Commodity pool optimization method and system, storage medium and commodity pool optimization terminal

Abstract

The invention provides a commodity pool optimization method and system, a storage medium and a commodity pool optimization terminal, and the method comprises the following steps: obtaining daily store dimension sales data of a commodity, and obtaining a commodity power index based on the daily store dimension sales data; obtaining commodity pool commodity elimination scores of the commodities based on the commodity force indexes, and eliminating end commodities based on the commodity elimination scores; and obtaining a homogeneous store group of the target store, and realizing commodity renewal based on the homogeneous store group and the number of eliminated commodities. According to the commodity pool optimization method and system, the storage medium and the commodity pool optimization terminal, elimination and renewal of the commodities in the commodity pool are realized through the commodity power index and the commodity difference index, so that the commodity efficiency and the sales amount are effectively improved.

Description

Technical Field

[0001] This invention belongs to the technical field of data processing, and in particular relates to a product pool optimization method, system, storage medium, and product pool optimization terminal. Background Technology

[0002] In e-commerce and retail scenarios, with limited product display space and shelf space, a more precise and scientific assessment of the product's competitiveness and the overall decision-making regarding product placement and removal are crucial for businesses seeking to increase sales and gross profit. By leveraging product exposure in display areas and on shelves, and analyzing user purchase data, businesses can meticulously calculate the economic benefits of individual products. This allows for the elimination of end-products and the introduction of internal and external opportunistic products, ultimately achieving better sales gains and product turnover performance with the same sales resources.

[0003] However, the existing technology for replacing outdated products with new ones has the following problems:

[0004] (1) Only considering gross profit, without eliminating interfering factors in the evaluation of product strength, such as sales opportunities, sales anomalies, promotions, fake orders, stockouts, and store weight;

[0005] (2) The model was not modeled from the consumer's perspective as a whole, and the overall demand coverage of consumers was not considered, such as demand characteristics such as brand, specification range, price range, and function.

[0006] (3) Product recommendations did not take into account the differences in consumer profiles and consumption characteristics in a detailed manner;

[0007] (4) The constraints of shelf space resources were not considered.

[0008] Therefore, existing technologies lack sophisticated and scientific evaluation methods for product category elimination; for new product launches, business operations often have vague frameworks and ideas, and there are no digitized indicators to be transformed into operable system algorithm processes, resulting in low efficiency of multi-department collaboration and difficulty in improving product quality and performance. Summary of the Invention

[0009] The purpose of this invention is to provide a product pool optimization method, system, storage medium, and product pool optimization terminal, which realizes the elimination and addition of products in the product pool through product strength index and product differentiation index, thereby effectively improving product efficiency and sales.

[0010] In a first aspect, the present invention provides a product pool optimization method, the method comprising the following steps: obtaining daily store-level sales data of products, obtaining product strength indicators based on the daily store-level sales data; obtaining product elimination scores for products in the product pool based on the product strength indicators, and eliminating end-stage products based on the product elimination scores; obtaining a group of homogeneous stores of the target store, and launching new products based on the group of homogeneous stores and the number of eliminated products.

[0011] In one implementation of the first aspect, the daily store-level sales data includes the product's sales revenue, gross profit, sales volume, order volume, discount amount, and whether it is out of stock.

[0012] Obtaining product performance indicators based on the aforementioned daily store sales data includes the following steps:

[0013] Calculate the updated sales revenue p' sale =p sale -p prom , where p sale p represents the sales amount. prom This indicates the amount of the discount;

[0014] Calculate the updated gross profit p' gm =p gm -p prom , where p gm This indicates the gross profit margin;

[0015] Delete the daily store-level sales data that is fraudulent and obtain valid daily store-level sales data; fraudulent sales refer to the ratio of sales volume to order volume being less than a preset threshold when there is no stock shortage.

[0016] Aggregate the effective daily store-level sales data by store and date within the statistical interval to obtain a sample set of sales revenue after removing abnormal sales data;

[0017] For the aforementioned sales volume sample set, select the sales volume of the store with the largest sales volume. As a benchmark for adjustment, the target adjusted store sales volume is... Obtain adjusted sales figures

[0018] Obtain the commodity strength index g i =(p' s ' ale ,p' g ' m ,p perm ), where p' g ' m This represents the gross profit within the statistical interval.

