A clothing size pushing method and device and electronic equipment

Abstract

The one or more embodiments of the specification disclose a clothing size pushing method, device and electronic equipment, the method comprises: determining a user size of a user when accessing a page where a target clothing commodity is located, and a commodity size table corresponding to the target clothing commodity; determining a size matching algorithm corresponding to the target service commodity according to a commodity category to which the clothing commodity belongs; and determining a commodity size that meets a preset matching condition with the user size based on the size matching algorithm and the commodity size table, and pushing to the user. Therefore, the set error corresponding to the commodity category can be determined according to the size matching algorithm corresponding to the size attribute under different commodity categories, the clothing commodities of different commodity categories are distinguished, and the commodity size meeting the preset matching condition is selected for pushing, thereby improving the accuracy of clothing size matching and pushing and improving the user experience.

Description

TECHNICAL FIELD

[0001] The present document relates to the technical field of computer technology, and particularly relates to a clothing size pushing method and device and electronic equipment. BACKGROUND

[0002] In the clothing e-commerce scene, based on the browsing and collection operations of a consumer user on clothing goods, appropriate clothing sizes are pushed to the user according to the user size, which is a current competition demand in the e-commerce field.

[0003] However, considering that the user size is often between adjacent clothing sizes, there is a fuzzy pushing situation, and there is a lack of differentiation of different types of clothing goods. Therefore, the existing clothing size pushing solution does not accurately push the clothing size to the consumer user, and the user experience is poor. SUMMARY

[0004] An object of one or more embodiments of the present specification is to provide a clothing size pushing method, device and electronic equipment, to determine the goods size matched with the user size according to the size matching algorithm corresponding to different goods categories, thereby improving the accuracy of clothing size matching and pushing, and improving the user experience.

[0005] To solve the above technical problems, one or more embodiments of the present specification are implemented as follows:

[0006] In a first aspect, a clothing size pushing method is provided, comprising:

[0007] determining a user size of a user when accessing a page where a target clothing good is located, and a goods size table corresponding to the target clothing good, wherein the goods size table contains a plurality of goods sizes, and each goods size contains size attribute values corresponding to a plurality of size attributes one by one;

[0008] determining a size matching algorithm corresponding to the target service good based on a goods category to which the target clothing good belongs, and determining a goods size satisfying a preset matching condition with the user size based on the size matching algorithm and the goods size table;

[0009] pushing the goods size.

[0010] In a second aspect, a clothing size pushing device is provided, comprising:

[0011] a determination module configured to determine a user size of a user when accessing a page where a target clothing good is located, and a goods size table corresponding to the target clothing good, wherein the goods size table contains a plurality of goods sizes, and each goods size contains size attribute values corresponding to a plurality of size attributes one by one;

[0012] The selection module is used to determine the size matching algorithm corresponding to the target service product based on the product category to which the target clothing product belongs, and to determine the product size that meets the preset matching conditions with the user's size based on the size matching algorithm and the product size table.

[0013] The push module is used to push the product size.

[0014] Thirdly, an electronic device is proposed, comprising:

[0015] Processor; and

[0016] A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform the clothing size push method described in the first aspect.

[0017] Fourthly, a computer-readable storage medium is proposed, which stores one or more programs that, when executed by an electronic device including multiple applications, cause the electronic device to perform the clothing size push method described in the first aspect.

[0018] As can be seen from the technical solutions provided by one or more embodiments in the above specification, the size matching algorithm is selected based on the product category to which the clothing product belongs. Specifically, when the product category to which the clothing product belongs matches a set of product categories, the size matching algorithm corresponding to the target service product can be determined based on the product category to which the clothing product belongs. Based on the size matching algorithm and the product size table, the product size matching the user's size is determined and pushed to the user. Therefore, based on the size matching algorithms corresponding to different product categories, the setting error corresponding to different size attributes under the product category can be determined, clothing products of different product categories can be distinguished, and product sizes that meet preset matching conditions can be selected and pushed to them, thereby improving the accuracy of clothing size matching and pushing, and enhancing the user experience. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in one or more embodiments or prior art of this specification, the accompanying drawings used in the description of one or more embodiments or prior art will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments recorded in this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a schematic diagram illustrating the steps of a clothing size push method provided in the embodiments of this specification.

[0021] Figure 2is a processing flow schematic diagram of a clothing size recommendation scheme provided by an embodiment of the present specification.

[0022] Figure 3 is a structural schematic diagram of a clothing size pushing device provided by an embodiment of the present specification.

[0023] Figure 4 is a structural schematic diagram of an electronic device provided by an embodiment of the present specification. DETAILED DESCRIPTION

[0024] In order for those skilled in the art to better understand the technical solutions in the present specification, the technical solutions in one or more embodiments of the present specification will be clearly and completely described below in conjunction with the drawings in one or more embodiments of the present specification. Obviously, the described one or more embodiments are only a part of the embodiments of the present specification, not all embodiments. Based on one or more embodiments in the present specification, all other embodiments obtained by those skilled in the art without creative labor should belong to the protection scope of the present document.

