WO2017028687A1

WO2017028687A1 - Unused commodity object information processing method and device

Info

Publication number: WO2017028687A1
Application number: PCT/CN2016/093492
Authority: WO
Inventors: 李雨前; 石志伟; 曾俊瑀; 郭东波; 张晓莹; 杨建明
Original assignee: 阿里巴巴集团控股有限公司
Priority date: 2015-08-14
Filing date: 2016-08-05
Publication date: 2017-02-23
Also published as: CN106469382A

Abstract

An unused commodity object information processing method and device. The method comprises: a server establishing a candidate commodity object set according to released and unsold personal unused commodity objects and dynamically maintaining same (S101); when a commodity object list display page browsing request submitted by a client of a first user is received, determining individualized preference information about the first user (S102); determining at least one target commodity object meeting a pre-set condition according to the candidate commodity object set and the individualized preference of the first user (S103); and generating an individualized commodity object list according to the target commodity object information, and providing the individualized commodity object list for the client of the first user (S104), so that the client of the first user can display the individualized commodity object list in the page. By means of the method, users' demands of an unused commodity object trading platform can be described more accurately.

Description

Idle commodity object information processing method and device

The present application claims the priority of the Chinese Patent Application No. 201510502854.4, the entire disclosure of which is hereby incorporated by reference.

Technical field

The present application relates to the field of commodity object information processing technology, and in particular, to a method and apparatus for processing idle commodity object information.

Background technique

The e-commerce trading platform provides a convenient way for goods to be traded. Merchants or sellers can publish product objects through the platform, and buyers can browse and purchase through the platform. However, in real life, there are also some users who have the need to sell their personal idle items online. Such personal idle items may be items that have not been used or used for a period of time after purchase. That is to say, idle goods can be either new or second-hand goods, but whether it is new or second-hand goods, they all have the same characteristics: compared to the original price, the current sale price discount is relatively large, based on this feature, some buyers Users may be interested in this product. Therefore, in order to meet the trading needs of buyers and sellers for personal idle goods, some e-commerce platforms provide corresponding support.

However, compared with new products, such personal idle goods generally have the following characteristics: first, they are issued by individual users, not the behavior of a certain merchant; secondly, each product generally has only one or a few pieces, and after sale, No longer, unlike a new product, a commodity object corresponds to multiple pieces of inventory; in addition, the amount of personal idle goods is large and scattered, and individual users usually do not have the special staff to refresh their published messages like professional businesses. Therefore, if sorted by publication time, published messages are often overwhelmed by a large number of subsequent new posts, and so on. In short, how to show this kind of personal idle goods to buyers and users is a problem to be considered.

In the prior art, some idle commodity trading platforms distinguish users according to the “location” characteristic, that is, when the user browses the homepage of the platform, the user first needs to select the city in which the user is located, or automatically identify the user according to the positioning function of the terminal device. In the city where it is located, for example, when it is determined that the user in Beijing is browsing, only the idle commodity object issued by the seller of Beijing is provided. However, this method in the prior art does not fully describe the user requirements of the idle commodity object trading platform. From the actual effect, there are still many shortcomings. For example, commodity objects are easily overwhelmed, exposure is insufficient, resulting in long-term failure to sell, and so on.

Summary of the invention

The application provides an idle commodity object information processing method and device, which can more accurately describe the user requirements of the idle commodity object trading platform, facilitate the user to search and view, and submit the disposal efficiency of the idle commodity object.

This application provides the following solutions:

A method for processing information of an idle commodity object, comprising:

The server establishes and dynamically maintains a set of candidate commodity objects according to the personal idle commodity objects that have been released and not yet sold, wherein the dynamic maintenance process is: monitoring the sales situation of the commodity objects, and deleting the sold commodity objects from the collection;

Determining the personalized preference information of the first user when receiving the product object list submitted by the first user client to display the page browsing request;

Determining, according to the set of candidate commodity objects and the first user personalized preference, at least one target commodity object that meets a preset condition;

Generating a personalized product object list according to the target product object information, and providing the first user object to the first user client, so that the first user client displays the personalized product object list in the page.

A method for processing information of an idle commodity object, comprising:

The first user client receives the product object list display page browsing request;

Submitting the browsing request to the server, so that the server determines the personalized preference information of the first user, and determining, according to the set of candidate product objects maintained in real time and the first user personalized preference, at least the preset conditions are met. a target product object, the personalized product object list is generated according to the target product object information; wherein the dynamic maintenance process of the candidate product object set by the server is: monitoring the sales situation of the product object, and the sold product object is from the Delete from the collection;

The personalized item object list is displayed in the page.