[0019] In one implementation of the first aspect, the sample set of sales revenue after removing abnormal sales data includes:

[0020] Effective daily store sales data are excluded from [Q1-1.5*IQR, Q3+1.5*IQR], where Q1 is the first quartile of the sales distribution, Q3 is the third quartile of the sales distribution, and IQR = Q3-Q1.

[0021] In one implementation of the first aspect, obtaining the product elimination score of the product pool based on the product strength index includes the following steps:

[0022] The attributes of the products are divided into categorical variables and continuous variables;

[0023] For the categorical variables, calculate the categorical variable dissimilarity of product i. Where r i,v =1-d i,v v represents a product attribute, V represents the set of product attributes, and d i,v This indicates the percentage of SKUs with the same attributes as product i in the product pool;

[0024] For the continuous variable, calculate the degree of variability of the numerical variable for product i. in v i This represents the distance between product i and other products of the same category currently on sale.

[0025] according to Calculate the product pool elimination score for each product, where α and β represent weights. These represent the normalized values ​​of the commodity strength index and the categorical variable difference / numerical variable difference for commodity i, respectively.

[0026] In one implementation of the first aspect, eliminating end-stage products based on the product elimination score includes the following steps:

[0027] Set a product rejection rate;

[0028] Starting from the last item in the product elimination score of the product pool, the corresponding product is eliminated based on the elimination rate.

[0029] In one implementation of the first aspect, acquiring a group of homogeneous stores and launching new products based on the group of homogeneous stores and the number of obsolete products includes the following steps:

[0030] Obtain the user profile feature vector and the consumer product category distribution feature vector of the consumer group;

[0031] One-hot encoding is performed on the categorical variables in the user profile feature vector and the consumer product category distribution feature vector, and continuous variables are normalized to obtain effective variables.

[0032] The effective variables are clustered using the k-means clustering algorithm to obtain homogeneous store groups.

[0033] For the products in the homogeneous store group, a product recommendation ranking is generated based on the product elimination score of the product pool;

[0034] Based on the product recommendation ranking, select the number of eliminated products to add new products.

[0035] In one implementation of the first aspect, clustering the effective variables based on the k-means clustering algorithm to obtain a homogeneous store group includes the following steps:

[0036] If the number of homogeneous store groups obtained by clustering is less than a preset value, the similarity between the target store and the candidate stores in the same area is calculated, and the top-N candidate stores in the same area with the highest similarity are selected to enter the homogeneous store group.

[0037] Secondly, the present invention provides a product pool optimization system, the system comprising an acquisition module, an elimination module, and a new product addition module;

[0038] The acquisition module is used to acquire daily store-level sales data of the product, and to acquire product performance indicators based on the daily store-level sales data;

[0039] The elimination module is used to obtain the product elimination score of the product pool based on the product strength index, and to eliminate the end products based on the product elimination score;

[0040] The new product module is used to obtain a group of similar stores of the target store, and to add new products based on the group of similar stores and the number of eliminated products.

[0041] Thirdly, the present invention provides a product pool optimization terminal, the product pool optimization terminal comprising: a processor and a memory; the memory for storing a computer program; the processor for executing the computer program stored in the memory, so that the product pool optimization terminal performs the above-described product pool optimization method.

[0042] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a product pool optimization terminal, implements the above-described product pool optimization method.

[0043] As described above, the product pool optimization method, system, storage medium, and product pool optimization terminal of the present invention have the following beneficial effects:

[0044] (1) Taking into account the confusing factors that affect the evaluation of product strength, the factors such as sales opportunities, sales anomalies, promotions, order brushing, stockouts, and store size of distribution stores are eliminated or corrected in the product level sales data, and a fair product strength evaluation system under the normalized evaluation standard is established.

[0045] (2) Under the constraints of shelf space and elimination business rules, further consider the differences in segmented demand between single products and product pools in terms of brand, specification range and price range to ensure the richness of the existing product pool category structure. Calculate the product strength of products under the category and the comprehensive score of elimination of single products and category product pool differences, and give the elimination rate of products under the category to carry out the elimination of the last-ranked products.

