CN116664143A

CN116664143A - Size information processing method, apparatus and storage medium

Info

Publication number: CN116664143A
Application number: CN202310669473.XA
Authority: CN
Inventors: 吴健君; 昝树勋
Original assignee: Taobao China Software Co Ltd
Current assignee: Taobao China Software Co Ltd
Priority date: 2023-06-06
Filing date: 2023-06-06
Publication date: 2023-08-29

Abstract

The application provides a size information processing method, equipment and storage medium, which are used for target users needing to estimate the size of a figure, wherein the method comprises the following steps: acquiring the input body sizes of a plurality of reference users who have placed a list on the target category item and the original sizes of the target category item; determining the standard size of the target class according to the input stature size and the original size; determining a predicted figure size of a target user applicable to the target class according to the standard size and the target class; and determining the final figure size of the target user suitable for the target class according to the estimated figure size and the input information of the target user. The application improves the calculation precision of the figure size of the user, further can provide high-precision size information for size recommendation, improves the accuracy of size recommendation and improves the user experience.

Description

Size information processing method, apparatus and storage medium

Technical Field

The present application relates to the field of information processing technologies, and in particular, to a size information processing method, apparatus, and storage medium.

Background

In the electronic market of apparel, the size is a very important factor for the consumer to make decisions, and a considerable part of the reasons for the user to return are that the size of apparel is not suitable, so how to recommend proper size information to the user in the electronic market is a very important problem.

The technical scheme for recommending the sizes of the users depends on the self-size files provided by the users and the size table of the commodities, in an actual scene, the user size files have the problem that a large number of size attributes are lost, and many times the user is unclear about the self-size attribute values (such as shoulder width, foot length and other data), so that the provided self-size files also have inaccurate conditions, the accuracy of the size recommendation results based on the user size files is very low, the dissatisfaction rate and the unintelligy rate of the users on the recommendation results are high, and the user experience is poor.

Disclosure of Invention

The main purpose of the embodiment of the application is to provide a size information processing method, equipment and storage medium, which can improve the calculation precision of the figure size of a user, further can provide high-precision size information for size recommendation, improve the accuracy of size recommendation and improve the user experience.

In a first aspect, an embodiment of the present application provides a size information processing method, for a target user who needs to estimate a size, the method including: acquiring the input body sizes of a plurality of reference users who have placed a list on the target category item and the original sizes of the target category item; determining the standard size of the target class according to the input stature size and the original size; determining a predicted figure size of a target user applicable to the target class according to the standard size and the target class; and determining the final figure size of the target user suitable for the target class according to the estimated figure size and the input information of the target user.

In an embodiment, the obtaining the entered stature sizes of the plurality of reference users who have placed the order for the target category item includes: acquiring first historical order information of a target category item, wherein the first historical order information comprises a plurality of reference user identifiers for placing an order for the target category item; and acquiring the input stature sizes of the plurality of reference users according to the plurality of reference user identifications.

In one embodiment, the target category item includes a plurality of size-identified items; the determining the standard size of the target class according to the input stature size and the original size comprises the following steps: determining an average size of the entered stature sizes corresponding to the plurality of reference users for the target category item identified by the single size; determining the confidence coefficient of the average size according to the first historical order information of the target category item, wherein the confidence coefficient is positively correlated with the number of times of the target category item is placed; and if the confidence coefficient is larger than a first preset threshold value, determining the average size as the standard size of the target category, otherwise, if the confidence coefficient is smaller than or equal to the first preset threshold value, determining the standard size corresponding to the target category according to the original size.

In one embodiment, the original size includes: the page display size and merchant input size of the target category article; and if the confidence coefficient is smaller than or equal to the first preset threshold, determining a standard size corresponding to the target category according to the original size, including: if the confidence coefficient is smaller than or equal to the first preset threshold value, judging whether the page display size is empty or not; if the page display size is not empty, determining the page display size as the standard size of the target class; and if the page display size is empty, the merchant input size is defined as the standard size of the target class.

In an embodiment, the standard size includes value information of a plurality of size attributes, and the size attributes are used for representing size information of a user body part to which the article is applicable; the determining, according to the standard size and the target category, the estimated stature size of the target user applicable to the target category includes: acquiring second historical order information of the target user on the target category item, and acquiring a mapping relation between the item category and the size attribute; inquiring to obtain a target size attribute corresponding to the target category according to the target category and the mapping relation; determining the order size identification of the target user on the target category item according to the second historical order information; and determining the target size attribute value corresponding to the order size identifier from the value information, and determining the estimated figure size of the target user suitable for the target class according to the target size attribute value.

In an embodiment, the target user makes a plurality of orders for the target category item; the target size attribute value is a size value sequence comprising a plurality of values; the determining, according to the target size attribute value, that the target user is suitable for the target class purpose, which includes: determining the median of the size value sequence, selecting a target value which is larger than the median and has a difference value smaller than a preset value from the size value sequence, and generating a new size value sequence corresponding to the target size attribute based on the target value; and calculating the average value of the new size value sequence, and determining the average value as the estimated stature size of the target user suitable for the target class purpose.

In an embodiment, before said determining the median of said sequence of size values, further comprising: removing outliers in the size value sequence according to the target category; and/or if the target category belongs to a preset size larger category, carrying out reduction processing on the size value sequence according to a preset reduction amount; and if the target category belongs to the preset size smaller category, amplifying the size value sequence according to the preset amplifying amount.

In an embodiment, the determining, based on the estimated stature size and the input information of the target user, the final stature size applicable to the target class by the target user includes: if the target input stature size exists in the input information of the target user, calculating an error rate between the estimated stature size and the target input stature size; judging whether the error rate is smaller than a second preset threshold value, if the error rate is smaller than the second preset threshold value, determining the average value of the estimated stature size and the target input stature size as the final stature size suitable for the target class of the target user, otherwise, determining the target input stature size as the final stature size suitable for the target class of the target user.

In an embodiment, the target category includes functional category information and first gender information to which the target category item belongs; the input information of the target user comprises second gender information of the target user, and the second gender information is matched with the first gender information.

In a second aspect, an embodiment of the present application provides a size information pushing method, including: responding to the access operation of a current user to a current page, and acquiring the current category of the current commodity in the current page; obtaining a final figure size of the current user applicable to the current category, wherein the final figure size is determined according to an original size of the current category, the input figure sizes of a plurality of reference users and the input information of the current user, and the plurality of reference users are users who have placed a list on the commodity of the current category; and providing the final stature size to the current user.

In a third aspect, an embodiment of the present application provides a size information processing apparatus for a target user who needs to estimate a size, the apparatus including:

the acquisition module is used for acquiring the input body sizes of a plurality of reference users who have placed the list on the target category item and the original sizes of the target category item;

the first determining module is used for determining a standard size corresponding to the target category to which the target category object belongs according to the input stature size and the original size;

the second determining module is used for determining the estimated stature size of the target user suitable for the target category according to the standard size and the target category;

and the third determining module is used for determining the final figure size of the target user applicable to the target class based on the estimated figure size and the input information of the target user.

In an embodiment, the obtaining module is configured to: acquiring first historical order information of a target category item, wherein the first historical order information comprises a plurality of reference user identifiers for placing an order for the target category item; and acquiring the input stature sizes of the plurality of reference users according to the plurality of reference user identifications.

In one embodiment, the target category item includes a plurality of size-identified items; the first determining module is used for determining average sizes of the input stature sizes of the plurality of reference users aiming at the target category articles with single size identification; determining the confidence coefficient of the average size according to the first historical order information of the target category item, wherein the confidence coefficient is positively correlated with the number of times of the target category item is placed; and if the confidence coefficient is larger than a first preset threshold value, determining the average size as the standard size of the target category, otherwise, if the confidence coefficient is smaller than or equal to the first preset threshold value, determining the standard size corresponding to the target category according to the original size.

