature, and the second inventory feature.

5. The method according to claim 1, characterized in that After determining the popularity of the commodity according to the unit sales volume, the second sales volume feature, and the second inventory feature, the method further includes: Based on the trained second Catboost model, the replenishment upper limit of the product is determined according to the popularity of the product, the product sales cycle corresponding to the popularity, the first sales feature, and the first inventory feature.

6. The method according to claim 5, characterized in that After determining the replenishment upper limit of the commodity according to the popularity of the commodity, the commodity sales cycle corresponding to the popularity, the first sales feature, and the first inventory feature, the method further includes: A replenishment plan for the commodity is determined according to the unit sales volume and the replenishment upper limit.

7. The method according to any one of claims 1 to 6, characterized in that: After determining the popularity of the commodity according to the unit sales volume, the second sales volume feature, and the second inventory feature, the method further includes: The commodity space planning of the warehouse is determined according to the popularity of the commodity.

8. A device for determining the popularity of a commodity, characterized in that: include: An acquisition unit, used to acquire sales information and inventory information of commodities in a warehouse within a preset period of time; A first determining unit, configured to determine a first sales feature, a second sales feature, a first inventory feature, and a second inventory feature of the commodity according to the sales information and the inventory information; a second determining unit, configured to determine a unit sales volume of the commodity according to the first sales volume characteristic and the first inventory characteristic; a third determining unit, configured to determine the popularity of the commodity according to the unit sales volume, the second sales volume feature, and the second inventory feature; The third determining unit is further used to perform data continuity processing on the number of days the commodity can be sold in the second inventory feature to obtain a processed second inventory feature; Based on a linear weighted product function, the popularity of the product is determined according to the unit sales volume, the second sales volume feature, and the processed second inventory feature.

9. An electronic device, characterized in that: It comprises a processor and a memory, wherein the memory stores a computer program, and when the processor calls the computer program in the memory, the method for determining the popularity of a commodity as claimed in any one of claims 1 to 7 is executed.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute the method for determining the heat of a commodity according to any one of claims 1 to 7.

Images