An idle commodity object information processing device is applied to a server, including:

a collection maintenance unit, configured to establish and dynamically maintain a set of candidate commodity objects according to a personal idle commodity object that has been released and not yet sold, wherein the dynamic maintenance process is: monitoring sales of the commodity object, and the sold commodity object is from the Delete from the collection;

a user information determining unit, configured to determine personalized preference information of the first user when receiving a product object list presentation page browsing request submitted by the first user client;

a target item object determining unit, configured to perform personalization according to the set of candidate item objects and the first user Preference, determining at least one target commodity object that meets a preset condition;

a list generating unit, configured to generate a personalized item object list according to the target item object information, and provide the first item to the first user client, so that the first user client displays the personalized item in the page A list of objects.

An idle commodity object information processing apparatus is applied to a first user client, including:

a request receiving unit, configured to receive a product object list display page browsing request;

a request submitting unit, configured to submit the browsing request to a server, so that the server determines the personalized preference information of the first user, and determines according to the set of candidate commodity objects maintained in real time and the first user personalized preference And generating, by the server, the personalized product object list according to the target product object information; wherein the dynamic maintenance process of the candidate product object set by the server is: monitoring the sales of the product object, The sale item object is removed from the collection;

a page display unit for displaying the personalized item object list in the page.

According to a specific embodiment provided by the present application, the present application discloses the following technical effects:

According to the embodiment of the present application, in consideration of the characteristics of the personal idle commodity object, when the browsing page for the first user is provided, according to the personalized preference information of the first user, a personalized product object list that more closely meets the requirements may be recommended. When displaying the product object list page, the personalized product object list may be used as the main content in the page, so that the content content of each first user may be displayed due to different personalization preferences of each first user. It is different, and it is "one thousand people". In this way, more idle commodity objects can be made to be exposed, and since they are recommended according to the first user preference, it is also advantageous to facilitate the achievement of the transaction. In addition, considering the characteristics of the individual idle product object "orphan", the candidate product object set can be dynamically maintained, and the sales of the product object can be monitored in real time. Once a product object has been sold, it can be selected from the candidate. The deletion in the collection has improved the timeliness of the recommended information. In short, by using personalized recommendation content as the main content of the page and solving the "orphan" problem, the user needs of the idle commodity object trading platform can be more accurately described, which is convenient for users to search and view, and submit the disposal of idle commodity objects. effectiveness.

Of course, implementing any of the products of the present application does not necessarily require all of the advantages described above to be achieved at the same time.

DRAWINGS

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings to be used in the embodiments will be briefly described below. Obviously, the drawings in the following description are only some of the present application. The embodiments can also be used by those skilled in the art without any creative work. The figure obtains other figures.

1 is a flowchart of a method provided by an embodiment of the present application;

2 is a flowchart of another method provided by an embodiment of the present application;

3 is a schematic diagram of an apparatus provided by an embodiment of the present application;

4 is a schematic diagram of another apparatus provided by an embodiment of the present application.

detailed description

The technical solutions in the embodiments of the present application are clearly and completely described in the following with reference to the drawings in the embodiments of the present application. It is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application are within the scope of the present disclosure.

In the embodiment of the present application, in order to more accurately describe the user requirement of the idle commodity object trading platform, considering the characteristics of the personal idle commodity object, when the browsing page is provided for the first user (for example, the buyer), according to the first The user's personalized preference information, recommend a list of product objects that more closely match their needs. Since each of the first users has different personalization preferences, the pages that are ultimately displayed to each of the first users can be different, and the "thousands of thousands of faces" can be achieved. In other words, since the personal idle product object often has the characteristics of “orphan”, that is, there is usually only one piece, the sales volume is no longer the target pursued by the seller user, but only needs to be sold, therefore, the embodiment of the present application In the display of idle commodity objects, the purpose of not displaying the same product object to more first users is not for the purpose of making more idle commodity objects exposed, and as much as possible The "good" way makes the first user who has the opportunity to browse to an idle commodity object, which is interested in the idle commodity object, and therefore can effectively promote the transaction.

For example, suppose there are a million users in the idle commodity trading platform, and assume that when the user browses the product object list display page, the effective pageview is 100 (the so-called effective pageview, that is, although the list can be displayed The number of items is very large, but the actual number that users are browsing may be a limited number in front of the list. For example, if the page is displayed, the user may not turn to the second or third page. Flip the page backwards; in the way of performing more information by performing a "pull-down" on the touch screen, it may also not pull more after pulling twice or three times, if using the prior art The method, that is, the list of commodity objects displayed for each user is the same, in theory, for the access request received at the same time, only 100 commodity objects may actually obtain the exposure. However, if the method of the embodiment of the present application is used, assuming that the product objects provided to each first user are different, the maximum value that can be theoretically obtained by the exposure amount of the commodity object is: 1 million×100. Of course, the amount of exposure in practical applications will be less than the theoretical maximum, but it will certainly be greater than 100 in the prior art.