In one embodiment, the original size includes: the page display size and merchant input size of the target category article; the first determining module is further configured to determine whether the page display size is empty if the confidence coefficient is less than or equal to the first preset threshold; if the page display size is not empty, determining the page display size as the standard size of the target class; and if the page display size is empty, the merchant input size is defined as the standard size of the target class.

In an embodiment, the standard size includes value information of a plurality of size attributes, and the size attributes are used for representing size information of a user body part to which the article is applicable; the second determining module is used for obtaining second historical order information of the target user on the target category item and obtaining a mapping relation between the item category and the size attribute; inquiring to obtain a target size attribute corresponding to the target category according to the target category and the mapping relation; determining the order size identification of the target user on the target category item according to the second historical order information; and determining the target size attribute value corresponding to the order size identifier from the value information, and determining the estimated figure size of the target user suitable for the target class according to the target size attribute value.

In an embodiment, the target user makes a plurality of orders for the target category item; the target size attribute value is a size value sequence comprising a plurality of values; the second determining module is further configured to determine a median of the sequence of size values, select a target value that is greater than the median and has a difference value with the median that is less than a preset value from the sequence of size values, and generate a new sequence of size values corresponding to the target size attribute based on the target value; and calculating the average value of the new size value sequence, and determining the average value as the estimated stature size of the target user suitable for the target class purpose.

In one embodiment, the apparatus further comprises: the preprocessing module is used for eliminating outliers in the size value sequence according to the target category before the median of the size value sequence is determined; and/or if the target category belongs to a preset size larger category, carrying out reduction processing on the size value sequence according to a preset reduction amount; and if the target category belongs to the preset size smaller category, amplifying the size value sequence according to the preset amplifying amount.

In an embodiment, the third determining module is configured to calculate an error rate between the estimated stature size and the target input stature size if the target input stature size exists in the input information of the target user; judging whether the error rate is smaller than a second preset threshold value, if the error rate is smaller than the second preset threshold value, determining the average value of the estimated stature size and the target input stature size as the final stature size suitable for the target class of the target user, otherwise, determining the target input stature size as the final stature size suitable for the target class of the target user.

In a fourth aspect, an embodiment of the present application provides an electronic device, including:

at least one processor; and

a memory communicatively coupled to the at least one processor;

wherein the memory stores instructions executable by the at least one processor to cause the electronic device to perform the method of any of the above aspects.

In a fifth aspect, an embodiment of the present application provides a cloud device, including:

at least one processor; and

a memory communicatively coupled to the at least one processor;

wherein the memory stores instructions executable by the at least one processor to cause the cloud device to perform the method of any of the above aspects.

In a sixth aspect, an embodiment of the present application provides a computer readable storage medium, where computer executable instructions are stored, and when executed by a processor, implement the method according to any one of the above aspects.

In a seventh aspect, embodiments of the present application provide a computer program product comprising a computer program which, when executed by a processor, implements the method of any of the above aspects.

According to the size information processing method, the size information processing equipment and the storage medium, the final commodity size of the commodity is determined according to the purchase records of a plurality of reference users on the commodity, the input size of each first user and the original size of the commodity, then the estimated size of the commodity is determined for the target user who has placed the commodity based on the final commodity size and the category of the commodity, and then the final size of the target user is determined based on the estimated size and the input information of the target user, so that the historical order data of the user is fully utilized, and the commodity size table is enriched by utilizing the size data maintained by the user and the original size of the commodity; finally, the final commodity size code table and purchase record data of the target user are utilized to estimate the size suitable for the target user, size calibration is carried out based on the estimated size and target user input information, the final size of the target user for the commodity is obtained, the accuracy of user size estimation is improved, high-accuracy size information can be provided for size recommendation, the size recommendation accuracy is improved, and user experience is improved.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application. It will be apparent to those of ordinary skill in the art that the drawings in the following description are of some embodiments of the application and that other drawings may be derived from them without inventive faculty.

Fig. 1 is a schematic structural diagram of an electronic device according to an embodiment of the present application;

fig. 2 is a schematic diagram of an application scenario of a size information processing scheme according to an embodiment of the present application;

FIG. 3 is a flow chart of a size information processing method according to an embodiment of the present application;

fig. 4 is a flow chart of a size information processing method according to an embodiment of the present application;

fig. 5 is a flow chart of a size information pushing method according to an embodiment of the present application;

fig. 6 is a schematic structural diagram of a size information processing apparatus according to an embodiment of the present application;

fig. 7 is a schematic structural diagram of a cloud device according to an embodiment of the present application.

Specific embodiments of the present application have been shown by way of the above drawings and will be described in more detail below. The drawings and the written description are not intended to limit the scope of the inventive concepts in any way, but rather to illustrate the inventive concepts to those skilled in the art by reference to the specific embodiments.

Detailed Description

Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the application.

The term "and/or" is used herein to describe association of associated objects, and specifically indicates that three relationships may exist, for example, a and/or B may indicate: a exists alone, A and B exist together, and B exists alone.

It should be noted that, the user information (including but not limited to user equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are information and data authorized by the user or fully authorized by each party, and the collection, use and processing of the related data need to comply with the related laws and regulations and standards of the related country and region, and provide corresponding operation entries for the user to select authorization or rejection.

In order to clearly describe the technical solution of the embodiments of the present application, firstly, the terms involved in the present application are explained:

sku: stock Keeping Unit, minimum inventory units.

OCR: optical Character Recognition, optical character recognition.

average charging: and (5) carrying out average pooling.

Two-part diagram: the vertex set V may be divided into two mutually disjoint subsets, and the two vertices to which each edge in the graph depends are all divided into the two mutually disjoint subsets, with the vertices within the two subsets not being adjacent.

As shown in fig. 1, the present embodiment provides an electronic apparatus 1 including: at least one processor 11 and a memory 12, one processor being exemplified in fig. 1. The processor 11 and the memory 12 are connected by a bus 10. The memory 12 stores instructions executable by the processor 11, and the instructions are executed by the processor 11, so that the electronic device 1 can execute all or part of the methods in the embodiments described below, so as to improve the calculation accuracy of the user figure size, further provide high-accuracy size information for size recommendation, improve the accuracy of size recommendation, and improve the user experience.

In an embodiment, the electronic device 1 may be a mobile phone, a tablet computer, a notebook computer, a desktop computer, or a large computing system composed of a plurality of computers.

Fig. 2 is a schematic diagram of an application scenario 200 of a size information processing system according to an embodiment of the present application. As shown in fig. 2, the system includes: server 210 and terminal 220, wherein:

The server 210 may be a data platform that provides a size information processing service, such as an e-commerce shopping platform. In a practical scenario, one e-commerce shopping platform may have multiple servers 210, for example 1 server 210 in fig. 2.

The terminal 220 may be a computer, a mobile phone, a tablet, or other devices used when the user logs in to the shopping platform of the electronic commerce, or a plurality of terminals 220 may be provided, and 2 terminals 220 are illustrated in fig. 2 as an example.

Information transmission between the terminal 220 and the server 210 may be performed through the internet, so that the terminal 220 may access data on the server 210. The terminal 220 and/or the server 210 may be implemented by the electronic device 1.

The size information processing scheme of the embodiment of the application can be deployed on the server 210, the terminal 220 or the server 210 and the terminal 220. The actual scene may be selected based on actual requirements, which is not limited in this embodiment.

When the size information processing scheme is deployed in whole or in part on the server 210, a call interface may be opened to the terminal 220 to provide algorithmic support to the terminal 220.

The method provided by the embodiment of the application can be realized by the electronic equipment 1 executing corresponding software codes and by carrying out data interaction with a server. The electronic device 1 may be a local terminal device. When the method is run on a server, the method can be implemented and executed based on a cloud interaction system, wherein the cloud interaction system comprises the server and the client device.