[0025] The e-commerce industry is currently highly competitive, especially in the clothing e-commerce scenario. It is a necessity to recommend appropriate sizes to consumer users, but it is difficult to select and push appropriate product sizes according to product size tables for consumer users of various body shapes. The main problems are as follows: First, for consumer users, the scenario where the SKU products of adjacent sizes in the product size table of certain clothing products can be worn causes ambiguity in matching. For example, a consumer user is 168 cm tall and weighs 105 kg; the height of this consumer user belongs to M, and the weight belongs to L, so the product size of M and L can be pushed to this consumer user. SKU (Stock keeping Unitsku) refers to the smallest inventory unit, which can be understood as the clothing product number here. SKU refers to a product, each product has a SKU, which is convenient for e-commerce brands to identify products. For example, a product has multiple colors, so it has multiple SKU numbers. For example, a pair of shoes has 6 colors, and each color has 12 sizes, so the SKU of this pair of shoes is 72. Second, different clothing products have different silhouettes, and consumer users have different size preferences. However, the current size recommendation cannot match according to the product category, and the user experience is not good.

[0026] To this end, the embodiment of the present specification proposes a clothing size pushing method, the inventive concept of which is to select a matching size pushing algorithm according to the product category to which the clothing product belongs, and in particular, when the set product category set is hit for the product category to which the clothing product belongs, the clothing size that meets the preset matching condition can be selected from the product size table according to the set error corresponding to at least one size attribute under the product category to which the clothing product belongs, and pushed to the user. Thus, the clothing products of different product categories can be distinguished according to the set error corresponding to different size attributes under different product categories, and the product size that meets the preset matching condition is selected for them, thereby improving the accuracy of clothing size matching and pushing and improving the user experience.

[0027] Embodiment one

[0028] Referring to Figure 1 Fig. 1 is a step schematic diagram of a clothing size pushing method provided by the embodiment of the present specification, it should be understood that the method is applied in an e-commerce scenario, especially an e-commerce selling scenario involving clothing products, and the execution subject can be a clothing size pushing device, which can be a server providing e-commerce platform services, such as a cloud server or a distributed server, etc. or a certain service module integrated in the server. The clothing size pushing method can include the following steps:

[0029] Step 102: determining the user size of the user when accessing the page where the target clothing product is located, and the product size table corresponding to the target clothing product, wherein the product size table contains a plurality of product sizes, and each product size contains a size attribute value corresponding to a plurality of size attributes.

[0030] In the embodiments of the present application, when a user accesses a page of a target clothing commodity, the user's own user size can be automatically determined. In fact, the user can add his / her own body size in advance in his / her account, and can also add the body sizes of relatives or friends, wherein the body sizes of the relatives or friends can be taken as role identifiers based on the relationship between the user and the relatives or friends, for example, "I-female-user size 1", "Mom-female-user size 2", "Husband-male-user size 3", and the like, so as to establish a user size archive. In the user size of each role, a plurality of size attributes are contained, for example, height, weight, waistline, bust, hip, shoulder width, arm circumference, foot length, and the like. These size attributes can be divided into basic attributes, upper body attributes, lower body attributes, and foot attributes according to body structure. The basic attributes can include height and weight; the upper body attributes can include shoulder width, arm length, arm circumference, upper bust, lower bust, and the like; the lower body attributes can include waistline, hip, leg length, thigh circumference, and the like; and the foot attributes can include foot length, foot width, and the like. In fact, a historical purchase size, that is, the size of the clothing usually worn by the user role, can also be set in the size attribute, for example, a usual shoe size. The user can add his / her own and the relatives' or friends' user sizes in the account according to these size attributes, and pre-establish a user size archive.

[0031] When the user accesses the page of the target clothing commodity, the user can be automatically matched with a selected role according to the commodity related information (for example, commodity category, commodity details, and the like) of the page of the target clothing commodity accessed by the user, and the user size corresponding to the selected role is determined; or the user can be matched with the user size of the role selected by the user according to the selection operation of the user, for example, the user size of the role desired to be served is selected from the size archive.

[0032] Meanwhile, when the user accesses the page of the target clothing commodity, the commodity size table of the target clothing commodity can also be determined according to the commodity details of the page of the target clothing commodity accessed by the user. The commodity size table can include a plurality of commodity sizes, for example, S size, M size, L size, XL size, and the like; each commodity size includes size attribute values corresponding to a plurality of size attributes one by one. Referring to Table 1 shown below, the commodity size table of the target clothing commodity-male trousers is shown, wherein M, L, XL, 2XL, 3XL, and 4XL are included, and the size attribute values corresponding to M size are weight (kg) 55, waistline (cm) 74, height (cm) 160, and hip (cm) 53; the size attribute values corresponding to L size are weight (kg) 60, waistline (cm) 76, height (cm) 165, and hip (cm) 55, and the remaining commodity sizes are not described in detail.

