CN107967637B

CN107967637B - Commodity object model recommendation method and device and electronic equipment

Info

Publication number: CN107967637B
Application number: CN201610916477.3A
Authority: CN
Inventors: 刘晓倩
Original assignee: Alibaba Group Holding Ltd
Current assignee: Alibaba Group Holding Ltd
Priority date: 2016-10-20
Filing date: 2016-10-20
Publication date: 2022-04-29
Anticipated expiration: 2036-10-20
Also published as: CN107967637A

Abstract

The application discloses a method and a device for recommending commodity object models and electronic equipment, a method and a device for selecting commodity object models and electronic equipment, and a system for selecting commodity object models. The method for recommending the commodity object model comprises the following steps: receiving a model recommendation request aiming at a specific commodity object sent by a first user client; determining model recommendation information of the specific commodity object provided to the first user according to comment information of purchased users of the specific commodity object on actual purchase models of the purchased users; and sending the model recommendation information back to the first user client. By the adoption of the method for recommending the commodity object model, model recommendation information can be automatically provided for a new purchasing user according to comment information of the purchasing user on the actual purchasing model, and therefore the effect of improving commodity model recommendation efficiency and recommendation precision is achieved.

Description

Commodity object model recommendation method and device and electronic equipment

Technical Field

The application relates to the technical field of data processing, in particular to a method for recommending commodity object models; corresponding to the method, the application also relates to a recommendation device and an electronic device for the commodity object model, a selection method and a selection device for the commodity object model, an electronic device, a selection system for the commodity object model, and a selection method and a selection device for the commodity object model.

Background

When a buyer purchases non-standard goods (such as clothes, hats, shoes and the like) on an e-commerce platform, the selection of the model (such as the size model or the color model) is a link which is difficult to determine because the buyer cannot try on the goods. In order to avoid purchasing goods with improper models, part of buyers may therefore abandon the online shopping mode, thereby having an influence on the conversion rate of the goods to some extent.

At present, when a buyer purchases a commodity on an e-commerce platform, the following two ways are mainly adopted to determine the model of the commodity to be purchased:

1) the method is characterized in that the commodity model to be purchased is determined by questioning in a commodity model questioning and answering area, for example, a ' questioning everybody ' module is arranged in a baby detail page of a mobile phone Taobao, for non-standard commodities like ' women's dress ', most buyers ask the question of what size the height and weight of the buyers should buy, and then the buyers answer the question.

2) The model of the commodity to be purchased is determined by looking at keywords about the model extracted from the evaluation information of the commodity, for example, in a treasure detail page of the mobile phone Taobao, keywords about size information given by a buyer who has purchased the commodity (such as: keywords with larger size, smaller size or suitable size) are extracted from the evaluation information of the goods and placed in front of the evaluation of the baby for reference of future buyers; when a user wants to purchase the product, the user can refer to the information such as the keywords and make a size selection.

However, in both of the above methods, the buyer is required to select the commodity model by himself by looking up the existing information, and the e-commerce platform cannot automatically recommend the commodity model suitable for the buyer. In conclusion, the prior art has the problem that the commodity model cannot be automatically recommended.

Disclosure of Invention

The application provides a method for recommending commodity object models, which aims to solve the problem that the commodity models cannot be automatically recommended in the prior art. The application also provides a recommendation device and an electronic device for the commodity object model, a selection method and a selection device for the commodity object model, a selection system for the commodity object model of the electronic device, and a selection method and a selection device for the commodity object model.

The application provides a method for recommending commodity object models, which comprises the following steps:

receiving a model recommendation request aiming at a specific commodity object sent by a first user client;

determining model recommendation information of the specific commodity object provided to the first user according to comment information of purchased users of the specific commodity object on actual purchase models of the purchased users;

and sending the model recommendation information back to the first user client.

Optionally, the purchased users include purchased users having a model association relationship with the first user.

Optionally, the determining, according to information on comments made by the purchased users of the specific commodity object on the actual purchase model of the specific commodity object, model recommendation information of the specific commodity object provided to the first user includes:

acquiring a purchased user having a model association relationship with the first user;

selecting a specific user from purchased users having model association relation with the first user according to a preset user selection rule;

and determining the model recommendation information according to the comment information of the specific user on the actual purchase model of the specific user.

Optionally, the preset user selection rule includes: and selecting the user with the highest model correlation degree.

Optionally, the obtaining of the purchased user having a model association relationship with the first user includes:

acquiring user identifications of purchased users of the specific commodity object according to the transaction record of the specific commodity object;

and acquiring the purchased users having model association relation with the first user according to the user identification of the first user carried by the model recommendation request, the pre-generated model correlation degree information among different users and the user identification of each purchased user.

obtaining a model comment information set of the specific commodity object;

acquiring user identifications of purchased users giving the model comment information to the specific commodity object according to the model comment information set;

Optionally, the obtaining of the model comment information set of the specific commodity object includes:

acquiring a commodity comment information set of the specific commodity object;

extracting comment information related to the model from the commodity comment information set through a semantic analysis technology;

and generating the model comment information set according to the extracted comment information about the model.

Optionally, the model comprises a size model; the model relevancy information comprises size relevancy information;

the model relevancy information among different users is generated by adopting the following method:

for each commodity object in a pre-stored commodity object library, executing the following steps:

acquiring a size comment information set of the commodity object;

acquiring actual purchase size of the user corresponding to the size comment information aiming at each size comment information of the commodity object; extracting size appropriateness information from the size comment information; determining the applicable size of the user to the commodity object according to the extracted size appropriateness information and the actual purchase size;

and according to the applicable size corresponding to each size comment information of the commodity object, increasing one by one the size relevancy among users with the same applicable size.

Optionally, the suitable size of the user for the commodity object is determined according to the extracted size suitable information and the actual purchase size, and the following method is adopted:

if the appropriate size information is larger than the actual purchasing size, setting the size of the commodity object suitable for the user to be one size smaller than the actual purchasing size;

if the size appropriateness information is that the size is smaller, setting the size of the commodity object suitable for the user to be one size larger than the actual purchasing size;

and if the size appropriateness information is that the size is appropriate, setting the size of the commodity object which is applicable to the commodity object by the user as the actual purchasing size.

Optionally, the determining the model recommendation information according to the comment information of the specific user on the actual purchase model thereof includes:

extracting model appropriateness information from comment information of the specific user on the actual purchase model of the specific user;

and determining the model recommendation information according to the extracted model appropriateness information and the actual purchase model of the specific user.

Optionally, the model suitability information is extracted from comment information of the specific user on the actual purchase model thereof, and the following method is adopted:

and extracting model appropriateness information from comment information of the specific user on the actual purchase model thereof through a semantic analysis technology.

Optionally, the model includes a size model, the model appropriateness information includes size appropriateness information, the actual purchase model includes an actual purchase size, and the model recommendation information includes size recommendation information;

determining the model recommendation information according to the extracted model appropriateness information and the actual purchase model of the specific user, and adopting the following mode:

if the appropriate size information is larger than the actual purchase size, generating the size recommendation information according to a size which is one size smaller than the actual purchase size;

if the appropriate size information is a size slightly smaller, generating the size recommendation information according to a size which is one size larger than the actual purchase size;

and if the size appropriateness information is the appropriate size, generating the size recommendation information according to the actual purchased size.

acquiring a standard model or a user-specified model of the first user;

generating model appropriateness information of the specific commodity object according to comment information of each purchased user on the actual purchase model of the purchased user;

and determining the model recommendation information according to the model appropriateness information and the standard model or the model appointed by the user.

acquiring a standard model or a user-specified model of the first user;

generating model appropriateness information of the specific commodity object according to the comment information of the purchased user on the model, which has purchased the standard model or the model designated by the user;

Correspondingly, this application still provides a recommendation device of commodity object model, includes:

the request receiving unit is used for receiving a model recommendation request aiming at a specific commodity object, which is sent by a first user client;

a recommendation information determining unit, configured to determine, according to comment information of a purchased user of the specific commodity object on an actual purchase model thereof, model recommendation information of the specific commodity object provided to the first user;

and the recommendation information returning unit is used for returning the model recommendation information to the first user client.