In addition, since it is a recommendation to the first user, the first thing to consider is the problem of the candidate recommendation data source. In Taobao, Tmall and other trading platforms, when recommending new products, it is generally first to establish a "commodity object pool", and since the new product generally has multiple pieces of inventory, the product object pool is usually very stable, therefore, directly based on Different users' individual needs can be selected from the product pool to meet the first user's preference. However, since the personal idle product object usually has the characteristics of “orphan”, once sold, it is no longer necessary to continue selling. Therefore, in the embodiment of the present application, after the candidate recommended product collection is established, the sales can be performed in real time. The situation is monitored. Once a product object has been sold, it can be deleted from the candidate recommended product object, thereby solving the problem of "orphan" of the individual idle product object.

The specific implementation is described in detail below.

Embodiment 1

Referring to FIG. 1, a first embodiment of the present application provides a method for processing an idle commodity object information from a server perspective, and the method may include the following steps:

S101: The server establishes and dynamically maintains a set of candidate commodity objects according to a personal idle commodity object that has been released and has not yet been sold, wherein the dynamic maintenance process is: monitoring sales of the commodity object, and deleting the sold commodity object from the collection ;

When the candidate product object set is created, the currently idle and unsold personal idle product object can be added to the set. Since the individual idle product object has the characteristics of “orphan”, the collection can also be real-time. maintain. The maintenance process is to monitor the sales of the product object in real time, and delete the sold product object from the collection in time to avoid recommending it to the first user.

S102: When receiving the product object list presentation page browsing request submitted by the first user client, determining personalization preference information of the first user;

In the embodiment of the present application, the received browsing request may be a request to browse the client's homepage, or may be a search result display page browsing request when searching based on a certain keyword, wherein, if browsing the client's homepage The request may directly perform subsequent personalized recommendation according to the dynamically maintained candidate product object set, and for the keyword-based search page browsing request, first screening the candidate product object set based on the keyword, and then based on the key The word screening results for subsequent personalized recommendations.

The personal preference information about the first user can be determined in various ways. For example, in one mode, the first personalized bias of the first user may be analyzed according to historical behavior data of the first user. Good information; wherein the so-called historical behavior data may include the first user in the past preset time period (for example, in the last month or may be longer, etc.), for the individual idle commodity object and/or new product The operational behavior data of the object, wherein the operational behavior may include purchase, browsing, and/or collection.

That is to say, it is possible to perform statistics on the commodity objects that the current first user has browsed, purchased, or collected in the past, from which the commodity object category that the first user prefers can be analyzed. For example, a first user has purchased 5 items in the last month, 3 of which are digital and 2 are clothing, and it can be determined that the user is interested in categories including digital and clothing. In addition, according to the browsing record of the first user, it can be known that the first user often browses the home appliance category in addition to the product objects of the digital class and the clothing class. Therefore, the home appliance class can also be interested in the home appliance. Category. Moreover, the first user also collects some cosmetic object objects, which proves that the first user has a relatively strong purchasing tendency for cosmetics products, and correspondingly, is also a category of interest, and therefore, Adding a cosmetic class to the first user's personalized preference information, and the like.

The historical behavior record may include not only the behavior record of the first user in the current transaction platform, but also the collection and analysis of the historical behavior record across the platform. For example, it is also possible to collect a record of the operational behavior of the first user on the new product in the new product trading platform, and the like. In the specific implementation, the current trading platform and the preset new product trading platform can be opened in advance, that is, the user of the idle commodity trading platform can log in using the account registered in the new trading platform, so that it can naturally pass The user account obtains the historical behavior record of the user from the new product trading platform.

In addition to analyzing the historical behavior record of the user, the analysis may also be performed based on the real-time behavior record of the user, that is, the second personalized preference information of the first user may also be analyzed according to the real-time behavior data of the first user. The so-called real-time behavior data may include operational behavior data that the first user is currently performing on the displayed personal idle commodity object, and the operational behavior may also include purchase, browsing, and/or collection. For example, if a user is currently browsing an item of the apparel category using the idle commodity trading platform, it may be determined that the first user is interested in the apparel item object, and the like.

There are various ways for dividing the real-time behavior data and the historical behavior data. For example, the operation behavior currently occurring by the first user may be determined as a real-time behavior, and all other behaviors are all historical behavior data. Alternatively, it is also possible to determine the operational behavior generated by the first user on the day as real-time behavior data, the previous day and earlier data as historical behavior data, and the like.

It should be noted that, by analyzing the historical behavior record and obtaining the personalized personalized preference information, the stable behavior characteristics of the user can be precipitated, and the recommended products are more gathered, closer to the user's browsing and purchase intention, and the cold start problem is solved ( For example, the user has not performed any behavior just after logging in to the idle commodity platform. Therefore, real-time behavior data has not yet been generated. At this time, historical behavior data needs to be used to provide a part of the commodity object for the current first user. In addition, the use of cross-platform historical behavior data can also make up for new users in idle products. The problem of sparse historical behavior data in the trading platform (of course, as users use the idle commodity trading platform, the role of cross-platform historical behavior records can be gradually weakened). After the user starts to perform specific browsing, collection, purchase, etc., it can make more accurate recommendations based on the generated real-time behavior data. Among them, real-time behavior data can more accurately reflect the user's current preferences.