[0033] Size Weight (kg) Waist (cm) Height (cm) Hip (cm) M 55 74 160 53 L 60 76 165 55 XL 65 78 170 57 2XL 70 82 175 59 3XL 75 86 180 63 4XL 80 88 185 67

[0034] Table 1

[0035] Step 104: determining the size matching algorithm corresponding to the target service commodity based on the commodity category to which the target clothing commodity belongs, and determining the commodity size satisfying the preset matching condition with the user size based on the size matching algorithm and the commodity size table.

[0036] In the embodiments of the present specification, in order to improve the matching and pushing accuracy of clothing sizes, different size matching schemes can be set according to different commodity categories to which clothing commodities belong. In specific implementation, the commodity categories of different clothing commodities can be counted, for example, shoes, bras, underwear, coats, skirts, shirts, etc. Among them, except for shoes, the clothing commodities of other categories can be matched in size according to height and weight. However, considering the defect of inaccurate size matching, the present specification introduces another new size matching and pushing scheme; and the commodity category using the new size matching and pushing scheme can be selected according to the size attributes contained in each commodity category. For example, the commodity category of shoes does not depend on height and weight, so the new size matching and pushing scheme can be used; underwear is generally elastic clothing, as long as the weight or BMI is within a certain range, the existing height and weight can be used for size matching; actually, underwear can also use the new size matching and pushing scheme. Therefore, the set commodity category set can be determined according to the size attributes contained in different commodity categories. If the size attributes for decision-making size matching contain height and / or weight, and size matching can be completed only by relying on height and / or weight, then the commodity category can not be added to the set commodity category set, otherwise, the commodity category should be added to the set commodity category set. It should be noted that even if the size attributes for decision-making size matching contain height and / or weight, and size matching can be completed only by relying on height and / or weight, the commodity category can be added to the set commodity category set.

[0037] It should be understood that for the commodity category for which size matching can be completed using height and / or weight size attributes, an experience identifier can be added, for example, the “isSgMain” identifier parameter is added, and “isSgMain=true” indicates that the commodity category selects the height and / or weight matching scheme.

[0038] Therefore, in the embodiments of the present specification, the commodity categories are classified in advance, and different matching schemes are assigned. If the commodity category to which the clothing commodity belongs exists in the set commodity category set, the new size matching scheme proposed in the present specification is adopted for the clothing commodity; otherwise, the existing height and / or weight size matching scheme is adopted for the clothing commodity. Thus, the size attributes for decision-making matching scheme in the commodity category to which the clothing commodity belongs.

[0039] In the embodiment of the present specification, in step 104, based on the size matching algorithm corresponding to the target service commodity determined based on the commodity category to which the target clothing commodity belongs, and based on the commodity size table determined based on the size matching algorithm and the commodity size table, the matching degree of the user size and each commodity size in the commodity size table can be determined based on the set error corresponding to at least one size attribute in the commodity category to which the target clothing commodity belongs. The commodity size satisfying the preset matching condition with the user size is selected from the commodity size table based on the determined matching degree. Wherein, the matching degree refers to the matching degree of the user size and the commodity size, which can be determined based on the set error according to the number of user size hitting commodity size.

[0040] In the embodiment of the present specification, in step 104, based on the size matching algorithm corresponding to the target service commodity determined based on the commodity category to which the target clothing commodity belongs, and based on the commodity size table determined based on the size matching algorithm and the commodity size table, the matching degree of the user size and each commodity size in the commodity size table can be determined based on the set error corresponding to at least one size attribute in the commodity category to which the target clothing commodity belongs. The commodity size satisfying the preset matching condition with the user size is selected from the commodity size table based on the determined matching degree. Wherein, the matching degree refers to the matching degree of the user size and the commodity size, which can be determined based on the set error according to the number of user size hitting commodity size.

[0041] In the embodiment of the present specification, in step 104, based on the size matching algorithm corresponding to the target service commodity determined based on the commodity category to which the target clothing commodity belongs, and based on the commodity size table determined based on the size matching algorithm and the commodity size table, the matching degree of the user size and each commodity size in the commodity size table can be determined based on the set error corresponding to at least one size attribute in the commodity category to which the target clothing commodity belongs. The commodity size satisfying the preset matching condition with the user size is selected from the commodity size table based on the determined matching degree. Wherein, the matching degree refers to the matching degree of the user size and the commodity size, which can be determined based on the set error according to the number of user size hitting commodity size.

[0042] Step 1, from the set error corresponding to at least one size attribute in the commodity category to which the target clothing commodity belongs, the set error corresponding to the size attribute contained in the commodity size table is obtained.