Optionally, the recommendation information determining unit includes:

a first user acquisition subunit, configured to acquire a purchased user having a model association relationship with the first user;

the specific user selection subunit is used for selecting a specific user from purchased users having model association with the first user according to a preset user selection rule;

and the recommendation information determining subunit is used for determining the model recommendation information according to the comment information of the specific user on the actual purchase model.

Optionally, the recommendation information determining subunit includes:

a model appropriateness information extraction subunit, configured to extract model appropriateness information from comment information of the specific user on an actual purchase model thereof;

and the first recommendation information determining subunit is used for determining the model recommendation information according to the extracted model appropriateness information and the actual purchase model of the specific user.

Optionally, the recommendation information determining unit includes:

an initial model obtaining subunit, configured to obtain a standard model or a user-specified model of the first user;

the model appropriateness information generating subunit is configured to generate model appropriateness information of the specific commodity object according to comment information of each purchased user on an actual purchase model of the purchased user;

and the recommendation information determining subunit is used for determining the model recommendation information according to the model appropriateness information and the standard model or the model designated by the user.

Optionally, the recommendation information determining unit includes:

a model appropriateness information generating subunit, configured to generate model appropriateness information of the specific commodity object according to information about comments on models of purchased users who have purchased the standard models or the models specified by the users;

Correspondingly, the present application also provides an electronic device, comprising:

a display;

a processor; and

a memory for storing a program for implementing a method for recommending a model of a merchandise object, the apparatus performing the following steps after being powered on and running the program for recommending the model of the merchandise object through the processor: receiving a model recommendation request aiming at a specific commodity object sent by a first user client; determining model recommendation information of the specific commodity object provided to the first user according to comment information of purchased users of the specific commodity object on actual purchase models of the purchased users; and sending the model recommendation information back to the first user client.

Correspondingly, the application also provides a method for selecting the model of the commodity object, which comprises the following steps:

sending a model recommendation request aiming at a specific commodity object to a server;

receiving model recommendation information of the specific commodity object returned by the server;

and selecting the selected model of the specific commodity object according to the model recommendation information.

Optionally, the model recommendation request includes a user identifier of the first user;

the model recommendation information comprises a standard model of the first user and a recommendation model provided for the first user.

Optionally, the model selection page of the specific commodity object includes a first page element corresponding to the standard model and a second page element corresponding to the recommended model.

Optionally, the recommending information according to the model and selecting the selected model of the specific commodity object includes:

selecting a standard model corresponding to the first page element as a preliminarily selected selection model;

visually representing the change process of the selected model in the change mode of the preset display parameters of the page elements, and changing the selected model of the specific commodity object from the preliminarily selected model to the recommended model corresponding to the second page element.

Optionally, the model recommendation request includes a model specified by a user;

the model recommendation information includes a recommended model provided for the first user.

Optionally, the model selection page of the specific commodity object includes a first page element corresponding to the specified model of the user and a second page element corresponding to the recommended model.

Optionally, the selection model of the specific commodity object is selected according to the model recommendation information, and the following method is adopted:

visually representing the change process of the selected model in the change mode of the preset display parameters of the page elements, and changing the selected model of the specific commodity object from the model specified by the user to the recommended model corresponding to the second page element.

Optionally, the preset display parameter includes a background color;

the change process of the selected model is visually represented in the change mode of the preset display parameters of the page elements, and the following mode is adopted:

and gradually moving the background color of the first page element to the second page element according to preset change time to be used as the background color of the second page element.

Correspondingly, this application still provides a device is selected to commodity object model, includes:

a request sending unit, configured to send a model recommendation request for a specific commodity object to a server;

an information receiving unit, configured to receive model recommendation information of the specific commodity object returned by the server;

and the model selecting unit is used for selecting the selected model of the specific commodity object according to the model recommendation information.

a display;

a processor; and

a memory for storing a program for implementing a method for selecting a model of a merchandise object, the apparatus performing the following steps after being powered on and running the program for the method for selecting a model of a merchandise object through the processor: sending a model recommendation request aiming at a specific commodity object to a server; receiving model recommendation information of the specific commodity object returned by the server; and selecting the selected model of the specific commodity object according to the model recommendation information.

Correspondingly, the present application further provides a system for selecting a model of a commodity object, including: a recommendation device for the model of the commodity object according to any one of the above items; and a selection device for the commodity object model according to any one of the above.

acquiring a recommended model of a specific commodity object;

visually representing the change process of the selection model by the change mode of the preset display parameters of the page elements, and changing the selection model of the specific commodity object from the preliminarily selected selection model corresponding to the first page element to the recommended model corresponding to the second page element in the model selection page of the specific commodity object.

Optionally, the preset display parameter includes a background color;

a recommended model acquiring unit for acquiring a recommended model of a specific commodity object;

and the model selecting unit is used for visually representing the change process of the selected model in the change mode of the preset display parameters of the page elements, and changing the selected model of the specific commodity object from the preliminarily selected model corresponding to the first page element to the recommended model corresponding to the second page element in the model selecting page of the specific commodity object.

Compared with the prior art, the method for recommending the model of the commodity object provided by the application comprises the steps of receiving a model recommendation request aiming at a specific commodity object sent by a first user client, determining model recommendation information of the specific commodity object provided for a first user according to comment information of a purchased user of the specific commodity object on the actual purchased model of the purchased user, and then returning the model recommendation information to the first user client. By the adoption of the method for recommending the commodity object model, model recommendation information can be automatically provided for a new purchasing user according to comment information of the purchasing user on the actual purchasing model, and therefore the effect of improving commodity model recommendation efficiency and recommendation precision is achieved.

Drawings

FIG. 1 is a flowchart of an embodiment of a method for recommending a model of a merchandise object provided by the present application;

FIG. 2 is a schematic diagram of an embodiment of a recommendation device for merchandise object model numbers provided by the present application;

FIG. 3 is a schematic diagram of an embodiment of an electronic device provided herein;

FIG. 4 is a flowchart of an embodiment of a method for selecting a model of a merchandise object provided by the present application;

FIG. 5 is a schematic interface diagram illustrating an embodiment of a method for selecting a model of a commodity object according to the present disclosure;

FIG. 6 is a schematic diagram of an embodiment of a merchandise object model selection device provided herein;

FIG. 7 is a schematic diagram of an embodiment of an electronic device provided herein;

FIG. 8 is a schematic diagram of a merchandise object model selection system provided herein;

FIG. 9 is a flowchart of an embodiment of a method for selecting a model of a merchandise object provided herein;

fig. 10 is a schematic diagram of an embodiment of a selecting device for selecting a model of an object of merchandise provided by the present application.

Detailed Description

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. This application is capable of implementation in many different ways than those herein set forth and of similar import by those skilled in the art without departing from the spirit and scope of this application, and it is therefore not limited to the specific implementations disclosed below.

