Resource allocation method, device and server

Abstract

The present invention provides a resource allocation method, device and server, including: obtaining basic information corresponding to each commodity category in the target classification dimension; calculating the current cumulative sales proportion corresponding to each commodity category according to the basic information corresponding to each commodity category; calculating the estimated total quantity of commodities based on the current cumulative sales proportion corresponding to each commodity category, and judging whether the estimated total quantity of commodities meets the iteration end condition; wherein the iteration end condition is calculated based on the target total quantity of commodities; if not, respectively updating the current cumulative sales proportion corresponding to each commodity category, and calculating the estimated total quantity of commodities based on the updated current cumulative sales proportion corresponding to each commodity category, until the estimated total quantity of commodities meets the iteration end condition, and obtaining the resource allocation result. The present invention can allocate online commodities more reasonably, thereby significantly improving the user experience.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a resource allocation method, device and server. Background Art

[0002] As the O2O (Online to Offline) model sweeps across all industries, the retail industry has long since changed from pure offline sales to an "online + offline" dual-core model. The online model is not only crucial to new retail formats, but also an indispensable "handle" for traditional supermarkets. While promoting overall consumption, it has established more communication channels with customers, and significantly improved the ability to deliver messages and acquire customers. At present, although online product sales are not affected by the actual offline store / shelf space, the total amount of online exposure is relatively constant. Unlimited increase in the total amount of online products cannot linearly increase sales. Moreover, due to the unreasonable allocation of product resources, it is very likely to cause customers to be distracted or difficult to quickly find the desired products, reducing user experience. Summary of the invention

[0003] In view of this, an object of the present invention is to provide a resource allocation method, device and server, which can allocate online products more reasonably, thereby significantly improving user experience.

[0004] In a first aspect, an embodiment of the present invention provides a resource allocation method, which is applied to a server, and the server stores a plurality of pre-configured classification dimensions, each of which includes a plurality of commodity categories, including: obtaining basic information corresponding to each of the commodity categories in the target classification dimension; wherein the basic information is calculated based on historical statistical data of online commodities, each of which includes a plurality of online commodities, and the historical statistical data includes historical sales data; calculating the current cumulative sales proportion corresponding to each of the commodity categories according to the basic information corresponding to each of the commodity categories; calculating the estimated total quantity of commodities based on the current cumulative sales proportion corresponding to each of the commodity categories, and judging whether the estimated total quantity of commodities meets the iteration end condition; wherein the iteration end condition is calculated based on the target total quantity of commodities; if not, respectively updating the current cumulative sales proportion corresponding to each of the commodity categories, and calculating the estimated total quantity of commodities based on the updated current cumulative sales proportion corresponding to each of the commodity categories, until the estimated total quantity of commodities meets the iteration end condition, and obtaining the resource allocation result.

[0005] In one embodiment, the historical statistical data also includes historical click data and historical search data; the step of obtaining basic information corresponding to each of the commodity categories in the target classification dimension includes: obtaining historical click data, historical search data and historical sales data of each of the commodity categories in the target classification dimension; determining multiple click levels and a first adjustment ratio corresponding to each click level based on the historical click data of each of the commodity categories; and determining multiple search levels and a second adjustment ratio corresponding to each search level based on the historical search data of each of the commodity categories; and determining multiple dynamic sales levels and a third adjustment ratio corresponding to each dynamic sales level based on the historical sales data of each of the commodity categories; and determining multiple month-on-month growth levels and a fourth adjustment ratio corresponding to each month-on-month growth level based on the historical sales data of each of the commodity categories; for each of the commodity categories, determining the commodity category from the click level based on the historical click data corresponding to the commodity category. The target click level of the product category, and the first adjustment ratio corresponding to the target click level is determined as the first adjustment ratio corresponding to the product category; and, according to the historical search data corresponding to the product category, the target search level to which the product category belongs is determined from the search level, and the second adjustment ratio corresponding to the target search level is determined as the second adjustment ratio corresponding to the product category; and, according to the historical sales data corresponding to the product category, the target dynamic sales level to which the product category belongs is determined from the dynamic sales level, and the third adjustment ratio corresponding to the target dynamic sales level is determined as the third adjustment ratio corresponding to the product category; and, according to the historical sales data corresponding to the product category, the target monthly month-on-month growth level to which the product category belongs is determined from the monthly month-on-month growth level, and the fourth adjustment ratio corresponding to the target monthly month-on-month growth level is determined as the fourth adjustment ratio corresponding to the product category; wherein the basic information includes the first adjustment ratio, the second adjustment ratio, the third adjustment ratio and the fourth adjustment ratio.

[0006] In one embodiment, the step of calculating the current cumulative sales share corresponding to each of the commodity categories based on the basic information corresponding to each of the commodity categories includes: obtaining the initial cumulative sales share; for each of the commodity categories, determining the sum of the first adjustment ratio, the second adjustment ratio, the third adjustment ratio, the fourth adjustment ratio and the initial cumulative sales share corresponding to the commodity category as the current cumulative sales share corresponding to the commodity category.

[0007] In one embodiment, the step of obtaining the initial cumulative sales share includes: obtaining an upper limit value of the cumulative sales share and a lower limit value of the cumulative sales share, and determining a first average value of the upper limit value of the cumulative sales share and the lower limit value of the cumulative sales share as the initial cumulative sales share.

[0008] In one embodiment, the historical sales data includes historical sales share; the step of calculating the estimated total number of goods based on the current cumulative sales share corresponding to each of the product categories includes: for each of the product categories, determining the target product according to the historical sales share corresponding to each online product in the product category, and judging whether the historical sales share corresponding to the target product is equal to the current cumulative sales share; if not, determining the next target product according to the historical sales share corresponding to each online product in the product category, until the sum of the historical sales share corresponding to each of the target products is equal to the current cumulative sales share, and taking the sum of the quantity of each target product as the sub-quantity of the product in the product category; calculating the sum of the sub-quantity of products in each product category to obtain the estimated total number of products.