[0046] (3) Construct homogeneous store groups based on the user profile feature vector of consumer groups and the distribution feature vector of consumer categories. Calculate the new product recommendation score within the homogeneous store group based on the product strength evaluation system and product difference model. Extract all-star products and sort them in order. Under the constraints of the number of distributed products and the business rules for introducing new products, recommend new products that have not yet been distributed in the target store or unit in order.

[0047] (4) Intelligently complete the replacement of products with poor product performance and redundant product categories, and introduce products with opportunities, so as to efficiently help improve product efficiency and increase sales. Attached Figure Description

[0048] Figure 1 The diagram shown is a structural schematic of the commodity pool optimization terminal according to an embodiment of the present invention.

[0049] Figure 2 The flowchart shown is a sample pool optimization method according to an embodiment of the present invention;

[0050] Figure 3 The diagram shown is a schematic diagram of an embodiment of the present invention, illustrating the implementation of new product launches based on the homogeneous store group and the number of obsolete products.

[0051] Figure 4 The diagram shown is a structural schematic of the commodity pool optimization system according to an embodiment of the present invention;

[0052] Figure 5 The diagram shown is a structural schematic of a product pool optimization terminal according to an embodiment of the present invention. Detailed Implementation

[0053] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, unless otherwise specified, the following embodiments and features described therein can be combined with each other.

[0054] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0055] The following embodiments of the present invention provide a product pool optimization method, which can be applied to, for example... Figure 1 The product pool optimization terminal shown in this invention may include a mobile phone 11 with wireless charging function, a tablet computer 12, a laptop computer 13, a wearable device, an in-vehicle device, an augmented reality (AR) / virtual reality (VR) device, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), etc. The embodiments of this invention do not impose any restrictions on the specific type of product pool optimization terminal.

[0056] For example, the product pool optimized terminal can be a station (STAION, ST) in a WLAN with wireless charging capability, or a cellular phone, cordless phone, Session Initiation Protocol (SIP) phone, Wireless Local Loop (WLL) station, Personal Digital Assistant (PDA) device, handheld device with wireless charging capability, computing device or other processing device, computer, laptop computer, handheld communication device, handheld computing device, and / or other devices for communication over a wireless system, as well as next-generation communication systems, such as mobile terminals in 5G networks, mobile terminals in future evolved Public Land Mobile Networks (PLMNs), or mobile terminals in future evolved Non-terrestrial Networks (NTNs).

[0057] For example, the product pool optimization terminal can communicate with networks and other devices wirelessly. The aforementioned wireless communication can use any communication standard or protocol, including but not limited to Global System for Mobile communication (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, Short Messaging Service (SMS), BT, GNSS, WLAN, NFC, FM, and / or IR technologies. The GNSS can include Global Positioning System (GPS), Global Navigation Satellite System (GLONASS), BeiDou Navigation Satellite System (BDS), Quasi-Zenith Satellite System (QZSS), and / or Satellite Based Augmentation Systems (SBAS).

[0058] The technical solutions of the present invention will now be described in detail with reference to the accompanying drawings.

[0059] First, the proper nouns appearing in this invention will be explained.

[0060] Product pool: A collection of products filtered from the product tag dataset according to specific conditions. It includes a product ID field as a unique identifier for the product and is used as a range of candidate products when recommending products.

[0061] like Figure 2 As shown, in one embodiment, the product pool optimization method of the present invention includes steps S1-S3.

[0062] Step S1: Obtain daily store-level sales data for the product, and obtain the product performance index based on the daily store-level sales data.

[0063] Specifically, the daily store-level sales data includes product sales revenue, gross profit, sales volume, order volume, discount amount, and out-of-stock status. For each product i within a specific category, its daily store-level sales data is denoted as... Where p sale ,p gm ,p qty ,p order ,p prom ,p oos These represent the product's sales revenue, gross profit, sales volume, order volume, discount amount, and whether it is out of stock.

[0064] In one embodiment, obtaining product performance indicators based on the daily store sales data includes the following steps:

[0065] 11) Calculate the updated sales revenue p' sale =p sale -p prom , where p sale p represents the sales amount. prom This indicates the amount of the discount.