The application provides a recommendation method and device for commodity object models and electronic equipment, a selection system for commodity object models, and a selection method and device for commodity object models. Details are described in the following examples one by one.

The core basic idea of the recommendation method for the commodity object model provided by the application is as follows: and providing model recommendation information of the specific commodity object for the purchasing user according to comment information of the purchasing user of the specific commodity object on the actual purchasing model. The model recommendation information can be automatically provided for the newly-purchased user according to the comment information of the purchased user on the actual purchase model, so that the commodity model recommendation efficiency and recommendation precision are improved.

Please refer to fig. 1, which is a flowchart illustrating an embodiment of a method for recommending a model of a commodity object according to the present application. The method comprises the following steps:

step S101: and receiving a model recommendation request aiming at a specific commodity object, which is sent by a first user client.

The specific commodity object comprises a non-standard class commodity object. The commodity object refers to a data expression form of a commodity, for example, a commodity displayed on an e-commerce platform is a commodity object, not a commodity itself. The non-standard goods are as follows: are not manufactured according to the unified industry standards and specifications promulgated by the state. For example, the clothing, shoes, or hats are non-standard goods because the goods have the characteristics of non-uniform size and specification, and color difference.

The model may be a model of different angles, such as a size model, a color model, a material model, or a performance model. Taking clothing commodities as an example, the size models of the clothing commodities can be small, medium, large and the like; the color model can be white, red, blue, etc; the material model can be cotton, hemp, real silk and the like; the style and the type can be long sleeves, short sleeves, sleeveless sleeves and the like. In the inventory management process, the model is usually used as a basic Unit for inventory entry and exit metering, and therefore, the model is also called Stock Keeping Unit (SKU).

The first user is a user who is interested in the model recommendation information of the specific commodity object. The first user sends a model recommendation request aiming at a specific commodity object through a first user client. The first user client includes but is not limited to a mobile communication device, namely: the mobile phone or the smart phone also includes terminal devices such as a personal computer, a PAD, and an iPad.

The model recommendation request from the first user client at least needs to include the identification of the specific commodity object, and the recommendation method of the commodity object model provided by the application determines the specific commodity object according to the identification of the specific commodity object. Furthermore, the model recommendation request needs to include at least one of the following data: the user identification of the first user, the specified model of the specific commodity object by the first user (namely, the user specified model).

The user identifier is used for uniquely identifying a user. When the model recommendation request does not include the user-specified model of the specific commodity object, the standard model applicable to the first user may be determined according to the user identifier of the first user, that is: the normal model of the user. According to the method for recommending the commodity object model, model recommendation can be performed according to the standard model applicable to the first user or the model appointed by the user.

After receiving the model recommendation request, the next step can be entered, and the model recommendation information is determined according to the comment information of the purchased users of the specific commodity object on the actual purchased models.

Step S103: and determining the model recommendation information of the specific commodity object provided to the first user according to the comment information of the purchased user of the specific commodity object on the actual purchase model of the purchased user.

By adopting the method for recommending the commodity object model, an important premise for providing the model recommendation information for the first user is as follows: the specific merchandise object has at least one purchased user. The purchased user may be a user having a model association relationship with the first user or a user not having a model association relationship with the first user.

Judging whether the users have model association relation, various specific implementation modes can be adopted, and two optional implementation modes are given below.

In the first mode, if the users have the same standard model, it can be determined that the users have the model association relationship, for example, if the standard sizes of the user a and the user B are both L-size, the user a and the user B have the model association relationship.

In the second mode, if a plurality of users purchase a certain commodity of the same model at the same time, it is determined that there is a model association relationship between the users, for example, if user a, user B, and user C purchase the same type of jackets of the L code at the same time, there is a model association relationship between the three users.

Further, the association degree between users may also be set according to the number of times users purchase the same goods of the same model, for example, if user a, user B, and user C purchase the same-style coats of L codes at the same time, and user a and user B purchase the same-style shoes of 40 codes at the same time, user a, user B, and user C have a model association relationship and an association degree between each other is 1, and user a and user B have a model association relationship and an association degree between each other is 2.

It should be noted that the above-mentioned various types of changes for determining whether or not there is a relationship between model numbers and for determining the degree of relationship between users are merely changes of the specific embodiments, and do not depart from the core of the present application, and therefore, are all within the scope of protection of the present application.

According to the method for recommending the model of the commodity object, the step S103 can be implemented by adopting different implementation manners according to the specific situation that whether the purchased user includes a user having a model association relationship with the first user. Different embodiments in these two cases are explained below.

When the purchased user of the specific commodity object does not include the user having the model association relationship with the first user, the model recommendation information of the specific commodity object provided to the first user can be determined according to the standard model or the designated model of the first user and the comment information of the purchased user on the actual purchase model of the first user.

As an alternative, the model recommendation information provided to the first user is determined according to the standard model or the specified model of the first user and the comment information of the purchased user on the actual purchased model, and the following method can be adopted: the model recommendation information provided to the first user is determined according to the evaluation information (i.e. model appropriateness information) of the most purchased users for the model, for example, if the evaluation information of the most (e.g. more than 50%) purchased users for the model is larger in size, and the standard model or the designated model of the first user is L-code, the model recommendation information provided to the first user may include: the size is larger, and the recommended size is M.

As still another alternative, the model recommendation information provided to the first user is determined according to the standard model or the specified model of the first user and the comment information of the purchased user on the actual purchased model, and the following method may also be adopted: the model recommendation information provided to the first user is determined according to the evaluation information (i.e. model appropriateness information) of the model of the user with the standard model or the specified model suitable for most of the purchased first users, for example, the standard model or the specified model of the first user is L-code, and the evaluation information of the model of most of (e.g. more than 50%) users who have purchased L-code is larger in size, and then the model recommendation information provided to the first user may include: the size is larger, and the recommended size is M.

When the model recommendation request includes the identifier of the specific commodity object and the user identifier of the first user, but does not include the model specified by the user, the method for recommending the model of the commodity object provided by the application may first determine the standard model of the first user according to the user identifier of the first user, and then determine the model recommendation information provided to the first user according to the identifier of the specific commodity object, the standard model of the first user, and the comment information of the purchased user on the actual purchase model of the purchased user.

To implement the function of determining the standard model number applicable to the user according to the user identifier, various specific embodiments may be adopted, and several alternative embodiments are given below.

In the first mode, various types of information suitable for the user is recorded in the user characteristic data of the first user, and the types are regarded as standard types, for example, the type information such as the size of a jacket, the size of trousers, the size of shoes and the like, so that the standard type of the user can be obtained from the user characteristic data of the first user according to the user identification of the first user.

And secondly, recording body shape information of the first user, such as height, weight and the like, in the user characteristic data of the first user, obtaining the body shape information of the user according to the user identification of the first user, comparing the body shape information with the size details (waist circumference, chest circumference, sleeve length and the like) of the clothes commodity to be purchased, and calculating to obtain the model required by the user for the clothes, wherein the model can also be regarded as a standard model.

And thirdly, the user characteristic data of the first user does not record the height, weight and other type information, but records other users with type association relation with the first user, and the user characteristic data of the other users record the height, weight, type and other information, so that the other users with type association relation with the first user can be firstly obtained according to the user identification of the first user, and then the height, weight, type and other information of the other users can be referred to, and the type information of the first user is obtained to be used as the standard type of the first user.

When the model recommendation request comprises the identification of the specific commodity object and the model designated by the user of the specific commodity object, the model recommendation method of the commodity object provided by the application can determine the model recommendation information of the specific commodity object provided for the first user directly according to the two information and the comment information of the purchased user on the actual purchased model.