[0009] In one implementation, the iteration end condition includes that the estimated total quantity of commodities is greater than or equal to the difference between the target total quantity of commodities and a specified value, and is less than or equal to the sum of the target total quantity of commodities and the specified value.

[0010] In one embodiment, the step of respectively updating the current cumulative sales share corresponding to each of the commodity categories includes: updating the initial cumulative sales share; for each commodity category, taking the sum of the updated initial cumulative sales share and the first adjustment ratio, the second adjustment ratio, the third adjustment ratio, and the fourth adjustment ratio corresponding to the commodity category as the updated current cumulative sales share of the commodity category; the step of updating the initial cumulative sales share includes: if the estimated total number of commodities is less than the difference between the target total number of commodities and the specified value, calculating the second average value of the upper limit value of the cumulative sales share and the initial cumulative sales share, and taking the second average value as the updated initial cumulative sales share; or, if the estimated total number of commodities is greater than the sum of the target total number of commodities and the specified value, calculating the third average value of the lower limit value of the cumulative sales share and the initial cumulative sales share, and taking the third average value as the updated initial cumulative sales share.

[0011] In a second aspect, an embodiment of the present invention further provides a resource allocation device, which is applied to a server, and the server stores a plurality of pre-configured classification dimensions, each of which includes a plurality of commodity categories, including: an information acquisition module, used to acquire basic information corresponding to each of the commodity categories in the target classification dimension; wherein the basic information is calculated based on historical statistical data of online commodities, each of which includes a plurality of online commodities, and the historical statistical data includes historical sales data; a proportion determination module, used to calculate the current cumulative sales proportion corresponding to each of the commodity categories according to the basic information corresponding to each of the commodity categories; a judgment module, used to calculate the estimated total quantity of commodities based on the current cumulative sales proportion corresponding to each of the commodity categories, and judge whether the estimated total quantity of commodities satisfies the iteration end condition; wherein the iteration end condition is calculated based on the target total quantity of commodities; an allocation module, used to update the current cumulative sales proportion corresponding to each of the commodity categories respectively when the judgment result of the judgment module is no, and calculate the estimated total quantity of commodities based on the updated current cumulative sales proportion corresponding to each of the commodity categories, until the estimated total quantity of commodities meets the iteration end condition, and obtain the resource allocation result.

[0012] In a third aspect, an embodiment of the present invention further provides a server, comprising a processor and a memory, wherein the memory stores computer-executable instructions that can be executed by the processor, and the processor executes the computer-executable instructions to implement any one of the methods provided in the first aspect.

[0013] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement any one of the methods provided in the first aspect.

[0014] A resource allocation method, device and server provided by an embodiment of the present invention first obtain basic information corresponding to each commodity category (including multiple online commodities) in a target classification dimension, where the basic information is calculated based on historical statistical data (including historical sales data) of online commodities, and then calculate the current cumulative sales share corresponding to each commodity category based on the basic information corresponding to each commodity category, and then calculate the estimated total quantity of commodities based on the current cumulative sales share corresponding to each commodity category, and when the estimated total quantity of commodities is judged to not meet the iteration end condition calculated based on the target total quantity of commodities, the current cumulative sales share corresponding to each commodity category is updated respectively, and the estimated total quantity of commodities is calculated based on the updated current cumulative sales share corresponding to each commodity category, until the estimated total quantity of commodities meets the iteration end condition, and the resource allocation result is obtained. The above method deeply mines the historical statistical data of online goods to obtain the basic information of each commodity category, and on this basis calculates the current cumulative sales share corresponding to each commodity category. The coverage of the current cumulative sales share is regarded as the degree of satisfaction of user needs. The estimated total number of commodities is calculated based on the current cumulative sales share corresponding to each of the commodity categories, and the current cumulative sales share is adjusted in combination with the iteration end condition calculated based on the total number of target commodities. This can realize the "bottom-up" intelligent planning of the number of online commodities under each commodity category, make the resource allocation results more reasonable, and can cover user needs as much as possible, greatly improving the user experience.

[0015] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.

[0016] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 A schematic diagram of a flow chart of a resource allocation method provided by an embodiment of the present invention;

[0019] Figure 2A schematic diagram of a flow chart of another resource allocation method provided by an embodiment of the present invention;

[0020] Figure 3 A schematic diagram of the structure of a resource allocation device provided by an embodiment of the present invention;

[0021] Figure 4 A schematic diagram of the structure of a server provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described in combination with the embodiments below. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] At present, the resource allocation of online goods is rather unreasonable, and has affected the user experience to a certain extent, especially in some special scenarios, where the riders' capacity is very limited, making it difficult to meet the purchase demand of a large number of categories, and only able to meet the delivery demand of a small number of daily necessities. At present, the existing online commodity resource allocation usually adopts the following two schemes: (1) After setting the total number of online sales target goods, based on the sales amount proportion of each level of commodity category (for example, three-level categories of groceries-beer-domestic beer), the number of commodity resources is allocated for each level of commodity category according to the sales amount proportion. The disadvantages are as follows: a) Only the sales amount factor is considered, which is too one-sided to describe the user demand situation and lacks rationality; b) Inferring from the sales result of sales amount may lead to "the strong get stronger and the weak get weaker", lacking insight into market dynamics and business opportunities. (2) After setting the total number of online merchandise sales targets, a comprehensive score is calculated based on the sales amount, gross profit and month-on-month growth rate of each merchandise category at a certain ratio. The comprehensive score is then normalized and the number of merchandise resources are allocated according to the normalized ratio. The shortcomings are as follows: a) Although the profit, total sales volume and growth information are taken into consideration, there is still a lack of insight into customer demand for online scenarios (for example, the click-through rate and search intensity of online app categories); b) Resource planning is allocated proportionally from top to bottom. The allocation process is not linked to specific merchandise, and it is impossible to determine whether there are enough merchandise to support the planned number of merchandise sold.

[0024] Based on this, the present invention provides a resource allocation method, device and server, which can allocate online products more reasonably, thereby significantly improving user experience.