S103: Determine, according to the candidate product object set and the first user personalized preference, at least one target commodity object that meets a preset condition;

After determining the personalized preference of the first user, the target product object that meets the personalized preference may be determined from the set of candidate product objects. Specifically, if the first personalized preference information obtained by using the historical behavior data and the second personalized preference information obtained by the real-time behavior data are determined, the candidate products in the set may be respectively based on the first one. The sexual preference information and the second personalized preference information are scored, and finally the scores are combined to determine the total score of the candidate commodity object, and then the target commodity object meeting the preset condition is determined according to the total score.

For example, the first personalized preference information obtained based on the historical behavior data is: the category of interest of the first user is apparel, cosmetics, and digital, and the second personalized preference information obtained based on the real-time behavior record is: If the category of interest of the first user is a digital class, if a certain product object is a clothing category for each candidate product object in the collection, the score may be increased by 1 because the first personalized preference information is met. For the cosmetics category, the score may be increased by 1 according to the first personalized preference information, and for the digital category, since the first personalized preference information and the second personalized preference information are met, therefore, The score is increased by 2, and the commodity object of other categories has a score of 0 because it neither meets the first personalized preference information nor the second personalized preference information. Further, the product object under the category with a score of less than 1 can be used as the target product object that meets the personalized preference, that is, for the case in the foregoing example, only the apparel, cosmetics, and digital categories are recommended to the current user. Idle product objects, other categories will not be recommended.

S104: Generate a personalized product object list according to the target product object information, and provide the first user object to the first user client, so that the first user client displays the personalized product object list in the page.

After determining the target product objects that meet the first user personalized preference information, the personalized product object list may be generated according to the target product objects and provided to the first user client. Wherein, when generating the personalized product object list, each target product object may be sorted according to the calculated score. For example, the digital product object may be arranged before the clothing and cosmetics, and of course, other products may be used. Sort by the way. For example, for each target product object in the same category, when sorting, factors such as the release time, the distance between the publisher user and the current first user may also be considered.

After the personalized product object list is generated, it can be provided to the first user client, so that the client can display the personalized product object list in the current page, and the personalized product object list can be used in the page. For the main content. The current page in the embodiment of the present application may be the front page of the client, or may be a search result page based on the keyword input by the first user, or may be selected according to the model of the client device system. Different recommendation strategies. For example, iso is aimed at Apple mobile phone users and generally pushes high-end products. Try not to recommend clothes for male users.

It should be noted that, regardless of whether the client displays the client home page or the search result display page, when providing the product object list, based on the user's personalized preference, the page can be personalized, and the personalized product object list can be In addition to the main content, the page can no longer contain general product object information. Here, the so-called general product object information is relative to the personalized product object information, and refers to the same product object information list provided for different first users. This versatile list of commodity object information is more common in the pages of the new trading platform. For example, when the first user logs in to a new trading platform client such as Taobao or Tmall, the most prominent display on the page is this. General product object information, for example, the Tmall home page includes multiple topics. After each theme is entered, the list of product objects seen by different users is the same, although it may pass through a specific page on the home page or other pages. The page area provides some personalized recommendation information, but such recommendation information is generally only for reference, and plays a secondary role relative to the general product object list. In the embodiment of the present application, the personalized product object list exists as the most important content in the page, and the universal product object list is no longer included, and the first user only needs to be based on the personalized product object list recommended for the user. You can browse, purchase, and so on. It can be seen that, in terms of page content, the manner provided in the embodiment of the present application is different from the page provided by the traditional new product trading platform, and the manner of “thousands of thousands of people” is more in line with the characteristics of the individual idle commodity object, Conducive to making more commodity objects get exposure opportunities.

The solution provided by the embodiment of the present application is introduced. In the specific implementation, in the process of performing personalized recommendation, in addition to considering the personalized preference information of the first user, the characteristic information of the product object itself may be comprehensively considered, combining two Information on all aspects, get the final recommendation results.

Specifically, the product object in the candidate product object set may be scored according to the first user personalized preference to obtain a first score (the first score may also be obtained by integrating historical behavior data and real-time behavior data), and Sorting the product objects in the candidate product object set according to the characteristic information of the product object to obtain a second score, and then combining the first score and the second score to determine a comprehensive score of the product object, and finally re-rooting According to the comprehensive score, at least one target commodity object meeting the preset condition is determined.

Among them, the property information of the product object may include, on the one hand, the saleability information when the product object is sold as a personal idle product. For example, in the case of products such as fresh foods, fruits and vegetables, when sold as personal idle products, the saleability is not high due to factors such as the shelf life, and therefore, the product objects for these categories can be lowered. Right processing.