The above section explains a specific embodiment that can be adopted in step S103 when the purchased user of the specific merchandise object does not include a user having a model association relationship with the first user.

The following will describe a processing procedure in the case where the purchased user of the specific merchandise object includes a user having a model association relationship with the first user.

Secondly, when the purchased users of the specific commodity object comprise users having model association relations with the first user, the model recommendation information of the specific commodity object provided to the first user can be determined according to comment information of a certain (or some) users having model association relations with the first user on actual purchased models of the users.

In this embodiment, the model recommendation information provided to the first user is determined according to comment information on an actual purchase model of a certain user having a model association relationship with the first user. To implement the function of determining model recommendation information provided to the first user according to comment information about an actual purchase model of a specific user having a model association relationship with the first user, the step S103 may include the following specific steps:

step S1031: and acquiring a purchased user having a model association relationship with the first user.

To determine the model recommendation information provided to the first user according to the comment information of a certain user having a model association relationship with the first user on the actual purchase model, first, a purchased user having a model association relationship with the first user needs to be acquired. For example, if there are 20 users having a model association relationship with the first user, 100 users who have purchased a specific merchandise object, and only 3 users among the 20 users having a model association relationship with the first user have purchased the specific merchandise object, the 3 users are purchased users having a model association relationship with the first user.

To obtain the purchased user having the model association relationship with the first user, various specific embodiments may be adopted, and two alternative embodiments are given below.

The first mode, the processing procedure of this mode is as follows: firstly, acquiring user identifications of purchased users of a specific commodity object according to a transaction record of the specific commodity object; and then, acquiring the purchased users having model association relation with the first user according to the user identification of the first user, the pre-generated model correlation degree information among different users and the user identification of each purchased user.

The purchased users having model association relationship with the first user are obtained according to the transaction record of the specific commodity object, so that the purchased users having model association relationship with the first user obtained in the first mode include all the purchased users having model association relationship with the first user of the specific commodity object.

The second method is as follows: firstly, acquiring a model comment information set of a specific commodity object; then, according to the model comment information set, acquiring user identifications of all purchased users giving model comment information to the specific commodity object; and finally, acquiring the purchased users having model association relation with the first user according to the user identification of the first user, the pre-generated model correlation degree information among different users and the user identification of each purchased user.

The model review information set is a set of product review information related to models. The model number comment information set of a specific commodity object is formed from the comment information on the relevant model number of the commodity object by a user who has purchased the commodity object.

Since the purchased users having model association relationship with the first user are obtained according to the model comment information set of the specific commodity object, the purchased users having model association relationship with the first user obtained in the second way may only include the purchased users having model association relationship with the first user of "part" of the specific commodity object, that is: and only the purchased users having model association relation with the first user who have model comment on the specific commodity object.

To perform the processing in the second mode, the model comment information set of the specific commodity object needs to be acquired first. In specific implementation, the step of obtaining the model comment information set of the specific commodity object may include the following specific steps: 1) acquiring a commodity comment information set of the specific commodity object; 2) extracting comment information related to the model from the commodity comment information set through a semantic analysis technology; 3) and generating the model comment information set according to the extracted comment information about the model. These steps are briefly described below.

1) And acquiring a commodity comment information set of the specific commodity object.

After a user purchases a commodity object, the user can criticize or discuss the commodity object, that is: and giving commodity comment information. The commodity comment information is the subjective opinion of the purchased user, and the purchased user can comment on the purchased commodity object from various angles (such as size, color, material, style, comfort level and the like). Taking a garment as an example, the commodity comment information of a purchased user on a certain garment is shown in table 1:

TABLE 1 Commodity review information List

Each item comment information of the commodity object identified by the purchased user as "1" for the commodity object in table 1 constitutes a comment information set for the commodity object.

Since the commodity comment information includes comments made by the purchased users on the commodity from different angles, and the model comment information only includes comments made by the purchased users on the model of the commodity, the model comment information set is usually a subset of the commodity comment information set, for example, the model is a size model, and the commodity comment information with comment identifiers of 2, 3, 4, 5, 76, 78, 79 in table 1 includes size comment information, where the size comment information with comment identifiers of 2, 3, 4 constitutes the size comment information set of the commodity object 1.

2) And extracting the comment information of the relevant model from the commodity comment information set by a semantic analysis technology.

The model rating information set is a subset of information extracted from the commercial rating information set. In specific implementation, the comment information about the model can be extracted from the product comment information through a semantic analysis technology, for example, the comment information about the model included in the product comment information identified as "2" in table 1 is "fit", the comment information about the model included in the product comment information identified as "3" is "but one code larger than usual", and the comment information about the model included in the product comment information identified as "4" is "slightly smaller in number, but slightly smaller in number.

3) And generating the model comment information set according to the extracted comment information about the model.

And in the step, the comment information about the model extracted from the commodity comment information set in the previous step is used for forming the model comment information set.

Whether the above-mentioned first or second method is adopted to implement the step S103, the pre-generated information about the correlation degree between the models of different users is applied. The pre-generated information on the relevance of the model between different users may be the relevance of any two users in the aspect of the model, or the relevance of multiple users in the aspect of the model. Taking the model as the size model as an example, the size relevancy information between any two users is shown in table 2:

identification	Associating users	Size correlation
			1	User A, user B	23
2	User A, user C	10
			3	User A, user X	2
4	User A, user Y	1
			…	…	…
10001	User Y, user B	13
			10002	User Y, user C	8
10003	User Y, user X	5
			10004	User Y, user Z	1
…	…	…

TABLE 2 size correlation information between different users

The information on the degree of correlation in size between the plurality of different users in table 2 constitutes the size correlation information between the different users generated in advance.

An alternative to generating information on the relevance of the model between the different users is given below, taking the size model as an example. In this embodiment, the size correlation information between different users may be generated as follows: aiming at each commodity object in a pre-stored commodity object library, the following specific steps are executed: 1) acquiring a size comment information set of the commodity object; 2) acquiring actual purchase size of the user corresponding to the size comment information aiming at each size comment information of the commodity object; extracting size appropriateness information from the size comment information; determining the applicable size of the user to the commodity object according to the extracted size appropriateness information and the actual purchase size; 3) and according to the applicable size corresponding to each size comment information of the commodity object, increasing one by one the size relevancy among users with the same applicable size.

First, the steps 1 to 3 are performed once for each of the commodity objects in the commodity object library stored in advance. The following is a detailed description of each of the above steps 1 to 3.

1) And acquiring a size comment information set of the commodity object.

For any commodity object, firstly, size comment information made on the commodity object by a purchased user needs to be acquired, and the size comment information forms a size comment information set of the commodity object.

2) Acquiring actual purchase size of the user corresponding to the size comment information aiming at each size comment information of the commodity object; extracting size appropriateness information from the size comment information; and determining the size suitable for the commodity object by the user according to the extracted size suitable degree information and the actual purchasing size.

For each size comment information of the commodity object obtained in the previous step, the actual purchase size of the user corresponding to the size comment information needs to be further obtained, and in specific implementation, the commodity size actually purchased by the purchased user can be extracted from the order corresponding to the size comment information.

Meanwhile, size appropriateness information needs to be extracted from the size comment information. In specific implementation, size appropriateness information may be extracted from the size comment information through a semantic analysis technique, for example, in table 1, the size appropriateness information included in the commodity object comment information identified as "2" is "appropriateness", the size appropriateness information included in the commodity object comment information identified as "3" is "slightly larger in size", and the size appropriateness information included in the commodity object comment information identified as "4" is "slightly smaller in size".

