CN110020194B

CN110020194B - Resource recommendation method, device and medium

Info

Publication number: CN110020194B
Application number: CN201810903422.8A
Authority: CN
Inventors: 陈大年; 苏勇
Original assignee: Nanjing Shangwang Network Technology Co ltd
Current assignee: Nanjing Shangwang Network Technology Co.,Ltd.
Priority date: 2018-08-09
Filing date: 2018-08-09
Publication date: 2021-10-08
Anticipated expiration: 2038-08-09
Also published as: CN110020194A

Abstract

The application provides a resource recommendation method, a resource recommendation device and a computer readable medium. The method comprises the following steps: displaying a first number of recommended resource information columns, wherein the first number of recommended resource information columns are selected from recommended resource sets provided by a server; determining characteristic information of the user according to the triggering behavior information of the user on the first number of recommended resource information columns; after the display of the recommended resource information columns of the first number is finished, selecting a recommended resource information column of a second number matched with the characteristic information from the rest recommended resource information columns in the recommended resource set; and displaying the recommended resource information columns of the second quantity. Compared with the prior art, the resource recommendation method provided by the first aspect of the application can make recommendations matched with users through batch display based on the recommended resource set provided by the server at one time under the condition of no user portrait, and has high recommendation efficiency.

Description

Resource recommendation method, device and medium

Technical Field

The application relates to the technical field of personalized recommendation, in particular to a resource recommendation method, a resource recommendation device and a computer readable medium.

Background

With the rapid development and popularization of the internet, especially the mobile internet, more and more people browse news, read articles, buy commodities, participate in education, entertainment activities and the like through the network, and the network gradually becomes an indispensable important part in daily life of people. However, the network brings convenience to life, and simultaneously, the problem of self development, namely information lost, information in the network grows exponentially, the data volume is too large, a user cannot easily and directly find the required information in the huge network information, and a great amount of time is spent in the information searching and docking process. Aiming at the problem, a personalized recommendation technology is developed, the personalized recommendation technology can analyze interest preference of a user according to behavior data of the user, construct a user portrait according to the interest preference of the user, then screen information according to the user portrait, and recommend information which is possibly interested by the user to the user.

However, in the related art, when a new user is recommended, because the user portrait is not available at this time, the information that is refreshed by the user at the client for the first time is some tentative recommendation information, and after the tentative recommendation information is fed back by the user, the user portrait is constructed according to the user feedback, and when the user refreshes for the second time, a targeted recommendation can be made according to the user portrait. Therefore, in the related technology, the recommendation of the new user needs to be carried out at least twice for information request and push so as to give the recommendation information according with the user portrait, and the recommendation efficiency is low.

Disclosure of Invention

The application aims to provide a resource recommendation method, a resource recommendation device and a computer readable medium.

A first aspect of the present application provides a resource recommendation method, for a client, including:

displaying a first number of recommended resource information columns, wherein the first number of recommended resource information columns are selected from recommended resource sets provided by a server;

determining characteristic information of the user according to the triggering behavior information of the user on the first number of recommended resource information columns;

after the display of the recommended resource information columns of the first number is finished, selecting a recommended resource information column of a second number matched with the characteristic information from the rest recommended resource information columns in the recommended resource set;

and displaying the recommended resource information columns of the second quantity.

In some modified embodiments of the first aspect of the present application, before displaying the first number of recommended resource information bars, the method further includes:

and after the operation of triggering and displaying the recommended resource information bars is detected, acquiring the recommended resource set from the server, wherein the recommended resource set comprises a plurality of recommended resource information bars, and each recommended resource information bar in the plurality of recommended resource information bars is provided with at least one characteristic label.

In some modified embodiments of the first aspect of the present application, the determining, according to the trigger behavior information of the user to the first number of recommended resource information columns, the feature information of the user includes:

and determining the characteristic information of the user according to the triggering behavior information of the user on each recommended resource information column in the first number of recommended resource information columns and the characteristic label of each recommended resource information column.

In some modified embodiments of the first aspect of the present application, the determining, according to the triggering behavior information of the user on each recommended resource information column in the first number of recommended resource information columns and the feature tag of each recommended resource information column, the feature information of the user includes:

determining preference characteristics of the user corresponding to each characteristic label according to the triggering behavior information of the user on each recommended resource information column in the first number of recommended resource information columns and the characteristic label of each recommended resource information column;

and determining the characteristic information of the user according to the preference characteristics.

determining the positive characteristic information of the user according to the characteristic label of the recommended resource information column triggered by the user, and/or determining the negative characteristic information of the user according to the characteristic label of the recommended resource information column not triggered by the user;

and determining the characteristic information of the user according to the positive characteristic information and/or the negative characteristic information.

In some variations of the first aspect of the present application, the trigger behavior information includes at least one of: triggering the recommended resource information column, not triggering the recommended resource information column, viewing duration of recommended resources corresponding to the recommended resource information column after triggering the recommended resource information column, and feedback information of recommended resources corresponding to the recommended resource information column after triggering the recommended resource information column.

In some modified embodiments of the first aspect of the present application, the selecting, from the remaining recommended resource information fields in the recommended resource set, a second number of recommended resource information fields that match the feature information includes:

and selecting a second number of recommended resource information columns matched with the characteristic information from the rest recommended resource information columns in the recommended resource set according to the characteristic labels of the recommended resource information columns in the recommended resource set.

In some modified embodiments of the first aspect of the present application, before the presenting the second number of recommended-resource information bars, the method further includes:

and displaying the hot spot resource information columns of the third quantity.