In a specific implementation, the saleable property information when each product object category is sold as a personal idle product may be pre-stored, and then the target category to which the product object in the candidate product object set belongs may be determined, and according to the target category and the target category The pre-stored information identifies the saleable information of the product object, and scores the corresponding product object based on the saleability information. For example, for commodity objects of fresh fruits, fruits and vegetables, a "-1" score can be given, and so on.

Further, regarding the characteristic information of the product object, it may further include whether the product object is associated with a preset keyword. The preset keywords may be various, for example, may be related to current news hotspot events, current hot TV dramas, and the like, and the like. For example, in a TV series that is currently broadcast, if a costume of a protagonist is very distinctive, you can use "someone with the same paragraph" as a key word. In a specific implementation, it may be determined whether the product object in the candidate product object set is associated with a preset keyword, and for the product object associated with the keyword, a bonus process may be performed.

Of course, in practical applications, other factors may be considered regarding the characteristic information of the product object, for example, the related information between the products (the association between the mobile phone and the mobile phone accessories, etc.), and in addition, the credit information of the seller user may also be considered. Wait, there is no longer a list here.

In summary, the product object can be scored from multiple dimensions such as the first user personalized preference and the product object's own characteristics, and finally the display content in the first user's personalized product object list is comprehensively determined.

It should be noted that, in a specific implementation, the set of candidate product objects used for scoring by using the first user personalized preference may be different from the set of candidate product objects used for scoring by using the product self-characteristics, but the two may exist. A certain intersection. Specifically, the personal idle commodity object that has been released and not yet sold may be filtered according to preset screening conditions to establish a first candidate product object set; wherein the screening condition is determined according to a publishing time and/or a price (for example, whether "Buy price", etc.), for example, it is possible to add the idle item object that has been released within the last 3 days and is "Buy It Now" to the first candidate item object set. Of course, in practical applications, it may also be considered. Other screening criteria. When scoring based on the personalized preference information of the first user, the product object in the first candidate product object set may be scored. In addition, the second candidate product object set may be directly established according to the released personal product object that has not been sold, that is, the condition is not used for screening, and then, when the product is characterized by the product itself, the second candidate product may be based on the second candidate product. The collection of objects is done.

The reason for distinguishing the collection of candidate product objects is to: in accordance with the user's personalized preference letter When scoring information, since this part of the information is more important, it is possible to make better product object information candidates. When scoring based on the characteristics of the product object itself, it is possible to break the limitation of the quality of the product object information, so that more product objects have an opportunity to be exposed.

In addition, it should be noted that, in practical applications, for the product object that has been recommended to the first user, the repeated recommendation may not be performed, so that more product objects may be further exposed to the exposure opportunity, and the first opportunity is also avoided. User received invalid information. Therefore, in the specific implementation, each recommendation result may be saved, and when the recommendation is made next time, the last recommendation result may be used for deduplication, and then provided to the first user client. The execution timing of the deduplication operation may be various. For example, the deduplication operation may be performed before the user personalization preference information or the product object self-characteristics are scored, or the deduplication may be performed after the scoring. and many more.

Embodiment 2

The second embodiment is corresponding to the first embodiment. From the perspective of the first user client, a method for processing idle commodity object information is provided. Referring to FIG. 2, the method may include the following steps:

S201: The first user client receives the product object list display page browsing request;

S202: submit the browsing request to the server, so that the server determines the personalized preference information of the first user, and determines that the preset condition is met according to the set of candidate product objects maintained in real time and the personalized preference of the first user. The at least one target product object generates a personalized product object list according to the target product object information; wherein the dynamic maintenance process of the candidate product object set by the server is: monitoring the sales situation of the product object, and the sold product object is Deleted in the collection;

S203: Display the personalized item object list in the page.

For details of the specific implementation in the second embodiment, refer to the introduction in the first embodiment, and details are not described herein again.

Corresponding to the first embodiment, the embodiment of the present application further provides an idle commodity object information processing device, which is applied to a server. Referring to FIG. 3, the device may include:

The collection maintenance unit 301 is configured to establish and dynamically maintain a set of candidate product objects according to the released personal item that has not been sold, wherein the dynamic maintenance process is: monitoring the sales situation of the product object, and Deleted in the collection;

The user information determining unit 302 is configured to: when receiving the product object list display page browsing request submitted by the first user client, determine the personalized preference information of the first user;

The target product object determining unit 303 is configured to determine, according to the candidate product object set and the first user personalized preference, at least one target product object that meets a preset condition;

a list generating unit 304, configured to generate a personalized item object list according to the target item object information, and provide the first item to the first user client, so that the first user client displays the personalized in the page A list of product objects.