Then, the applicable size of the purchased user to the commodity object can be determined according to the extracted size appropriateness information and the size actually purchased by the purchased user.

In specific implementation, the step of determining the applicable size of the user to the commodity object according to the extracted size appropriateness information and the actual purchase size may adopt the following method: if the appropriate size information is larger than the actual purchasing size, setting the size of the commodity object suitable for the user to be one size smaller than the actual purchasing size; if the size appropriateness information is that the size is smaller, setting the size of the commodity object suitable for the user to be one size larger than the actual purchasing size; and if the size appropriateness information is that the size is appropriate, setting the size of the commodity object which is applicable to the commodity object by the user as the actual purchasing size.

3) And according to the applicable size corresponding to each size comment information of the article, increasing one by one the size relevancy among users with the same applicable size.

After the applicable sizes of the purchased users to the commodity objects are obtained through the previous step, the step adds one to the size correlation degree between different users with the same applicable sizes according to the applicable size information, for example, if the user A and the user B both purchase a commodity object, and if the commodity objects are the same applicable sizes, the size correlation degree between the user A and the user B is added with one; if the user A and the user B purchase another commodity object at the same time and the commodity objects are the same applicable size, the size correlation degree between the user A and the user B is increased by one.

After the above steps 1 to 3 are performed once for each commodity object in the pre-stored commodity object library, the size correlation information between different users as shown in table 2 is generated. After the model relevancy information between the different users is generated, the purchased users having the model association relationship with the first user can be obtained by applying the pre-generated model relevancy information between the different users in the first mode or the second mode.

Step S1033: and selecting a specific user from purchased users having model association relation with the first user according to a preset user selection rule.

The preset user selection rules include, but are not limited to: and selecting the user with the highest model relevancy, and after selecting the purchased user by adopting the selection rule, recommending the size of the comment information of the actually purchased model by referring to the user, thereby obtaining a better recommendation effect. Of course, in the implementation, other user selection rules may be set, for example, one user is selected from the users greater than the preset minimum correlation threshold, and the like.

Step S1035: and determining the model recommendation information according to the comment information of the specific user on the actual purchase model of the specific user.

The actual purchase model of the specific commodity object purchased by the specific user can be extracted from the trade order of the user for the commodity object.

The model recommendation information may include a specific model recommended to the first user, and may further include size evaluation information (i.e., model appropriateness information) for the specific commodity object, for example, model appropriateness information such as a larger size or a smaller size of the commodity. In addition, the model recommendation information may further include a standard model of the first user for reference by the first user.

In specific implementation, the step S1035 may include the following specific steps: 1) extracting model appropriateness information from comment information of the specific user on the actual purchase model of the specific user; 2) and determining the model recommendation information according to the extracted model appropriateness information and the actual purchase model of the specific user.

The model appropriateness information is extracted from comment information of the specific user on the actual purchase model, and the following method can be adopted: and extracting model appropriateness information from comment information of the specific user on the actual purchase model thereof through a semantic analysis technology. For example, in table 1, the size appropriateness information included in the commodity object comment information identified by the comment "2" is "appropriateness", the size appropriateness information included in the commodity object comment information identified by the comment "3" is "large in size", and the size appropriateness information included in the commodity object comment information identified by the comment "4" is "small in size".

In this embodiment, the model is a size model, and correspondingly, the model appropriateness information is size appropriateness information, the model recommendation information is size recommendation information, and the actual purchase model is an actual purchase size. In a specific implementation, the step S1035 can be implemented as follows: if the size appropriateness information is that the size is larger, recommending a size which is one size smaller than the actual purchase size of the specific user to the first user; if the size appropriateness information is that the size is smaller, recommending a size which is one size larger than the actual purchase size of the specific user to the first user; if the size appropriateness information is a suitable size, the actual purchase size of the specific user can be recommended to the first user.

For example, user X wants to purchase the merchandise object identified as "1" in Table 1; as can be seen from table 2, the size correlation between user X and user a is 2, and the size correlation between user X and user Y is 5; as can be seen from table 1, of the users having a size correlation with the user X, only the user a and the user Y purchase an article whose commodity object is identified as "1"; because the highest degree of size correlation between the user X and the user Y is 5, the size can be recommended to the user X according to the comment information of the user Y on the commodity; since the size appropriateness information included in the commodity comment information of the user Y is "a small size" and the size actually purchased is L, the XL size is recommended to the user X.

Step S105: and sending the model recommendation information back to the first user client.

And returning the model recommendation information acquired in the step to the first user client for reference by the first user client.

In the above embodiment, a method for recommending a model of a commodity object is provided, and correspondingly, a device for recommending a model of a commodity object is also provided. The apparatus corresponds to an embodiment of the method described above.

Please refer to fig. 2, which is a schematic diagram of an embodiment of a recommendation device for merchandise object model of the present application. Since the apparatus embodiments are substantially similar to the method embodiments, they are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for relevant points. The device embodiments described below are merely illustrative.

The recommendation device for the commodity object model of the embodiment comprises:

a request receiving unit 101, configured to receive a model recommendation request for a specific commodity object sent by a first user client;

a recommendation information determining unit 103, configured to determine, according to comment information of a purchased user of the specific commodity object on an actual purchase model thereof, model recommendation information of the specific commodity object provided to the first user;

a recommendation information returning unit 105, configured to return the model recommendation information to the first user client.

Optionally, the recommendation information determining unit 105 includes:

Optionally, the recommendation information determining subunit includes:

Optionally, the recommendation information determining unit 105 includes:

Please refer to fig. 3, which is a schematic diagram of an embodiment of an electronic device according to the present application. Since the apparatus embodiments are substantially similar to the method embodiments, they are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for relevant points. The device embodiments described below are merely illustrative.

An electronic device of the present embodiment includes: a processor 101; and a memory 103 for storing a program for implementing a recommendation method for a model of a merchandise object, the apparatus being powered on and executing the program for the recommendation method for a model of a merchandise object by the processor 101, and performing the steps of: receiving a model recommendation request aiming at a specific commodity object sent by a first user client; determining model recommendation information of the specific commodity object provided to the first user according to comment information of purchased users of the specific commodity object on actual purchase models of the purchased users; and sending the model recommendation information back to the first user client.

According to the method, the device and the electronic equipment for recommending the model of the commodity object, the model recommendation request for the specific commodity object sent by the first user client is received, the model recommendation information of the specific commodity object provided for the first user is determined according to the comment information of the purchased user of the specific commodity object on the actual purchase model of the purchased user, and then the model recommendation information is returned to the first user client. By adopting the method and the device for recommending the commodity object model and the electronic equipment, model recommendation information can be automatically provided for a newly-purchased user according to comment information of the purchased user on the actual purchased model, so that the effects of improving commodity model recommendation efficiency and recommendation precision are achieved.

Corresponding to the recommendation method of the commodity object model, the application also provides a selection method of the commodity object model. Please refer to fig. 4, which is a flowchart illustrating an embodiment of a method for selecting a model of a commodity object according to the present application, where details of the same portion as that in the first embodiment are not repeated, and please refer to corresponding portions in the first embodiment. The method for selecting the commodity object model comprises the following steps:

step S101: and sending a model recommendation request aiming at the specific commodity object to a server.

The model recommendation request at least includes an identification of the specific merchandise object, and the model recommendation request may further include: at least one of a user identification of the first user and a user-specified model of the particular merchandise object.

