CN112000266A

CN112000266A - Page display method and device, electronic equipment and storage medium

Info

Publication number: CN112000266A
Application number: CN202010848016.3A
Authority: CN
Inventors: 樊星; 张曼; 韩少鹏
Original assignee: Beijing Dajia Internet Information Technology Co Ltd
Current assignee: Beijing Dajia Internet Information Technology Co Ltd
Priority date: 2020-08-21
Filing date: 2020-08-21
Publication date: 2020-11-27
Anticipated expiration: 2040-08-21
Also published as: CN112000266B

Abstract

The invention discloses a page display method, a device, electronic equipment and a storage medium, the method comprises the steps of receiving a play stop operation of a target user account on a currently played target multimedia resource, determining a corresponding recommended multimedia resource and a resource interaction control aiming at the target user account and the target multimedia resource, further responding to the play stop operation, setting the target multimedia resource to stop playing, displaying the recommended multimedia resource and the resource interaction control in a corresponding resource play stop page, enabling the target user account to realize more interaction meeting self information requirements through the recommended multimedia resource and the resource interaction control displayed in the resource play stop page, and realizing the interaction directly on a user account providing the target multimedia resource through the resource interaction control displayed in the resource play stop page, or an operation on a target multimedia resource or a recommended multimedia resource, etc.

Description

Page display method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of internet technologies, and in particular, to a page display method and apparatus, an electronic device, and a storage medium.

Background

With the development of internet technology, more and more people are used to wear off idle time by watching videos, and therefore, video applications have become an essential part of people's lives.

In the related art, after a user triggers a play stop operation in the process of watching a video, usually, only a pause button is simply displayed or a page is filled in a floating advertisement mode, so that the user cannot realize more interaction meeting the information requirement of the user through the page.

Disclosure of Invention

The disclosure provides a page display method, a page display device, an electronic device and a storage medium, which are used for at least solving the problem that more interaction meeting the self information requirement cannot be realized through a display page after a play stop operation is triggered in the process of watching a video in the related art. The technical scheme of the disclosure is as follows:

according to a first aspect of the embodiments of the present disclosure, there is provided a page display method, including:

receiving a play stop operation of a target user account on a currently played target multimedia resource;

determining corresponding recommended multimedia resources and resource interaction controls aiming at a target user account and target multimedia resources;

and responding to the play stop operation, setting the target multimedia resource to stop playing, and displaying the recommended multimedia resource and the resource interaction control in the corresponding resource play stop page.

In one embodiment, determining a resource interaction control comprises: acquiring historical behavior data of a target user account, wherein the historical behavior data comprises historical operation records of the target user account on a preset resource interaction control; and acquiring a target resource interaction control preferred by the target user account according to the historical operating record of the target user account on the preset resource interaction control, and determining the target resource interaction control as the resource interaction control.

In one embodiment, the obtaining of the target resource interaction control preferred by the target user account according to the historical operation record of the target user account on the preset resource interaction control includes: acquiring the operation times of each preset resource interaction control by a target user account according to the historical operation record of the target user account on the preset resource interaction controls; and acquiring the preset resource interaction control with the highest operation frequency and the target quantity as the target resource interaction control preferred by the target user account.

In one embodiment, the obtaining of the preset resource interaction control with the highest target number of operation times as the target resource interaction control preferred by the target user account includes: sequencing each preset resource interaction control according to the operation times of each preset resource interaction control; and taking the preset resource interaction control with the top-ranked target quantity as a target resource interaction control preferred by the target user account.

In one embodiment, determining the corresponding recommended multimedia resource includes: acquiring a preference multimedia resource set of a target user account; generating a first eigenvector matrix corresponding to the preference multimedia resource set and a second eigenvector matrix of the candidate recommendation multimedia resource set according to the set content tag; and selecting the matched candidate multimedia resources from the candidate recommended multimedia resource set as corresponding recommended multimedia resources according to the feature similarity between the first feature vector matrix and the second feature vector matrix.