The user information determining unit includes:

a first preference information determining subunit, configured to analyze first personalized preference information of the first user according to historical behavior data of the first user; the historical behavior data includes a preset time period of the first user Within the operating behavior data for a personal idle item object and/or a new item item, the operational behavior includes purchase, browsing, and/or collection.

Alternatively, the user information determining unit includes:

a second preference information determining subunit, configured to analyze second personalized preference information of the first user according to real-time behavior data of the first user; the real-time behavior data includes that the first user is currently performing an individual to the displayed The operational behavior data performed by the idle commodity object, including the purchase, browsing, and/or collection.

In specific implementation, the device may further include:

a commodity characteristic information determining unit, configured to determine characteristic information of the commodity object in the candidate commodity object set;

The target commodity object determining unit includes:

a first hitting unit, configured to score the commodity objects in the set of candidate commodity objects according to the first user personalized preference, to obtain a first score;

a second playing unit, configured to score the product object in the candidate product object set according to the characteristic information of the product object, to obtain a second score;

a comprehensive score determining subunit for synthesizing the first score and the second score to determine a comprehensive score of the commodity object;

The commodity object determining subunit is configured to determine, according to the comprehensive score, at least one target commodity object that meets a preset condition.

In a specific implementation, the characteristic information of the commodity object includes: saleable property information when the commodity object is sold as a personal idle product;

The second molecular unit includes:

a saleable information storage subunit for pre-storing saleable property information when each product object category is sold as a personal idle item;

a vendability information determining subunit, configured to determine a target category to which the product object in the set of candidate product objects belongs, and determining the marketability information of the product object according to the target category and the pre-saved information;

The saleable molecular unit is for scoring the corresponding commodity object based on the saleability information.

Or the characteristic information of the commodity object includes: whether the commodity object is associated with a preset keyword;

The second molecular unit includes:

a keyword association determination subunit, configured to determine whether a commodity object in the candidate commodity object set is associated with a preset keyword;

The keyword association molecular unit is configured to score the commodity object in the candidate product object set according to the determination result.

In a specific implementation, the set maintenance unit may include:

a first set establishing subunit, configured to filter, according to a preset screening condition, a personal idle commodity object that has been released and not yet sold, to establish a first candidate product object set; and the screening condition is determined according to a publishing time and/or a price setting manner. determine;

a second set establishing subunit, configured to establish a second set of candidate product objects according to the personal idle item object that has been released and not yet sold;

At this time, the first molecular unit is specifically used for:

Classifying the commodity objects in the first candidate commodity object set according to the first user personalized preference;

The second molecular unit is specifically used for:

The scoring the product object in the second candidate product object set according to the characteristic information of the product object.

In addition, the device may further include:

a sorting unit, configured to sort the commodity objects according to the level of the comprehensive score.

Furthermore, the device may further comprise:

a saving unit, configured to save a personalized product object list generated by the last recommendation process for the first user;

The de-duplication processing unit is configured to perform deduplication processing on the target commodity object by using the last generated personalized product object list.

The product object list display page browsing request includes:

The client home page browses the request, or the keyword search result displays a page view request.

Corresponding to the second embodiment, the embodiment of the present application further provides an idle commodity object information processing device, and an application thereof. In the first user client, referring to FIG. 4, the apparatus may include:

The request receiving unit 401 is configured to receive a product object list display page browsing request;

The request submitting unit 402 is configured to submit the browsing request to the server, so that the server determines the personalized preference information of the first user, and according to the set of candidate commodity objects maintained in real time and the first user personalized preference, Determining at least one target product object that meets the preset condition, and generating a personalized product object list according to the target product object information; wherein the dynamic maintenance process of the candidate product object set by the server is: monitoring the sales situation of the product object, The sold item object is deleted from the collection;

The page display unit 403 is configured to display the personalized item object list in the page. The page may be the main content of the personalized product object list.

In summary, according to the embodiment of the present application, in consideration of the characteristics of the personal idle commodity object, when the browsing page for the first user is provided, the personalized product object list that is more in line with the demand may be recommended according to the personalized preference information of the first user. When the product object list page is displayed, the personalized product object list may be used as the main content in the page, so that each first user's personalized preference is different, so the page content of each first user is finally displayed. Can be different, to achieve "thousands of thousands of people." In this way, more idle commodity objects can be made to be exposed, and since they are recommended according to the first user preference, it is also advantageous to facilitate the achievement of the transaction. In addition, considering the characteristics of the individual idle product object "orphan", the candidate product object set can be dynamically maintained, and the sales of the product object can be monitored in real time. Once a product object has been sold, it can be selected from the candidate. The deletion in the collection has improved the timeliness of the recommended information. In short, by using personalized recommendation content as the main content of the page and solving the "orphan" problem, the user needs of the idle commodity object trading platform can be more accurately described.