In a possible implementation manner, the method provided by the embodiment of the present application provides a graphical user interface through a terminal device, where the terminal device may be the aforementioned local terminal device or the aforementioned client device in the cloud interaction system.

The size information processing mode of the embodiment of the application can be applied to any field needing to determine the size of the user.

In order to solve the above problems, an embodiment of the present application provides a size information processing scheme, which determines a final commodity size of a commodity according to purchase records of a plurality of reference users on the commodity, an input size of each reference user, and an original size of the commodity, then determines an estimated size of the commodity for a target user who has placed a list of the commodity based on the final commodity size and a category to which the commodity belongs, and then determines the final size of the target user based on the estimated size and input information of the target user, thus fully utilizing historical order data of the user, and performing detail excavation in dimensions such as a mapping relation between the commodity category and the size, and enriches a commodity size table by using size data maintained by the user and the original size of the commodity. Finally, the final commodity size code table and purchase record data of the target user are utilized to estimate the size suitable for the target user, size calibration is carried out based on the estimated size and target user input information, the final size of the target user for the commodity is obtained, the accuracy of user size estimation is improved, high-accuracy size information can be provided for size recommendation, the size recommendation accuracy is improved, and user experience is improved.

Some embodiments of the present application are described in detail below with reference to the accompanying drawings. In the case where there is no conflict between the embodiments, the following embodiments and features in the embodiments may be combined with each other. In addition, the sequence of steps in the method embodiments described below is only an example and is not strictly limited.

Please refer to fig. 3, which is a size information processing method according to an embodiment of the present application, the method may be executed by the electronic device 1 shown in fig. 1, and may be applied to an application scenario of size information processing shown in fig. 2, so as to improve accuracy of user figure size estimation, further provide high-accuracy size information for size recommendation, improve accuracy of size recommendation, and improve user experience. In this embodiment, taking the terminal 220 as an executing terminal as an example, the method includes the following steps:

step 301: the method comprises the steps of acquiring the input body sizes of a plurality of reference users who have placed a list of target items and the original sizes of the target items.

In this step, the items are classified into items in advance, and, taking the e-commerce scenario as an example, the clothing items may be classified into items such as a coat, a lower skirt, trousers, shoes, etc., or may be further classified into more slender items, the coat may be classified into items such as a body shirt, a coat, etc., and the lower skirt may be further classified into: the trousers can be divided into shorts, trousers and the like, and the shoes can be divided into sports shoes, casual shoes, cotton shoes, sandals and the like. The target category is the classification category to which the target commodity belongs. The target items refer to a class of items which can be ordered by a user, for example, the target items in an electronic market are target items, such as a certain type of T-shirt, a certain type of shoes and the like, and the target items can comprise a plurality of items with different size identifications, such as S (small) numbers, M (medium) numbers and L (large) numbers of the T-shirt. The target category of a type a, M, for example, a t may be a coat and the target category of B type 42 athletic footwear may be a shoe. The method can be used for target users needing to estimate the figure size, the target users can refer to users who have placed a list of target items, for example, the target commodity is sports shoes of type B42, and the target users refer to users who have placed a list of shoes. The reference user refers to a user who has once ordered the target category item and has entered a stature size, such as a user who has purchased a certain commodity in an electronic market, has confirmed receipt, and has filled in his stature size in personal information. The step of inputting the figure size refers to the figure size data actively input by the user, such as the figure size data input by the user on a personal information archive page, including but not limited to the information of the height, weight, shoulder width, chest circumference, waistline, hip circumference, foot length, foot width, upper chest circumference, lower chest circumference and the like of the user. The entered stature size can be read directly from the personal information archive of the reference user. The original size of the target category item refers to a preset size of the target category item, such as size data marked when the commodity leaves the factory in an e-commerce scene, size data filled in by a merchant for the commodity, and the like. The original size may be entered manually or read from a database.

In one embodiment, step 301 may specifically include: first historical order information of the target category item is obtained, wherein the first historical order information comprises a plurality of reference user identifiers for placing orders for the target category item. And acquiring the input stature sizes of the plurality of reference users according to the plurality of reference user identifications.

In this step, the first historical order information refers to historical order information for the target category item over a period of time, such as completed order information for the apparel industry in the electronic marketplace. The historical order information records the identification of each ordering user, such as the user name, the user identification code and other information of the ordering user, namely the reference user identification. If the first historical order is the historical order information of the target category item in the past year, the reference users for ordering the target category item in the past year generally comprise a plurality of reference users, the user identifications in the first historical order information can be counted to determine a plurality of contained reference user identifications, then the corresponding reference user personal information files are respectively searched according to the reference user identifications, and the input stature sizes of the plurality of reference users are read from the reference user personal information files. Thus, the historical order data of the user is fully utilized, reliable figure size information is mined, and the corresponding relation among the reference user, the input figure size and the target commodity can be determined.

In an embodiment, taking an e-commerce scenario as an example, order data of a user in the clothing industry (such as historical order data of clothing commodities on an e-commerce platform in one year) and size information maintained by the user (such as a user ruler code table filled in by the user in a personal information page) may be adopted, and gender filtering is performed to generate the data in a cross manner, where the data includes: referring to table a of user-gender-size-sku, the size in table a refers to size information maintained by the reference user. It should be noted here that when associating order data with a user rule table, it is necessary to consider that the sex attribute of the commodity and the sex attribute of the user character do not conflict, so as to avoid the influence of cross-sex buying data as much as possible.

Step 302: and determining the standard size corresponding to the target category to which the target category object belongs according to the input stature size and the original size.

In this step, the standard size refers to size information indicating that the target item is adapted to the wearer, for example, the size of the garment is characterized by the size information of the wearer, and the size of a body shirt may include information such as chest circumference, sleeve length, etc. In an actual scene, an inaccurate phenomenon may exist in an original size of an article, for example, when a clothing commodity is on line in an electronic market scene, a merchant can fill the original size for the clothing commodity or make a ruler code table of a display page for the clothing commodity by other staff, and the original size filled by the merchant or the ruler code table of the display page may have the conditions of filling in errors, filling out errors and the like, so that the original size is not necessarily accurate. The reference user has purchased the clothing commodity and confirms the receipt, and the size of the clothing commodity purchased by the reference user is fit, so that the original size of the clothing commodity can be corrected according to the size input by the reference user, and the more accurate standard size of the clothing commodity can be obtained.

In one embodiment, the step 302 may specifically include: for a single size identified target category item, an average size of the entered stature sizes corresponding to the plurality of reference users is determined. And determining the confidence coefficient of the average size according to the first historical order information of the target category item, wherein the confidence coefficient is positively correlated with the number of times of the target category item is placed. If the confidence coefficient is larger than a first preset threshold value, determining the average size as the standard size of the target category, otherwise, if the confidence coefficient is smaller than or equal to the first preset threshold value, determining the standard size corresponding to the target category according to the original size.