[0043] It should be noted that the commodity category is a category representing a type of clothing commodity, so the types of size attributes corresponding to the commodity category are relatively comprehensive; and the target clothing commodity is a specific commodity for sale, which can have different commodity size tables according to different merchants or platforms, and the difference mainly lies in the types of size attributes contained. For example, for the commodity category of skirts, the size attributes that can be contained are: height, waist circumference, weight, shoulder width, bust, sleeve length, hem circumference, and sleeve opening; and the size attributes contained in the commodity size table corresponding to the target clothing commodity-Skirt A are: waist circumference, weight, shoulder width, bust, sleeve length, hem circumference, and sleeve opening; and the size attributes contained in the commodity size table corresponding to the target clothing commodity-Skirt B are: waist circumference, shoulder width, hem circumference, and sleeve opening. Therefore, even if different target clothing commodities belong to the same commodity category, they can have different size attributes, or only contain part of the size attributes under the commodity category according to the characteristic style of the clothing commodity itself. Therefore, the set error corresponding to the size attributes contained in the commodity size table of the target clothing commodity is obtained from the set error of the size attributes under the commodity category to which the target clothing commodity belongs.

[0044] In step 2, each set error obtained is substituted into the size attribute value corresponding to different commodity sizes to obtain a size attribute range value.

[0045] In the embodiments of the present specification, the set error can be predicted based on a size attribute error model, which is obtained by repeatedly training a model based on the purchase size and user size in historical purchase behavior data. The set error can be an absolute error or a relative error, where the absolute error can be the difference between the size attribute value of the user size and the size attribute value of the commodity size; and the relative error can be the ratio of the absolute error to the size attribute value of the user size. There are two types of size attribute error models, one is an absolute error size attribute error model, and the other is a relative error size attribute error model. Since the calculation formulas are different, the required basic data can be determined from the purchase size and user size in the historical purchase behavior data, substituted into the corresponding calculation formula, and repeatedly trained to obtain.

[0046] It should be understood that in the embodiments of the present specification, the set error can be a specific error value or an error range. Here, no specific limitation is made, and it can be predicted from the corresponding model according to the type of set error.

[0047] It should be noted that in the matching and pushing scheme for the target clothing size, the user can be matched with a suitable clothing size based on the absolute error or the relative error corresponding to the size attributes contained in the commodity size table, or both the absolute error and the relative error.

[0048] Step 3, for each product size, calculate the number of size attribute range values in the product size that the user size hits, and determine the matching degree of the user size and each product size in the product size table according to the obtained number of hits.

[0049] In other words, each size attribute value in the user size hits the corresponding size attribute range value in the product size. For example, the product size table of the target clothing product contains size attributes: height, weight, waist, and leg length. The size attribute values in the user size are: height 159, weight 55, waist 21, and leg length 60. For the S size in the product size table, calculate whether the height 159 in the user size is within the corresponding size attribute range value, whether the weight 55 is within the corresponding size attribute range value, whether the waist 21 is within the corresponding size attribute range value, and whether the leg length 60 is within the corresponding size attribute range value. If it is determined that the height, weight, and waist are within the corresponding size attribute range values, then the number of size attribute range values in the S size that the user size hits is 3. Similarly, calculate for the M size, L size, and other sizes respectively. Suppose it is determined that the number of size attribute range values in the M size that the user size hits is 3, the number of size attribute range values in the L size that the user size hits is 1, and the number of size attribute range values in the XL size that the user size hits is 0. Then, according to the number of size attribute range values in the product size that the user size hits, determine the matching degree of the user size and the product size. Generally, the more hits, the higher the matching degree.

[0050] The set error is an absolute error or a relative error. Then, for each product size, calculate the number of size attribute range values in the product size that the user size hits based on the absolute error or the relative error, and determine the matching degree of the user size and each product size in the product size table according to the number of hits based on the absolute error or the relative error. At this time, the user size and each product size determine a matching degree, i.e., the matching degree corresponding to the absolute error or the matching degree corresponding to the relative error.

[0051] The setting error includes an absolute error and a relative error (both of which are greater than zero); for each commodity size, a first number of the user size hitting a size attribute range value determined based on the absolute error in the commodity size is calculated, and a second number of the user size hitting a size attribute range value determined based on the relative error in the commodity size is calculated; a first matching degree of the user size and each commodity size in the commodity size table is determined according to the first number of hits, and a second matching degree of the user size and each commodity size in the commodity size table is determined according to the second number of hits. At this time, two matching degrees of the user size and each commodity size are determined, one is the matching degree corresponding to the absolute error, and the other is the matching degree corresponding to the relative error.

[0052] In fact, step 104 can also determine the setting error of the key size attribute based on the setting error of at least one size attribute corresponding to the commodity category to which the target clothing commodity belongs, and then determine the commodity size in the commodity size table hit by the user size based on the setting error of the key size attribute, and select the commodity size that meets the preset matching condition with the user size from the hit commodity size. The preset matching condition here can be that the relative error is not greater than the second threshold or the relative error is the smallest, that is, the commodity size with the relative error not greater than the second threshold with the user size is selected from the hit commodity size, or the commodity size with the smallest relative error with the user size is selected from the hit commodity size.