It will be apparent to those skilled in the art from the above description of the embodiments that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such understanding, the technical solution of the present application may be embodied in the form of a software product in essence or in the form of a software product, which may be stored in a storage medium such as a ROM/RAM or a disk. , an optical disk, etc., includes instructions for causing a computer device (which may be a personal computer, server, or network device, etc.) to perform the methods described in various embodiments of the present application or portions of the embodiments.

The various embodiments in the specification are described in a progressive manner, and the same or similar parts between the various embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for a system or system embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiment. The system and system embodiments described above are merely illustrative, in which The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment. Those of ordinary skill in the art can understand and implement without any creative effort.

The method and device for processing the idle commodity object information provided by the present application are described in detail above. The principles and implementation manners of the present application are described in the specific examples. The description of the above embodiments is only used to help understand the present application. The method and its core idea; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation and application scope. In summary, the content of this specification should not be construed as limiting the application.

Claims

A method for processing information of an idle commodity object, comprising:

The server establishes and dynamically maintains a set of candidate commodity objects according to the personal idle commodity objects that have been released and not yet sold, wherein the dynamic maintenance process is: monitoring the sales situation of the commodity objects, and deleting the sold commodity objects from the collection;

Determining the personalized preference information of the first user when receiving the product object list submitted by the first user client to display the page browsing request;

Determining, according to the set of candidate commodity objects and the first user personalized preference, at least one target commodity object that meets a preset condition;

Generating a personalized product object list according to the target product object information, and providing the first user object to the first user client, so that the first user client displays the personalized product object list in the page.
The method according to claim 1, wherein the determining the personalized preference information of the first user comprises:

And analyzing, according to the historical behavior data of the first user, the first personalized preference information of the first user; the historical behavior data includes, by the first user, in the past preset time period, for the personal idle commodity object and/or The operational behavior data of the new product object, including the purchase, browsing, and/or collection.
The method according to claim 1, wherein the determining the personalized preference information of the first user comprises:

And analyzing, according to the real-time behavior data of the first user, the second personalized preference information of the first user; the real-time behavior data includes operation behavior data that the first user is currently performing on the displayed personal idle commodity object. The operational actions include purchasing, browsing, collecting, and/or interactive messages.
The method of claim 1 further comprising:

Determining characteristic information of the commodity object in the set of candidate commodity objects;

Determining, according to the candidate product object set and the first user personalized preference, the at least one target product object that meets the preset condition, including:

And classifying the commodity objects in the candidate commodity object set according to the first user personalized preference, to obtain a first score;

Sorting the product objects in the candidate product object set according to the characteristic information of the product object to obtain a second score;

Combining the first score and the second score to determine a comprehensive score of the commodity object;

Based on the comprehensive score, at least one target commodity object that meets the preset condition is determined.
The method according to claim 4, wherein the characteristic information of the commodity object comprises: saleable property information when the commodity object is sold as a personal idle product;

The scoring the product objects in the candidate product object set according to the characteristic information of the product object includes:

Pre-storing information on the saleability of each product object category as a personal idle item for sale;

Determining a target category to which the product object in the candidate product object set belongs, and determining the marketability information of the product object according to the target category and the pre-saved information;

The corresponding product object is scored based on the saleability information.
The method according to claim 4, wherein the characteristic information of the commodity object comprises: whether the commodity object is associated with a preset keyword;

The scoring the product objects in the candidate product object set according to the characteristic information of the product object includes:

Determining whether the product object in the candidate product object set is associated with a preset keyword;

According to the determination result, the product objects in the candidate product object set are scored.
The method of claim 4, wherein the establishing a set of candidate product objects based on the released personal product objects that have not yet been sold comprises:

Filtering the personal idle commodity objects that have been released and not yet sold according to preset screening conditions, and establishing a first candidate commodity object set; the screening conditions are determined according to a publishing time and/or a price setting manner;

Establishing a second set of candidate product objects based on the personal idle item objects that have been released and not yet sold;

The scoring the product objects in the candidate product object set according to the first user personalized preference includes:

Classifying the commodity objects in the first candidate commodity object set according to the first user personalized preference;

The scoring the product objects in the candidate product object set according to the characteristic information of the product object includes:

The scoring the product object in the second candidate product object set according to the characteristic information of the product object.
The method of claim 4, further comprising:

The commodity objects are sorted according to the level of the comprehensive score.
The method according to any one of claims 1 to 8, further comprising:

Saving a list of personalized product objects generated by the first user for the first user process;

The target product object is subjected to deduplication processing using the last generated personalized product object list.
The method according to any one of claims 1 to 8, wherein the product object list display page browsing request comprises:

The client home page browses the request, or the keyword search result displays a page view request.
A method for processing information of an idle commodity object, comprising:

The first user client receives the product object list display page browsing request;