The user identifier is used for uniquely identifying a user. When the model recommendation request comprises a user identification, a user client firstly acquires the user identification of the current user and forms a model recommendation request according to the user identification; after receiving the request, the server determines the standard model applicable to the user according to the user identifier carried by the request, namely: and (4) the server side can recommend the model according to the standard model suitable for the user according to the normal model of the user.

As an optional scheme, a user may first select a specific model of a commodity object, and then may send a model recommendation request for a specific commodity object to a server by clicking a button similar to "please check a size recommendation table" or the like, where the model recommendation request carries a model specified by the user; the server side generates the recommendation information of the type (such as the size) of the commodity object suitable for the user according to the request and returns the recommendation information to the requester.

Step S103: and receiving the model recommendation information of the specific commodity object returned by the server.

The model recommendation information may include a specific model recommended to the first user. When the model recommendation request includes the user identification of the first user, the model recommendation information may further include a standard model of the first user.

Furthermore, the model recommendation information may further include model evaluation information (i.e., model appropriateness information) for a specific commodity object, for example, a size of the commodity is larger or smaller.

Step S105: and selecting the selected model of the specific commodity object according to the model recommendation information.

According to the method for selecting the commodity object model, after model recommendation information returned by the server is received, the commodity model suitable for the user is automatically selected according to the information.

As an alternative, if the model recommendation request includes a user identifier of the first user, the model recommendation information includes a standard model and a recommended model of the first user, and the model selection page of the specific merchandise object includes a first page element corresponding to the standard model and a second page element corresponding to the recommended model, this step S105 may include the following specific steps: firstly, selecting a standard model corresponding to a first page element, and taking the standard model as a preliminarily selected selection model; and then visually representing the change process of the selected model in the change mode of the preset display parameters of the page elements, and changing the selected model of the specific commodity object from the preliminarily selected model to the recommended model corresponding to the second page element.

The preset display parameters are preset parameters which affect the visual effect of the page elements. The preset display parameters include, but are not limited to, at least one of the following display parameters: the background color, the border color, and the size may also be other display parameters, such as font size, font color, etc., which all affect the visual effect of the page elements.

The method for visually representing the change process of the selected model by the change mode of the preset display parameters of the page elements means that the user can visually perceive the change process from the initial selected model to the recommended model by changing the preset display parameters of the page elements corresponding to the initial selected model and the recommended model.

Taking the preset display parameter as the background color as an example, the change process of the selected model is visually represented by the change mode of the preset display parameter of the page element, which may be as follows: and gradually moving the background color of the first page element to the second page element according to preset change time to be used as the background color of the second page element.

The preset change time is time consumed for completely moving the background color of the first page element to the second page element. The preset change time may be set according to specific service requirements, for example, set to 5 seconds.

Please refer to fig. 5, which is an interface schematic diagram of an embodiment of a method for selecting a model of a commodity object according to the present application, and the model change effect of the above embodiment can be intuitively perceived through fig. 5. As can be seen from FIG. 5, when a user wants to purchase a T-shirt, the user client may automatically send a model (size) recommendation request for the merchandise object to the server when the user selects to view details of the merchandise object, the request including the user identification of the current user (i.e., the first user); the server generates the model (size) recommendation information of the commodity object suitable for the user according to the request and returns the recommendation information to the requester; the model recommendation information returned by the server comprises: standard size: XL code, recommended size: XXL code, and model suitability information: the size is smaller.

The model change process referred to in fig. 5 is explained below. FIG. 5, panel a, shows the effect of initially selecting the selected model of a particular merchandise object as the standard model (i.e., the normal size of the user), at which point the background color of the page element corresponding to the standard model is the completely filled background color; as time goes on, the background color of the page element corresponding to the standard model begins to change, the background color of the page element gradually moves to the page element corresponding to the recommended size, the small graph b shows the effect when the model just begins to change, and at the moment, the background color of the page element corresponding to the standard model is the partially filled background color; as time continues to lapse, a part of the background color of the page element corresponding to the standard model has moved to the page element corresponding to the recommended size, the c small graph shows the effect of the model change at this time, and at this time, the background color of the page element corresponding to the recommended model is the partially filled background color; and (3) along with further time lapse, when the preset change time is reached, the background color of the page element corresponding to the standard model is completely moved to the page element corresponding to the recommended size, at the moment, the background color of the page element corresponding to the recommended size is the completely filled background color, the d small graph shows the effect of finally selecting the selected model of the specific commodity object as the recommended model, and also shows information of appropriate model (small size, suggested selection) for direct reference of the user. As can be seen from the four pictures from the small image a to the small image d, the change process of the selected model can be visually perceived by the user by gradually moving the background color of the first page element to the second page element and finally serving as the background color of the second page element.

As another optional scheme, if the model recommendation request includes a model specified by a user, the model recommendation information includes a recommended model, and the model selection page of the specific commodity object includes a first page element corresponding to the model specified by the user and a second page element corresponding to the recommended model, then this step S105 may adopt the following manner: visually representing the change process of the selected model in the change mode of the preset display parameters of the page elements, and changing the selected model of the specific commodity object from the model specified by the user to the recommended model corresponding to the second page element.

It should be noted that, other specific embodiments may also be adopted in step S105, for example, the recommended model may be directly selected as the selection model of the specific commodity object, instead of selecting the standard model as the initially selected model, and then visually representing the change process of the selected model in the change mode of the preset display parameters of the page elements. In practical applications, the specific implementation manner may be selected according to specific business requirements, and these different manners are all modifications of the specific implementation manner, and do not depart from the core of the present application, and therefore, are all within the protection scope of the present application.

In the foregoing embodiment, a method for selecting a commodity object model is provided, and correspondingly, an apparatus for acquiring a commodity object model is also provided in the present application. The apparatus corresponds to an embodiment of the method described above.

Please refer to fig. 6, which is a schematic diagram of an embodiment of an apparatus for obtaining a merchandise object model according to the present application. Since the apparatus embodiments are substantially similar to the method embodiments, they are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for relevant points. The device embodiments described below are merely illustrative.

The apparatus for acquiring a commodity object model of this embodiment includes:

a request sending unit 101, configured to send a model recommendation request for a specific commodity object to a server;

an information receiving unit 103, configured to receive model recommendation information of the specific commodity object returned by the server;

a model selecting unit 105, configured to select a selected model of the specific commodity object according to the model recommendation information.

Please refer to fig. 7, which is a schematic diagram of an embodiment of an electronic device according to the present application. Since the apparatus embodiments are substantially similar to the method embodiments, they are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for relevant points. The device embodiments described below are merely illustrative.

An electronic device of the present embodiment includes: a display 101; a processor 102; and a memory 103 for storing a program for implementing a method for selecting a model of a merchandise object, the apparatus performing the following steps after being powered on and running the program for selecting the model of the merchandise object through the processor 102: sending a model recommendation request aiming at a specific commodity object to a server; receiving model recommendation information of the specific commodity object returned by the server; and selecting the selected model of the specific commodity object according to the model recommendation information.

The embodiment of the present application further provides a system for selecting a type of a commodity object, as shown in fig. 8, the system includes a recommendation device 101 for a type of a commodity object and a selection device 102 for a type of a commodity object, which are described in the foregoing embodiment. The recommendation device 101 for the commodity object model is usually deployed in a server, but is not limited to the server, and may be any device capable of implementing a recommendation method for the commodity object model; the selection device 102 for the commodity object model is generally deployed in terminal devices such as mobile communication devices, personal computers, PADs, ipads, and the like.