In some modified embodiments of the first aspect of the present application, the third number of hot spot resource information columns are displayed after the first number of recommended resource information columns, or the third number of hot spot resource information columns and the first number of recommended resource information columns are displayed in a mixed manner.

In some modified embodiments of the first aspect of the present application, after the presenting the second number of recommended resource information columns, the method further includes:

and updating the characteristic information of the user according to the triggering behavior information of the user to the second quantity of recommended resource information columns.

In some variations of the first aspect of the present application, the method further comprises:

and after the second number of recommended resource information columns are displayed, requesting the recommended resource information columns matched with the updated characteristic information of the users from the server and displaying.

In some variations of the first aspect of the present application, the recommended resource information field includes at least one of a name, a summary, a brief summary, a preview, and a preview image of the recommended resource.

A second aspect of the present application provides a resource recommendation apparatus, including:

the resource information bar display system comprises a first resource information bar display module, a second resource information bar display module and a resource information bar display module, wherein the first resource information bar display module is used for displaying a first number of recommended resource information bars, and the first number of recommended resource information bars are selected from recommended resource sets provided by a server;

the user characteristic information determining module is used for determining the characteristic information of the user according to the triggering behavior information of the user on the first number of recommended resource information columns;

the second resource information column determining module is used for selecting a second number of recommended resource information columns matched with the characteristic information from the rest recommended resource information columns in the recommended resource set after the display of the first number of recommended resource information columns is finished;

and the second resource information bar display module is used for displaying the recommended resource information bars with the second quantity.

In some variations of the second aspect of the present application, the apparatus further comprises:

the recommendation resource set obtaining module is configured to obtain a recommendation resource set from the server after an operation of triggering presentation of recommendation resource information columns is detected, where the recommendation resource set includes a plurality of recommendation resource information columns, and each recommendation resource information column in the plurality of recommendation resource information columns has at least one feature tag.

In some modified embodiments of the second aspect of the present application, the user characteristic information determination module includes:

and the user characteristic information determining unit is used for determining the characteristic information of the user according to the triggering behavior information of the user on each recommended resource information column in the first number of recommended resource information columns and the characteristic label of each recommended resource information column.

In some modified embodiments of the second aspect of the present application, the user characteristic information determination unit includes:

a preference feature determining subunit, configured to determine, according to the trigger behavior information of the user on each recommended resource information column in the first number of recommended resource information columns and the feature tag of each recommended resource information column, a preference feature of the user corresponding to each feature tag;

a first characteristic information determining subunit, configured to determine characteristic information of the user according to the preference characteristic.

the positive/negative characteristic determining subunit is configured to determine positive characteristic information of the user according to a characteristic tag of a recommended resource information column triggered by the user, and/or determine negative characteristic information of the user according to a characteristic tag of a recommended resource information column not triggered by the user;

and the second characteristic information determining subunit is configured to determine the characteristic information of the user according to the positive characteristic information and/or the negative characteristic information.

In some variations of the second aspect of the application, the trigger behavior information comprises at least one of: triggering the recommended resource information column, not triggering the recommended resource information column, viewing duration of recommended resources corresponding to the recommended resource information column after triggering the recommended resource information column, and feedback information of recommended resources corresponding to the recommended resource information column after triggering the recommended resource information column.

In some modified embodiments of the second aspect of the present application, the second resource information column determination module includes:

and the second resource information column determining unit is used for selecting a second number of recommended resource information columns matched with the characteristic information from the rest recommended resource information columns in the recommended resource set according to the characteristic labels of the recommended resource information columns in the recommended resource set.

and the hot resource information bar display module is used for displaying the hot resource information bars with the third quantity.

In some modified embodiments of the second aspect of the present application, the third number of hot spot resource information columns are displayed after the first number of recommended resource information columns, or the third number of hot spot resource information columns and the first number of recommended resource information columns are displayed in a mixed manner.

and the characteristic information updating module is used for updating the characteristic information of the user according to the triggering behavior information of the user to the second quantity of recommended resource information columns.

and the matched resource request module is used for requesting and displaying the recommended resource information columns matched with the updated characteristic information of the user from the server after the display of the second number of recommended resource information columns is finished.

In some variations of the second aspect of the present application, the recommended resource information field includes at least one of a name, a summary, a brief summary, a preview, and a preview image of the recommended resource.

A third aspect of the present application provides a resource recommendation method, for a server, including:

receiving a recommended resource acquisition request sent by a client;

and responding to the recommended resource acquisition request, and sending a recommended resource set to the client so that the client can recommend resources in batches according to the recommended resource set.

In some modified embodiments of the third aspect of the present application, the recommended resource set includes a plurality of recommended resource information columns, and each recommended resource information column in the plurality of recommended resource information columns has at least one feature tag, so that the client performs resource recommendation in batches according to the feature tags corresponding to the recommended resource information columns in the recommended resource set.

In some variations of the third aspect of the present application, the sending, to the client, a recommended resource set in response to the recommended resource obtaining request includes:

responding to the recommended resource acquisition request, and inquiring a user portrait corresponding to the client;

and if the user portrait corresponding to the client is not inquired, sending a recommended resource set to the client.

A fourth aspect of the present application provides a resource recommendation device, including:

the resource acquisition request receiving module is used for receiving a recommended resource acquisition request sent by a client;

and the resource set sending module is used for responding to the recommended resource acquisition request and sending a recommended resource set to the client so that the client can recommend resources in batches according to the recommended resource set.

In some modified embodiments of the fourth aspect of the present application, the recommended resource set includes a plurality of recommended resource information columns, and each recommended resource information column in the plurality of recommended resource information columns has at least one feature tag, so that the client performs resource recommendation in batches according to the feature tags corresponding to the recommended resource information columns in the recommended resource set.

