Sales complementing method and device based on e-commerce platform, and storage medium

Abstract

The invention relates to a sales volume completion method and device based on an e-commerce platform and a storage medium, and the method comprises the steps: carrying out the aggregation of the public sales volume of each standardized product unit according to first public sales volume data, and obtaining second public sales volume data corresponding to each standardized product unit; establishing a relation pair between the sales ranking information corresponding to each standardized product unit and the second public sales volume data, and based on interpolation processing, performing data completion on the sales volume data of the standardized product unit with the missing sales volume under the target commodity category to obtain target completion sales volume data of the standardized product unit with the missing sales volume; and according to the target complemented sales volume data, sub-body division is performed on the sales volume data of the inventory volume units corresponding to the standardized product units, so that total sales volume data of total commodities in the target commodity category can be obtained. The method can achieve the determination of the sales volume of all commodities of the e-commerce platform, and completes the complementation of part of missing sales volume data.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a sales volume completion method, device and storage medium based on an e-commerce platform. Background Art

[0002] Product sales can reflect the changes in the strength of market demand for products. Predicting product sales on e-commerce platforms plays a vital role in e-commerce operations. At present, product sales forecasts for e-commerce platforms often focus on the sales ranking performance of products to comprehensively predict sales. For example, for the Amazon platform, sales are estimated based on the Best Sellers Rank (BSR) performance of the product. Recently, the Amazon platform has gradually opened up the sales of product variants corresponding to each category. Due to the cost and difficulty of collecting samples, only part of the public sales can be obtained.

[0003] Therefore, there is still a problem of incomplete sales data acquisition in the current relevant technology. Summary of the invention

[0004] In this embodiment, a sales volume completion method, device and storage medium based on an e-commerce platform are provided to solve the problem of incomplete sales volume data acquisition in related technologies.

[0005] In the first aspect, in this embodiment, a sales volume completion method based on an e-commerce platform is provided, including:

[0006] Obtaining first public sales data of the inventory unit corresponding to each standardized product unit under the target commodity category, and obtaining sales ranking information of each standardized product unit;

[0007] Aggregating the public sales volume of each standardized product unit according to the first public sales volume data to obtain second public sales volume data corresponding to each standardized product unit;

[0008] Establishing a relationship pair between the sales ranking information corresponding to each standardized product unit and the second public sales data, and completing the sales data of the standardized product units with missing sales under the target commodity category based on the relationship pair based on interpolation processing to obtain the target completed sales data of the standardized product units with missing sales;

[0009] According to the target completed sales data, the sales data of the inventory units corresponding to each of the standardized product units are divided into sub-bodies to obtain the full sales data of all commodities under the target commodity category.

[0010] In some embodiments, obtaining first public sales data of a stock keeping unit corresponding to each standardized product unit under a target commodity category, and obtaining sales ranking information of each standardized product unit, includes:

[0011] Obtaining the inventory units corresponding to each standardized production unit under the target commodity category, the candidate public sales data within the collection time interval corresponding to the target date, and the candidate sales ranking information within the collection time interval; the collection time interval is composed of a preset number of days before the target date, the target date, and the preset number of days after the target date;

[0012] Among the candidate public sales data, the public sales data collected the closest to the target date is used as the first public sales data corresponding to the target date;

[0013] Among the candidate sales ranking information, the ranking information whose collection time is closest to the target date is used as the sales ranking information corresponding to the target date.

[0014] In some of the embodiments, obtaining first public sales data of a stock keeping unit corresponding to each standardized product unit under a target commodity category includes:

[0015] Determining sales search information corresponding to keywords associated with the target product category based on a preset data analysis method for product sales;

[0016] The first public sales data of the inventory units corresponding to each standardized product unit under the target commodity category is determined according to the sales search information.

[0017] In some of the embodiments, obtaining first public sales data of a stock keeping unit corresponding to each standardized product unit under a target commodity category includes:

[0018] The first public sales data of the inventory units corresponding to each standardized product unit under the target commodity category is obtained, and the commodity detail data of all the inventory units on the e-commerce platform is obtained.

[0019] In some embodiments, the public sales volume of each standardized product unit is aggregated according to the first public sales volume data to obtain the second public sales volume data corresponding to each standardized product unit, including:

[0020] According to a preset acquisition rate, sampling the first public sales data corresponding to each standardized product unit to obtain sampled public sales data;

[0021] The sampled public sales data corresponding to each standardized product unit are added up, and the second public sales data corresponding to each standardized product unit is obtained based on the summed result and the acquisition rate.

[0022] In some embodiments, according to the relationship pair, the sales data of the standardized product unit with missing sales under the target commodity category is supplemented based on interpolation processing to obtain the target supplemented sales data of the standardized product unit with missing sales, including:

[0023] According to the relationship pair, based on the nearest neighbor interpolation processing, the sales data of the standardized product unit with missing sales are completed to obtain the target completed sales data of the standardized product unit with missing sales.