[0053] In the embodiments of the present application, when selecting the commodity size that meets the preset matching condition with the user size from the commodity size table based on the determined matching degree, step 104 can be specifically implemented as: selecting the commodity size with the matching degree reaching a first threshold with the user size from the commodity size table based on the determined matching degree. If there are multiple commodity sizes in the commodity size table with the matching degree reaching the first threshold with the user size, the commodity size with the relative error not greater than the second threshold calculated with the user size can be further selected from the multiple commodity sizes with the matching degree reaching the first threshold. In this way, the commodity size with the matching degree reaching a certain threshold can be selected, ensuring the accuracy of the matching size. Further, when there is more than one commodity size with the matching degree reaching the first threshold, the relative error of the user size and the corresponding commodity size can be calculated to analyze which commodity size is closer to the user size, thereby improving the size matching accuracy. Moreover, by pushing one or more matched commodity sizes to the user for the user to select, the user has accurate and selectable space, and the user shopping experience is improved.

[0054] The relative error between user size and product size can be calculated by selecting the size attribute values ​​of key size attributes in the product size table and using the result as the relative error between user size and product size. Alternatively, the relative error between the size attribute value of each size attribute in the product size table and the corresponding size attribute value in the user size table can be calculated separately, and the sum of these relative errors can be used as the relative error between user size and product size. Or, the relative error between the size attribute value of each size attribute in the product size table and the corresponding size attribute value in the user size table can be calculated separately, and the average of these relative errors can be used as the relative error between user size and product size.

[0055] Ideally, the product size with the smallest relative error calculated from the user's size can be selected from multiple product sizes that have reached the first threshold of matching degree.

[0056] Step 106: Push product size.

[0057] Based on the product sizes matched in step 104, one or more (usually two) selected product sizes are pushed to the user. These multiple product sizes can be one size larger and / or one size smaller than the determined optimal product size.

[0058] The following reference Figure 2 The diagram shown illustrates the processing flow of the clothing size recommendation scheme, using different clothing product categories as examples.

[0059] First, iterate through the product sizes of the target apparel items. Specifically, iterate through the SKU numbers of the target apparel items, determine the product sizes based on the SKU numbers, and initialize the setting error corresponding to the size attributes in the product size table to zero. Also, determine the user size of the user's selected role and iterate through the size attributes of the product sizes.

[0060] Then, different matching schemes are executed based on the product category of the target apparel item. Among them, shoes, bras, and other apparel items can be grouped into a set of defined product categories, while underwear can select an appropriate matching scheme based on its accompanying identifiers.

[0061] For shoes, the optional error bias of the size attributes including foot length and foot width is unidirectional, that is, the product size larger than the user size should be selected. Then, the corresponding absolute error range = x and relative error errorrange = y of the foot length and foot width in the corresponding shoes are obtained. The values determined by the absolute error x and the relative error y are substituted into the shoe size, and the user size is determined by the formula: shoe size <= user size <= shoe size + x; and (shoe size - user size) / user size <= y, so as to determine the user size >= shoe size / (1 + y), and the shoe size of the user size falling within the above size range is selected, and here multiple shoe sizes may be hit. Then, the relative error abs((user size - product size) / user size) of the multiple shoe sizes and the user size is calculated respectively, and the shoe size with the minimum relative error is taken as the push result.

[0062] For a bra, the upper bust circumference and the difference between the upper bust circumference and the lower bust circumference are required for size matching, so the absolute error range = x and the relative error errorrange = y of the two size attributes are obtained. The user's lower bust circumference sku_xxw is within the range [-x + sku_xxw, x + sku_xxw], and the bust circumference difference sku_delta is within the range [-x + sku_delta, x + sku_delta]; and the user's lower bust circumference sku_xxw is within the range [sku_xxw / (1 + y), sku_xxw / (1 - y)]. Here, the absolute error x of the two size attributes is the same, and the relative error y is the same. The bra size of the user size falling within the above size range is selected, and here multiple bra sizes may be hit. Then, the relative error abs((user size - product size) / user size) of the multiple bra sizes and the user size is calculated respectively, and the bra size with the minimum relative error is taken as the push result.

[0063] For an underwear, in the case of carrying experience identification, the height matching scheme is preferred. If the height sku_sg in the user size is within the range [-x + sku_sg, x + sku_sg], it is further considered whether the weight or obesity rate in the user size is less than or equal to the set threshold. In the case of determining less than or equal to the set threshold, the product size corresponding to sku_sg is directly pushed to the user. Otherwise, the size attribute range value determined by the absolute error and the relative error of other size attributes is considered to determine the product size hit by the user size, which can refer to the formula in the bra matching scheme. Then, the relative error abs((user size - product size) / user size) of the multiple underwear sizes and the user size is calculated respectively, and the underwear size with the minimum relative error is taken as the push result.

[0064] For other clothing, the absolute error and the relative error of the size attribute range value determined by the size attribute can be considered to determine the size of the user size hit the product size, which can refer to the formula in the bra matching scheme. Then, the relative error of the user size and the product size abs((user size-product size) / user size) in multiple product sizes can be calculated respectively, and the product size with the smallest relative error is taken as the push result.

[0065] In the above scheme, the matching degree of the user size and the product size is determined by setting the error, and then the product size with smaller relative error is selected from the product size table as the push result. The error between the user size and the product size is constrained in a reliable range by absolute error or relative error, which improves the accuracy of matching the product size to the user size.