[0025] To facilitate understanding of this embodiment, a resource allocation method disclosed in an embodiment of the present invention is first described in detail. The method is applied to a server, and the server stores multiple pre-configured classification dimensions. Figure 1 The schematic diagram of a resource allocation method shown in FIG. 1 mainly includes the following steps S102 to S108:

[0026] Step S102, obtaining basic information corresponding to each commodity category in the target classification dimension. The multi-level classification dimension may include a large classification dimension, a medium classification dimension, and a small classification dimension, or may be divided into multiple classification dimensions based on other standards. Commodity categories are the categories to which commodities belong. Each classification dimension includes multiple commodity categories, and each commodity category includes multiple online commodities. For example, the large classification includes commodity categories such as "beverages" and "snacks", and the medium classification corresponding to "beverages" includes commodity categories such as "drinking water" and "carbonated beverages", and the small classification corresponding to "drinking water" includes commodity categories such as "pure water bottled", "pure water barreled", and "mineral water bottled".

[0027] The basic information is calculated based on the historical statistical data of online products, including historical sales data, historical click data, historical search data, etc. The basic information includes multiple adjustment ratios. For example, the basic information includes a first adjustment ratio, a second adjustment ratio, a third adjustment ratio, and a fourth adjustment ratio, wherein the first adjustment ratio is based on historical click data, the second adjustment ratio is based on historical search data, and the third adjustment ratio and the fourth adjustment ratio are both based on historical sales data. Optionally, the above basic information may also include other adjustment ratios, such as a shopping cart adjustment ratio, etc. The basic information required may be calculated based on actual needs.

[0028] Exemplarily, the target classification dimension may be a medium classification dimension, and the basic information corresponding to each commodity category under the medium classification dimension is calculated based on the above historical statistical data.

[0029] Step S104, calculate the current cumulative sales share corresponding to each commodity category based on the basic information corresponding to each commodity category. The cumulative sales share is the accumulated value of multiple sales shares, and the coverage of the current cumulative sales share corresponding to the commodity category can be regarded as the degree of satisfaction of user needs. In one embodiment, the initial cumulative sales share can be pre-configured, and the same initial cumulative sales share can be configured for each commodity category at the initial stage of resource allocation. For each commodity type, the sum of the initial cumulative sales share and the basic information corresponding to the commodity category is used as the current cumulative sales share corresponding to the commodity type.

[0030] Step S106, calculate the estimated total number of goods based on the current cumulative sales ratio corresponding to each commodity category, and determine whether the estimated total number of goods meets the iteration end condition. The iteration end condition is calculated based on the target total number of goods. In one embodiment, for each commodity category, the number of commodity sub-items corresponding to the commodity category can be determined based on the historical sales ratio of each online commodity under the commodity category and the current sales ratio corresponding to the commodity category, and the sum of each commodity sub-item is used as the estimated total number of goods. In addition, the total number of target commodities can be set manually. In one embodiment, an upload channel for the total number of target commodities can be provided to the staff, and then a numerical range is calculated based on the preset specified value and the target total number. When the estimated total number of commodities is not within the numerical range, it can be determined that the estimated total number of commodities does not meet the iteration end condition.

[0031] Step S108, if not, update the current cumulative sales ratio corresponding to each commodity category respectively, and calculate the estimated total quantity of commodities based on the updated current cumulative sales ratio corresponding to each commodity category, until the estimated total quantity of commodities meets the iteration end condition, and obtain the resource allocation result.

[0032] In one embodiment, the above-mentioned initial cumulative sales share can be updated based on the dichotomy method, and then the current cumulative sales share can be updated based on the updated initial cumulative sales share and the basic information. For example, when the estimated total number of goods is greater than the maximum value of the above-mentioned numerical interval, the average value of the initial cumulative sales share and the lower limit value of the cumulative sales share is used as the new initial cumulative sales share, and the sum of the new initial cumulative sales share and the basic information is used as the new current cumulative sales share; when the estimated total number of goods is less than the minimum value of the above-mentioned numerical interval, the average value of the initial cumulative sales share and the upper limit value of the cumulative sales share is used as the new initial cumulative sales share, and the sum of the new initial cumulative sales share and the basic information is used as the new current cumulative sales share, and the above process is repeated until the estimated total number of goods meets the iteration end condition.

[0033] In addition, the resource allocation result can be understood as the number of goods allocated to each online product. In actual applications, when calculating the estimated total number of goods based on the current cumulative sales ratio, the estimated total number of goods is obtained by adding up the numbers of multiple online goods, that is, the number of goods allocated to each online product is known. Therefore, when the iteration ends, the number of goods allocated to each online product in the process of calculating the estimated total number of goods can be used as the resource allocation result.

[0034] The above-mentioned resource allocation method provided by the embodiment of the present invention deeply mines the historical statistical data of online commodities to obtain the basic information of each commodity category, and calculates the current cumulative sales share corresponding to each commodity category on this basis. The coverage of the current cumulative sales share is regarded as the degree of satisfaction of user needs. The estimated total number of commodities is calculated based on the current cumulative sales share corresponding to each commodity category, and the current cumulative sales share is adjusted in combination with the iteration end condition calculated based on the target total number of commodities. This can realize the "bottom-up" intelligent planning of the number of online commodities under each commodity category, make the resource allocation results more reasonable, and can cover user needs as much as possible, greatly improving the user experience.

[0035] The core idea of ​​the above-mentioned resource allocation method provided by the embodiment of the present invention is to make the online commodity combination cover the original needs of customers as reasonably as possible within the limited number of commodity space, so as to achieve a better sales target. In practical applications, there are multi-level category divisions for supermarket commodities. Different categories theoretically have different levels of original customer needs, and different customer demand levels require differentiated numbers of commodities to cover. First, each category will be given a current cumulative sales share, and then the current cumulative sales share will be increased or decreased according to the different customer demand levels. Among them, the demand level is measured from multiple aspects. The number of online category searches, the number of classification clicks, the category dynamic sales level and the category growth level all reflect the size and changes of customer demand from different angles. These factors will directly affect the demand coverage ratio of each category, and ultimately reach a category with large demand and at a growth level, giving more items, while categories with small demand and negative growth will be given a small number or even no items.