In some modified embodiments of the fourth aspect of the present application, the resource set transmitting module includes:

the user portrait query unit is used for responding to the recommended resource acquisition request and querying a user portrait corresponding to the client;

and the resource set sending unit is used for sending a recommended resource set to the client if the user portrait corresponding to the client is not inquired.

A fifth aspect of the present application provides a resource recommendation apparatus, including: memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing when executing the computer program to implement the method of any of the first or third aspects of the present application.

A sixth aspect of the present application provides a computer readable medium having computer readable instructions stored thereon which are executable by a processor to implement the method of any one of the first or third aspects of the present application.

The resource recommendation method provided by the first aspect of the present application is applied to a client, and includes: displaying a first number of recommended resource information columns, wherein the first number of recommended resource information columns are selected from recommended resource sets provided by a server; determining characteristic information of the user according to the triggering behavior information of the user on the first number of recommended resource information columns; after the display of the recommended resource information columns of the first number is finished, selecting a recommended resource information column of a second number matched with the characteristic information from the rest recommended resource information columns in the recommended resource set; and displaying the recommended resource information columns of the second quantity. Compared with the prior art, the resource recommendation method provided by the first aspect of the application can make recommendations matched with users through batch display based on the recommended resource set provided by the server at one time under the condition of no user portrait, and has high recommendation efficiency.

Drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the application. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:

FIG. 1 illustrates a flow chart of a resource recommendation method for a client provided by some embodiments of the present application;

FIG. 2 illustrates a schematic diagram of a resource recommendation apparatus provided in some embodiments of the present application;

FIG. 3 illustrates a flow chart of a resource recommendation method for a server provided by some embodiments of the present application;

FIG. 4 illustrates a schematic diagram of another resource recommendation apparatus provided by some embodiments of the present application;

FIG. 5 illustrates a schematic diagram of a resource recommendation apparatus provided in some embodiments of the present application;

FIG. 6 illustrates a schematic diagram of a computer-readable medium provided by some embodiments of the present application.

Detailed Description

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

It is to be noted that, unless otherwise specified, technical or scientific terms used herein shall have the ordinary meaning as understood by those skilled in the art to which this application belongs.

In addition, the terms "first" and "second", etc. are used to distinguish different objects, rather than to describe a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.

Firstly, an application scenario of the application is briefly introduced as follows, when a user opens a client or opens a specific recommendation page for the first time, since the client or the server does not have a user portrait of the user at this time, accurate recommendation cannot be made to the user, and a solution in the prior art is as follows: the server firstly recommends a large amount of tentative resources to a user, then constructs a user portrait of the user by the server according to triggering behavior information of the user on the tentative resources, and only then can the server make targeted recommendation to the user according to the user portrait, wherein the technical route is as follows: the method comprises the steps that a client requests resources, a server provides a large number of tentative resources, the client displays the tentative resources, collects trigger behavior information of a user and uploads the trigger behavior information to the server, the server constructs a user portrait according to the trigger behavior information, the client requests the resources again, and the server provides targeted recommended resources according to the user portrait.

The above solution has many disadvantages, one is that the client and the server need to perform data request and data transmission for many times, and the server can give targeted recommended resources, the whole process is complex and tedious, and the recommendation efficiency is low; the method has the following disadvantages that the whole recommendation process is mainly completed by the server, a large amount of system resources of the server are consumed in the processes of providing tentative resources, constructing a user portrait, providing recommended resources according to the user portrait and the like, so that the load of the server is large, the service capacities such as recommendation efficiency and the like are severely restricted, if the server is expanded to improve the service capacity, on one hand, the cost is increased, and on the other hand, more severe challenges are provided for the load balancing capacity; the third disadvantage is that the construction of the user portrait usually needs a large amount of data support and consumes a large amount of computing resources of the server, the server bears the construction work of the user portrait of all users, and when the concurrent request amount is high, the construction of the user portrait cannot be completed in time, so that the recommendation cannot be realized quickly, and the recommendation efficiency is further reduced; the fourth disadvantage is that the limitation of the server service capability and the low recommendation efficiency can seriously affect the user experience of the client, and can not well retain new users, thereby causing the loss of a large number of new users.

The embodiments of the present application provide an improved solution for the above application scenarios, prior art solutions, and their disadvantages, and specifically provide a resource recommendation method, device, and computer readable medium, which are described below with reference to the accompanying drawings.

Referring to fig. 1, a flowchart of a resource recommendation method for a client according to some embodiments of the present application is shown, where as shown, the resource recommendation method includes the following steps:

step S101: and displaying a first number of recommended resource information columns, wherein the first number of recommended resource information columns are selected from recommended resource sets provided by the server.

In the embodiment of the present application, the client may include hardware or software. When the client includes hardware, it may be a variety of electronic devices having a display screen and supporting information interaction, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like. When the client includes software, it may be installed in the electronic device, and it may be implemented as a plurality of software or software modules, or as a single software or software module. And is not particularly limited herein.

In some embodiments, the recommended resource information bar may include at least one of a name, a summary, a brief introduction, a preview image and a preview image of a recommended resource, where the recommended resource is a resource recommended to the user, the resource includes, but is not limited to, articles (including novels, essays, and the like), news information, videos, music, web pages, merchandise information, desktop wallpaper, and APP (Application), and accordingly, the software described in the above description may include, but is not limited to, article reading software, news information software, video keys, music software, web browser, shopping software, software market, and the like.