For example, the selecting device 102 for the model of the commodity object is deployed on a smartphone, and can send a model recommendation request for a specific commodity object to a server and receive model recommendation information of the specific commodity object returned by the server; the commodity object model recommendation device 101 is deployed on a server and receives a model recommendation request for a specific commodity object sent by a first user client; determining model recommendation information of the specific commodity object provided to the first user according to comment information of purchased users of the specific commodity object on actual purchase models of the purchased users; returning the model recommendation information to the first user client; after receiving the model recommendation information, the selecting device 102 for the model of the commodity object automatically selects the selected model of the specific commodity object according to the model recommendation information.

By adopting the commodity object model selecting system, the user does not need to execute the model selecting operation, the user operation is simplified, the duration of the model selecting process is shortened, and the effect of improving the model selecting efficiency is achieved.

Corresponding to the selection method of the commodity object model, the application also provides another selection method of the commodity object model. Please refer to fig. 9, which is a flowchart illustrating an embodiment of a method for selecting a commodity object model according to another embodiment of the present application, and details of the same portions in this embodiment as those in the embodiment of the method for selecting a commodity object model are not repeated, please refer to corresponding portions in this embodiment. The application provides a further method for selecting a commodity object model, which comprises the following steps:

step S101: and acquiring the recommended model of the specific commodity object.

Step S103: visually representing the change process of the selection model by the change mode of the preset display parameters of the page elements, and changing the selection model of the specific commodity object from the preliminarily selected selection model corresponding to the first page element to the recommended model corresponding to the second page element in the model selection page of the specific commodity object.

The preset display parameters include at least one of the following display parameters: background color, border color, size.

The preliminarily selected model can be a standard model of a user or a model designated by the user.

As a preferable scheme, the preset display parameter includes a background color; the change process of the selected model is visually represented by the change mode of the preset display parameters of the page elements, and the following mode can be adopted: and gradually moving the background color of the first page element to the second page element according to preset change time to be used as the background color of the second page element.

For example, when a user selects a model of a certain commodity object in a detail page of the commodity object, the model is a preliminarily selected selection model, which is generally applicable to the user, and when a client displaying the detail page acquires a recommended model of the commodity object provided for the user, the background color of a first page element corresponding to the preliminarily selected selection model is gradually moved to a second page element corresponding to the recommended model to serve as the background color of the second page element, so that the user can visually perceive a selection change process from the initially selected model to the recommended model.

According to the method for obtaining the model of the commodity object, the change process of the selected model is visually represented in the change mode of the preset display parameter of the page element, and in the model selection page of the specific commodity object, the selected model of the specific commodity object is changed from the preliminarily selected model corresponding to the first page element to the recommended model corresponding to the second page element; the processing mode enables the user to visually perceive the selection change process from the initially selected model to the recommended model; therefore, the user experience can be effectively improved.

In the above embodiment, a method for selecting another type of commodity object is provided, and correspondingly, an apparatus for acquiring another type of commodity object is provided in the present application. The apparatus corresponds to an embodiment of the method described above.

Please refer to fig. 10, which is a schematic diagram of an embodiment of an apparatus for obtaining a merchandise object model according to the present application. Since the apparatus embodiments are substantially similar to the method embodiments, they are described in a relatively simple manner, and reference may be made to some of the descriptions of the method embodiments for relevant points. The device embodiments described below are merely illustrative.

The apparatus for obtaining a model of a commodity object of this embodiment includes:

a recommended model acquiring unit 101 configured to acquire a recommended model of a specific commodity object;

the model selecting unit 103 is configured to visually represent a change process of a selected model in a change manner of a preset display parameter of a page element, and change the selected model of the specific commodity object from a preliminarily selected model corresponding to a first page element to the recommended model corresponding to a second page element in a model selecting page of the specific commodity object.

Although the present application has been described with reference to the preferred embodiments, it is not intended to limit the present application, and those skilled in the art can make variations and modifications without departing from the spirit and scope of the present application, therefore, the scope of the present application should be determined by the claims that follow.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

1. Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include non-transitory computer readable media (transient media), such as modulated data signals and carrier waves.

2. As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

Claims

1. A method for recommending a commodity object model is characterized by comprising the following steps:

determining model recommendation information of the specific commodity object provided to the first user according to comment information of purchased users of the specific commodity object on actual purchase models of the purchased users, wherein the purchased users of the specific commodity object comprise purchased users having model association relations with the first user;

returning the model recommendation information to the first user client;

the method further comprises the following steps: according to the model recommendation request, acquiring a purchased user having a model association relationship with the first user, including: acquiring a purchased user having a model association relationship with the first user according to the user identifier of the first user carried by the model recommendation request, pre-generated model correlation degree information among different users and the user identifier of the purchased user of the specific commodity object; and the pre-generated model correlation degree information among different users is determined according to each size comment information in the size comment information set of the commodity object.

2. The method for recommending a model of a merchandise object according to claim 1, wherein said determining model recommendation information of the specific merchandise object provided to the first user according to comment information of a purchased user of the specific merchandise object on an actual purchase model thereof comprises:

3. The method for recommending a commodity object model according to claim 2, wherein said preset user selection rule comprises: and selecting the user with the highest model correlation degree.

4. The recommendation method for model of merchandise object according to claim 1, wherein the user identification of the purchased user of the specific merchandise object is obtained from a transaction record of the specific merchandise object.

5. The recommendation method for model of merchandise object according to claim 1, wherein the user identification of the purchased user of the specific merchandise object is obtained by:

obtaining a model comment information set of the specific commodity object;

and acquiring user identifications of all purchased users giving the model comment information to the specific commodity object according to the model comment information set.

6. The method for recommending a model of a merchandise object according to claim 5, wherein said obtaining a model comment information set of said specific merchandise object comprises:

acquiring a commodity comment information set of the specific commodity object;

7. The method of recommending a merchandise object model according to claim 4 or 5, characterized in that:

the model comprises a size model; the model relevancy information comprises size relevancy information;

acquiring a size comment information set of the commodity object;

8. The method for recommending a model of a merchandise object according to claim 7, wherein said determining a size applicable to said merchandise object by said user based on said extracted size appropriateness information and said actual purchase size is performed by:

9. The method for recommending a model of a merchandise object according to claim 2, wherein said determining said model recommendation information according to the comment information of said specific user on the actual purchase model thereof comprises:

10. The method for recommending a model of a merchandise object according to claim 9, wherein said extracting model suitability information from comment information of said specific user on an actual purchase model thereof is performed by:

11. The recommendation method of a commodity object model according to claim 9, characterized in that:

the model comprises a size model, the model appropriateness information comprises size appropriateness information, the actual purchase model comprises an actual purchase size, and the model recommendation information comprises size recommendation information;

12. The method for recommending a model of a merchandise object according to claim 1, wherein said determining model recommendation information of the specific merchandise object provided to the first user according to comment information of a purchased user of the specific merchandise object on an actual purchase model thereof comprises:

acquiring a standard model or a user-specified model of the first user;

13. The method for recommending a model of a merchandise object according to claim 1, wherein said determining model recommendation information of the specific merchandise object provided to the first user according to comment information of a purchased user of the specific merchandise object on an actual purchase model thereof comprises:

acquiring a standard model or a user-specified model of the first user;

14. The method of recommending a model of a merchandise object according to claim 1, wherein the model recommendation information includes at least one of recommended model and model fitness information.

15. The method of recommending a model of a merchandise object according to claim 14, wherein said model recommendation information further includes a standard model of said first user.

16. The recommendation method for model number of commodity object according to claim 1, wherein said specific commodity object comprises clothes, shoes, or hats.