[0036] Based on this, the embodiment of the present invention comprehensively obtains the basic information corresponding to each commodity category in the target classification dimension through the number of online category searches, the number of category clicks, the category dynamic sales level and the category growth level, see the following steps 1 to 6:

[0037] Step 1, obtain the historical click data, historical search data and historical sales data of each product category in the target classification dimension. The time span of historical statistical data can be the same month and the recent month, or the recent 30 days or the recent 2 months. For example, the time span of historical click data and historical search data are both the same month and the recent month, the time span of historical sales data required to calculate the animation effect level is the recent 30 days, and the time span of historical sales data required to calculate the month-on-month growth level is the recent 2 months.

[0038] Step 2, determine multiple click levels and the first adjustment ratio corresponding to each click level based on the historical click data of each commodity category; and, determine multiple search levels and the second adjustment ratio corresponding to each search level based on the historical search data of each commodity category; and, determine multiple dynamic sales levels and the third adjustment ratio corresponding to each dynamic sales level based on the historical sales data of each commodity category; and, determine multiple month-on-month growth levels and the fourth adjustment ratio corresponding to each month-on-month growth level based on the historical sales data of each commodity category. Among them, the above-mentioned click level, search level, dynamic sales level and month-on-month growth level can all be set to 5, and each level is given an adjustment ratio from high to low, and the adjustment ratio is used to adjust the cumulative sales share.

[0039] Exemplarily, for the above-mentioned click level, when the product categories stored in the server backend are inconsistent with the product categories provided by the application software foreground, the foreground categories and the background categories can be mapped. After determining the correspondence between the two, the number of category clicks on the APP (application) classification page is used to calculate the number of category clicks on each product category in the classification dimension. The number of category clicks is the number of times online APP users click on each "product category" category on the homepage. Statistical methods are used to divide them into 5 levels (including the first level, the second level, the third level, the fourth level, and the fifth level), and the "cumulative sales share" adjustment ratios from high to low are +2K1, +K1, 0, -K1, and -2K1, respectively, recorded as P1, where K1 can be understood as a weight, and the K1 value is configurable.

[0040] Exemplarily, for the above-mentioned search levels, after mapping the foreground categories with the backend categories, the search times of each product category in the classification dimension is calculated through the APP search times information, where the search times are the times that online APP users search for products belonging to each "product category". Statistical methods are used to divide them into 5 levels, and the "cumulative sales share" adjustment ratios from high to low are +2K2, +K2, 0, -K2, and -2K2, respectively, recorded as P2, where K2 can be understood as a weight, and the K2 value is configurable.

[0041] Exemplarily, for the above-mentioned dynamic sales level, the dynamic sales ratio of each commodity category in the classification dimension is calculated based on the historical sales data of online commodities. The dynamic sales ratio of the category within a period of time is equal to the quotient of the number of commodities in the transaction records of the commodity category and the total number of commodities in the commodity category. Statistical methods are used to divide it into 5 levels, and the "cumulative sales share" adjustment ratios from high to low are +2K3, +K3, 0, -K3, and -2K3, respectively, recorded as P3, where K3 can be understood as a weight, and the K3 value is configurable.

[0042] Exemplarily, for the above-mentioned month-on-month growth level, the month-on-month growth of the classification dimension is calculated based on the historical sales data of online goods. Specifically, for each commodity category, the number of commodities sold in this commodity category this month is subtracted from the number of commodities sold in this commodity category last month to get the difference, and the quotient obtained by dividing the difference by the number of commodities sold in this commodity category is the month-on-month growth. Statistical methods are used to divide it into 5 levels, and the "cumulative sales share" adjustment ratios from high to low are +2K4, +K4, 0, -K4, and -2K4, respectively, recorded as P4, where K4 can be understood as a weight, and the K4 value is configurable.

[0043] Step 3, for each product category, determine the target click level of the product category from the click level based on the historical click data corresponding to the product category, and determine the first adjustment ratio corresponding to the target click level as the first adjustment ratio corresponding to the product category. Taking the click level as an example, if the number of classified clicks of the product category is higher than the first threshold, it is determined that the product category belongs to the first level; if the number of classified clicks of the product category is between the first threshold and the second threshold, it is determined that the product category belongs to the second level; if the number of classified clicks of the product category is between the second threshold and the third threshold, it is determined that the product category belongs to the third level, and so on. Furthermore, if the product category belongs to the first level, the first adjustment ratio corresponding to the category is determined to be 2k1.

[0044] Step 4: Determine the target search level to which the product category belongs from the search level according to the historical search data corresponding to the product category, and determine the second adjustment ratio corresponding to the target search level as the second adjustment ratio corresponding to the product category. For details, please refer to the above step 3, and the embodiment of the present invention will not be repeated here.

[0045] Step 5: Determine the target dynamic sales level of the product category from the dynamic sales level according to the historical sales data corresponding to the product category, and determine the third adjustment ratio corresponding to the target dynamic sales level as the third adjustment ratio corresponding to the product category. For details, please refer to the above step 3, and the embodiment of the present invention will not be repeated here.

[0046] Step 6: Determine the target monthly month-on-month growth level of the commodity category from the monthly month-on-month growth levels according to the historical sales data corresponding to the commodity category, and determine the fourth adjustment ratio corresponding to the target monthly month-on-month growth level as the fourth adjustment ratio corresponding to the commodity category. For details, please refer to the aforementioned step 3, and the embodiment of the present invention will not be repeated here.

[0047] For the aforementioned step S104, the embodiment of the present invention provides an implementation method for calculating the current cumulative sales proportion corresponding to each commodity category according to the basic information corresponding to each commodity category, see the following steps a to b:

[0048] Step a, obtaining the initial cumulative sales share. In one embodiment, the upper limit value of the cumulative sales share and the lower limit value of the cumulative sales share can be obtained, and the first average value of the upper limit value of the cumulative sales share and the lower limit value of the cumulative sales share is determined as the initial cumulative sales share. Exemplarily, the upper limit value of the cumulative sales share is recorded as max, the lower limit value of the cumulative sales share is recorded as min, and the initial cumulative sales share TOPX = (max + min) / 2.