For example, for an article reading software, when a user uses the software, article recommendation can be performed on a software home page or a specific recommendation page, and the recommended resource information column may include titles, summaries, and the like of the articles and may be presented in a list form. For video software, when a user uses the software, video recommendation can be performed on a software home page or a specific recommendation page, and the recommended resource information bar may include at least one of a preview of a video, a preview image of the video (for example, a dynamic picture formed by a plurality of video screenshots), a name, an author, and classification information (for example, a fun class, a science and technology class, a sports class, and the like), and may be displayed in a list form or a stacked form; for the shopping software, when the user uses the software, the user may recommend a commodity on a software home page or a specific recommendation page, or recommend a commodity on a search result page after the user inputs a keyword for search (the commodity recommendation process may also be understood as a presentation process of a search result), and the recommended resource information column may include at least one of a photo, a preview, a name, a merchant, a sales volume, and classification information (such as women's clothing, men's shoes, home appliances, and the like) of the commodity, and may be displayed in a list form or a stacked form, and the like; for a software market (also called an application store), when a user uses the software, APP recommendation can be performed on a software home page or a specific recommendation page, and the recommended resource information column can include at least one of a bulletin, a name, a profile, a download amount, classification information (such as tools, social classes, game classes, and the like) of the APP, and can be presented in a list form, a stack form, and the like.

It should be noted that the recommended resource set may include a set of recommended resource information bars, each recommended resource information bar is provided with a link connected to a content page of the recommended resource corresponding to the recommended resource information bar, and a user may trigger the link to display the recommended resource by clicking the recommended resource information bar, dragging the recommended resource information bar to a specified trigger position (for example, the top or middle position of the display interface), and other trigger operations.

For example, in one embodiment, the corresponding recommended resource may be requested from the server according to the link, and the embodiment may specifically and selectively request the server for the corresponding recommended resource according to the triggering operation of the user, so that the method has strong pertinence, and thus, the transmission flow of the recommended resource can be effectively saved and the load of the server can be reduced; in another embodiment, the server may package the recommended resource and the recommended resource information bar into the recommended resource set in advance, and then the client retrieves the corresponding recommended resource from the recommended resource set according to the link.

In addition, the recommended resource set may be a recommended resource set in a list form, that is, the recommended resource set may include a recommended resource list, or the recommended resource set may be a set of recommended resources generated in a formatted text, for example, a recommended resource set of a component in a JSON format, an XML format, or the like, which is not specifically limited in the embodiment of the present application.

In some embodiments, before this step S101, the method may further include: and after the operation of triggering and displaying the recommended resource information bars is detected, acquiring the recommended resource set from the server, wherein the recommended resource set comprises a plurality of recommended resource information bars, and each recommended resource information bar in the plurality of recommended resource information bars is provided with at least one characteristic label.

With reference to the foregoing description, in the embodiment of the present application, the operation of triggering to display the recommended resource information bar may include, but is not limited to: the present application is not limited to opening an application, entering an application home page, opening a specific recommendation page, entering a search term to search, or moving a resource display page to the bottom of the page (for example, a recommendation may be performed based on the resource displayed on the page, but since the resource may have multiple attributes, features, or categories, a situation that a targeted recommendation needs to be further performed), and so on.

It should be noted that the operation of triggering and displaying the recommended resource information bar may be a first operation, for example, a new user uses the recommended resource information bar for the first time immediately after the new user installs the reading software; the method can also be performed for the first time within a period of time, for example, an old user uses the method before one month, but does not use the method again within the one month, and the preference of the old user may change, especially for shopping applications, the characteristic information of the old user needs to be determined again, for example, a male user searches for clothing in the shopping application before one month and only looks up men's clothing, but after one month, the male user may have girlfriend, and then searches for clothing again and may only look up women's clothing, which is also applicable to the resource recommendation method provided by the present application; and the like, will not be described in detail.

In some embodiments, after the client detects the operation of triggering the display of the recommended resource information bar, the client may send a recommended resource acquisition request to the server once, the server responds to the recommended resource acquisition request and sends a recommended resource set to the client, and the client selects a first number of recommended resource information bars from the recommended resource set and executes the step S101. The first number of recommended resource information columns may be selected according to the specification of the server, or may be selected by the client autonomously.

It should be noted that the feature tags may be determined according to information such as attributes and classifications of recommended resources, based on the recommended resources, recommended resource information columns, and the feature tags form a corresponding relationship, each recommended resource information column in the recommended resource information columns has at least one feature tag, the recommended resource set may include a plurality of recommended resource information columns of different attributes and categories, and a first number of recommended resource information columns are selected from the recommended resource set, that is, the first number of recommended resource information columns are used as trial resources to determine feature information of the user.

Step S102: and determining the characteristic information of the user according to the triggering behavior information of the user to the recommended resource information bars of the first number.

In this embodiment of the application, the trigger behavior information may include at least one of the following: triggering the recommended resource information column, not triggering the recommended resource information column, viewing duration of recommended resources corresponding to the recommended resource information column after triggering the recommended resource information column, and feedback information of recommended resources corresponding to the recommended resource information column after triggering the recommended resource information column.

Triggering the recommended resource information bar, generally representing that a user is interested in the recommended resource information bar, and recommending similar resources; the recommended resource information bar is not triggered, generally representing that the user is not interested in the recommended resource information bar, and the similar resource recommendation is not needed; after the recommended resource information bar is triggered, whether the user is interested or not can be further determined, for example, if the watching duration is less than a preset first watching duration threshold, the user may have a possibility of misoperation, or if the user does not want to continue watching in the midway, that is, the user may not be interested although triggered, the user does not need to recommend the similar resource, if the watching duration is greater than a preset second watching duration threshold, the interest is indicated, the similar resource can be recommended, wherein the first watching duration threshold and the second watching duration threshold can be flexibly set according to actual needs, and the application is not particularly limited; similarly, the feedback information of the recommended resource corresponding to the recommended resource information column after the recommended resource information column is triggered may include approval, comment making, good comment, bad comment and the like, and according to the feedback information, whether the user is interested in the recommended resource may also be more accurately determined, and the detailed implementation may be flexibly implemented by combining the above description and the actual requirement, and is not repeated one by one here.