[0024] In some embodiments, according to the target completed sales data, the sales data of the inventory units corresponding to the standardized product units are divided into sub-bodies to obtain the full sales data of all commodities under the target commodity category, including:

[0025] Determine the stock keeping unit with missing sales volume under each standardized product unit as the first stock keeping unit;

[0026] Determine the stock quantity unit with public sales volume under each standardized product unit as the second stock quantity unit;

[0027] Obtaining to-be-divided public sales data for the first inventory unit according to the target completed sales data of each standardized product unit and the first public sales data of the second inventory unit;

[0028] According to the commodity evaluation index corresponding to the first inventory unit, the public sales data to be divided is divided into different first inventory units to obtain the full sales data of all commodities under the target commodity category.

[0029] In a second aspect, a sales result evaluation method is provided in this embodiment, and the method includes:

[0030] Get preset verification sales data;

[0031] According to the sales volume completion method described in the first aspect, obtaining sales volume completion data corresponding to the verified sales volume data;

[0032] Based on a preset accuracy evaluation index, the sales volume completion data corresponding to the verified sales volume data is evaluated for accuracy to obtain an accuracy evaluation result.

[0033] In a third aspect, in this embodiment, a sales volume completion device based on an e-commerce platform is provided, comprising: an acquisition module, an aggregation module, a data completion module, and a division module; wherein:

[0034] The acquisition module is used to acquire the first public sales volume data of the inventory unit corresponding to each standardized product unit under the target commodity category, and acquire the sales ranking information of each standardized product unit;

[0035] The aggregation module is used to aggregate the public sales volume of each standardized product unit according to the first public sales volume data to obtain the second public sales volume data corresponding to each standardized product unit;

[0036] The data completion module is used to establish a relationship pair between the sales ranking information corresponding to each standardized product unit and the second public sales data, and according to the relationship pair, based on interpolation processing, complete the sales data of the standardized product unit with missing sales under the target commodity category to obtain the target completed sales data of the standardized product unit with missing sales;

[0037] The division module is used to complete the sales data according to the target, divide the sales data of the inventory units corresponding to each standardized product unit into sub-bodies, and obtain the full sales data of all commodities under the target commodity category.

[0038] In a fourth aspect, a storage medium is provided in this embodiment, on which a computer program is stored, and when the program is executed by a processor, the sales volume completion method based on the e-commerce platform described in the first aspect above is implemented.

[0039] Compared with the related art, the present embodiment provides a sales completion method, device and storage medium based on an e-commerce platform. The sales completion method based on the e-commerce platform obtains the first public sales data of the inventory unit corresponding to each standardized product unit under the target commodity category, and obtains the sales ranking information of each standardized product unit; aggregates the public sales of each standardized product unit according to the first public sales data to obtain the second public sales data corresponding to each standardized product unit; establishes a relationship pair between the sales ranking information corresponding to each standardized product unit and the second public sales data, and based on the relationship pair, performs data completion on the sales data of the standardized product unit with missing sales under the target commodity category based on interpolation processing to obtain the target completed sales data of the standardized product unit with missing sales; and divides the sales data of the inventory unit corresponding to each standardized product unit into sub-bodies according to the target completed sales data to obtain the full sales data of all commodities under the target commodity category. It can utilize the mapping relationship between public sales and sales rankings to complete the missing sales data based on interpolation, thereby determining the sales volume of all products on the e-commerce platform based on partial public sales and full sales ranking information, and completing the completion of some missing sales data.

[0040] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0042] Figure 1 is a hardware structure block diagram of a terminal of the sales volume completion method based on an e-commerce platform in this embodiment;

[0043] Figure 2 is a flow chart of the sales volume completion method based on the e-commerce platform of this embodiment;

[0044] Figure 3 is a flow chart of the sales result evaluation method of this embodiment;

[0045] Figure 4 is a flow chart of a sales volume completion method based on an e-commerce platform in some of the embodiments;

[0046] Figure 5 This is a structural block diagram of the sales volume completion device based on the e-commerce platform of this embodiment. DETAILED DESCRIPTION

[0047] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0048] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the general meaning understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the", "these" and the like in this application do not represent quantitative restrictions, and they can be singular or plural. The terms "include", "comprise", "have" and any variants thereof involved in this application are intended to cover non-exclusive inclusions; for example, a process, method and system, product or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether directly or indirectly. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. Usually, the character " / " indicates that the objects associated with each other are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0049] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. For example, running on a terminal, Figure 1 is a hardware structure block diagram of a terminal of the sales volume completion method based on an e-commerce platform in this embodiment. Figure 1 As shown, the terminal may include one or more ( Figure 1 Only one is shown in the figure) processor 102 and memory 104 for storing data, wherein processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. The above terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0050] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the sales volume completion method based on the e-commerce platform in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0051] The transmission device 106 is used to receive or send data via a network. The above network includes a wireless network provided by the communication provider of the terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0052] In this embodiment, a sales volume completion method based on an e-commerce platform is provided. Figure 2 is a flow chart of the sales volume completion method based on the e-commerce platform of this embodiment. Figure 2 As shown, the process includes the following steps:

[0053] Step S210, obtaining the first public sales data of the inventory unit corresponding to each standardized product unit under the target commodity category, and obtaining the sales ranking information of each standardized product unit.