[0049] Step b, for each commodity category, the sum of the first adjustment ratio, the second adjustment ratio, the third adjustment ratio, the fourth adjustment ratio and the initial cumulative sales ratio corresponding to the commodity category is determined as the current cumulative sales ratio corresponding to the commodity category. Among them, "cumulative sales ratio" can be regarded as the coverage of the commodity under the commodity category to customer needs. For example, 20 products are selected in the online O2O drinking water category, and the 20 products cumulatively account for 80% of the sales of all drinking water products under the omni-channel sub-category, which means that the customer demand for drinking water can be covered by 80% of these 20 products. In actual applications, the current cumulative sales ratio corresponding to the commodity category is affected by the aforementioned first adjustment ratio, the second adjustment ratio, the third adjustment ratio, and the fourth adjustment ratio. For example, the current cumulative sales ratio corresponding to the commodity category is TOPN=P1+P2+P3+P4. It should be noted that since the first adjustment ratio, the second adjustment ratio, the third adjustment ratio, and the fourth adjustment ratio corresponding to different commodity categories are different, the current cumulative sales ratios corresponding to each commodity category calculated also have certain differences.

[0050] In one implementation, the above historical sales data also includes historical sales percentages. Based on this, an embodiment of the present invention provides an implementation for calculating the estimated total quantity of goods based on the current cumulative sales percentage corresponding to each commodity category, see (i) to (iii) below:

[0051] (I) For each commodity category, determine the target commodity according to the historical sales ratio corresponding to each online commodity in the commodity category, and determine whether the historical sales ratio corresponding to the target commodity is equal to the current cumulative sales ratio. In one implementation, the target commodities can be selected from the online commodities in order of historical sales ratio from high to low. When the first target commodity is selected, it can be determined whether the historical sales ratio of the target commodity is equal to the current cumulative sales ratio. If so, the commodity quantity of the target commodity is determined as the commodity sub-quantity corresponding to the commodity category. If not, execute the following step (II).

[0052] (ii) Determine the next target product based on the historical sales share corresponding to each online product in the product category, until the sum of the historical sales share corresponding to each target product is equal to the current cumulative sales share, and use the sum of the quantity of each target product as the sub-quantity of products in the product category. The sub-quantity of products is the sum of the quantity of all target products under the product category. In one embodiment, continue to select target products from the online products in order of historical sales share from high to low, and add up the historical sales share corresponding to each selected target product until the sum is equal to the current cumulative sales share TOPN. Since the selected target products and the quantity of each target product are known in the above process, the sub-quantity of products corresponding to the product category can be obtained by adding up the quantity of each target product.

[0053] (III) Calculating the sum of the commodity sub-quantities of each commodity category to obtain the estimated total commodity quantity. In one implementation, the estimated total commodity quantity S1 is obtained by accumulating the commodity sub-quantities of each commodity category.

[0054] In practical applications, it can be determined whether the estimated total number of goods meets the iteration end condition, wherein the iteration end condition includes that the estimated total number of goods is greater than or equal to the difference between the target total number of goods S and the specified value, and is less than or equal to the sum of the target total number of goods S and the specified value, the difference is the minimum value of the above numerical interval, and the sum is the maximum value of the above numerical interval. Exemplarily, based on actual experience, the above specified value can be set to 10, that is, the numerical interval is [S-10, S+10]. Based on this, an embodiment of the present invention provides an implementation method for updating the current cumulative sales proportion corresponding to each commodity category respectively, first updating the initial cumulative sales proportion, and then for each commodity category, the sum of the updated initial cumulative sales proportion and the first adjustment ratio, the second adjustment ratio, the third adjustment ratio, and the fourth adjustment ratio corresponding to the commodity category is used as the updated current cumulative sales proportion of the commodity category. For example, TOPN (new) = TOPX (new) + P1 + P2 + P3 + P4, wherein TOPN (new) is also the updated current cumulative sales proportion, and TOPX (new) is also the updated initial cumulative sales proportion.

[0055] Furthermore, the embodiment of the present invention also provides an implementation method for updating the initial cumulative sales ratio, including the following cases 1 and 2:

[0056] Case 1: If the estimated total number of products is less than the difference between the target total number of products and the specified value, calculate the second average value of the upper limit of the cumulative sales ratio and the initial cumulative sales ratio, and use the second average value as the updated initial cumulative sales ratio. For example, when S1 < S - 10, the updated initial cumulative sales ratio TOP X (new) = (TOP X (original) + max) / 2, where TOP X (original) is the initial cumulative sales ratio before the update.

[0057] Case 2: If the estimated total number of products is greater than the sum of the target total number of products and the specified value, calculate the third average value of the lower limit of the cumulative sales ratio and the initial cumulative sales ratio, and use the third average value as the updated initial cumulative sales ratio. For example, when S1 > S + 10, the updated initial cumulative sales ratio TOP X (new) = (TOP X (original) - min) / 2.

[0058] When the estimated total number of products S1 is within the range of [S - 10, S + 10], the TOP N (new) at this time can be determined as the final cumulative sales ratio. In the embodiment of the present invention, after determining the initial cumulative sales ratio and the adjustment ratio, the cumulative sales ratio TOP N that each product category is recommended to cover can be obtained, that is, TOP N = TOP X + P1 + P2 + P3 + P4. In practical applications, TOP N can be restricted, such as TOP N not exceeding 95% at most.

[0059] For the convenience of understanding the foregoing embodiments, the embodiment of the present invention also provides an application example of a resource allocation method. Refer to Figure 2 the flowchart of another resource allocation method shown in

[0060] Step S202: Obtain historical statistical data. Specifically, refer to the foregoing step 1, which will not be elaborated in the embodiment of the present invention this time.