In some embodiments, the determining the feature information of the user according to the trigger behavior information of the user on the first number of recommended resource information bars may include:

In addition, in the embodiment of the present application, the feature information of the user may be determined according to the feature tag corresponding to the recommended resource information bar, and the feature information of the user (the user portrait is also one of the feature information) may also be determined by referring to a method for constructing a user portrait provided in the prior art without using the feature tag, which all should be within the protection scope of the present application, and no further description is given here, and only an exemplary description is given below for the method for determining the feature information of the user by using the feature tag.

In some embodiments, the first number of recommended resource information columns may correspond to the same feature tag, and if the user does not trigger any of the first number of recommended resource information columns, it indicates that the user is not interested in the resource of the feature tag, the client may select a resource that may be interested in the user after excluding the feature tag from the recommended resource set for recommendation, where the method is suitable for recommending a resource that is less classified, especially a resource that is classified two, for example, the feature tag corresponding to the first number of recommended resource information columns is "suitable for a male user to read", and if the current user is a female, the client may not trigger the first number of recommended resource information columns, and then the client may determine that the feature information of the current user is a female, and then select a resource whose feature tag is "suitable for a female user to read" from the recommended resource set for recommendation, therefore, targeted and accurate recommendation is realized.

In other embodiments, the first number of recommended resource information columns may also correspond to a plurality of feature tags, where one recommended resource information column may correspond to one feature tag, for example, the first number of recommended resource information columns may include recommended resource information columns corresponding to three feature tags, such as "old," "middle year," "teenager," and the like, in this case, the client may determine the feature information of the user according to the trigger behavior information of the user on each recommended resource information column, for example, if the user only clicks the recommended resource information column corresponding to the feature tag that looks at "middle year," the feature information of the user may be middle year, and then the client may select a resource whose feature tag is "middle year" from the recommended resource set to recommend the resource set, so as to implement targeted accurate recommendation.

In order to accurately determine the feature information of the user, quantitative features may also be used to determine the feature information of the user, for example, in some embodiments, the determining the feature information of the user according to the trigger behavior information of the user to each recommended resource information column of the first number of recommended resource information columns and the feature tag of each recommended resource information column may include:

The preference feature may include a feature of equalizing the preference degree and the correlation degree, and may be determined according to the number of times of triggering, the viewing duration after triggering, the feedback information after triggering, and the like of the user on the plurality of recommended resource information columns corresponding to the feature tag.

For example, in some specific examples, the first number of recommended resource information columns corresponds to a plurality of feature tags, one of the recommended resource information columns may correspond to feature tags of a plurality of dimensions, for example, a certain recommended resource information column may correspond to a plurality of feature tags such as "middle year", "male", "football hobby", and the like, in this case, the number of times of triggering, the triggering ratio, and the like of the user to each feature tag may be counted according to the triggering behavior information of the user, the preference of the user to each feature tag may be determined according to the number of times of triggering or the triggering ratio, then, according to the ranking of the preference, a plurality of feature tags ranked in the top may be selected to be determined as the feature information of the user, or a feature vector may be constructed according to each feature tag and its corresponding preference, and determined as the feature information of the user, which are all reasonable modification embodiments of the present application, are all within the scope of the present application.

Through the embodiment, the characteristic information of the user can be determined according to the quantized characteristics, so that the determined characteristic information of the user has higher accuracy, and resource recommendation can be performed more accurately.

In addition, in other embodiments, the triggering behaviors of the user may be divided into a positive triggering behavior and a negative triggering behavior, where a triggering behavior that the user prefers a certain resource may be denoted as a positive triggering behavior, a triggering behavior that the user does not prefer the certain resource is denoted as a negative triggering behavior (including a non-triggering situation), for example, a non-triggering recommended resource information field may be denoted as a negative triggering behavior, a triggering of the recommended resource information field may be denoted as a positive triggering behavior, and so on, then negative characteristic information of the user is determined according to the negative triggering behavior, positive characteristic information of the user is determined according to the positive triggering behavior, and finally characteristic information of the user is determined according to the positive characteristic information and/or the negative characteristic information. The negative feature information may be information obtained based on the feature tag disliked by the user, for example, the feature tag disliked by the user may be directly used as the negative feature information, or information that is mapped to the feature tag disliked by the user and used for describing features of the user may be used as the negative feature information; the forward feature information may be information obtained based on a feature tag preferred by the user, for example, the feature tag preferred by the user may be directly used as the forward feature information, or information describing features of the user and mapped to the feature tag preferred by the user may be used as the forward feature information, and so on; the user preference or dislike of the feature tag can be determined according to the triggering times, triggering proportion and the like of the feature tag by the user. Correspondingly, the determining the feature information of the user according to the triggering behavior information of the user on each recommended resource information column in the first number of recommended resource information columns and the feature tag of each recommended resource information column may include:

Through the implementation mode, the characteristic information of the user can be determined according to the positive triggering behavior and the negative triggering behavior of the user and the corresponding characteristic labels, for example, the characteristic information can be 'football preference, basketball dislike' and the like, so that more accurate pushing can be performed according to the characteristic information, and resources disliked by the user are prevented from being pushed to the user.