Submitting the browsing request to the server, so that the server determines the personalized preference information of the first user, and determining, according to the set of candidate product objects maintained in real time and the first user personalized preference, at least the preset conditions are met. a target product object, the personalized product object list is generated according to the target product object information; wherein the dynamic maintenance process of the candidate product object set by the server is: monitoring the sales situation of the product object, and the sold product object is from the Delete from the collection;

The personalized item object list is displayed in the page.
An idle commodity object information processing apparatus, characterized in that, applied to a server, comprising:

a collection maintenance unit, configured to establish and dynamically maintain a set of candidate commodity objects according to a personal idle commodity object that has been released and not yet sold, wherein the dynamic maintenance process is: monitoring sales of the commodity object, and the sold commodity object is from the Delete from the collection;

a user information determining unit, configured to determine personalized preference information of the first user when receiving a product object list presentation page browsing request submitted by the first user client;

a target item object determining unit, configured to determine, according to the set of candidate item objects and the first user personalized preference, at least one target item object that meets a preset condition;

a list generating unit, configured to generate a personalized item object list according to the target item object information, and provide the first item to the first user client, so that the first user client displays the personalized item in the page A list of objects.
The device according to claim 12, wherein the user information determining unit comprises:

a first preference information determining subunit, configured to analyze first personalized preference information of the first user according to historical behavior data of the first user; the historical behavior data includes a preset time period of the first user Within the operating behavior data for a personal idle item object and/or a new item item, the operational behavior includes purchase, browsing, and/or collection.
The device according to claim 12, wherein the user information determining unit comprises:

a second preference information determining subunit, configured to analyze second personalized preference information of the first user according to real-time behavior data of the first user; the real-time behavior data includes that the first user is currently performing an individual to the displayed The operational behavior data performed by the idle commodity object, including the purchase, browsing, and/or collection.
The device according to claim 12, further comprising:

a commodity characteristic information determining unit, configured to determine characteristic information of the commodity object in the candidate commodity object set;

The target commodity object determining unit includes:

a first hitting unit, configured to score the commodity objects in the set of candidate commodity objects according to the first user personalized preference, to obtain a first score;

a second playing unit, configured to score the product object in the candidate product object set according to the characteristic information of the product object, to obtain a second score;

a comprehensive score determining subunit for synthesizing the first score and the second score to determine a comprehensive score of the commodity object;

The commodity object determining subunit is configured to determine, according to the comprehensive score, at least one target commodity object that meets a preset condition.
The apparatus according to claim 15, wherein the characteristic information of the commodity object comprises: saleable property information when the commodity object is sold as a personal idle product;

The second molecular unit includes:

a saleable information storage subunit for pre-storing saleable property information when each product object category is sold as a personal idle item;

a vendability information determining subunit, configured to determine a target category to which the product object in the set of candidate product objects belongs, and determining the marketability information of the product object according to the target category and the pre-saved information;

The saleable molecular unit is for scoring the corresponding commodity object based on the saleability information.
The apparatus according to claim 15, wherein the characteristic information of the commodity object comprises: whether the commodity object is associated with a preset keyword;

The second molecular unit includes:

a keyword association determination subunit, configured to determine whether a commodity object in the candidate commodity object set is associated with a preset keyword;

The keyword association molecular unit is configured to score the commodity object in the candidate product object set according to the determination result.
The device according to claim 15, wherein the collection maintenance unit comprises:

a first set establishing subunit, configured to filter, according to a preset screening condition, a personal idle commodity object that has been released and not yet sold, to establish a first candidate product object set; and the screening condition is determined according to a publishing time and/or a price setting manner. determine;

a second set establishing subunit, configured to establish a second set of candidate product objects according to the personal idle item object that has been released and not yet sold;

The first molecular unit is specifically used for:

Classifying the commodity objects in the first candidate commodity object set according to the first user personalized preference;

The second molecular unit is specifically used for:

The scoring the product object in the second candidate product object set according to the characteristic information of the product object.
The device according to claim 15, further comprising:

a sorting unit, configured to sort the commodity objects according to the level of the comprehensive score.
The device according to any one of claims 12 to 19, further comprising:

a saving unit, configured to save a personalized product object list generated by the last recommendation process for the first user;

The de-duplication processing unit is configured to perform deduplication processing on the target commodity object by using the last generated personalized product object list.
The device according to any one of claims 12 to 19, wherein the product object list display page browsing request comprises:

The client home page browses the request, or the keyword search result displays a page view request.
An idle commodity object information processing apparatus is characterized in that it is applied to a first user client, and includes:

a request receiving unit, configured to receive a product object list display page browsing request;

a request submitting unit, configured to submit the browsing request to a server, so that the server determines the personalized preference information of the first user, and determines according to the set of candidate commodity objects maintained in real time and the first user personalized preference And generating, by the server, the personalized product object list according to the target product object information; wherein the dynamic maintenance process of the candidate product object set by the server is: monitoring the sales of the product object, The sale item object is removed from the collection;

a page display unit for displaying the personalized item object list in the page.