[0061] Step S204: Calculate the adjustment ratio. Specifically, refer to the foregoing steps 2 to 6, which will not be elaborated in the embodiment of the present invention this time.

[0062] Step S206: Calculate the cumulative sales ratio. Specifically, refer to the foregoing steps a to b, which will not be elaborated in the embodiment of the present invention this time.

[0063] Step S208, calculation of resource allocation results. The resource allocation results (also referred to as the recommended number of allocated products) may include the number of each online product in each product category under the major, medium and minor categories. Exemplarily, based on the historical sales data of all channels in the same period (recent period), the products in the medium category are arranged from high to low by sales volume, and the products that need to be selected to meet the cumulative sales coverage ratio of the medium category are calculated (the number of products is also determined at the same time). Through the binding relationship between the products and the major / medium / minor categories, the recommended number of allocated products for each major category and minor category can be obtained at the same time. The example results are shown in Table 1 below (assuming the total number of products is 1588):

[0064] Table 1

[0065]

[0066] In summary, the resource allocation method provided in the embodiment of the present invention has constructed a set of perfect dimension combinations for describing customer needs, and uses online and offline information to reasonably reflect user needs. It also implements a set of online product quantity planning system solutions oriented to user needs, realizes intelligent planning of the number of products sold under each product category, and promotes the online product combination to cover customer needs as reasonably as possible, ultimately achieving the purpose of promoting sales.

[0067] The resource allocation method provided in the embodiment of the present invention combines multiple aspects of online and offline information to provide a complete dimensional combination characterization solution for customer needs, so that user needs can be reasonably reflected by data. Accurate mining of online user needs is an important basis for the reasonable allocation of the number of commodities. And guided by user needs, the coverage of "cumulative sales share" under the category is regarded as the degree of satisfaction of customer needs; by combining the current cumulative sales share with the adjustment ratio, the coverage of "cumulative sales share" is dynamically adjusted according to the total number of commodities, so as to realize the "bottom-up" intelligent planning of the number of commodities sold under each commodity category, so as to promote the online commodity combination to cover customer needs as reasonably as possible, and finally achieve the purpose of improving customer purchase satisfaction and promoting sales.

[0068] For the resource allocation method provided in the above embodiment, an embodiment of the present invention provides a resource allocation device, which is applied to a server, and the server stores a plurality of pre-configured classification dimensions, each of which includes a plurality of commodity categories, see Figure 3 The schematic diagram of the structure of a resource allocation device shown in FIG. 1 mainly includes the following parts:

[0069] The information acquisition module 302 is used to acquire basic information corresponding to each commodity category in the target classification dimension; wherein the basic information is calculated based on historical statistical data of online commodities, each commodity category includes multiple online commodities, and the historical statistical data includes historical sales data;

[0070] The proportion determination module 304 is used to calculate the current cumulative sales proportion corresponding to each commodity category according to the basic information corresponding to each commodity category;

[0071] A judgment module 306 is used to calculate the estimated total quantity of goods based on the current cumulative sales proportion corresponding to each commodity category, and to judge whether the estimated total quantity of goods meets the iteration end condition; wherein the iteration end condition is calculated based on the target total quantity of goods;

[0072] The allocation module 308 is used to update the current cumulative sales ratio corresponding to each commodity category respectively when the judgment result of the judgment module is no, and calculate the estimated total quantity of commodities based on the updated current cumulative sales ratio corresponding to each commodity category, until the estimated total quantity of commodities meets the iteration end condition, and obtain the resource allocation result.

[0073] The above-mentioned resource allocation device provided by the embodiment of the present invention deeply mines the historical statistical data of online commodities to obtain the basic information of each commodity category, and calculates the current cumulative sales share corresponding to each commodity category on this basis. The coverage of the current cumulative sales share is regarded as the degree of satisfaction of user needs. The estimated total number of commodities is calculated based on the current cumulative sales share corresponding to each commodity category, and the current cumulative sales share is adjusted in combination with the iteration end condition calculated based on the target total number of commodities. This can realize the "bottom-up" intelligent planning of the number of online commodities under each commodity category, make the resource allocation results more reasonable, and can cover user needs as much as possible, greatly improving the user experience.

[0074] In one embodiment, the information acquisition module 302 is also used to: obtain historical click data, historical search data, and historical sales data for each commodity category within the target classification dimension; determine multiple click levels and a first adjustment ratio corresponding to each click level based on the historical click data of each commodity category; and determine multiple search levels and a second adjustment ratio corresponding to each search level based on the historical search data of each commodity category; and determine multiple dynamic sales levels and a third adjustment ratio corresponding to each dynamic sales level based on the historical sales data of each commodity category; and determine multiple month-on-month growth levels and a fourth adjustment ratio corresponding to each month-on-month growth level based on the historical sales data of each commodity category; for each commodity category, determine the target click level to which the commodity category belongs from the click level based on the historical click data corresponding to the commodity category, and adjust the first adjustment ratio corresponding to the target click level; The first adjustment ratio is determined as the first adjustment ratio corresponding to the commodity category; and, the target search level to which the commodity category belongs is determined from the search level according to the historical search data corresponding to the commodity category, and the second adjustment ratio corresponding to the target search level is determined as the second adjustment ratio corresponding to the commodity category; and, the target dynamic sales level to which the commodity category belongs is determined from the dynamic sales level according to the historical sales data corresponding to the commodity category, and the third adjustment ratio corresponding to the target dynamic sales level is determined as the third adjustment ratio corresponding to the commodity category; and, the target month-on-month growth level to which the commodity category belongs is determined from the month-on-month growth level according to the historical sales data corresponding to the commodity category, and the fourth adjustment ratio corresponding to the target month-on-month growth level is determined as the fourth adjustment ratio corresponding to the commodity category; wherein the basic information includes the first adjustment ratio, the second adjustment ratio, the third adjustment ratio and the fourth adjustment ratio.