Step S103: and after the display of the recommended resource information columns of the first number is finished, selecting a recommended resource information column of a second number matched with the characteristic information from the rest recommended resource information columns in the recommended resource set.

In some embodiments, the selecting a second number of recommended resource information fields matching the feature information from the remaining recommended resource information fields in the recommended resource set may include:

For example, if the feature information of the user is "football preferred and basketball disliked", a second number of recommended resource information columns matching the feature information "football preferred and basketball disliked" may be selected from the remaining recommended resource information columns in the recommended resource set, and for example, a second number of recommended resource information columns with a feature label of "football" may be selected for recommendation.

For another example, if the feature information of the user is preference degrees for multiple tags, then a quota may be respectively allocated to the multiple tags according to the magnitude of each preference degree, and then a second number of recommended resource information fields may be selected from the remaining recommended resource information fields in the recommended resource set according to the quota. For example, if the feature information of the user is "30% of entertainment consultation-preference degree, 30% of sports consultation-preference degree, 30% of financial consultation and 20% of preference degree", 5, 3 and 2 quotas can be respectively allocated to the feature labels "entertainment consultation", "sports consultation" and "financial consultation", then 5 feature labels are selected from the rest recommended resource information columns in the recommended resource set as "entertainment consultation" recommended resource information columns, 3 feature labels are "sports consultation" recommended resource information columns, and 2 feature labels are "financial consultation" recommended resource information columns, and 10 recommended resource information columns are selected as the second number of recommended resource information columns for recommendation. Through the implementation mode, a quantitative mode can be adopted, and resources with corresponding quantity are recommended according to the preference degree of the user, so that the method has higher accuracy.

In addition, the ending includes stopping and ending, and may be triggered to be executed according to the operation of the user, for example, if the user performs a refresh operation in the presentation process of the first number of recommended resource information bars, the presentation is stopped; for another example, after the user moves the display page of the recommended resource information bar of the first number upward to the bottom of the page, the display may be ended.

Step S104: and displaying the recommended resource information columns of the second quantity.

In some modified embodiments, before displaying the second number of recommended resource information bars, the method may further include:

and displaying the hot spot resource information columns of the third quantity.

The specific display mode can be as follows: the third number of hot resource information columns are displayed behind the first number of recommended resource information columns, or the third number of hot resource information columns and the first number of recommended resource information columns are displayed in a mixed manner.

The third quantity of hotspot resource information columns may be sent together with the recommended resource set by the server, or may be sent together by packaging the third quantity of hotspot resource information columns into the recommended resource set by the server, which is not limited in this application. The mixed display may refer to that each recommended resource information column in the first number of recommended resource information columns and each recommended resource information column in the third number of hotspot resource information columns are mixed in a manner of cross placement, interval arrangement, and the like, and then are displayed.

For example, after the presentation of the recommended resource information fields of the first number is finished, sufficient time can be reserved for the client to perform statistics of the trigger behavior information, determination of the user characteristic information and selection of the recommended resource information fields of the second number by presenting the hot resource information fields of the third number, so that higher continuity and fluency can be ensured when the recommended resource information fields of the second number are continuously presented. In some variations, after the presenting the second number of recommended resource information bars, the method may further include:

Through the foregoing embodiments, the feature information of the user may be continuously updated, so as to facilitate performing more targeted and accurate recommendation based on the updated feature information, for example, a part of recommended resource information columns may be continuously selected from the recommended resource set to be displayed based on the updated feature information, or a targeted request resource may be recommended from a server according to the feature information, and in some embodiments, the method may further include:

It should be noted that the recommended resource information columns in the present application may be displayed in a page form, for example, a first number of recommended resource information columns are displayed in a first page, when a user triggers a page turning operation (including key page turning, page left sliding, page up sliding, and the like), a second page is called out, a third number of hot resource information columns are displayed in the second page, when the user continues to trigger the page turning operation, a third page is called out, and a second number of recommended resource information columns are displayed in the third page.

Compared with the prior art, the resource recommendation method for the client provided by the embodiment of the present application is exemplarily described above, and can make recommendations matching with the user through batch display based on the recommended resource set provided by the server once without the user portrait, so that the recommendation efficiency is higher.

Specifically, please refer to many drawbacks of the solutions in the prior art provided in the above description, and for one drawback, in the embodiment of the present application, a client can give targeted recommended resources in a batch display manner through one data request and transmission process, and the process is simple and has higher recommendation efficiency; aiming at the second disadvantage, the determination of the user characteristic information and the selection of the subsequent recommended resources are completed by the client, and the idle computing resources of the client are fully utilized, so that the load of the server can be effectively shared, the service capability of the server is improved, and the problems of cost increase and the like caused by capacity expansion of the server are avoided; in the embodiment of the application, as the determination of the user characteristic information and the selection of the recommended resources are completed by the client, the problem of high concurrency of the server is not considered, the related calculation can be quickly completed locally at the client, the determination of the user characteristic information and the selection of the recommended resources can be quickly completed in real time, the timeliness is high, and the recommendation efficiency is further improved; aiming at the fourth disadvantage, based on the advantages, the embodiment of the application can make full use of the computing resources of the client and reduce the computing load of the server, can quickly and timely complete the recommendation of the resources by adopting a simpler process, has higher recommendation efficiency, and can provide better use experience for users, thereby retaining new and old users.

In the foregoing embodiment, a resource recommendation method for a client is provided, and correspondingly, the application further provides a resource recommendation device. The resource recommendation device provided by the embodiment of the application can implement the resource recommendation method, and the resource recommendation device can be implemented by software, hardware or a combination of software and hardware. For example, the resource recommendation device may include integrated or separate functional modules or units to perform the corresponding steps of the above methods. Please refer to fig. 2, which is a schematic diagram of a resource recommendation device according to some embodiments 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.