In this embodiment, the target category item may include a plurality of size-identified items, such as S (small), M (medium), and L (large) numbers of a type a body shirt, and standard size calculation is performed for each size-identified target category item. For a single size mark, the corresponding multiple reference users are users who purchase target items with the same type and the same size mark, in an electronic market, the target items can be target commodities, such as a small-size, xiao Hua and a small-size and M-size-respectively-placed T-shirt, the A-size and M-size-respectively-placed T-shirt is the target commodity, and the small-size, xiao Hua and the small-size-respectively-placed T-shirt are the corresponding multiple reference users. In an actual scene, in order to make data richer, data aggregation can be carried out on first historical order information of the A type and M type of T-shirt for one year, so that average sizes of body sizes can be recorded by a plurality of reference users within one year, the average sizes represent the body sizes of the A type and M type of T-shirt suitable for users, the average sizes are assumed to be the average sizes of chest circumference, the value is 110cm, and the A type and M type of T-shirt is indicated to be suitable for the users with chest circumference of 110cm to wear. And then determining the confidence level of the average size based on the first historical order information, wherein the confidence level is positively correlated with the number of times of the object items to be placed, that is, the greater the number of times of purchasing the shirts of the A type M number by a plurality of reference users in one year, the greater the confidence level of the chest circumference of 110cm (average size), so that the confidence level can be used for representing the universality between the average size and the shirts of the A type M number, the greater the confidence level is, the greater the universality between the shirts of the A type M number is, the more accurate the average size is used for representing the commodity size corresponding to the M number of the A type M number, and otherwise, the lower the accuracy is obtained by adopting the average size to represent the commodity size corresponding to the M number of the A type M shirt. The first preset threshold is used to divide which average sizes are accurate and which are inaccurate. If the confidence coefficient of the average size is larger than the first preset threshold value, the confidence coefficient of the average size is larger, and the average size can be used as the standard size of the A-style M-number shirt, otherwise, if the confidence coefficient of the average size is smaller than or equal to the first preset threshold value, the confidence coefficient of the average size is smaller, and the confidence coefficient of the average size is insufficient to prove the universality between the A-style M-number shirt and the average size, the standard size corresponding to the A-style M-number shirt can be determined according to the original size of the A-style M-number shirt, and in an E-commerce scene, the standard size is the commodity size of the target commodity. Thus, the historical order records of the users are comprehensively considered to determine the commodity size of a certain type of commodity, and the accuracy of the commodity size is improved.

In an embodiment, the number of times of the target category item is ordered may be directly used as the confidence of the average size, and step 302 may specifically include: an average size of the entered stature sizes of the plurality of reference users is determined. And judging whether the number of times of the ordered items of the target category is larger than a first preset threshold according to the first historical order information of the items of the target category. If the number of times of the ordered list is larger than a first preset threshold value, the average size is determined to be the standard size of the target class. And if the number of times of the list is smaller than or equal to a first preset threshold value, determining a standard size corresponding to the target category according to the original size.

In this embodiment, taking the e-commerce scenario as an example, the standard size is the commodity size of the target commodity, and the table a of one year data output in the foregoing step 301 may be: the data of the user-gender-size-sku are aggregated to obtain an aggregation result b of each sku on each size attribute item, wherein the aggregation result b can comprise an average size attribute value obtained after pooling and a confidence uv value of attribute coverage of the average size, the confidence uv can be represented by the number of times that a target category item is ordered, and the aggregation result b can be represented as: sku-size-buy uv. The aggregation result b of a certain commodity sku_id: skin_id-frame size 110-frame size uv:15, representing frame size data of 15 reference users purchasing the skin_id commodity aggregated, with the average size of the frame sizes in the 15 reference users' entered body sizes being 110cm.

If the number of times of the placing of the number A and the number M of the T-shirt is larger than the first preset threshold value within one year, the number of times of the placing of the number A and the number M of the T-shirt is indicated to be large enough, and the confidence of the average size is indicated to be large, and the average size can be used as the standard size of the target category (such as the T-shirt) of the number A and the number M of the T-shirt. Otherwise, if the number of times of the list of the number A and the number M is smaller than the first preset threshold value within one year, the fact that the number A and the number M are smaller indicates that the number A and the number M are smaller in number of times of the list of the number A and the number M is smaller, the fact that the confidence of the average size is smaller is insufficient to prove universality between the number A and the average size is not enough, the commodity size corresponding to the target category can be determined according to the original size of the number A and the number M of the list of the number A, the commodity size of a certain commodity is determined by comprehensively considering the historical order records of users, and the accuracy of the commodity size is improved.

In one embodiment, the original size includes: the page display size and merchant entry size of the target category item. If the confidence coefficient is less than or equal to the first preset threshold in the foregoing step 302, determining, according to the original size, the standard size corresponding to the target category may specifically include: if the confidence coefficient is smaller than or equal to a first preset threshold value, judging whether the page display size is empty or not. If the page display size is not empty, determining the page display size as the standard size of the target class. If the page display size is empty, the merchant input size is defined as the standard size of the target class.

In this embodiment, taking an e-commerce scenario as an example, the original size of the target commodity may include a page display size of the commodity, for example, a size table displayed on a detail page of the target commodity, and the size table in the detail page of the target commodity may be identified by using an OCR recognition technology, so as to obtain page display size information of the target commodity. The original size can also comprise a merchant input size, when the target commodity is put on shelf in an electronic market, a merchant user is required to input size information of the target commodity in a page through a terminal, the input size information can be maintained by the merchant user, and the merchant input size of the target commodity can be obtained through merchant user maintenance information. When the confidence of the average size is smaller than or equal to a first preset threshold, the fact that the average size cannot accurately represent the actual size information of the target commodity is indicated, whether the page display size of the target commodity is empty or not can be further judged, if the page display size is not empty, the page display size can be used as the commodity size of the target commodity when the page display size of the target commodity exists, otherwise, if the page display size is empty, the fact that the target commodity does not exist in an effective page display size is indicated, and the merchant can enter the size as a commodity size code table c of the target category of the target commodity.

For example, the target commodity is a type a and type M shirt, and the type a and type M shirt (numbered as sku_am) corresponds to the aggregation result b: sky_am-chest circumference: and (3) the average chest circumference of the reference user purchasing the A-type and M-type T-shirt in the past year is shown as the confidence level of 110cm, 3, the confidence level of 3 is smaller than 10 if the first preset threshold is 10, the average chest circumference of 110cm cannot accurately represent the suitable user figure size of the A-type and M-type T-shirt, the OCR recognition result of the commodity detail page rule code table of the A-type and M-type T-shirt can be obtained, if the OCR recognition result is not empty, the page display size in the OCR recognition result is used as the commodity size of the target class of the A-type and M-type T-shirt, if the OCR recognition result is empty, the merchant input size of the A-type and M-type T-shirt is obtained, and the merchant input size is used as the commodity size of the target class of the A-type and M-type T-shirt. Therefore, the display size data of the commodity detail page and the merchant maintenance size data are fully utilized to enrich the commodity size code table of the target category, and the accuracy of commodity size is improved.

And (3) performing the operation of the process on other size marks of the A type T-shirt, so that all standard sizes corresponding to the target category to which the A type T-shirt belongs can be determined. The goods ruler code table c of the shirt, for example, can comprise the following contents:

S number: chest circumference 100cm. Shoulder width: 40cm.

M: chest circumference 110cm. Shoulder width: 45cm.

L: chest circumference 120cm. Shoulder width: 50cm.

For example, the commodity ruler code table c of shoes can be as follows:

36 codes: the foot length was 265mm.

36 codes: the foot length was 270mm.

37 codes: the feet are 275mm long.

Step 303: and determining the estimated stature size of the target user suitable for the target category according to the standard size and the target category.

In the step, assuming that the target category is a shoe, after the commodity size of the shoe is determined, the shoe size suitable for the target user can be estimated according to the commodity size of the shoe and the target category of the shoe as key information, so that the estimated figure size suitable for the shoe of the target user is obtained, the order record of the target user is fully utilized to estimate the proper figure size for a certain commodity, a two-part diagram is constructed by utilizing the user size, the commodity size and the consumption relation of the user size and the commodity size, and the problem of low coverage rate of the consumer/commodity size is solved through the migration of the diagram, and the accuracy of the figure size estimation of the user is improved.

In one embodiment, step 303 may specifically include: and acquiring second historical order information of the target user on the target category item, and acquiring a mapping relation between the item category and the size attribute. And inquiring to obtain the target size attribute corresponding to the target category according to the target category and the mapping relation. And determining the order size identification of the target user on the target category item according to the second historical order information. And determining the value of the target size attribute corresponding to the order size identifier from the value information, and determining the estimated figure size of the target user suitable for the target category according to the value of the target size attribute.