[0054] The target commodity category is the commodity category for which sales volume acquisition and sales volume completion are currently required. The target commodity category may be an orderly and systematic classification of commodities according to the commodity attributes, uses, production methods, raw materials, varieties, etc., during the commodity circulation or sales process. For example, the target commodity category may be clothing, office supplies, electronic products, etc. This embodiment may distinguish different commodity categories and determine the full sales volume of different commodity categories respectively.

[0055] The above-mentioned Standard Product Unit (SPU) is a product or commodity with a unique identifier and a set of standardized attributes under the target commodity category of the e-commerce platform. The Stock Keeping Unit (SKU) is a code or identifier used to identify and manage each unique commodity or product variant on the e-commerce platform. It is a key tool for merchants to track, manage and control inventory when selling goods on e-commerce platforms (such as Amazon platforms). One standardized product unit can correspond to multiple stock keeping units. Therefore, a standardized product unit can be used as a parent, and the corresponding stock keeping unit can be used as a child of the parent. The correspondence between the parent and the child can be one-to-one or one-to-many.

[0056] The first public sales volume may be the public sales volume corresponding to each inventory unit sampled and extracted from the e-commerce platform; the sales ranking information may be the ranking information of each standardized product unit provided by the e-commerce platform, such as the Best Sellers Ranking (BSR) provided by the Amazon platform. The sales ranking information is used to display the ranking index of the sales performance of a product in its category. For the Amazon platform, the BSR is updated every day to reflect the sales of the product. For a product, the smaller the BSR value, the better the sales performance of the product in its category.

[0057] Category sharing means that the parent and corresponding child share the BSR ranking, that is, the BSR of the parent and the BSR of the child under the category are exactly the same, otherwise the category is not shared. Currently on the Amazon platform, the categories that are not shared include the following: 3C categories (computer categories, communication categories, consumer electronics products), computer accessories categories (computer accessories categories), video categories (video categories), and the rest of the categories are shared categories.

[0058] Step S220, aggregating the public sales volume of each standardized product unit according to the first public sales volume data to obtain second public sales volume data corresponding to each standardized product unit.

[0059] Specifically, according to the correspondence between the parent body and the child body, the first public sales data of all child bodies corresponding to a parent body can be aggregated to obtain the public sales data corresponding to the parent body, that is, the above-mentioned second public sales data.

[0060] Step S230, establish a relationship pair between the sales ranking information corresponding to each standardized product unit and the second public sales data, and based on the relationship pair, complete the sales data of the standardized product units with missing sales under the target commodity category based on interpolation processing to obtain the target completed sales data of the standardized product units with missing sales.

[0061] That is, after obtaining the public sales of the parent, the mapping relationship between the public sales of the parent and the sales ranking information of the parent can be matched to establish a relationship pair between the above sales ranking information and the second public sales data. Afterwards, based on the arrangement relationship between different sales rankings in the relationship pair, for the parent with missing sales, interpolation processing can be used to complete the sales data corresponding to the parent with missing sales according to other parents with public sales, so as to complete the missing sales of the parent. It can be understood that the sales completion achieved in this step can realize the sales completion of the corresponding parent for different categories, and distinguish between category sharing and category non-sharing. Among them, the BSR of the parent shared by the category is consistent with the BSR of the child, and the category non-shared can directly obtain the BSR marked on the parent by the e-commerce platform. The sales ranking information can reflect the sales performance of the product under its category. This embodiment is to complete the sales of the parent that already has sales data, but the sales data is missing, and has a corresponding sales ranking. Specifically, considering the correlation between sales data and sales ranking information, a mapping relationship between public sales and sales ranking information is established, and based on other sales rankings that are close and have obtained the parent of public sales, the data of the missing parent of the current sales is completed. Therefore, the sales completion problem in this embodiment can actually be a data interpolation completion problem implemented based on the mapping relationship.

[0062] Step S240 , according to the target completed sales data, the sales data of the inventory units corresponding to each standardized product unit are divided into sub-bodies to obtain the total sales data of all commodities under the target commodity category.

[0063] After completing the completion of the parent sales volume based on step S230, the child sales volume data is divided according to the mapping relationship between the parent and the child. Among them, for the child whose public sales volume has been obtained, the original corresponding public sales volume can be used directly; for the child whose public sales volume is missing, the child division of the sales volume data can be realized based on the completed public sales volume of the corresponding parent, combined with other sales reference information, such as historical public sales volume, number of comments, etc. Based on this, for a parent, the sales volume data of all the child bodies under the parent can be obtained. Based on this, this step can obtain the full sales volume data of all the child bodies under the target product category.