As shown in fig. 2, the resource recommendation device 10 may include:

the resource information display system comprises a first resource information bar display module 101, a second resource information bar display module, a resource information selection module and a resource information display module, wherein the first resource information bar display module is used for displaying a first number of recommended resource information bars, and the first number of recommended resource information bars are selected from recommended resource sets provided by a server;

the user characteristic information determining module 102 is configured to determine characteristic information of the user according to the trigger behavior information of the user to the first number of recommended resource information columns;

a second resource information bar determining module 103, configured to select, after the presentation of the first number of recommended resource information bars is finished, a second number of recommended resource information bars that are matched with the feature information from the remaining recommended resource information bars in the recommended resource set;

and a second resource information bar display module 104, configured to display the second number of recommended resource information bars.

In some variations of the embodiments of the present application, the apparatus 10 further includes:

In some variations of the embodiments of the present application, the user characteristic information determining module 102 includes:

In some modifications of the embodiments of the present application, the user characteristic information determination unit includes:

In some variations of the embodiments of the present application, the trigger behavior information includes at least one of: triggering the recommended resource information column, not triggering the recommended resource information column, viewing duration of recommended resources corresponding to the recommended resource information column after triggering the recommended resource information column, and feedback information of recommended resources corresponding to the recommended resource information column after triggering the recommended resource information column.

In some modifications of the embodiments of the present application, the second resource information column determining module 103 includes:

In some variations of the embodiments of the present application, the third number of hot spot resource information columns are displayed after the first number of recommended resource information columns, or the third number of hot spot resource information columns and the first number of recommended resource information columns are displayed in a mixed manner.

In some variations of the embodiments of the present application, the recommended resource information field includes at least one of a name, an abstract, a brief description, a preview, and a preview image of the recommended resource.

The resource recommendation device provided by the embodiment of the application and the resource recommendation method provided by the previous embodiment of the application have the same inventive concept and the same beneficial effects.

In the foregoing embodiments, a resource recommendation method applied to a client is provided, and correspondingly, the present application also provides a resource recommendation method applied to a server, where the resource recommendation method applied to the server is implemented in cooperation with the resource recommendation applied to the client, and belongs to the same inventive concept, so that the following description of the resource recommendation method applied to the server can be understood with reference to the foregoing description of the embodiment of the resource recommendation method applied to the client, and some contents are not described again.

Referring to fig. 3, a flowchart of a resource recommendation method applied to a server according to some embodiments of the present application is shown, where as shown, the resource recommendation method includes the following steps:

step S201: and receiving a recommended resource acquisition request sent by a client.

Step S202: and responding to the recommended resource acquisition request, and sending a recommended resource set to the client so that the client can recommend resources in batches according to the recommended resource set.

In some embodiments, the recommended resource set includes a plurality of recommended resource information columns, and each recommended resource information column in the plurality of recommended resource information columns has at least one feature tag, so that the client performs resource recommendation in batches according to the feature tags corresponding to the recommended resource information columns in the recommended resource set. For a specific description, reference may be made to the foregoing description of an embodiment of a resource recommendation method applied to a client, which is not described herein again.

In some embodiments, the sending, to the client, the set of recommended resources in response to the recommended resource acquisition request includes:

Through the embodiment, after receiving a recommended resource acquisition request, a user portrait corresponding to the client side can be inquired first, if the user portrait can be found, resource recommendation is carried out based on the user portrait, and if the user portrait corresponding to the client side cannot be inquired, a recommended resource set is sent to the client side. Therefore, more appropriate recommended resources are flexibly provided for the client, and the resource recommendation efficiency and accuracy are improved.

The resource recommendation method applied to the server provided by the embodiment of the application and the resource recommendation method applied to the client provided by the embodiment of the application have the same beneficial effects with the same inventive concept.

In the foregoing embodiment, a resource recommendation method for a server is provided, and correspondingly, the present application further provides a resource recommendation apparatus. The resource recommendation device provided by the embodiment of the application can implement the resource recommendation method, and the resource recommendation device can be implemented by software, hardware or a combination of software and hardware. For example, the resource recommendation device may include integrated or separate functional modules or units to perform the corresponding steps of the above methods. Please refer to fig. 4, which is a schematic diagram of another resource recommendation apparatus according to some embodiments 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.

As shown in fig. 4, the resource recommendation device 20 may include:

a resource obtaining request receiving module 201, configured to receive a recommended resource obtaining request sent by a client;

a resource set sending module 202, configured to send a recommended resource set to the client in response to the recommended resource obtaining request, so that the client performs resource recommendation in batches according to the recommended resource set.

In some variations of the embodiments of the present application, the recommended resource set includes a plurality of recommended resource information columns, and each recommended resource information column in the plurality of recommended resource information columns has at least one feature tag, so that the client performs resource recommendation in batches according to the feature tags corresponding to the recommended resource information columns in the recommended resource set.

In some variations of the embodiments of the present application, the resource set sending module 202 includes:

The resource recommendation device 20 provided in the embodiment of the present application has the same beneficial effects as the resource recommendation method for a server provided in the foregoing embodiment of the present application.