In this embodiment, the standard size includes values of a plurality of size attributes, and the size attributes are used to represent dimension information of a body part of the user to which the article is applicable, for example, the size attributes may include height, weight, shoulder width, chest circumference, waistline, hip circumference, foot length, foot width, upper chest circumference, lower chest circumference, and the like of the user. Each size attribute may correspond to a value of 100cm, for example, the size attribute is the chest circumference, and the value of 100cm. The standard size determined in step 302 may include the value information of multiple size attributes, and when the commodity size is taken as an example, and the average size is taken as the commodity size for the target commodity a type M, the input body sizes of the multiple reference users often include the value information of multiple size attributes, where the size attributes are assumed to include a chest circumference and a foot length, the average size of the chest circumference is 110cm, and the average size of the foot length is 265mm, the commodity size of the target commodity a type M will include the value information of two size attributes of 110cm and 265 mm.

The second historical order data may be order data of the target user over a period of time, such as apparel type order data of the target user on the e-commerce platform over the past year, and may be obtained from personal record data of the target user. The mapping relation between the item category and the size attribute is used for representing the size attribute that the item of each category needs to pay attention to, for example, the size attribute that the coat needs to pay attention to can comprise information such as height, weight, shoulder width, chest circumference, sleeve length and the like, and the size attribute that the shoe needs to pay attention to can comprise: the mapping relation can be set by professionals in industry based on actual demands.

When the stature size of the target user is estimated, a mapping relation between the item category and the size attribute can be introduced, and the value of the size attribute matched with the target category can be screened from the commodity size of the target category in a fuzzy matching mode, for example, if the target category is a shoe, the target size attribute concerned by the shoe is: if the identification of the sole size of the target user is 36, the foot length value information and the foot width value information corresponding to 36 are determined from the commodity size of the target class. The estimated figure size of the target user applicable to the shoes of the target category can be determined according to the foot length value information and the foot width value information corresponding to the 36-size, so that the accuracy of the figure size estimation of the user is further improved.

In one embodiment, the target category includes functional category information and first gender information to which the target category item belongs. The input information of the target user comprises second gender information of the target user, and the second gender information is matched with the first gender information.

In this embodiment, considering that there are more buying behaviors in the apparel industry, it is considered that one user may have buying behaviors across sexes and corresponding size data at the same time, and commodities are classified into men, women, and neutrals according to the commodity category, for example, clothing may be classified into women's clothing, men's clothing, and neutral clothing. Shoes can be classified into women's shoes, men's shoes and neutral shoes. And forming a mapping relation with the user to generate structural data containing the user-gender-commodity. When the size suitable for the target user is estimated, the first gender information of the adopted commodity is matched with the second gender information of the target user, and the estimated size is matched with the gender of the target user. For example, the input information of the target user shows that the target user is female, the sex information of the target commodity is female, for example, the target commodity is a women's coat, so that the estimated stature size of the target user is a size suitable for the women's coat, and the accuracy of stature size estimation is improved.

Taking a clothing e-commerce scene as an example, a specific flow for estimating the stature size of a target user can be as follows:

1. the target user's one year confirmation receipt order data is used to assist in determining the target user's order size identification for the target category of goods.

2. Considering that the clothing industry has more buying behaviors, it is considered that a target user may have cross-gender buying behaviors and corresponding size data at the same time, and commodities can be classified into men, women and neutrality according to commodity categories, and a mapping relation is formed between the commodities and the user, so that a data set containing the user-gender-commodity is generated.

3. The mapping relationship between the commodity size, the commodity category and the size attribute determined in step 302 is introduced, and the data generated in step 2 is mapped to generate a data set containing the user-gender-commodity-size attribute.

4. The confirming and receiving order data of the target user for one year is cleaned as follows in the step 3: structured data of the target user-sex-commodity-size attribute are aggregated according to the structured data, the estimated figure size of the target user suitable for the target category is calculated, and the corresponding relation between the commodity category and the size attribute, such as trousers-height, weight, waistline, hip circumference and shoe-foot length, is required to be considered during the aggregation calculation, so that the accuracy of the calculation result is ensured.

In one embodiment, the target user orders the target category item a plurality of times. The target size attribute is valued as a sequence of size values comprising a plurality of values. In step 303, determining, according to the target size attribute value, the estimated size of the target user suitable for the target category may specifically include: and determining the median of the size value sequence, selecting a target value which is larger than the median and has a difference value smaller than a preset value from the size value sequence, and generating a new size value sequence corresponding to the target size attribute based on the target value. And calculating the average value of the new size value sequence, and determining the average value as the estimated figure size of the target user suitable for the target category.

In this embodiment, taking an e-commerce scenario as an example, for a single target user, multiple purchases of the same category of merchandise may be performed within a year, so that the target user may make multiple orders for the target category of merchandise, in which case the target user may purchase skus with different size identifiers for the same category of merchandise, such as xiao Li, and purchase 5 pairs of shoes within the past year, each size identifier corresponds to a size attribute value, such as a foot length and a foot width, so that xiao Li will include 5 size values for the target size attribute corresponding to the lower size identifier of the shoe, that is, the target size attribute value is a size sequence including 5 size values. The size sequence is assumed to be: at this time, the median of the 5 values may be determined, and a target value greater than the median and having a difference from the median less than a preset value is selected from the 5 values, to generate a new size value sequence. For example, 5 values are: 211mm, 215mm, 218mm, 219mm, 225mm. Wherein the median is 218mm, and a new sequence of size values can be obtained assuming a preset value of 5: 215mm, 218mm and 219mm, and the new size value sequence after screening is more concise. And averaging the new size value sequence, for example, averaging and pooling the new size value sequence to obtain an average value, and taking the average value as the estimated size of xiao Li pair shoes. The preset value can be set based on actual requirements so as to ensure the accuracy of the data. Through the data calibration processing of the median, adverse effects of buying instead of buying on the figure size estimation can be indirectly reduced, and the accuracy of the figure size estimation result of the user is improved.

In one embodiment, before determining the median of the sequence of size values, it may further comprise: and eliminating outliers in the size value sequence according to the target category.

In this embodiment, for example, xiao Li purchased 10 pairs of shoes in the past year, wherein 8 pairs of shoes of 36, 1 pairs of shoes of 44, 1 pairs of shoes of 25, it is obvious that the deviations of 44 and 25 from 8 pairs of shoes of 36 are too great, the foot length and/or foot width values corresponding to 44 and 25 belong to outliers in the size value sequence, possibly being purchased by Li Bang individuals, and the foot length and/or foot width values corresponding to the remaining 8 pairs of shoes of 36 are kept as the constituent elements of the size value sequence, so that the data of the size value sequence is cleaned, not only improving the calculation accuracy, but also reducing the data calculation amount.

In one embodiment, before determining the median of the sequence of size values, it may further comprise: if the target category belongs to the preset size larger category, the size value sequence is reduced according to the preset reduction. If the target category belongs to the preset size smaller category, amplifying the size value sequence according to the preset amplifying amount.

In this embodiment, the size sequence may be calibrated according to the commodity category, for example, in an actual scene, in order to wear comfortable and attractive, the chest circumference of the jacket purchased by the user is always much larger than the chest circumference of the user, the chest circumference of the body shirt is much closer to the chest circumference of the user, so that the problem that the chest circumference of the jacket is larger and the chest circumference of the body shirt is smaller when the size of the user is represented by the jacket and the body shirt, in order to solve the adverse effect caused by the problem, the size bias category (such as the jacket) and the size bias category (such as the body shirt) may be preset according to the commodity category, if the target category belongs to the preset size bias category, the size sequence is reduced according to the preset reduction amount, and correspondingly, if the target category belongs to the preset size bias category, the size sequence is enlarged according to the preset amplification amount, the accuracy of the size sequence of the user after calibration is obtained, and the accuracy of the size sequence representing the size of the user may be improved.