[0075] In one embodiment, the proportion determination module 304 is also used to: obtain the initial cumulative sales proportion; for each commodity category, determine the sum of the first adjustment ratio, the second adjustment ratio, the third adjustment ratio, the fourth adjustment ratio and the initial cumulative sales proportion corresponding to the commodity category as the current cumulative sales proportion corresponding to the commodity category.

[0076] In one embodiment, the proportion determination module 304 is also used to: obtain an upper limit value and a lower limit value of the cumulative sales proportion, and determine a first average value of the upper limit value and the lower limit value of the cumulative sales proportion as the initial cumulative sales proportion.

[0077] In one embodiment, the judgment module 306 is also used to: for each commodity category, determine the target commodity according to the historical sales ratio corresponding to each online commodity in the commodity category, and judge whether the historical sales ratio corresponding to the target commodity is equal to the current cumulative sales ratio; if not, determine the next target commodity according to the historical sales ratio corresponding to each online commodity in the commodity category, until the sum of the historical sales ratios corresponding to each target commodity is equal to the current cumulative sales ratio, and use the sum of the commodity quantity of each target commodity as the commodity sub-quantity of the commodity category; calculate the sum of the commodity sub-quantity of each commodity category to obtain the estimated total commodity quantity.

[0078] In one embodiment, the iteration end condition includes that the estimated total quantity of commodities is greater than or equal to the difference between the target total quantity of commodities and the specified value, and is less than or equal to the sum of the target total quantity of commodities and the specified value.

[0079] In one embodiment, the allocation module 308 is also used to: update the initial cumulative sales share; for each commodity category, use the sum of the updated initial cumulative sales share and the first adjustment ratio, the second adjustment ratio, the third adjustment ratio, and the fourth adjustment ratio corresponding to the commodity category as the updated current cumulative sales share of the commodity category; the allocation module 308 is also used to: if the estimated total number of commodities is less than the difference between the target total number of commodities and the specified value, calculate the second average value of the upper limit value of the cumulative sales share and the initial cumulative sales share, and use the second average value as the updated initial cumulative sales share; or, if the estimated total number of commodities is greater than the sum of the target total number of commodities and the specified value, calculate the third average value of the lower limit value of the cumulative sales share and the initial cumulative sales share, and use the third average value as the updated initial cumulative sales share.

[0080] The device provided in the embodiment of the present invention has the same implementation principle and technical effects as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference may be made to the corresponding contents in the aforementioned method embodiment.

[0081] An embodiment of the present invention provides a server. Specifically, the server includes a processor and a storage device. The storage device stores a computer program, and when the computer program is executed by the processor, it executes the method described in any one of the above-mentioned embodiments.

[0082] Figure 4 A structural diagram of a server provided in an embodiment of the present invention, the server 100 includes: a processor 40, a memory 41, a bus 42 and a communication interface 43, wherein the processor 40, the communication interface 43 and the memory 41 are connected via the bus 42; the processor 40 is used to execute an executable module stored in the memory 41, such as a computer program.

[0083] The memory 41 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 43 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0084] The bus 42 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0085] Among them, the memory 41 is used to store programs, and the processor 40 executes the program after receiving the execution instruction. The method executed by the device for flow process definition disclosed in any embodiment of the above-mentioned embodiment of the present invention can be applied to the processor 40 or implemented by the processor 40.

[0086] The processor 40 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 40. The above processor 40 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 gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in the embodiment of the present invention can be directly embodied as a hardware decoding processor to be executed, or the hardware and software modules in the decoding processor can be executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 41, and the processor 40 reads the information in the memory 41 and completes the steps of the above method in combination with its hardware.

[0087] The computer program product of the readable storage medium provided in the embodiment of the present invention includes a computer-readable storage medium storing program code, and the instructions included in the program code can be used to execute the methods described in the previous method embodiments. The specific implementation can be referred to the previous method embodiments, which will not be repeated here.

[0088] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0089] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A resource allocation method, characterized in that: The method is applied to a server, and the server stores a plurality of pre-configured classification dimensions, each of which includes a plurality of commodity categories, including: Obtaining basic information corresponding to each of the commodity categories within the target classification dimension; wherein the basic information is calculated based on historical statistical data of online commodities, each of the commodity categories includes multiple online commodities, and the historical statistical data includes historical sales data, historical click data, and historical search data; Calculate the current cumulative sales ratio corresponding to each of the commodity categories according to the basic information corresponding to each of the commodity categories; Calculating an estimated total quantity of goods based on the current cumulative sales percentage corresponding to each of the commodity categories, and determining whether the estimated total quantity of goods satisfies an iteration end condition; wherein the iteration end condition is calculated based on the total quantity of target goods; If not, respectively update the current cumulative sales proportion corresponding to each of the commodity categories, and calculate the estimated total quantity of commodities based on the updated current cumulative sales proportion corresponding to each of the commodity categories, until the estimated total quantity of commodities meets the iteration end condition, and obtain the resource allocation result; The step of calculating the current cumulative sales share corresponding to each of the commodity categories based on the basic information corresponding to each of the commodity categories includes: configuring the same initial cumulative sales share for each of the commodity categories at the initial stage of resource allocation, and for each of the commodity categories, using the sum of the initial cumulative sales share and the basic information corresponding to the commodity category as the current cumulative sales share corresponding to the commodity category; wherein the basic information includes a first adjustment ratio, a second adjustment ratio, a third adjustment ratio and a fourth adjustment ratio, the first adjustment ratio is obtained based on the historical click data, the second adjustment ratio is obtained based on the historical search data, and the third adjustment ratio and the fourth adjustment ratio are both obtained based on the historical sales data.