The embodiment of the present application further provides a resource recommendation device corresponding to the resource recommendation method for the client or the resource recommendation method for the server provided in the foregoing embodiment, where the resource recommendation device may be a terminal device for the server, such as a server, and includes an independent server, a distributed server cluster, and the like; the resource recommendation device may also be any computing device with display function, data processing function and communication function, such as a mobile phone, a notebook computer, a tablet computer, a desktop computer, etc. Please refer to fig. 5, which illustrates a schematic diagram of a resource recommendation apparatus according to some embodiments of the present application. As shown in fig. 5, the resource recommendation device 30 includes: the system comprises a processor 300, a memory 301, a bus 302 and a communication interface 303, wherein the processor 300, the communication interface 303 and the memory 301 are connected through the bus 302; the memory 301 stores a computer program that can be executed on the processor 300, and when the processor 300 executes the computer program, the resource recommendation method for a client or the resource recommendation method for a user server provided in any of the foregoing embodiments of the present application is executed.

The Memory 301 may include a Random Access Memory (RAM) and a non-volatile Memory (non-volatile Memory), such as at least one disk Memory. The communication connection between the network element of the system and at least one other network element is realized through at least one communication interface 303 (which may be wired or wireless), and the internet, a wide area network, a local network, a metropolitan area network, and the like can be used.

Bus 302 can be an ISA bus, PCI bus, EISA bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 301 is configured to store a program, and the processor 300 executes the program after receiving an execution instruction, where the resource recommendation method for a client or the resource recommendation method for a user server disclosed in any of the foregoing embodiments of the present application may be applied to the processor 300, or implemented by the processor 300.

Processor 300 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 300. The Processor 300 may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in the memory 301, and the processor 300 reads the information in the memory 301 and completes the steps of the method in combination with the hardware thereof.

The resource recommendation device provided by the embodiment of the application, the resource recommendation method for the client and the resource recommendation method for the user server provided by the embodiment of the application have the same beneficial effects based on the same inventive concept.

Referring to fig. 6, a computer-readable storage medium is shown as an optical disc 40, on which a computer program (i.e., a program product) is stored, and when the computer program is executed by a processor, the computer program performs the resource recommendation method for a client or the resource recommendation method for a user server provided in any of the foregoing embodiments.

It should be noted that examples of the computer-readable storage medium may also 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 optical and magnetic storage media, which are not described in detail herein.

The computer-readable storage medium provided by the above-mentioned embodiment of the present application has the same beneficial effects as the resource recommendation method for the client and the resource recommendation method for the user server provided by the embodiment of the present application.

It should be noted that the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

Finally, it should be noted that: the above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present disclosure, and the present disclosure should be construed as being covered by the claims and the specification.

Claims

1. A resource recommendation method is used for a client, and is characterized by comprising the following steps:

displaying the recommended resource information columns of the second quantity;

under the condition that no user portrait exists, displaying in batches based on a recommended resource set provided by a server at one time;

before determining the characteristic information of the user, the method further comprises the following steps:

the recommended resources are downloaded to the local part of the client in advance before the user performs the triggering operation.

2. The method of claim 1, wherein before presenting the first number of recommended resource information bars, further comprising:

3. The method according to claim 1, wherein the determining the feature information of the user according to the trigger behavior information of the user on the first number of recommended resource information columns comprises:

4. The method according to claim 3, wherein the determining the feature information of the user according to the triggering behavior information of the user on each recommended resource information column in the first number of recommended resource information columns and the feature tag of each recommended resource information column comprises:

5. The method according to claim 3, wherein the determining the feature information of the user according to the triggering behavior information of the user on each recommended resource information column in the first number of recommended resource information columns and the feature tag of each recommended resource information column comprises:

6. The method according to any one of claims 1 to 5, wherein the trigger behavior information comprises at least one of: triggering the recommended resource information column, not triggering the recommended resource information column, viewing duration of recommended resources corresponding to the recommended resource information column after triggering the recommended resource information column, and feedback information of recommended resources corresponding to the recommended resource information column after triggering the recommended resource information column.

7. The method according to any one of claims 1 to 5, wherein the selecting a second number of recommended resource information columns matching the feature information from the remaining recommended resource information columns in the recommended resource set comprises:

8. The method according to any one of claims 1 to 5, wherein before presenting the second number of recommended resources information bars, further comprising:

and displaying the hot spot resource information columns of the third quantity.

9. The method according to claim 8, wherein the third number of hot spot resource information columns is shown after the first number of recommended resource information columns, or the third number of hot spot resource information columns is shown in a mixed manner with the first number of recommended resource information columns.

10. The method according to any one of claims 1 to 5, wherein after presenting the second number of recommended resources information bars, further comprising:

11. The method of claim 10, further comprising:

12. The method of claim 1, wherein the recommended resources information field comprises at least one of a name, a summary, a brief summary, a preview, and a preview image of the recommended resources.

13. A resource recommendation method for a server is characterized by comprising the following steps:

receiving a recommended resource acquisition request sent by a client;

responding to the recommended resource acquisition request, and sending a recommended resource set to the client so that the client can recommend resources in batches according to the recommended resource set;

if the user portrait corresponding to the client is not inquired, sending a recommended resource set to the client;

and the server packages the recommended resources and the recommended resource information bar into the recommended resource set in advance.

14. The method according to claim 13, wherein the recommended resource set includes a plurality of recommended resource information columns, and each recommended resource information column in the plurality of recommended resource information columns has at least one feature tag, so that the client performs resource recommendation in batches according to the feature tags corresponding to the recommended resource information columns in the recommended resource set.

15. The method of claim 13, wherein sending the set of recommended resources to the client in response to the request for obtaining recommended resources comprises:

16. A resource recommendation device, comprising: memory, processor and computer program stored on the memory and executable on the processor, characterized in that the processor executes when executing the computer program to implement the method according to any of claims 1 to 15.

17. A computer readable medium having computer readable instructions stored thereon which are executable by a processor to implement the method of any one of claims 1 to 15.