[0064] Through the above steps S210 to S240, the first public sales data of the inventory units corresponding to each standardized product unit under the target commodity category is obtained, and the sales ranking information of each standardized product unit is obtained; the public sales of each standardized product unit is aggregated according to the first public sales data to obtain the second public sales data corresponding to each standardized product unit; a relationship pair is established between the sales ranking information corresponding to each standardized product unit and the second public sales data, and based on the relationship pair, the sales data of the standardized product units with missing sales under the target commodity category are supplemented based on interpolation processing to obtain the target supplemented sales data of the standardized product units with missing sales; based on the target supplemented sales data, the sales data of the inventory units corresponding to each standardized product unit are divided into sub-bodies to obtain the full sales data of all commodities under the target commodity category. It can use the mapping relationship between public sales and sales ranking to achieve data supplement of missing sales based on interpolation, thereby determining the sales of all commodities on the e-commerce platform based on partial public sales and full sales ranking information, and completing the supplement of partial missing sales data.

[0065] In one embodiment, based on the above step S210, obtaining the first public sales volume data of the inventory unit corresponding to each standardized product unit under the target commodity category and obtaining the sales ranking information of each standardized product unit may specifically include:

[0066] Obtain the inventory units corresponding to each standardized production unit under the target commodity category, the candidate public sales data within the collection time interval corresponding to the target day, and the candidate sales ranking information within the collection time interval; the collection time interval is composed of the preset number of days before the target day, the target day, and the preset number of days after the target day; among the candidate public sales data, the public sales data with the collection time closest to the target day is used as the first public sales data corresponding to the target day; among the candidate sales ranking information, the ranking information with the collection time closest to the target day is used as the sales ranking information corresponding to the target day.

[0067] Next, the BSR of the Amazon platform, whose sales ranking information is an example, is used for explanation. In this embodiment, considering that the BSR of the commodity is collected according to the list provided by the e-commerce platform, such as the list marked as "active and popular" by the e-commerce platform, there is an incomplete coverage problem for the collection of BSR. In addition, considering that the value fluctuation of BSR in the preset time interval (excluding holidays) is small. Based on the above reasons, the time interval of data collection can be widened, and the collection of BSR can be realized by approximate processing. Specifically, when it is necessary to collect the BSR of the target day T, the most recently collected BSR within 5 days before and after T (that is, 5 days before T, 5 days after T and T together constitute the collection time interval corresponding to T) can be queried as the approximate BSR of the target day. In this way, for T, a total of 11 days of data are used, so the amount of valid data available per day can be expanded by 10 times. Correspondingly, this method can also be adopted for the collection of public sales books.

[0068] This embodiment implements approximate processing of data based on the collection time interval, which can avoid the problem of incomplete coverage of the collected data.

[0069] Additionally, in one embodiment, based on the above step S210, obtaining the first public sales data of the inventory unit corresponding to each standardized product unit under the target commodity category may specifically include:

[0070] Based on a preset data analysis method for commodity sales, sales search information corresponding to keywords associated with the target commodity category is determined; based on the sales search information, first public sales data of inventory units corresponding to each standardized product unit under the target commodity category is determined.

[0071] For example, a data analysis method provided by a third party or an e-commerce platform can be used to determine the sales search information associated with the target product category, and extract the first public sales data of each inventory unit corresponding to each standardized product unit under the target product category. Still taking the Amazon platform as an example, the keywords can be determined based on the data of the Amazon Brand Analytics (ABA) tool disclosed by the Amazon platform, and then the first three pages of search results corresponding to each keyword are retained as sales search information, from which the corresponding public sales can be determined.

[0072] In addition, in one embodiment, based on the above step S210, obtaining the first public sales data of the inventory unit corresponding to each standardized product unit under the target commodity category may specifically include:

[0073] The first public sales data of the inventory units corresponding to each standardized product unit under the target product category is obtained, and the product detail data of all inventory units on the e-commerce platform is obtained.

[0074] After obtaining the first public sales data based on keywords based on ABA, for product categories with a large number of variants such as clothing and office supplies, the public sales of all variants can be further collected separately, and the product details data corresponding to the variants can be collected, such as collecting product details page information set on the web page of the e-commerce platform. Based on this, the public sales of all child bodies corresponding to a parent body can be obtained. On the one hand, it can expand the collection coverage of child bodies under the parent body; on the other hand, it can effectively evaluate the sales completion based on the more complete data collected.

[0075] Additionally, in one embodiment, based on the above step S220, the public sales of each standardized product unit are aggregated according to the first public sales data to obtain the second public sales data corresponding to each standardized product unit, which may include:

[0076] According to a preset acquisition rate, the first public sales data corresponding to each standardized product unit is sampled to obtain sampled public sales data; the sampled public sales data corresponding to each standardized product unit is added up, and based on the sum result and the acquisition rate, the second public sales data corresponding to each standardized product unit is obtained.

[0077] For scenarios with multiple variants, there may be hundreds of variants at most. In order to ensure data collection efficiency, an acquisition rate can be set, such as 90%, and the public sales data of the child bodies under the parent body can be collected according to the acquisition rate. That is, if a parent body has 100 child bodies, then after obtaining the public sales data of 90 or more of the child bodies, it is considered that the public sales data of all the child bodies under the parent body have been collected, and then the aggregation of the child body sales to the parent body sales is completed. It can be understood that the above acquisition rate can also be set to other values ​​according to the actual application scenario, and this embodiment does not make specific limitations on this.