In one embodiment, obtaining a set of preferred multimedia resources for a target user account includes: generating an original multimedia resource list according to historical operation behavior data of a target user account; and selecting a first target number of original multimedia resources from the original multimedia resource list as a preference multimedia resource set of the target user account.

In one embodiment, obtaining the set of preferred multimedia resources for the target user account further comprises: acquiring a target multimedia resource currently played by a target user account; and if the playing time length of the target multimedia resource is longer than the set time length, taking the target multimedia resource and the original multimedia resources with the first target quantity selected from the original multimedia resource list as a preference multimedia resource set of the target user account.

In one embodiment, the method further comprises: and randomly selecting candidate multimedia resources with a second target quantity from the multimedia resource library to generate a candidate recommended multimedia resource set.

In one embodiment, generating a first eigenvector matrix corresponding to the preference multimedia resource set and a second eigenvector matrix of the candidate recommendation multimedia resource set according to the set content tag includes: respectively identifying the multimedia contents of the preference multimedia resources in the preference multimedia resource set and the multimedia contents of the candidate multimedia resources in the candidate recommendation multimedia resource set according to the set content tags to obtain a first content feature vector of the preference multimedia resources and a second content feature vector of the candidate multimedia resources corresponding to the content tags; respectively carrying out feature fusion and normalization processing on the first content feature vector and the second content feature vector to obtain a first target feature vector corresponding to the preference multimedia resource and a second target feature vector corresponding to the candidate multimedia resource; and generating a first eigenvector matrix of the preference multimedia resource set according to the first target eigenvector of each preference multimedia resource in the preference multimedia resource set, and generating a second eigenvector matrix of the candidate recommendation multimedia resource set according to the second target eigenvector of each candidate multimedia resource in the candidate recommendation multimedia resource set.

In one embodiment, selecting a matched candidate multimedia resource from the candidate recommended multimedia resource set as a corresponding recommended multimedia resource according to the feature similarity between the first feature vector matrix and the second feature vector matrix includes: acquiring a feature similarity matrix between the first feature vector matrix and the second feature vector matrix; screening candidate multimedia resources with similarity larger than a similarity threshold value from the candidate recommended multimedia resource set according to the characteristic similarity matrix; and generating a recommended multimedia resource set according to the candidate multimedia resources with the similarity greater than the similarity threshold value.

In one embodiment, generating the recommended set of multimedia resources according to the candidate multimedia resources with the similarity greater than the similarity threshold includes: and selecting candidate multimedia resources with a third target quantity from the candidate multimedia resources with the similarity larger than the similarity threshold value to generate a recommended multimedia resource set.

In one embodiment, determining the corresponding recommended multimedia resource and resource interaction control includes: and sending an information acquisition request to the server, and triggering the server to return the corresponding recommended multimedia resources and the resource interaction control.

According to a second aspect of the embodiments of the present disclosure, there is provided a page display method, including:

receiving an information acquisition request from a client, wherein the information acquisition request is generated by a target user account through a play stop operation carried out by the client aiming at a currently played target multimedia resource;

and determining the corresponding recommended multimedia resources and resource interaction controls according to the information acquisition request, returning to the client side, and displaying the recommended multimedia resources and the resource interaction controls to a target user account by the client side.

In one embodiment, obtaining the set of preferred multimedia resources for the target user account comprises: generating an original multimedia resource list according to historical operation behavior data of a target user account; and selecting a first target number of original multimedia resources from the original multimedia resource list as a preference multimedia resource set of the target user account.

According to a third aspect of the embodiments of the present disclosure, there is provided a page displaying apparatus, including:

a play stop operation receiving module configured to execute a play stop operation performed on a currently played target multimedia resource by receiving a target user account;

the information determining module is configured to execute the steps of determining corresponding recommended multimedia resources and resource interaction controls aiming at a target user account and target multimedia resources;

and the play stop operation response module is configured to execute a response to the play stop operation, set the target multimedia resource to stop playing, and display the recommended multimedia resource and the resource interaction control in the corresponding resource play stop page.