2. The method according to claim 1, characterized in that The step of obtaining basic information corresponding to each of the commodity categories in the target classification dimension includes: Obtain historical click data, historical search data, and historical sales data for each of the product categories within the target classification dimension; Determine multiple click levels and a first adjustment ratio corresponding to each click level based on the historical click data of each of the commodity categories; and determine multiple search levels and a second adjustment ratio corresponding to each search level based on the historical search data of each of the commodity categories; and determine multiple dynamic sales levels and a third adjustment ratio corresponding to each dynamic sales level based on the historical sales data of each of the commodity categories; and determine multiple month-on-month growth levels and a fourth adjustment ratio corresponding to each month-on-month growth level based on the historical sales data of each of the commodity categories; For each of the product categories, based on the historical click data corresponding to the product category, determine the target click level to which the product category belongs from the click levels, and determine the first adjustment ratio corresponding to the target click level as the first adjustment ratio corresponding to the product category; and, determining a target search level to which the product category belongs from the search levels according to the historical search data corresponding to the product category, and determining the second adjustment ratio corresponding to the target search level as the second adjustment ratio corresponding to the product category; and, determining a target dynamic sales level to which the commodity category belongs from the dynamic sales levels according to the historical sales data corresponding to the commodity category, and determining a third adjustment ratio corresponding to the target dynamic sales level as the third adjustment ratio corresponding to the commodity category; and, determining a target monthly month-on-month growth level to which the commodity category belongs from the monthly month-on-month growth levels according to the historical sales data corresponding to the commodity category, and determining a fourth adjustment ratio corresponding to the target monthly month-on-month growth level as the fourth adjustment ratio corresponding to the commodity category; The basic information includes a first adjustment ratio, a second adjustment ratio, a third adjustment ratio and a fourth adjustment ratio.

3. The method according to claim 2, characterized in that The step of configuring the same initial cumulative sales ratio for each of the commodity categories at the initial stage of resource allocation, and for each of the commodity categories, taking the sum of the initial cumulative sales ratio and the basic information corresponding to the commodity category as the current cumulative sales ratio corresponding to the commodity category, includes: Get the initial cumulative sales percentage; For each of the commodity categories, the sum of the first adjustment ratio, the second adjustment ratio, the third adjustment ratio, the fourth adjustment ratio and the initial cumulative sales share corresponding to the commodity category is determined as the current cumulative sales share corresponding to the commodity category.

4. The method according to claim 3, characterized in that The step of obtaining the initial cumulative sales percentage includes: Obtain an upper limit value of the cumulative sales proportion and a lower limit value of the cumulative sales proportion, and determine a first average value of the upper limit value of the cumulative sales proportion and the lower limit value of the cumulative sales proportion as the initial cumulative sales proportion.

5. The method according to claim 1, characterized in that: The historical sales data includes historical sales percentage; The step of calculating the estimated total quantity of goods based on the current cumulative sales proportion corresponding to each of the commodity categories includes: For each of the commodity categories, determine the target commodity according to the historical sales ratio of each online commodity in the commodity category, and determine whether the historical sales ratio of the target commodity is equal to the current cumulative sales ratio; If not, determine the next target product according to the historical sales ratio corresponding to each of the online products in the product category, until the sum of the historical sales ratios corresponding to each of the target products is equal to the current cumulative sales ratio, and use the sum of the product quantities of each of the target products as the product sub-quantity of the product category; The sum of the sub-quantities of each product category is calculated to obtain the estimated total quantity of the products.

6. The method according to claim 1, characterized in that The iteration end condition includes that the estimated total quantity of commodities is greater than or equal to the difference between the target total quantity of commodities and a specified value, and is less than or equal to the sum of the target total quantity of commodities and the specified value.

7. The method according to claim 4, characterized in that The step of respectively updating the current cumulative sales proportion corresponding to each of the commodity categories includes: Updating the initial cumulative sales ratio; for each commodity category, taking the sum of the updated initial cumulative sales ratio and the first adjustment ratio, the second adjustment ratio, the third adjustment ratio, and the fourth adjustment ratio corresponding to the commodity category as the updated current cumulative sales ratio of the commodity category; The step of updating the initial cumulative sales percentage includes: If the estimated total number of goods is less than the difference between the target total number of goods and the specified value, calculate the second average value of the upper limit value of the cumulative sales proportion and the initial cumulative sales proportion, and use the second average value as the updated initial cumulative sales proportion; or, if the estimated total number of goods is greater than the sum of the target total number of goods and the specified value, calculate the third average value of the lower limit value of the cumulative sales proportion and the initial cumulative sales proportion, and use the third average value as the updated initial cumulative sales proportion.

8. A resource allocation device, characterized in that: The device is applied to a server, and the server stores a plurality of pre-configured classification dimensions, each of which includes a plurality of commodity categories, including: An information acquisition module, used to acquire basic information corresponding to each of the commodity categories within the target classification dimension; wherein the basic information is calculated based on historical statistical data of online commodities, each of the commodity categories includes multiple online commodities, and the historical statistical data includes historical sales data, historical click data, and historical search data; A proportion determination module, used to calculate the current cumulative sales proportion corresponding to each of the commodity categories according to the basic information corresponding to each of the commodity categories; A judgment module, configured to calculate an estimated total quantity of goods based on the current cumulative sales proportion corresponding to each of the commodity categories, and to judge whether the estimated total quantity of goods satisfies an iteration end condition; wherein the iteration end condition is calculated based on the target total quantity of goods; an allocation module, configured to update the current cumulative sales proportion corresponding to each of the commodity categories respectively when the judgment result of the judgment module is no, and calculate the estimated total quantity of commodities based on the updated current cumulative sales proportion corresponding to each of the commodity categories, until the estimated total quantity of commodities meets the iteration end condition, thereby obtaining a resource allocation result; The proportion determination module is specifically used to: configure the same initial cumulative sales proportion for each of the commodity categories at the initial stage of resource allocation, and for each of the commodity categories, use the sum of the initial cumulative sales proportion and the basic information corresponding to the commodity category as the current cumulative sales proportion corresponding to the commodity category; wherein the basic information includes a first adjustment ratio, a second adjustment ratio, a third adjustment ratio and a fourth adjustment ratio, the first adjustment ratio is obtained based on the historical click data, the second adjustment ratio is obtained based on the historical search data, and the third adjustment ratio and the fourth adjustment ratio are both obtained based on the historical sales data.

9. A server, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the method according to any one of claims 1 to 7.

Images