[0078] A mapping relationship is established between the sales ranking and the corresponding public sales volume. The specific data format can be found in the following table:

[0079] BSR Sales 1000 5000 1001 Complete data 1002 Complete data … Complete data 1009 Complete data 1010 4900 1050 4950 1100 4800

[0080] This embodiment takes the acquisition rate into consideration when aggregating the parent sales. First, the parent sales are aggregated, and the parent public sales data is obtained by summing the public sales data of the child. Then, the parent public sales data is aggregated according to the acquisition rate s multiplied by a coefficient of 1 / s. Therefore, the second public sales data y can be obtained based on the following formula:

[0081]

[0082] Where s is the acquisition rate, m is the number of daughter bodies, l i It is the first public sales data obtained by a child. Based on this, through this embodiment, the aggregation of the parent's public sales can be achieved.

[0083] Additionally, in one embodiment, based on the above step S230, according to the relationship pairs, the sales data of the standardized product units with missing sales under the target commodity category are supplemented based on interpolation processing to obtain the target supplemented sales data of the standardized product units with missing sales, which may specifically include:

[0084] According to the relationship pairs, based on the nearest neighbor interpolation processing, the sales data of the standardized product units with missing sales are completed to obtain the target completed sales data of the standardized product units with missing sales.

[0085] After obtaining the relationship pair mapping between the sales ranking information and the public sales data, the missing public sales can be filled in order according to the relationship between the points in the relationship pair. In particular, considering the completion accuracy, this embodiment selects the nearest neighbor average interpolation processing. Based on the nearest neighbor average interpolation, for each sales ranking, the public sales corresponding to a preset number of sales ranking points with sales nearby can be selected as the completed sales corresponding to the sales ranking. For example, according to the above table, the public sales corresponding to the BSR of 1001 is missing, then the public sales corresponding to the BSR of 1001 is completed based on the public sales corresponding to the 10 BSRs nearby to the BSR of 1001.

[0086] Specifically, the public sales volume can be completed based on the following formula:

[0087]

[0088] in is the complete sales volume when BSR is k, y k+i It is the public sales volume of the parent corresponding to the ith BSR with sales volume that is closest to the kth BSR. In this way, the corresponding relationship between BSR and public sales volume in each category can be obtained to complete the missing sales volume of the parent. Therefore, in this embodiment, it is possible to complete the missing sales volume and smooth the small window volatility of the sales volume.

[0089] In addition, in some embodiments, the above-mentioned interpolation processing method can also be piecewise linear interpolation, fitting interpolation, etc., and the corresponding interpolation processing method can be selected according to the requirements of the actual application scenario and the requirements for accuracy.

[0090] In one embodiment, based on the above step S240, according to the target completed sales data, the sales data of the inventory units corresponding to each standardized product unit are divided into sub-bodies to obtain the total sales data of all commodities under the target commodity category, which may include:

[0091] Determine the inventory units with missing sales under each standardized product unit as the first inventory units; determine the inventory units with public sales under each standardized product unit as the second inventory units; obtain the public sales data to be divided for the first inventory units according to the target completion sales data of each standardized product unit and the first public sales data of the second inventory unit; divide the public sales data to be divided into different first inventory units according to the commodity evaluation index corresponding to the first inventory unit, and obtain the full sales data of all commodities under the target commodity category.

[0092] In this embodiment, a distinction is made between the sub-body whose public sales volume is obtained and the sub-body whose public sales volume is missing, that is, the first inventory unit corresponds to the sub-body whose public sales volume is missing, and the second inventory unit corresponds to the sub-body whose public sales volume is obtained. Afterwards, the sub-body sales volume that has been obtained is subtracted from the public sales volume of the parent body to obtain the public sales volume to be divided. The remaining sales volume (that is, the public sales volume to be divided) is divided into sub-bodies. For example, if the public sales volume of the corresponding sub-body is obtained within 5 days before and after the target date, the obtained public sales volume is directly determined as the public sales volume of the sub-body. Among them, there is an inseparable connection between the number of comments on the product, the historical public sales volume and the current sales volume of the product. Therefore, after subtracting the sub-body sales volume that has been obtained from the second public sales volume corresponding to the parent body, the public sales volume of the sub-body whose current sales volume is missing is divided according to reference indicators such as the number of comments and historical public sales data. For sub-bodies with more comments (corresponding to the larger purchase volume), the more public sales volume is obtained by division. Exemplarily, the sales data obtained by dividing the sub-body with missing sales volume can be:

[0093]

[0094] Among them, l k Indicates the sales data obtained by completing the sub-body; Indicates the completed sales data of the parent, that is, the completed sales data of the target mentioned above; L known represents the sum of the public sales data of the sub-body that has been obtained, c i Indicates the number of comments for the i-th sub-body with missing sales. If the number of comments for all sub-bodies with missing sales is 0, the public sales data to be divided will be evenly divided according to the number of sub-bodies with missing sales.