In one embodiment, the information determination module comprises a resource interaction control determination unit configured to perform determining a resource interaction control; the resource interaction control determining unit comprises: the historical behavior data acquisition subunit is configured to execute acquisition of historical behavior data of a target user account, wherein the historical behavior data comprises a historical operation record of the target user account on a preset resource interaction control; and the target resource interaction control acquiring subunit is configured to execute the historical operation record of the preset resource interaction control according to the target user account, acquire the target resource interaction control preferred by the target user account, and determine the target resource interaction control as the resource interaction control.

In one embodiment, the target resource interaction control acquisition subunit is configured to perform: acquiring the operation times of each preset resource interaction control by a target user account according to the historical operation record of the target user account on the preset resource interaction controls; and acquiring the preset resource interaction control with the highest operation frequency and the target quantity as the target resource interaction control preferred by the target user account.

In one embodiment, the target resource interaction control acquisition subunit is configured to perform: sequencing each preset resource interaction control according to the operation times of each preset resource interaction control; and taking the preset resource interaction control with the top-ranked target quantity as a target resource interaction control preferred by the target user account.

In one embodiment, the information determination module includes a recommended multimedia resource determination unit configured to perform determining a corresponding recommended multimedia resource; the recommended multimedia resource determining unit includes: a preference multimedia resource set acquisition subunit configured to perform acquisition of a preference multimedia resource set of a target user account; the characteristic vector matrix generation subunit is configured to generate a first characteristic vector matrix corresponding to the preference multimedia resource set and a second characteristic vector matrix of the candidate recommendation multimedia resource set according to the set content label; and the recommended multimedia resource determining subunit is configured to select the matched candidate multimedia resource from the candidate recommended multimedia resource set as the corresponding recommended multimedia resource according to the feature similarity between the first feature vector matrix and the second feature vector matrix.

In one embodiment, the preferred multimedia resource set acquiring subunit is configured to perform: generating an original multimedia resource list according to historical operation behavior data of a target user account; and selecting a first target number of original multimedia resources from the original multimedia resource list as a preference multimedia resource set of the target user account.

In one embodiment, the preferred multimedia resource set acquiring subunit is further configured to perform: acquiring a target multimedia resource currently played by a target user account; and if the playing time length of the target multimedia resource is longer than the set time length, taking the target multimedia resource and the original multimedia resources with the first target quantity selected from the original multimedia resource list as a preference multimedia resource set of the target user account.

In one embodiment, the recommended multimedia resource determining unit further includes a candidate recommended multimedia resource set generating subunit configured to perform: and randomly selecting candidate multimedia resources with a second target quantity from the multimedia resource library to generate a candidate recommended multimedia resource set.

In one embodiment, the feature vector matrix generation subunit is configured to perform: respectively identifying the multimedia contents of the preference multimedia resources in the preference multimedia resource set and the multimedia contents of the candidate multimedia resources in the candidate recommendation multimedia resource set according to the set content tags to obtain a first content feature vector of the preference multimedia resources and a second content feature vector of the candidate multimedia resources corresponding to the content tags; respectively carrying out feature fusion and normalization processing on the first content feature vector and the second content feature vector to obtain a first target feature vector corresponding to the preference multimedia resource and a second target feature vector corresponding to the candidate multimedia resource; and generating a first eigenvector matrix of the preference multimedia resource set according to the first target eigenvector of each preference multimedia resource in the preference multimedia resource set, and generating a second eigenvector matrix of the candidate recommendation multimedia resource set according to the second target eigenvector of each candidate multimedia resource in the candidate recommendation multimedia resource set.

In one embodiment, the recommended multimedia resource determining subunit is configured to perform: acquiring a feature similarity matrix between the first feature vector matrix and the second feature vector matrix; screening candidate multimedia resources with similarity larger than a similarity threshold value from the candidate recommended multimedia resource set according to the characteristic similarity matrix; and generating a recommended multimedia resource set according to the candidate multimedia resources with the similarity greater than the similarity threshold value.