[0066] It should be noted that the user information (including but not limited to user equipment information, user personal information, user size information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation portal for user to choose authorization or refusal.

[0067] Embodiment two

[0068] Referring to Figure 3 As shown in the figure, the clothing size push device provided by the embodiment of the present specification, the device 300 can include:

[0069] The determination module 302 is configured to determine the user size of the user when accessing the page where the target clothing product is located, and the product size table corresponding to the target clothing product, wherein the product size table contains multiple product sizes, and each product size contains size attribute values corresponding to multiple size attributes one by one;

[0070] The selection module 304 is configured to determine the size matching algorithm corresponding to the target service product based on the product category to which the target clothing product belongs, and determine the product size matched with the user size based on the size matching algorithm and the product size table;

[0071] The push module 306 is configured to push the product size.

[0072] Optionally, as an embodiment, the selection module 304 is specifically configured to: determine a matching degree of the user size and each product size in the product size table based on the set error corresponding to at least one size attribute in the product category to which the target clothing product belongs; and select a product size that satisfies a preset matching condition with the user size from the product size table based on the determined matching degree, when determining the product size matched with the user size based on the size matching algorithm corresponding to the target service product and the product size table based on the product category to which the target clothing product belongs.

[0073] In a specific implementation manner of the embodiments of the present specification, the selection module 304 is specifically configured to: obtain the set error corresponding to the size attribute included in the product size table from the set error corresponding to at least one size attribute in the product category to which the target clothing product belongs; and obtain a size attribute range value by substituting each obtained set error into the size attribute value corresponding to different product sizes, when determining the matching degree of the user size and each product size in the product size table based on the set error corresponding to at least one size attribute in the product category to which the target clothing product belongs; and calculate the number of hits of the user size in the size attribute range value of each product size, and determine the matching degree of the user size and each product size in the product size table according to the obtained hit number.

[0074] In another specific implementation manner of the embodiments of the present specification, the set error is an absolute error or a relative error; and the selection module 304 is specifically configured to: calculate the number of hits of the user size in the size attribute range value of each product size based on the absolute error or the relative error, and determine the matching degree of the user size and each product size in the product size table according to the hit number obtained based on the absolute error or the relative error, when calculating the number of hits of the user size in the size attribute range value of each product size, and determining the matching degree of the user size and each product size in the product size table according to the obtained hit number.

[0075] In a further specific implementation of the embodiments of the present disclosure, the setting error includes an absolute error and a relative error; and the selection module 304, when calculating the number of times that the user size hits the size attribute range value in each product size and determining the matching degree of the user size and each product size in the product size table according to the obtained number of hits, is specifically configured to: for each product size, calculate a first number of times that the user size hits the size attribute range value determined based on the absolute error in the product size, and calculate a second number of times that the user size hits the size attribute range value determined based on the relative error in the product size; and determine a first matching degree of the user size and each product size in the product size table according to the first number of hits, and determine a second matching degree of the user size and each product size in the product size table according to the second number of hits.

[0076] In a further specific implementation of the embodiments of the present disclosure, when the selection module 304 selects the product size that meets the preset matching condition with the user size from the product size table based on the determined matching degree, the selection module 304 is specifically configured to: select the product size whose matching degree with the user size reaches a first threshold value from the product size table based on the determined matching degree.

[0077] In a further specific implementation of the embodiments of the present disclosure, if there are multiple product sizes in the product size table whose matching degrees with the user size reach the first threshold value, the selection module 304 is further configured to: select the product size whose relative error calculated with the user size is not greater than a second threshold value from the multiple product sizes whose matching degrees reach the first threshold value.

[0078] In a further specific implementation of the embodiments of the present disclosure, when the selection module 304 selects the product size whose relative error calculated with the user size is not greater than the second threshold value from the multiple product sizes whose matching degrees reach the first threshold value, the selection module 304 is specifically configured to: select the product size with the minimum relative error calculated with the user size from the multiple product sizes whose matching degrees reach the first threshold value.

[0079] In a further specific implementation of the embodiments of the present disclosure, when the selection module 304 selects the product size with the minimum relative error calculated with the user size from the multiple product sizes whose matching degrees reach the first threshold value, the selection module 304 is specifically configured to: select the product size with the minimum relative error calculated with the user size from the multiple product sizes whose matching degrees reach the first threshold value.

[0080] In a further specific implementation of the embodiments of the present disclosure, the determination module 302, when determining the user size of the user when accessing the page where the target clothing product is located, is specifically configured to determine the user size corresponding to the role selected by the user when accessing the page where the target clothing product is located.

[0081] In still another specific implementation manner of the embodiments of the present disclosure, the setting error is predicted based on a size attribute error model, and the size attribute error model is obtained by repeatedly training a setting model based on the purchase size and the user size in historical purchase behavior data.