Step 304: and determining the final stature size of the target user applicable to the target category based on the estimated stature size and the input information of the target user.

In this step, the input information of the target user may be the information input by the target user in the personal information file, after the estimated size of the target user is obtained, the final size of the target user applicable to the target category may be determined by combining the input information maintained by the target user, so that the commodity size data is used when the size information of the user is estimated, the possible deviation between the commodity size and the size of the user is eliminated, the accuracy of the estimated result of the user size is improved, the final size of the user is determined in a personalized manner by combining the input information of the user, and the accuracy of the final size of the user is further improved.

In one embodiment, step 304 may specifically include: if the target input stature size exists in the input information of the target user, calculating an error rate between the estimated stature size and the target input stature size. And judging whether the error rate is smaller than a second preset threshold value, if the error rate is smaller than the second preset threshold value, determining the average value of the estimated stature size and the target input stature size as the final stature size suitable for the target category of the target user, otherwise, determining the target input stature size as the final stature size suitable for the target category of the target user.

In this embodiment, the target input stature size may refer to stature size information input by the target user in the personal information file, if the target input stature size exists in the input information of the target user, the input stature size maintained by the target user may be used as priori data, the estimated stature size produced in step 303 is used as posterior data, the user-gender is used as key (keyword), the posterior data is used to perform aggregation correction on the priori size data, and the corrected and supplemented final stature size is produced. Specifically, if the target user has a target entry figure size maintained by the target user, comparing the error rate between the estimated figure size and the target entry figure size, and if the error rate is smaller than a second preset threshold value, indicating that the error rate is within a reasonable error, taking the average value of the estimated figure size and the target entry figure size as a final figure size suitable for the target user in the target category. Otherwise, the error rate is not within a reasonable error, and the target input stature size is determined to be the final stature size suitable for the target category of the target user. Thus, the accuracy of the estimated result of the figure size of the user is improved.

In an embodiment, if the target input size does not exist in the input information of the target user, it is indicated that the target user may not maintain the self-body size information, and at this time, the estimated size may be directly used as the final size of the target user suitable for the target category, so as to ensure that the target user may have accurate size information.

According to the size information processing method, the final commodity size of the commodity is determined according to the purchasing records of a plurality of reference users on the commodity, the input size of each reference user and the original size of the commodity, then the estimated size of the commodity for the target user who has placed the commodity is determined based on the final commodity size and the category of the commodity, and then the final size of the target user is determined based on the estimated size and the input information of the target user, so that the historical order data of the user is fully utilized, fine digging is carried out in the dimensions such as the commodity category and the size mapping relation, and the commodity size code list is enriched by utilizing the size data maintained by the user and the commodity original size. Finally, the final commodity size code table and purchase record data of the target user are utilized to estimate the size suitable for the target user, size calibration is carried out based on the estimated size and target user input information, the final size of the target user for the commodity is obtained, the accuracy of user size estimation is improved, high-accuracy size information can be provided for size recommendation, the size recommendation accuracy is improved, and user experience is improved.

Historical consumption data of consumers are fully utilized, and the dimension such as gender, commodity category and size mapping relation is dug. The size data maintained by consumers, the size table of the commodity is enriched by technologies such as OCR (optical character recognition) of the commodity detail page size table and the like, so that the background size table is consistent with the visible size table of the user. Finally, the commodity ruler code list, the size information maintained by the user and the historical consumption behavior of the user are utilized to estimate the clothes size information of the user (the height, the weight, the foot length and the like of the user are predicted). Because the data are inferred through the high-confidence user consumption behaviors, the estimated user stature size is more accurate and more closely related to the real stature of the user, meanwhile, because commodity size data are used when the size information of the user is calculated, the possible deviation of commodity sizes and user stature sizes is eliminated, and the accuracy of the estimated result of the user stature size is improved.

Please refer to fig. 4, which is a size information processing method according to an embodiment of the present application, the method may be executed by the electronic device 1 shown in fig. 1, and may be applied to an application scenario of size information processing shown in fig. 2, so as to improve accuracy of user figure size estimation, further provide high-accuracy size information for size recommendation, improve accuracy of size recommendation, and improve user experience. In this embodiment, taking the terminal 220 as an executing terminal as an example, the method includes the following steps:

Step 401: determining a target user needing to estimate the figure size, wherein the target user is a user who places a list on a target category item; first historical order information of the target category item is obtained, wherein the first historical order information comprises a plurality of reference user identifiers for placing orders for the target category item. And acquiring the input stature sizes of the plurality of reference users according to the plurality of reference user identifications. The original size of the target category item is obtained.

Step 402: for a single size identified target category item, an average size of the entered stature sizes corresponding to the plurality of reference users is determined. And determining the confidence coefficient of the average size according to the first historical order information of the target category item, wherein the confidence coefficient is positively correlated with the number of times of the target category item is placed.

Step 403: and judging whether the confidence coefficient is larger than a first preset threshold value, if so, entering a step 404, otherwise, entering a step 405.

Step 404: if the confidence is greater than a first preset threshold, the average size is determined as the standard size of the target class. Step 408 is then entered.

Step 405: if the confidence coefficient is smaller than or equal to a first preset threshold value, judging whether the page display size is empty or not. If yes, go to step 407, otherwise go to step 406.

Step 406: if the page display size is not empty, determining the page display size as the standard size of the target class. Step 408 is then entered.

Step 407: if the page display size is empty, the merchant input size is defined as the standard size of the target class. Step 408 is then entered.

Step 408: the standard size comprises value information of a plurality of size attributes, second historical order information of a target user on the target category item is obtained, and a mapping relation between the item category and the size attributes is obtained. And inquiring to obtain the target size attribute corresponding to the target category according to the target category and the mapping relation.

Step 409: and determining the order size identification of the target user on the target category object according to the second historical order information, and determining the value of the target size attribute corresponding to the order size identification from the value information, wherein the value of the target size attribute is a size value sequence comprising a plurality of values.

Step 410: and determining the median of the size value sequence, selecting a target value which is larger than the median and has a difference value smaller than a preset value from the size value sequence, and generating a new size value sequence corresponding to the target size attribute based on the target value.

Step 411: and calculating the average value of the new size value sequence, and determining the average value as the estimated figure size of the target user suitable for the target category.

Step 412: and calculating an error rate between the estimated stature size and the target input stature size, judging whether the error rate is smaller than a second preset threshold value, if yes, entering step 413, otherwise, entering step 414.

Step 413: if the error rate is smaller than a second preset threshold value, determining the average value of the estimated stature size and the target input stature size as the final stature size suitable for the target category of the target user.

Step 414: and if the error rate is greater than or equal to a second preset threshold value, determining the target input stature size as the final stature size suitable for the target category of the target user.

The details of each step of the size information processing method can be referred to the related description of the above embodiment, and will not be repeated here.

Please refer to fig. 5, which is a size information pushing method according to an embodiment of the present application, the method may be executed by the electronic device 1 shown in fig. 1, and may be applied to an application scenario of size information processing shown in fig. 2, so as to improve accuracy of user figure size estimation, further provide high-accuracy size information for size recommendation, improve accuracy of size recommendation, and improve user experience. In this embodiment, the terminal 220 is taken as an executing end, and compared with the previous embodiment, in this embodiment, an e-commerce shopping scenario is taken as an example, and a size recommendation interaction process of a commodity on an e-commerce platform is taken as an example, the method includes the following steps:

Step 501: and responding to the access operation of the current user to the current page, and acquiring the current category of the current commodity in the current page.