[0095] In addition, in one embodiment, the critical point of long-tail sales can also be determined. Specifically, for daily sales data, for each category, for example, 25 major categories, the number of child reviews is 0, the parent rating ratio is 0, and the estimated shelf time on the e-commerce platform is 7 days. The three conditions are superimposed to comprehensively determine the child sample set with a possible sales volume of 0, so as to define the critical point of long-tail sales.

[0096] For the above sub-volume sample sets with possible sales of 0 and samples of the same category with recent sales below 100, the fitting function is obtained by fitting the relationship between sales and BSR. The BSR corresponding to the fitting result less than 0.001 is taken as the threshold to determine the critical point BSR when the sales are zero. After that, the critical point BSR can be output to the user so that the user can make product placement decisions based on the critical point.

[0097] Additionally, in one embodiment, a sales result evaluation method is provided. Figure 3 is a flow chart of the sales result evaluation method of this embodiment. Figure 3 As shown, the sales result evaluation method includes the following steps:

[0098] Step S301, obtaining preset verification sales data;

[0099] Step S302, according to the sales volume completion method provided in the above embodiment, obtaining sales volume completion data corresponding to the verified sales volume data;

[0100] Step S303, based on the preset accuracy evaluation index, the sales volume completion data corresponding to the verification sales volume data is evaluated for accuracy to obtain an accuracy evaluation result.

[0101] Specifically, the above-mentioned accuracy evaluation indicators can be mean error value (MAE), mean error rate (MAPE), Pearson correlation coefficient (R2-Pearson), Spearman correlation coefficient (R2-spearman), PK winning rate and other accuracy evaluation indicators to evaluate the accuracy of sales completion data.

[0102] Among them, MAE = ABS (completed sales data - public sales). That is, in the verification sales data used to verify accuracy, the difference between the completed sales data of each child and the corresponding public sales is summed and averaged to determine the completion accuracy of the child. This evaluation index can also be used to evaluate the completion accuracy of the parent.

[0103] MAPE = ABS (completed sales - public sales) / public sales. That is, the difference of the completed sales data of each child is summed up and averaged. This evaluation index can also be used to evaluate the completion accuracy of the parent.

[0104] In addition, the Pearson correlation coefficient can be introduced to measure the difference between the supplementary sales data of the sub-body and the public sales in each natural month. Specifically:

[0105]

[0106] Among them, r represents the correlation between the completed sales data and the public sales data; i represents the corresponding month; x i Indicates the completion of sales data, y i Indicates public sales data; Indicates the average completed sales data for the month; Indicates the average public sales data for the month.

[0107] In order to further evaluate volatility, the Spearman correlation coefficient can be introduced. The Spearman correlation coefficient pays more attention to the rise or fall of the numerical trend, and is relatively robust to the specific value of the fall. The calculation method of the Spearman correlation coefficient ρ can be:

[0108]

[0109] Among them, n is the number of samples for sales volume completion, d i is the sorting difference after sorting the i-th pair of completed sales data.

[0110] In addition, the PK winning rate method can also be used to verify the accuracy of sales completion. Select the sales forecast results obtained by using other sales forecasting methods, and the difference between the sales forecast results obtained by the sales completion method adopted in this embodiment. If the error value of the sales completion result of this embodiment is smaller within the selected period, it is considered that the sales completion method of this embodiment has been successfully verified, otherwise the verification has failed. The sales completion results of each month can be compared using the above-mentioned PK winning rate method, and the sales completion results corresponding to the larger number of winning months are used as the final completion results. If the number of winning months corresponding to the two methods is the same, the average error values ​​are further compared, and the sales forecast result corresponding to the method with a smaller average error value is selected as the final result.

[0111] In particular, in one embodiment, an evaluation angle of the consistency of sales and BSR ranking is also provided. Specifically, it can be considered that there is a correlation between BSR and sales, and for a BSR with a smaller value, the corresponding sales are higher. In order to quantify this correlation, this embodiment provides a ranking consistency index of sales and BSR, that is, the sales sequence rate, to evaluate the correlation between sales and BSR.

[0112] Specifically, the corresponding sales data can be sorted in ascending order according to BSR, and then the sales data in the latter order can be compared to see if it is less than the sales data in the former order; if so, the sales data is sorted in order, otherwise it is sorted in reverse order. Considering the volatility of sales, different data sampling windows can also be selected to avoid fluctuations, thereby ensuring the stability of the sorting results. Finally, the proportion of the sequential arrangement is calculated, and the consistency of BSR and sales is evaluated based on this proportion.

[0113] As shown in Table 2, there are 7 sampling points, corresponding to 7 BSRs, and the window size is 1. There are 6 relationship pairs (specifically, BSR value 1 to BSR value 2 corresponds to one relationship pair, BSR value 2 to BSR value 3 corresponds to one relationship pair, and so on), of which there are 3 reverse order pairs, and the ranking consistency rate (sequence rate) = 3 / 6 = 50%.