[0082] According to the technical solution, the matching size pushing algorithm is selected according to the product category to which the clothing product belongs, and when the product category set is hit, the setting error corresponding to at least one size attribute under the product category to which the clothing product belongs is selected to select the product size that meets the preset matching condition from the product size table and push it to the user. Thus, the setting error corresponding to different size attributes under different product categories is used to distinguish clothing products of different product categories and select product sizes that meet the preset matching condition for pushing, thereby improving the accuracy of clothing size matching and pushing and improving the user experience.

[0083] Embodiment Three

[0084] Figure 4 is a structural schematic diagram of an electronic device according to an embodiment of the present disclosure. Please refer to Figure 4 At the hardware level, the electronic device includes a processor, and optionally further includes an internal bus, a network interface, and a memory. The memory can include a memory such as a random-access memory (RAM), and can also include a non-volatile memory such as at least one disk memory. Of course, the electronic device can also include other hardware required by the business.

[0085] The processor, network interface, and memory can be connected to each other through an internal bus, which can be an industry standard architecture (ISA) bus, a peripheral component interconnect (PCI) bus, or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, and a control bus. For ease of representation, Figure 4 In the figure, only one bidirectional arrow is used to represent the bus, but it does not mean that there is only one bus or only one type of bus.

[0086] The memory is configured to store a program. Specifically, the program can include program code including computer operation instructions. The memory can include an internal memory and a non-volatile memory, and provide instructions and data to the processor.

[0087] The processor reads the corresponding computer program from the non-volatile memory into the internal memory and then runs, and forms a clothing size pushing device at a logical level. The processor executes the program stored in the memory, and is specifically configured to perform the following operations:

[0088] determine a user size of a user when the user accesses a page where a target clothing item is located, and a product size table corresponding to the target clothing item, wherein the product size table includes a plurality of product sizes, and each product size includes size attribute values corresponding to a plurality of size attributes; determine a size matching algorithm corresponding to the target service product based on a product category to which the target service product belongs, and determine a product size that satisfies a preset matching condition with the user size based on the size matching algorithm and the product size table; and push the product size.

[0089] The above as described in the specification Figure 1 and Figure 2The method performed by the device disclosed in the embodiments shown can be applied in a processor or implemented by the processor. The processor can be an integrated circuit chip having a signal processing capability. In the implementation, each step of the above method can be completed by integrated logic circuits or instructions in the form of software in the processor. The processor mentioned above can be a general processor, including a central processing unit (CPU), a network processor (NP), etc.; or can be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component. Each method, step and logic block disclosed in one or more embodiments of the present specification can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in combination with one or more embodiments of the present specification can be directly embodied as a hardware code processor for execution, or a combination of hardware and software modules in the code processor for execution. The software module can be located in a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register or other mature storage medium in the art. The storage medium is located in the memory, and the processor reads the information in the memory and combines the hardware to complete the steps of the above method.

[0090] The electronic device can further perform the method of Figure 1 and Figure 2 and implement the functions of the corresponding device in Figure 1 and Figure 2 the embodiments shown, and the embodiments of the present specification will not be repeated here.

[0091] Of course, in addition to the software implementation, the electronic device of the embodiments of the present specification does not exclude other implementation manners, such as logic devices or a combination of software and hardware, etc. That is, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or a logic device.

[0092] Embodiment Four

[0093] The embodiments of the present specification also propose a computer readable storage medium storing one or more programs, the one or more programs including instructions capable of causing the portable electronic device including a plurality of application programs to perform the method of Figure 1 andFigure 2 The method of the illustrated embodiment, and in particular for performing the following method:

[0094] determine a user size of a user when accessing a page where a target clothing item is located, and a product size table corresponding to the target clothing item, wherein the product size table contains a plurality of product sizes, and each product size contains a size attribute value corresponding to a plurality of size attributes; determine a size matching algorithm corresponding to the target service product based on a product category to which the target clothing item belongs, and determine a product size that meets a preset matching condition with the user size based on the size matching algorithm and the product size table; and push the product size.

[0095] In conclusion, the above only describes the preferred embodiments of the present specification, and is not used to limit the protection scope of the present specification. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification shall be included in the protection scope of the present specification.

[0096] The system, device, module or unit illustrated by one or more embodiments described above can be specifically implemented by a computer chip or entity, or by a product with certain functions. A typical implementation device is a computer. Specifically, the computer may, for example, be a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0097] The computer readable medium includes permanent and non-permanent, removable and non-removable media, which can be implemented by any method or technology to store information. The information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic tape disk storage or other magnetic storage device, or any other non-transmission medium that can be used to store information accessible by a computing device. According to the definition in this paper, computer readable medium does not include transitory media, such as modulated data signals and carriers.

[0098] It is also to be noted that the terms "comprising", "including", and any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises a... " does not, without more constraints, exclude the existence of additional identical elements in the process, method, article, or apparatus that comprises the recited element.

[0099] Each of the embodiments in the present specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each of the embodiments focuses on the difference from other embodiments. In particular, for the system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the part of the method embodiments.