In this step, the current user refers to the user who is browsing the merchandise, and the current page refers to the page where the information of the browsed merchandise is located, for example, may be a detail page of the target merchandise. The access operation may be an operation of opening the current page or triggering a request for the current page, and when the user performs an access operation on a detail page of the target product, for example, the user clicks on a detail page of the a type body shirt, and the current category of the a type body shirt in the current page may be obtained when triggering a size recommendation function for the a type body shirt.

Step 502: and acquiring a final figure size applicable to the current category of the current user, wherein the final figure size is determined according to the original size of the current category, the recorded figure sizes of a plurality of reference users and the recorded information of the current user.

In this step, assuming that the current category is a body shirt, obtaining a final figure size of the current user suitable for the body shirt, where the final figure size is obtained according to the original figure size of the current category, the entered figure sizes of the multiple reference users and the entered information of the current user by adopting a method in any of the foregoing embodiments, where the multiple reference users may be users who have been subjected to a list of the current category commodity, and details of the foregoing description of related embodiments will not be repeated herein.

Step 503: the final stature size is provided to the current user.

In this step, the determined final figure size of the current user applicable to the body shirt may be displayed on the user interface, for example, in a text information manner in a size selection field of the a-style body shirt, or in a current page as a rolling subtitle, and the method for displaying the prompt information of the final figure size is not limited in this embodiment. For example, the final body size of the current user applicable to the T-shirt is 100cm, the M number of the A-type T-shirt corresponds to 100cm, and the M number of the A-type T-shirt can be marked by a special color and displayed in the size selection bar of the A-type T-shirt, so that the user can know the size suitable for the user in time, the user can purchase the T-shirt with assistance, the size recommendation accuracy is improved, and the user experience is improved.

According to the size information pushing method, the historical consumption data of consumers are fully utilized, and the dimensions such as gender, commodity category, size mapping relation and the like are finely dug. Enriching commodity sizes by using the size data and the commodity detail page size table maintained by the consumer, and finally accurately estimating the clothes size information of the user by using the commodity size table, the size information maintained by the user and the historical consumption behavior of the user. Because the data are inferred through the high-confidence user consumption behaviors, the estimated user figure size is more accurate and more closely related to the real figure of the user, meanwhile, because commodity size data are used when the size information of the user is calculated, the possible deviation of commodity size and user figure size is eliminated, the accuracy of the estimated result of the user figure size is improved, the accuracy of the size recommending effect is higher, the interpretability is stronger, the problem of low estimated coverage rate of the user figure in the e-commerce clothing industry is solved, and the recommending rate of an online rule code table is greatly improved.

The details of each step of the size information pushing method can be referred to the related description of the above embodiment, and will not be repeated here.

Referring to fig. 6, an apparatus 600 for size information processing according to an embodiment of the present application is applicable to the electronic device 1 shown in fig. 1 and the application scenario of size information processing shown in fig. 2, so as to improve the accuracy of user figure size estimation, further provide high-accuracy size information for size recommendation, improve the accuracy of size recommendation, and improve user experience. The device comprises: the functional principles of the acquisition module 601, the first determination module 602, the second determination module 603 and the third determination module 604 are as follows:

an obtaining module 601 is configured to obtain the entered body sizes of the multiple reference users who have placed the list of the target category item and the original sizes of the target category item.

The first determining module 602 is configured to determine a standard size corresponding to the target category according to the entered stature size and the original size.

A second determining module 603 is configured to determine, according to the standard size and the target category, an estimated stature size of the target user applicable to the target category.

A third determining module 604 is configured to determine a final stature size applicable to the target category by the target user based on the estimated stature size and the input information of the target user.

In one embodiment, the obtaining module 601 is configured to: first historical order information of the target category item is obtained, wherein the first historical order information comprises a plurality of reference user identifiers for placing orders for the target category item. And acquiring the input stature sizes of the plurality of reference users according to the plurality of reference user identifications.

In one embodiment, the target category items include a plurality of size-identified items. A first determination module 602 is configured to determine an average size of the entered stature sizes corresponding to the plurality of reference users for the target category item identified by the single size. And determining the confidence coefficient of the average size according to the first historical order information of the target category item, wherein the confidence coefficient is positively correlated with the number of times of the target category item is placed. If the confidence coefficient is larger than a first preset threshold value, determining the average size as the standard size of the target category, otherwise, if the confidence coefficient is smaller than or equal to the first preset threshold value, determining the standard size corresponding to the target category according to the original size.

In one embodiment, the original size includes: the page display size and merchant entry size of the target category item. The first determining module 602 is further configured to determine whether the page display size is empty if the confidence level is less than or equal to a first preset threshold. If the page display size is not empty, determining the page display size as the standard size of the target class. If the page display size is empty, the merchant input size is defined as the standard size of the target class.

In one embodiment, the standard size includes a plurality of size attributes for characterizing the size information of the user's body part to which the article is adapted. The second determining module 603 is configured to obtain second historical order information of the target user on the target category item, and obtain a mapping relationship between the category of the item and the size attribute. And inquiring to obtain the target size attribute corresponding to the target category according to the target category and the mapping relation. And determining the order size identification of the target user on the target category item according to the second historical order information. And determining the value of the target size attribute corresponding to the order size identifier from the value information, and determining the estimated figure size of the target user suitable for the target category according to the value of the target size attribute.

In one embodiment, the target user orders the target category item a plurality of times. The target size attribute is valued as a sequence of size values comprising a plurality of values. The second determining module 603 is further configured to determine a median of the sequence of size values, select a target value from the sequence of size values that is greater than the median and has a difference from the median that is less than a preset value, and generate a new sequence of size values corresponding to the target size attribute based on the target value. And calculating the average value of the new size value sequence, and determining the average value as the estimated figure size of the target user suitable for the target category.

In one embodiment, the apparatus further comprises: and the preprocessing module is used for eliminating outliers in the size value sequence according to the target category before determining the median of the size value sequence. And/or if the target category belongs to the preset size larger category, carrying out reduction processing on the size value sequence according to the preset reduction amount. If the target category belongs to the preset size smaller category, amplifying the size value sequence according to the preset amplifying amount.

In one embodiment, the third determining module 604 is configured to calculate an error rate between the estimated size and the target size if the target size exists in the input information of the target user. And judging whether the error rate is smaller than a second preset threshold value, if the error rate is smaller than the second preset threshold value, determining the average value of the estimated stature size and the target input stature size as the final stature size suitable for the target category of the target user, otherwise, determining the target input stature size as the final stature size suitable for the target category of the target user.

For a detailed description of the size information processing apparatus 600, please refer to the description of the related method steps in the above embodiment, the implementation principle and technical effects are similar, and the detailed description of this embodiment is omitted here.

Fig. 7 is a schematic structural diagram of a cloud device 70 according to an exemplary embodiment of the present application. The cloud device 70 may be used to run the methods provided in any of the embodiments described above. As shown in fig. 7, the cloud device 70 may include: memory 704 and at least one processor 705, one for example in fig. 7.

Memory 704 for storing computer programs and may be configured to store various other data to support operations on cloud device 70. The memory 704 may be an object store (Object Storage Service, OSS).

The memory 704 may be implemented by any type or combination of volatile or nonvolatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.

The processor 705 is coupled to the memory 704, and is configured to execute a computer program in the memory 704, so as to implement the solutions provided by any of the method embodiments described above, and specific functions and technical effects that can be implemented are not described herein.

Further, as shown in fig. 7, the cloud device further includes: firewall 701, load balancer 702, communication component 706, power component 703, and other components. Only some components are schematically shown in fig. 7, which does not mean that the cloud device only includes the components shown in fig. 7.