In one embodiment, the recommended multimedia resource determining subunit is further configured to perform: and selecting candidate multimedia resources with a third target quantity from the candidate multimedia resources with the similarity larger than the similarity threshold value to generate a recommended multimedia resource set.

In one embodiment, the information determination module is configured to perform: and sending an information acquisition request to the server, and triggering the server to return the corresponding recommended multimedia resources and the resource interaction control.

According to a fourth aspect of the embodiments of the present disclosure, there is provided a page displaying apparatus, including:

the information receiving module is configured to execute receiving of an information obtaining request from the client, wherein the information obtaining request is generated by a target user account through a playing stop operation carried out by the client aiming at a currently played target multimedia resource;

the information determining module is configured to determine corresponding recommended multimedia resources and resource interaction controls according to the information obtaining request;

and the information sending module is configured to execute returning of the corresponding recommended multimedia resources and the resource interaction control to the client for the client to display to the target user account.

In one embodiment, the information determination module comprises a resource interaction control determination unit configured to execute the determination of the resource interaction control; the resource interaction control determining unit comprises: the historical behavior data acquisition subunit is configured to execute acquisition of historical behavior data of a target user account, wherein the historical behavior data comprises a historical operation record of the target user account on a preset resource interaction control; and the target resource interaction control acquiring subunit is configured to execute the historical operation record of the preset resource interaction control according to the target user account, acquire the target resource interaction control preferred by the target user account, and determine the target resource interaction control as the resource interaction control.

In one embodiment, the target resource interaction control acquisition subunit is configured to perform: acquiring the operation times of each preset resource interaction control by a target user account according to the historical operation record of the target user account on the preset resource interaction controls; and acquiring preset resource interaction controls with the highest operation times and the target quantity as target resource interaction controls preferred by the target user account.

According to a fifth aspect of embodiments of the present disclosure, there is provided an electronic apparatus including: a processor; a memory for storing the processor-executable instructions; wherein the processor is configured to execute the instructions to cause the electronic device to perform the page presentation method described in any embodiment of the first aspect.

According to a sixth aspect of embodiments of the present disclosure, there is provided a server including: a processor; a memory for storing the processor-executable instructions; wherein the processor is configured to execute the instructions to cause the server to execute the page presentation method described in any embodiment of the second aspect.

According to a seventh aspect of the embodiments of the present disclosure, there is provided a storage medium, where instructions, when executed by a processor of an electronic device or a server, enable the electronic device to perform the page presentation method described in any one of the first aspects or the server to perform the page presentation method described in any one of the second aspects.

According to an eighth aspect of the embodiments of the present disclosure, there is provided a page display system, including the electronic device described in any embodiment of the fifth aspect and the server described in any embodiment of the sixth aspect.

According to a ninth aspect of embodiments of the present disclosure, there is provided a computer program product, the program product comprising a computer program, the computer program being stored in a readable storage medium, from which the at least one processor of the device reads and executes the computer program, so that the device performs the page presentation method described in any of the embodiments of the first aspect or performs the page presentation method described in any of the embodiments of the second aspect.

The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects:

the method comprises the steps of receiving a play stop operation of a target user account on a currently played target multimedia resource, determining a corresponding recommended multimedia resource and a resource interaction control according to the target user account and the target multimedia resource, further responding to the play stop operation, setting the target multimedia resource to stop playing, displaying the recommended multimedia resource and the resource interaction control in a corresponding resource play stop page, and enabling the target user account to achieve more interaction meeting the self information requirement through the recommended multimedia resource and the resource interaction control displayed in the resource play stop page.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure and are not to be construed as limiting the disclosure.

FIG. 1 is a flow diagram illustrating a page presentation method in accordance with an exemplary embodiment.

FIG. 2 is a flowchart illustrating the step of determining a resource interaction control according to an exemplary embodiment.

Fig. 3 is a flowchart illustrating a step of determining a corresponding recommended multimedia resource according to an exemplary embodiment.

Fig. 4 is a flowchart illustrating a step of generating a feature vector matrix according to an exemplary embodiment.