[0066] This requires processing the daily store sales data to filter for valid samples. First, the sales figures are updated based on the discount amount.

[0067] 12) Calculate the updated gross profit p' gm =p gm -p prom , where p gm This refers to the gross profit.

[0068] Gross profit is updated based on the optimized amount.

[0069] 13) Delete the daily store-level sales data for fraudulent orders and obtain valid daily store-level sales data; fraudulent orders refer to the ratio of sales volume to order volume being less than a preset threshold when there is no shortage of stock.

[0070] Among these, the daily store-level sales data may contain fraudulent order data, therefore, this daily store-level sales data needs to be deleted. That is, when p qty / p order <qty_peroreder and p oos When the value is 0, delete the corresponding daily store sales data. `qty_peroreder` represents the preset threshold. oos =1 indicates that the item is out of stock on that day; p oos =0 indicates that there was no shortage of goods on that day.

[0071] 14) Aggregate the effective daily store-level sales data by store and date within the statistical interval to obtain a sample set of sales revenue after removing abnormal sales data.

[0072] Specifically, outlier sales data is removed by analyzing the sales revenue sample set distribution of effective daily store sales data. This is achieved using a quartile statistical threshold method, removing effective daily store sales data outside the range of [Q1 - 1.5 * IQR, Q3 + 1.5 * IQR]. Here, Q1 is the first quartile of the sales revenue distribution, Q3 is the third quartile, and IQR = Q3 - Q1.

[0073] 15) For the aforementioned sales volume sample set, select the store with the largest sales volume. As a benchmark for adjustment, the target adjusted store sales volume is... Obtain adjusted sales figures

[0074] Since different stores have different sales volumes and their sales revenues are not at the same level, it is necessary to normalize the product sales revenue by adjusting the store weight to the level of sales revenue under the same store size. Specifically, the category sales revenue of the store with the largest sales revenue within the statistical scope is selected. As a benchmark for adjustment, the target adjustment target is the category sales revenue of the stores. The adjusted sales revenue of product i is

[0075] In addition, the adjusted sales amount p' within the statistical interval is calculated. s ' ale and Maori p' g ' mThe ratio of sales volume to the number of distribution stores and the number of days yields the final gross profit, excluding distribution sales opportunities, representing the single-store daily sales revenue and single-store daily gross profit. The ratio of the order volume of product i within the statistical interval to the total order volume of distribution stores is calculated as the order penetration rate of product i.

[0076] 16) Obtain the commodity strength index g i =(p' s ' ale ,p' g ' m ,p perm ), where p' g ' m This represents the gross profit within the statistical interval.

[0077] Step S2: Obtain the product elimination score of the product pool based on the product strength index, and eliminate the end products based on the product elimination score.

[0078] Specifically, in the process of consumers selecting goods, the richness of the product category structure and the degree to which segmented needs are met are also among the goals pursued by the product pool. Therefore, this invention further constructs a difference model between product i and the existing product pool to quantify the coverage of segmented needs of the existing product pool by the product. Product difference refers to the degree of difference between the product and the existing product pool in terms of attribute characteristics, which include, but are not limited to, brand, specification range, price range, taste, and function. This invention considers brand, specification range, and price range attributes. The above attribute variables are divided into categorical variables and continuous variables.

[0079] In one embodiment, obtaining the product elimination score of the product pool based on the product strength index includes the following steps:

[0080] 21) Divide the attributes of the product into categorical variables and continuous variables.

[0081] 22) For the categorical variables, calculate the categorical variable dissimilarity for product i. Where r i,v =1-d i,v v represents a product attribute, V represents the set of product attributes, and d i,v This represents the percentage of SKUs with the same attributes as product i in the product pool.

[0082] 23) For the continuous variable, calculate the degree of variability of the numerical variable for commodity i. in v i This represents the distance between product i and other products of the same category currently on sale.

[0083] Where, for attribute v, product i and other products of the same category m ∈ Ω K average distance Ω K This represents a collection of products of the same category currently on sale.