In one embodiment, the communication component 706 of fig. 7 is configured to facilitate wired or wireless communication between the device in which the communication component 706 is located and other devices. The device in which the communication component 706 is located may access a wireless network based on a communication standard, such as a WiFi,2G, 3G, 4G, LTE (Long Term Evolution, long term evolution, LTE for short), 5G, or a combination thereof. In one exemplary embodiment, the communication component 706 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication component 706 further includes a near field communication (Near Field Communication, NFC for short) module to facilitate short range communications. For example, the NFC module may be implemented based on radio frequency identification (Radio Frequency Identification, RFID) technology, infrared data association (Infrared Data Association, irDA) technology, ultra Wide Band (UWB) technology, bluetooth (BT) technology, and other technologies.

In one embodiment, the power supply 703 of fig. 7 provides power to the various components of the device in which the power supply 703 is located. The power components 703 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the devices in which the power components reside.

The embodiment of the application also provides a computer readable storage medium, wherein computer executable instructions are stored in the computer readable storage medium, and when the processor executes the computer executable instructions, the method of any of the previous embodiments is realized.

Embodiments of the present application also provide a computer program product comprising a computer program which, when executed by a processor, implements the method of any of the preceding embodiments.

In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described device embodiments are merely illustrative, e.g., the division of modules is merely a logical function division, and there may be additional divisions of actual implementation, e.g., multiple modules may be combined or integrated into another system, or some features may be omitted or not performed.

The integrated modules, which are implemented in the form of software functional modules, may be stored in a computer readable storage medium. The software functional modules described above are stored in a storage medium and include instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or processor to perform some of the steps of the methods of the various embodiments of the application.

It should be appreciated that the processor may be a central processing unit (Central Processing Unit, CPU for short), other general purpose processors, digital signal processor (Digital Signal Processor, DSP for short), application specific integrated circuit (Application Specific Integrated Circuit, ASIC for short), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present application may be embodied directly in a hardware processor for execution, or in a combination of hardware and software modules in a processor for execution. The memory may include a high-speed RAM (Random Access Memory ) memory, and may further include a nonvolatile memory NVM (Nonvolatile memory, abbreviated as NVM), such as at least one magnetic disk memory, and may also be a U-disk, a removable hard disk, a read-only memory, a magnetic disk, or an optical disk.

The storage medium may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as Static Random-Access Memory (SRAM), electrically erasable programmable Read-Only Memory (Electrically Erasable Programmable Read Only Memory, EEPROM), erasable programmable Read-Only Memory (Erasable Programmable Read-Only Memory, EPROM), programmable Read-Only Memory (Programmable Read-Only Memory, PROM), read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk, or optical disk. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.

An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an application specific integrated circuit (Application Specific Integrated Circuits, ASIC for short). It is also possible that the processor and the storage medium reside as discrete components in an electronic device or a master device.

It should be noted that, in this document, the terms "comprises," "comprising," or 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 may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

The foregoing embodiment numbers of the present application are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.

From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method of the embodiments of the present application.

In the technical scheme of the application, the related information such as user data and the like is collected, stored, used, processed, transmitted, provided, disclosed and the like, which are all in accordance with the regulations of related laws and regulations and do not violate the popular public order.

The foregoing description is only of the preferred embodiments of the present application, and is not intended to limit the scope of the application, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.

Claims

1. A size information processing method for a target user who needs to estimate a size of a figure, the method comprising:

acquiring the input body sizes of a plurality of reference users who have placed a list on the target category item and the original sizes of the target category item;

determining the standard size of the target class according to the input stature size and the original size;

determining a predicted figure size of a target user applicable to the target class according to the standard size and the target class;

and determining the final figure size of the target user suitable for the target class according to the estimated figure size and the input information of the target user.

2. The method of claim 1, wherein the obtaining the entered stature sizes of the plurality of reference users who have placed the order for the target category item comprises:

acquiring first historical order information of a target category item, wherein the first historical order information comprises a plurality of reference user identifiers for placing an order for the target category item;

and acquiring the input stature sizes of the plurality of reference users according to the plurality of reference user identifications.

3. The method of claim 1, wherein the target category item comprises a plurality of size-identified items; the determining the standard size of the target class according to the input stature size and the original size comprises the following steps:

determining an average size of the entered stature sizes corresponding to the plurality of reference users for the target category item identified by the single size;

determining the confidence coefficient of the average size according to the first historical order information of the target category item, wherein the confidence coefficient is positively correlated with the number of times of the target category item is placed;

and if the confidence coefficient is larger than a first preset threshold value, determining the average size as the standard size of the target category, otherwise, if the confidence coefficient is smaller than or equal to the first preset threshold value, determining the standard size corresponding to the target category according to the original size.

4. A method according to claim 3, wherein the original size comprises: the page display size and merchant input size of the target category article; and if the confidence coefficient is smaller than or equal to the first preset threshold, determining a standard size corresponding to the target category according to the original size, including:

if the confidence coefficient is smaller than or equal to the first preset threshold value, judging whether the page display size is empty or not;

if the page display size is not empty, determining the page display size as the standard size of the target class;

and if the page display size is empty, the merchant input size is defined as the standard size of the target class.

5. The method of claim 1, wherein the standard size includes value information for a plurality of size attributes, the size attributes being used to characterize size information of a user body part to which the article is applicable; the determining, according to the standard size and the target category, the estimated stature size of the target user applicable to the target category includes:

acquiring second historical order information of the target user on the target category item, and acquiring a mapping relation between the item category and the size attribute;

Inquiring to obtain a target size attribute corresponding to the target category according to the target category and the mapping relation;

determining the order size identification of the target user on the target category item according to the second historical order information;

and determining the target size attribute value corresponding to the order size identifier from the value information, and determining the estimated figure size of the target user suitable for the target class according to the target size attribute value.

6. The method of claim 5, wherein the target user orders the target category item a plurality of times; the target size attribute value is a size value sequence comprising a plurality of values; the determining, according to the target size attribute value, that the target user is suitable for the target class purpose, which includes:

determining the median of the size value sequence, selecting a target value which is larger than the median and has a difference value smaller than a preset value from the size value sequence, and generating a new size value sequence corresponding to the target size attribute based on the target value;

and calculating the average value of the new size value sequence, and determining the average value as the estimated stature size of the target user suitable for the target class purpose.

7. The method of claim 6, further comprising, prior to said determining the median of the sequence of size values:

removing outliers in the size value sequence according to the target category;

and/or if the target category belongs to a preset size larger category, carrying out reduction processing on the size value sequence according to a preset reduction amount;

and if the target category belongs to the preset size smaller category, amplifying the size value sequence according to the preset amplifying amount.

8. The method of claim 1, wherein the determining, based on the estimated stature size and the target user's entered information, a final stature size for the target user to apply to the target category comprises:

if the target input stature size exists in the input information of the target user, calculating an error rate between the estimated stature size and the target input stature size;

judging whether the error rate is smaller than a second preset threshold value, if the error rate is smaller than the second preset threshold value, determining the average value of the estimated stature size and the target input stature size as the final stature size suitable for the target class of the target user, otherwise, determining the target input stature size as the final stature size suitable for the target class of the target user.

9. The method according to any one of claims 1-8, wherein the target category comprises functional category information and first gender information to which the target category item belongs; the input information of the target user comprises second gender information of the target user, and the second gender information is matched with the first gender information.

10. The size information pushing method is characterized by comprising the following steps of:

responding to the access operation of a current user to a current page, and acquiring the current category of the current commodity in the current page;

obtaining a final figure size of the current user applicable to the current category, wherein the final figure size is determined according to an original size of the current category, the input figure sizes of a plurality of reference users and the input information of the current user, and the plurality of reference users are users who have placed a list on the commodity of the current category;

and providing the final stature size to the current user.

11. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor;

Wherein the memory stores instructions executable by the at least one processor to cause the electronic device to perform the method of any one of claims 1-10.

12. A cloud device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor;

wherein the memory stores instructions executable by the at least one processor to cause the cloud device to perform the method of any of claims 1-10.

13. A computer readable storage medium having stored therein computer executable instructions which, when executed by a processor, implement the method of any of claims 1-10.