[0114] BSR 1 2 3 4 5 6 7 Sales 1000 500 600 350 400 700 100 Reverse 1 500 600 Reverse 2 350 400 Reverse 3 400 700

[0115] In addition, in one embodiment, a normalized monitoring strategy can also be implemented. That is, a batch of verification sets are selected, and the public sales of all historical periods of the verification set are evaluated. The sales are completed on a rolling basis every day at the time point when public sales exist, and then the difference between the collected public sales and the corresponding completed sales is compared. When the difference exceeds the preset difference threshold, the above completion process is optimized, for example, the parameters involved, such as the acquisition rate, the acquisition time interval, the interpolation processing method, etc. are optimized and adjusted.

[0116] Figure 4 is a flow chart of a sales volume completion method based on an e-commerce platform in some of the embodiments, such as Figure 4 As shown, the sales volume completion method includes the following steps:

[0117] Step S401, determine the first time interval for collecting the public sales data of the sub-body on the target day; wherein the first time collection interval is 5 days before the target day, the target day, and 5 days after the target day; execute step S403.

[0118] Step S402, determine a second time interval for collecting the BSR of the target day; wherein the second time interval for collecting the BSR is 5 days before the target day, the target day, and 5 days after the target day; and execute step S404.

[0119] Step S403, aggregating the child public sales data collected within the first collection time interval to obtain the parent public sales data.

[0120] Step S404, obtaining the parent BSR in the second acquisition time interval; wherein the parent BSR may be determined based on the average of the child BSRs.

[0121] Step S405: establish a relationship between the parent's BSR and public sales data.

[0122] Step S406, determining the above relationship pairs corresponding to different commodity categories.

[0123] Step S407, for each relationship pair, fill in the missing public sales data according to the interpolation processing algorithm; execute steps S408, S409 and step S410 respectively.

[0124] Step S408: for a sub-body with public sales, directly assign the corresponding public sales to the sub-body; and execute step S411.

[0125] Step S409: for the sub-bodies with missing public sales, divide the sub-bodies of public sales according to the number of comments; and execute step S411.

[0126] Step S410: For a single variant, directly complete it according to the sales volume of the parent; and execute step S411.

[0127] Step S411, obtaining the public sales volume of the restored sub-body.

[0128] In this embodiment, a sales volume completion device based on an e-commerce platform is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and will not be repeated hereafter. The terms "module", "unit", "subunit", etc. used below can implement a combination of software and / or hardware of predetermined functions. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0129] Figure 5 is a structural block diagram of the sales volume supplement device 50 based on the e-commerce platform of this embodiment, such as Figure 5 As shown, the sales volume supplement device 50 based on the e-commerce platform includes: an acquisition module 52, an aggregation module 54, a data supplement module 56 and a division module 58; wherein:

[0130] An acquisition module 52 is used to acquire first public sales data of the inventory unit corresponding to each standardized product unit under the target commodity category, and acquire sales ranking information of each standardized product unit;

[0131] The aggregation module 54 is used to aggregate the public sales of each standardized product unit according to the first public sales data to obtain the second public sales data corresponding to each standardized product unit; the data completion module 56 is used to establish a relationship pair between the sales ranking information corresponding to each standardized product unit and the second public sales data, and based on the relationship pair, based on the interpolation processing, the sales data of the standardized product units with missing sales under the target commodity category are completed to obtain the target completed sales data of the standardized product units with missing sales; the division module 58 is used to sub-divide the sales data of the inventory units corresponding to each standardized product unit according to the target completed sales data to obtain the full sales data of all commodities under the target commodity category.

[0132] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0133] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and will not be repeated in this embodiment.

[0134] In addition, in combination with the sales volume completion method based on the e-commerce platform provided in the above embodiment, a storage medium can also be provided in this embodiment to implement. The storage medium stores a computer program; when the computer program is executed by the processor, any one of the sales volume completion methods based on the e-commerce platform in the above embodiment is implemented.

[0135] It should be understood that the specific embodiments described herein are only used to explain the application, rather than to limit it. Based on the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the protection scope of this application.

[0136] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0137] Obviously, the drawings are only some examples or embodiments of the present application. For ordinary technicians in the field, the present application can also be applied to other similar situations based on these drawings without creative work. In addition, it is understandable that although the work done in this development process may be complicated and lengthy, for ordinary technicians in the field, certain changes in design, manufacturing or production based on the technical content disclosed in this application are only conventional technical means and should not be regarded as insufficient content disclosed in this application.

[0138] The term "embodiment" in this application refers to a specific feature, structure or characteristic described in conjunction with the embodiment that can be included in at least one embodiment of the present application. The appearance of this phrase in various locations in the specification does not necessarily mean the same embodiment, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. It is clearly or implicitly understood by those of ordinary skill in the art that the embodiments described in this application can be combined with other embodiments without conflict.

[0139] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of patent protection. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the scope of protection of the present application. Therefore, the scope of protection of the present application shall be subject to the attached claims.