[0084] 24) According to Calculate the product pool elimination score for each product, where α and β represent weights. These represent the product strength index and the normalized values ​​of the categorical variable difference and the numerical variable difference for product i, respectively. Specifically, for products whose attributes are categorical variables, the normalized value of the categorical variable difference is used; for products whose attributes are continuous variables, the normalized value of the numerical variable difference is used.

[0085] In addition to the constraints of shelf space and elimination business rules, further consideration is given to the differences in segmented demand between individual products and product pools in terms of brand, specification range, and price range to ensure the richness of the existing product pool category structure. This is followed by calculating the product pool elimination score for products within each category. in These are the maximum and minimum normalized scores for product strength and differentiation, respectively, where α and β are the preset weights for product strength and differentiation.

[0086] In addition, a product elimination rate is set. Starting from the last product in the product pool with an elimination score, the corresponding product is eliminated based on the elimination rate.

[0087] Step S3: Obtain the homogeneous store group of the target store, and launch new products based on the homogeneous store group and the number of eliminated products.

[0088] Specifically, a homogeneous store group is constructed based on the user profile feature vector of the consumer group and the distribution feature vector of the consumer category.

[0089] In one embodiment, such as Figure 3 As shown, acquiring a group of homogeneous stores and, based on this group and the number of obsolete products, implementing new product launches includes the following steps:

[0090] 31) Obtain the user profile feature vector and the consumer category distribution feature vector of the consumer group.

[0091] Feature engineering is the process of transforming raw data into features that better represent the essence of the problem, enabling the application of these features to predictive models and improve the accuracy of model predictions for data that is not readily available. Through feature engineering, excessively missing fields in the aforementioned feature vectors are removed, and for some fields with missing values, such as area, linear regression is used to complete the missing values.

[0092] The user profile feature vector includes the percentage of each type of user profile in the total number of users; the consumer product category distribution feature vector includes the percentage of each product category's sales revenue in the total sales revenue.

[0093] 32) Perform one-hot encoding on the categorical variables in the user profile feature vector and the consumer product category distribution feature vector, and normalize the continuous variables to obtain effective variables.

[0094] 33) Cluster the effective variables based on the k-means clustering algorithm to obtain homogeneous store groups.

[0095] For the homogeneous store groups obtained by the above clustering, if the number of homogeneous store groups for the target store is too small, it will not meet the requirements for constructing the baseline product pool. Therefore, when the number of homogeneous store groups obtained by clustering is less than a preset value, the similarity between the target store and the candidate stores in the same area is calculated, and the top-N candidate stores in the same area with the highest similarity are selected to enter the homogeneous store groups.

[0096] The similarity calculation method uses KL divergence distribution similarity calculation, and the specific formula is as follows: p(x) and q(x) are the feature vectors of the target store and other stores, respectively.

[0097] 34) For the products in the homogeneous store group, generate a product recommendation ranking based on the product elimination score of the product pool.

[0098] The product recommendation ranking is generated based on the product elimination scores in the product pool, from lowest to highest. Specifically, the lower the product elimination score, the higher the recommendation ranking; conversely, the higher the product elimination score, the lower the recommendation ranking.

[0099] 35) Based on the product recommendation ranking, select the number of eliminated products to add new products.

[0100] The scope of protection of the product pool optimization method described in this embodiment is not limited to the execution order of the steps listed in this embodiment. Any solution implemented by adding, subtracting, or replacing steps in the prior art based on the principle of this invention is included within the scope of protection of this invention.

[0101] This invention also provides a product pool optimization system, which can implement the product pool optimization method described in this invention. However, the implementation device of the product pool optimization method described in this invention includes, but is not limited to, the structure of the product pool optimization system listed in this embodiment. All structural modifications and substitutions of the prior art made according to the principles of this invention are included within the protection scope of this invention.

[0102] like Figure 4 As shown, in one embodiment, the product pool optimization system of the present invention includes an acquisition module 41, an elimination module 42, and a new product module 43.

[0103] The acquisition module 41 is used to acquire daily store-level sales data of the product and acquire product performance indicators based on the daily store-level sales data.

[0104] The elimination module 42 is connected to the acquisition module 41 and is used to obtain the product elimination score of the product pool based on the product strength index, and eliminate the end products based on the product elimination score.