17. The method for recommending a model of a merchandise object according to claim 1, wherein the model includes a size model, a color model, a material model, or a style model.

18. A recommendation apparatus for a model of a commodity object, comprising:

a recommendation information determination unit, configured to determine model recommendation information of the specific commodity object provided to the first user according to comment information of a purchased user of the specific commodity object on an actual purchase model of the purchased user, where the purchased user of the specific commodity object includes a purchased user having a model association relationship with the first user;

a recommendation information returning unit, configured to return the model recommendation information to the first user client;

the device further comprises: a first user obtaining subunit, configured to obtain, according to the model recommendation request, a purchased user having a model association relationship with the first user, including: acquiring a purchased user having a model association relationship with the first user according to the user identifier of the first user carried by the model recommendation request, pre-generated model correlation degree information among different users and the user identifier of the purchased user of the specific commodity object; and the pre-generated model correlation degree information among different users is determined according to each size comment information in the size comment information set of the commodity object.

19. The recommendation device for a commodity object model according to claim 18, wherein said recommendation information determination unit comprises:

20. The recommendation device for a model of a merchandise object according to claim 19, wherein the recommendation information determining subunit comprises:

21. The recommendation device for a commodity object model according to claim 18, wherein said recommendation information determination unit comprises:

22. The recommendation device for a commodity object model according to claim 18, wherein said recommendation information determination unit comprises:

23. An electronic device, comprising:

a display;

a processor; and

a memory for storing a program for implementing a method for recommending a model of a merchandise object, the apparatus performing the following steps after being powered on and running the program for recommending the model of the merchandise object through the processor: receiving a model recommendation request aiming at a specific commodity object sent by a first user client; determining model recommendation information of the specific commodity object provided to the first user according to comment information of purchased users of the specific commodity object on actual purchase models of the purchased users, wherein the purchased users of the specific commodity object comprise purchased users having model association relations with the first user; returning the model recommendation information to the first user client; after the equipment is powered on and the program of the recommendation method of the commodity object model is run through the processor, the following steps are also executed: according to the model recommendation request, acquiring a purchased user having a model association relationship with the first user, including: acquiring a purchased user having a model association relationship with the first user according to the user identifier of the first user carried by the model recommendation request, pre-generated model correlation degree information among different users and the user identifier of the purchased user of the specific commodity object; and the pre-generated model correlation degree information among different users is determined according to each size comment information in the size comment information set of the commodity object.

24. A method for selecting a commodity object model is characterized by comprising the following steps:

selecting the selection model of the specific commodity object according to the model recommendation information;

the server determines the model recommendation information of the specific commodity object by the following method: according to the model recommendation request, acquiring a purchased user having a model association relationship with the first user, including: acquiring a purchased user having a model association relationship with the first user according to the user identifier of the first user carried by the model recommendation request, pre-generated model correlation degree information among different users and the user identifier of the purchased user of the specific commodity object; the pre-generated model correlation degree information among different users is determined according to each size comment information in the size comment information set of the commodity object; determining model recommendation information of the specific commodity object provided to the first user according to comment information of purchased users of the specific commodity object on actual purchase models of the purchased users; wherein the purchased users of the specific merchandise object include purchased users having a model association relationship with the first user.

25. The method of selecting a merchandise object model according to claim 24, wherein:

the model recommendation request comprises a user identification of the first user;

26. The method for selecting model of merchandise object according to claim 25, wherein the model selection page of the specific merchandise object includes a first page element corresponding to the standard model and a second page element corresponding to the recommended model.

27. The method for selecting models of commodity objects according to claim 26, wherein the recommending information according to the model and selecting the selected model of the specific commodity object comprises:

28. The method of selecting a merchandise object model according to claim 24, wherein:

the model recommendation request comprises a model specified by a user;

29. The method for selecting model of merchandise object according to claim 28, wherein the model selection page of the specific merchandise object includes a first page element corresponding to the user-specified model and a second page element corresponding to the recommended model.

30. The method for selecting models of commodity objects according to claim 29, wherein the selection model of the specific commodity object is selected according to the model recommendation information in the following manner:

31. The method for selecting a model of a merchandise object according to claim 27 or 30, wherein the preset display parameters include at least one of the following display parameters: background color, border color, size.

32. The method of selecting a merchandise object model according to claim 31, wherein:

the preset display parameters comprise background colors;

33. The method of selecting a merchandise object model according to claim 24, wherein:

the model recommendation information comprises model appropriateness information;

the method further comprises the following steps:

and displaying the model appropriateness information.

34. A commodity object model selection device is characterized by comprising:

the model selecting unit is used for selecting the selected model of the specific commodity object according to the model recommendation information;

35. An electronic device, comprising:

a display;

a processor; and

a memory for storing a program for implementing a method for selecting a model of a merchandise object, the apparatus performing the following steps after being powered on and running the program for the method for selecting a model of a merchandise object through the processor: sending a model recommendation request aiming at a specific commodity object to a server; receiving model recommendation information of the specific commodity object returned by the server; selecting the selection model of the specific commodity object according to the model recommendation information; the server determines the model recommendation information of the specific commodity object by the following method: according to the model recommendation request, acquiring a purchased user having a model association relationship with the first user, including: acquiring a purchased user having a model association relationship with the first user according to the user identifier of the first user carried by the model recommendation request, pre-generated model correlation degree information among different users and the user identifier of the purchased user of the specific commodity object; the pre-generated model correlation degree information among different users is determined according to each size comment information in the size comment information set of the commodity object; determining model recommendation information of the specific commodity object provided to the first user according to comment information of purchased users of the specific commodity object on actual purchase models of the purchased users; wherein the purchased users of the specific merchandise object include purchased users having a model association relationship with the first user.

36. A system for selecting a model of a merchandise object, comprising: a recommendation device for the model of the merchandise object according to claim 18; and means for selecting a merchandise object model according to claim 34.

37. A method for selecting a commodity object model is characterized by comprising the following steps:

acquiring a recommended model of a specific commodity object;

visually representing the change process of the selection model in the change mode of the preset display parameters of the page elements, and changing the selection model of the specific commodity object from the preliminarily selected selection model corresponding to the first page element to the recommended model corresponding to the second page element in the model selection page of the specific commodity object;

wherein the recommended model of the specific commodity object is obtained by the following method: the method comprises the steps that a server receives a model recommendation request aiming at a specific commodity object sent by a first user client; according to the model recommendation request, acquiring a purchased user having a model association relationship with the first user, including: acquiring a purchased user having a model association relationship with the first user according to the user identifier of the first user carried by the model recommendation request, pre-generated model correlation degree information among different users and the user identifier of the purchased user of the specific commodity object; the pre-generated model correlation degree information among different users is determined according to each size comment information in the size comment information set of the commodity object; determining a recommended model of the specific commodity object provided to the first user according to comment information of a purchased user of the specific commodity object on an actual purchase model of the purchased user; wherein the purchased users of the specific merchandise object include purchased users having a model association relationship with the first user.

38. The method for selecting a merchandise object model according to claim 37, wherein the preset display parameters comprise at least one of the following display parameters: background color, border color, size.

39. The method of selecting a merchandise object model according to claim 38, wherein:

the preset display parameters comprise background colors;

40. A commodity object model selection device is characterized by comprising:

the model selecting unit is used for visually representing the change process of the selected model in the change mode of the preset display parameters of the page elements, and changing the selected model of the specific commodity object from the preliminarily selected model corresponding to the first page element to the recommended model corresponding to the second page element in the model selecting page of the specific commodity object;