Claims

1. A sales volume completion method based on an e-commerce platform, characterized in that: include: Obtaining first public sales data of the inventory unit corresponding to each standardized product unit under the target commodity category, and obtaining sales ranking information of each standardized product unit; Aggregating the public sales volume of each standardized product unit according to the first public sales volume data to obtain second public sales volume data corresponding to each standardized product unit; Establishing a relationship pair between the sales ranking information corresponding to each standardized product unit and the second public sales data, and completing the sales data of the standardized product units with missing sales under the target commodity category based on the relationship pair based on interpolation processing to obtain the target completed sales data of the standardized product units with missing sales; According to the target completed sales data, the sales data of the inventory units corresponding to each of the standardized product units are divided into sub-bodies to obtain the full sales data of all commodities under the target commodity category.

2. The sales volume supplementation method according to claim 1, characterized in that: Acquiring first public sales data of a stock quantity unit corresponding to each standardized product unit under a target commodity category, and acquiring sales ranking information of each standardized product unit, including: Obtaining the inventory units corresponding to each standardized production unit under the target commodity category, the candidate public sales data within the collection time interval corresponding to the target date, and the candidate sales ranking information within the collection time interval; the collection time interval is composed of a preset number of days before the target date, the target date, and the preset number of days after the target date; Among the candidate public sales data, the public sales data collected the closest to the target date is used as the first public sales data corresponding to the target date; Among the candidate sales ranking information, the ranking information whose collection time is closest to the target date is used as the sales ranking information corresponding to the target date.

3. The sales volume supplement method according to claim 1 or 2, characterized in that: Obtaining the first public sales data of the inventory unit corresponding to each standardized product unit under the target product category, including: Determining sales search information corresponding to keywords associated with the target product category based on a preset data analysis method for product sales; The first public sales data of the inventory units corresponding to each standardized product unit under the target commodity category is determined according to the sales search information.

4. The sales volume supplementation method according to claim 3, characterized in that: Acquiring the first public sales volume data of the inventory unit corresponding to each standardized product unit under the target commodity category, further comprising: The first public sales data of the inventory units corresponding to each standardized product unit under the target commodity category is obtained, and the commodity detail data of all the inventory units on the e-commerce platform is obtained.

5. The sales volume supplementation method according to claim 1, characterized in that: Aggregating the public sales volume of each standardized product unit according to the first public sales volume data to obtain second public sales volume data corresponding to each standardized product unit, including: According to a preset acquisition rate, sampling the first public sales data corresponding to each standardized product unit to obtain sampled public sales data; The sampled public sales data corresponding to each standardized product unit are added up, and the second public sales data corresponding to each standardized product unit is obtained based on the summed result and the acquisition rate.

6. The sales volume supplementation method according to claim 1, characterized in that: According to the relationship pair, the sales data of the standardized product unit with missing sales under the target commodity category is supplemented based on interpolation processing to obtain the target supplemented sales data of the standardized product unit with missing sales, including: According to the relationship pair, based on the nearest neighbor interpolation processing, the sales data of the standardized product unit with missing sales are completed to obtain the target completed sales data of the standardized product unit with missing sales.

7. The sales volume supplementation method according to claim 1, characterized in that: According to the target completed sales data, the sales data of the inventory units corresponding to the standardized product units are divided into sub-bodies to obtain the full sales data of all commodities under the target commodity category, including: Determine the stock keeping unit with missing sales volume under each standardized product unit as the first stock keeping unit; Determine the stock quantity unit with public sales volume under each standardized product unit as the second stock quantity unit; Obtaining to-be-divided public sales data for the first inventory unit according to the target completed sales data of each standardized product unit and the first public sales data of the second inventory unit; According to the commodity evaluation index corresponding to the first inventory unit, the public sales data to be divided is divided into different first inventory units to obtain the full sales data of all commodities under the target commodity category.

8. A sales result evaluation method, characterized in that: The method comprises: Get preset verification sales data; According to the sales volume completion method described in any one of claims 1 to 7, obtaining sales volume completion data corresponding to the verified sales volume data; Based on a preset accuracy evaluation index, the sales volume completion data corresponding to the verified sales volume data is evaluated for accuracy to obtain an accuracy evaluation result.

9. A sales volume supplement device based on an e-commerce platform, characterized in that: include: Acquisition module, aggregation module, data completion module and division module; among which: The acquisition module is used to acquire the first public sales volume data of the inventory unit corresponding to each standardized product unit under the target commodity category, and acquire the sales ranking information of each standardized product unit; The aggregation module is used to aggregate the public sales volume of each standardized product unit according to the first public sales volume data to obtain the second public sales volume data corresponding to each standardized product unit; The data completion module is used to establish a relationship pair between the sales ranking information corresponding to each standardized product unit and the second public sales data, and according to the relationship pair, based on interpolation processing, complete the sales data of the standardized product unit with missing sales under the target commodity category to obtain the target completed sales data of the standardized product unit with missing sales; The division module is used to complete the sales data according to the target, divide the sales data of the inventory units corresponding to each standardized product unit into sub-bodies, and obtain the full sales data of all commodities under the target commodity category.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the sales volume completion method described in any one of claims 1 to 7 are implemented.

Images