[0105] The new product module 43 is connected to the elimination module 42 and is used to obtain the homogeneous store group of the target store, and to realize the new product launch based on the homogeneous store group and the number of eliminated products.

[0106] The structure and principle of the acquisition module 41, the elimination module 42 and the new product module 43 correspond one-to-one with the steps in the above-mentioned product pool optimization method, so they will not be described again here.

[0107] In the embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, or methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules / units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or units may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of apparatuses or modules or units may be electrical, mechanical, or other forms.

[0108] The modules / units described as separate components may or may not be physically separate. The components shown as modules / units may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules / units can be selected to achieve the objectives of the embodiments of the present invention, depending on actual needs. For example, the functional modules / units in the various embodiments of the present invention may be integrated into one processing module, or each module / unit may exist physically separately, or two or more modules / units may be integrated into one module / unit.

[0109] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0110] This invention also provides a computer-readable storage medium. Those skilled in the art will understand that all or part of the steps in the methods of the above embodiments can be implemented by a program instructing a processor. The program can be stored in a computer-readable storage medium, which is a non-transitory medium, such as random access memory, read-only memory, flash memory, hard disk, solid-state drive, magnetic tape, floppy disk, optical disk, and any combination thereof. The storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. This available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., digital video disc (DVD)), or a semiconductor medium (e.g., solid-state drive (SSD)).

[0111] This invention also provides a product pool optimization terminal. The product pool optimization terminal includes a processor and a memory.

[0112] The memory is used to store computer programs.

[0113] The memory includes various media capable of storing program code, such as ROM, RAM, magnetic disk, USB flash drive, memory card, or optical disk.

[0114] The processor is connected to the memory and is used to execute the computer program stored in the memory so that the product pool optimization terminal performs the above-described product pool optimization method.

[0115] Preferably, the processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0116] like Figure 5 As shown, the product pool optimization terminal of the present invention is manifested in the form of a general-purpose computing device. The components of the product pool optimization terminal may include, but are not limited to: one or more processors or processing units 51, a memory 52, and a bus 53 connecting different system components (including the memory 52 and the processing unit 51).

[0117] Bus 53 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. Examples of these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0118] Commodity pool optimization terminals typically include a variety of computer system readable media. These media can be any available media that can be accessed by the commodity pool optimization terminal, including volatile and non-volatile media, and removable and non-removable media.

[0119] Memory 52 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 521 and / or cache memory 522. The product pool optimization terminal may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 523 may be used to read and write non-removable, non-volatile magnetic media (…). Figure 5 Not shown; usually referred to as a "hard drive"). Although Figure 5Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 53 via one or more data media interfaces. Memory 52 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0120] A program / utility 524 having a set (at least one) of program modules 5241 may be stored, for example, in memory 52. ​​Such program modules 5241 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 5241 typically perform the functions and / or methods described in the embodiments of the present invention.

[0121] The product pool optimized terminal can also communicate with one or more external devices (e.g., keyboard, pointing device, display, etc.), and with one or more devices that enable users to interact with the product pool optimized terminal, and / or with any device that enables the product pool optimized terminal to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed through input / output (I / O) interface 54. Furthermore, the product pool optimized terminal can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) through network adapter 55. Figure 5 As shown, network adapter 55 communicates with other modules of the commodity pool optimization terminal via bus 53. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the commodity pool optimization terminal, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0122] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. A commodity pool optimization method characterized by, The method comprises the following steps: Obtain daily store dimension sales data of the commodity, and obtain a commodity force index based on the daily store dimension sales data; Obtain a commodity pool commodity elimination score of the commodity based on the commodity force index, and eliminate end commodities based on the commodity elimination score; Obtain a homogeneous store group of the target store, and realize commodity restocking based on the homogeneous store group and the number of eliminated commodities.