[0100] The above describes specific embodiments of the present specification. Other embodiments are within the scope of the appended claims. In some cases, the acts or steps recited in the claims can be performed in a different order than the order in which the acts or steps are recited in the embodiments and still achieve desirable results. In addition, the processes depicted in the figures do not necessarily require the particular order shown, or sequential order, to achieve the desired results. In certain implementations, multitasking and parallel processing can be advantageous.

Claims

1. A method for pushing a clothing size, comprising: determining a user size of a user when accessing a page where a target clothing item is located, and a size table corresponding to the target clothing item, wherein the size table comprises a plurality of item sizes, and each item size comprises size attribute values corresponding to a plurality of size attributes; determining a number of size attributes of an item size in the size table hit by the user size based on a set error corresponding to at least one size attribute under a category to which the target clothing item belongs and the size attribute values of each item size in the size table, to obtain a matching degree of the user size and the item size; determining an item size matching the user size based on the matching degree; and pushing the item size. 2.The method of claim 1, wherein determining the item size matching the user size based on the matching degree comprises: determining an item size satisfying a preset matching condition from the size table based on the matching degree. 3.The method of claim 2, wherein determining the number of size attributes of the item size hit by the user size based on the set error corresponding to at least one size attribute under the category to which the target clothing item belongs and the size attribute values of each item size in the size table to obtain the matching degree of the user size and the item size comprises: obtaining a set error corresponding to a size attribute included in the size table from the set error corresponding to at least one size attribute under the category to which the target clothing item belongs; substituting each obtained set error into a size attribute value corresponding to a different item size to obtain a size attribute range value; calculating, for each item size, a number of size attribute range values hit by the user size, and determining the matching degree of the user size and each item size in the size table based on the obtained number. 4.The method of claim 3, wherein the set error is an absolute error or a relative error. calculating, for each item size, the number of size attribute range values hit by the user size, and determining the matching degree of the user size and each item size in the size table based on the obtained number, comprises: calculating, for each item size, the number of size attribute range values hit by the user size based on the absolute error or the relative error, and determining the matching degree of the user size and each item size in the size table based on the obtained number based on the absolute error or the relative error. 5.The method of claim 3, wherein the set error comprises an absolute error and a relative error. calculating, for each item size, the number of size attribute range values hit by the user size, and determining the matching degree of the user size and each item size in the size table based on the obtained number, comprises: For each product size, calculate a first number of the user size hitting the size attribute range value determined based on the absolute error in the product size, and calculate a second number of the user size hitting the size attribute range value determined based on the relative error in the product size; Determine a first matching degree of the user size and each product size in the product size table according to the first number of hits, and determine a second matching degree of the user size and each product size in the product size table according to the second number of hits.

6. The clothing size pushing method of claim 2, determining a product size satisfying a preset matching condition with the user size from the product size table based on the determined matching degrees, specifically comprising: Selecting a product size with a matching degree reaching a first threshold value with the user size from the product size table based on the determined matching degrees.

7. The clothing size pushing method of claim 6, if there are multiple product sizes in the product size table with a matching degree reaching the first threshold value with the user size, the method further comprises: Selecting a product size with a relative error calculated with the user size not greater than a second threshold value from the multiple product sizes with the matching degree reaching the first threshold value.

8. The clothing size pushing method of claim 7, selecting a product size with a relative error calculated with the user size not greater than a second threshold value from the multiple product sizes with the matching degree reaching the first threshold value, specifically comprising: Selecting a product size with a minimum relative error calculated with the user size from the multiple product sizes with the matching degree reaching the first threshold value.

9. The clothing size pushing method of claim 8, pushing the product size, specifically comprising: Pushing the product size with the minimum relative error calculated with the user size selected from the multiple product sizes with the matching degree reaching the first threshold value, and pushing a product size one size larger and / or one size smaller than the product size.

10. The clothing size pushing method of claim 1, determining the user size of the user when accessing a page where a target clothing product is located, specifically comprising: Determining a user size corresponding to a selected role of the user when accessing the page where the target clothing product is located.

11. The clothing size pushing method of any one of claims 2-10, the set error being predicted based on a size attribute error model, the size attribute error model being obtained through repeated training of a set model based on purchase size and user size in historical purchase behavior data.

12. A clothing size pushing device, comprising: A determination module configured to determine a user size of a user when accessing a page where a target clothing product is located, and a product size table corresponding to the target clothing product, wherein the product size table contains multiple product sizes, and each product size contains size attribute values corresponding to multiple size attributes one by one. The selecting module is configured to determine a number of size attributes of a product size in the product size table hit by the user size based on the set error corresponding to at least one size attribute under a product category to which the target product belongs and the size attribute value of each product size in the product size table, to obtain a matching degree of the user size and the product size; and determine the product size matched with the user size based on the matching degree. The pushing module is configured to push the product size. 13.An electronic device comprising: a processor; and a memory arranged to store computer-executable instructions that, when executed, cause the processor to perform the method of any one of claims 1-11. 14.A computer-readable storage medium storing one or more programs, the one or more programs, when executed by an electronic device including multiple applications, causing the electronic device to perform the method of any one of claims 1-11.

Images