2. The merchandise planogram optimization method of claim 1, wherein: The daily store dimension sales data comprises sales, gross profit, sales volume, order volume, discount amount, and out-of-stock data of the commodity; Obtaining the commodity force index based on the daily store dimension sales data comprises the following steps: computing the updated sales p' sale = p sale - p prom where p sale denotes the sales, p prom denotes the discount amount; The updated gross profit p' is calculated gm = p gm -p prom where p gm denotes the gross profit; Delete daily store dimension sales data of brushing, and obtain valid daily store dimension sales data; the brushing refers to a ratio of sales volume to order volume being less than a preset threshold value in a non-out-of-stock state; Aggregate the valid daily store dimension sales data in a store and a date interval, and obtain a sales sample set after eliminating sales abnormal data; For the sales sample set, the sales of the largest store is selected As the adjustment reference value, the sales of the target adjustment store is Obtain the adjusted sales acquiring the commodity force indicator g i = (p' s ' ale , p' g ' m , p perm ), where p' g ' m represents gross profit within a statistical interval.

3. The merchandise planogram optimization method of claim 2, wherein: Obtaining the sales sample set after eliminating the sales abnormal data comprises: Eliminate valid daily store dimension sales data outside [Q1-1.5*IQR, Q3+1.5*IQR], wherein Q1 is the first quartile of the sales distribution, Q3 is the third quartile of the sales distribution, and IQR=Q3-Q1.

4. The merchandise planogram optimization method of claim 1, wherein: Obtaining the commodity pool commodity elimination score of the commodity based on the commodity force index comprises the following steps: Divide attributes of the commodity into categorical variables and continuous variables; For the categorical variable, calculate the difference of the categorical variable of the commodity i where r i,v = 1 - d i,v , v represents a commodity attribute, V represents a set of commodity attributes, d i,v represents the proportion of the number of SKUs with the same attribute as commodity i in the commodity pool. For the continuous variable, calculate the numerical variable dissimilarity of good i wherein v i denotes the distance of good i and the on sale goods of the same category; According to a product pool product elimination score of the product is calculated, wherein a, b represent weights, respectively represent the normalized values of the product force index and the category variable difference / numerical variable difference of product i.

5. The merchandise planogram optimization method of claim 1, wherein: Eliminating the end commodities based on the commodity elimination score comprises the following steps: Set an elimination rate of the commodity; Starting from the end of the commodity pool commodity elimination score, eliminate corresponding commodities based on the elimination rate.

6. The merchandise planogram optimization method of claim 1, wherein: Obtaining the homogeneous store group and realizing commodity restocking based on the homogeneous store group and the number of eliminated commodities comprises the following steps: Obtain a user portrait feature vector and a consumer category distribution feature vector of a consumer group; One-hot encode categorical variables in the user portrait feature vector and the consumer category distribution feature vector, and normalize continuous variables to obtain valid variables; Cluster the valid variables based on a k-means clustering algorithm to obtain the homogeneous store group; For commodities of the homogeneous store group, generate a commodity recommendation ranking according to the commodity pool commodity elimination score of the commodities; Select commodities of the number of eliminated commodities for restocking based on the commodity recommendation ranking.

7. The merchandise planogram optimization method of claim 6, wherein: Clustering the valid variables based on the k-means clustering algorithm to obtain the homogeneous store group comprises the following steps: If the number of homogeneous store groups obtained by clustering is less than a preset value, calculate the similarity of the target store and a same-area candidate store, and select top-N same-area candidate stores with high similarity to enter the homogeneous store group.

8. A merchandise pool optimization system characterized by, The system comprises an obtaining module, an elimination module, and a restocking module; The obtaining module is configured to obtain daily store dimension sales data of a commodity, and obtain a commodity force index based on the daily store dimension sales data; The elimination module is configured to obtain a commodity pool commodity elimination score of the commodity based on the commodity force index, and eliminate end commodities based on the commodity elimination score; The restocking module is configured to obtain a homogeneous store group, and realize commodity restocking based on the homogeneous store group and the number of eliminated commodities.

9. A merchandise pool optimization terminal, characterized by, The commodity pool optimization terminal comprises a processor and a memory. The memory is configured to store a computer program. The processor is configured to execute the computer program stored in the memory, so that the commodity pool optimization terminal executes the commodity pool optimization method in any one of claims 1 to 7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the commodity pool optimization terminal to implement the commodity pool optimization method in any one of claims 1 to 7.

Images