FIG. 5 is a flowchart illustrating the step of obtaining a recommended multimedia asset according to an example embodiment.

Fig. 6 is a flowchart illustrating a page presentation method according to another exemplary embodiment.

Fig. 7 is a signaling diagram illustrating a page show method according to an example embodiment.

FIG. 8 is a block diagram illustrating a page presentation apparatus according to an example embodiment.

Fig. 9 is a block diagram illustrating a page presentation apparatus according to another exemplary embodiment.

FIG. 10 is a block diagram illustrating a page presentation system in accordance with an exemplary embodiment.

Fig. 11 is an internal block diagram of an electronic device shown in accordance with an example embodiment.

Fig. 12 is an internal block diagram of a server according to an example embodiment.

Detailed Description

In order to make the technical solutions of the present disclosure better understood by those of ordinary skill in the art, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

Since in the conventional technology, after a user triggers a play stop operation during the process of watching a video, only a pause button is usually simply displayed or a page is filled in the form of a floating advertisement. The inventor finds that, under the page, it is difficult for a user to directly call a control meeting requirements to realize more interactions meeting the self information requirements, such as difficulty in performing collection, praise and other interaction operations on a video which is stopped to be played currently, and difficulty in interacting with a user account providing the video, and when the interaction operations are required to be performed each time, the user needs to exit from a playing mode first and then perform corresponding interaction operations, so that the operation is very inconvenient.

Based on this, in an exemplary embodiment, as shown in fig. 1, a page display method is provided, and this embodiment is exemplified by applying the method to a terminal. It is understood that the method can also be applied to a server, and can also be applied to a system comprising a terminal and a server, and is realized through the interaction of the terminal and the server. Specifically, the terminal is provided with a multimedia client, and the server is a background server corresponding to the multimedia client. In this embodiment, the method includes the steps of:

in step 110, a play stop operation performed by the target user account on the currently played target multimedia asset is received.

The target multimedia asset is a multimedia asset currently being played through the multimedia client, and specifically, the multimedia asset includes a plurality of media forms such as text, sound, and image, for example, but not limited to short video and long video. The play stop operation is an operation of instructing the multimedia client to pause the play of the currently played target multimedia resource or to end the play. In this embodiment, when a target user account viewing a target multimedia resource initiates a play pause operation through a play interface of the multimedia client, or the multimedia client completes playing the currently played target multimedia resource, the multimedia client may acquire a corresponding play stop operation.

In step 120, a corresponding recommended multimedia resource and a resource interaction control are determined for the target user account and the target multimedia resource.

The recommended multimedia resources are multimedia recommended to the target user account. The resource interaction control is a functional component provided for the man-machine interaction type information communication, and specifically, the resource interaction control includes, but is not limited to, a collection control and a praise control for a target multimedia resource, or an attention control and a reward control for a user account providing the target multimedia resource. In this embodiment, based on the target user account and the target multimedia resource, the corresponding recommended multimedia resource and resource interaction control may be determined.

In step 130, in response to the play stop operation, the target multimedia resource is set to stop playing, and the recommended multimedia resource and the resource interaction control are displayed in the corresponding resource play stop page.

The resource playing stop page is a page which is correspondingly displayed after the multimedia client responds to the playing stop operation. Specifically, after a target user account viewing the target multimedia resource initiates a play stop operation through a play interface of the multimedia client, the client responds to the play stop operation, that is, sets the target multimedia resource to stop playing, and displays a corresponding resource play stop page, specifically, a recommended multimedia resource and a resource interaction control are displayed in the resource play stop page.

The page display method receives the play stop operation of the target user account to the currently played target multimedia resource, and determines corresponding recommended multimedia resources and resource interaction controls for the target user account and the target multimedia resources, further responding to the play stop operation, setting the target multimedia resource to stop playing, and displaying the recommended multimedia resource and the resource interaction control in the corresponding resource play stop page, through the recommended multimedia resources and the resource interaction control displayed in the resource playing stop page, the target user account can realize more interaction meeting the self information requirement, for example, the interaction of the user account providing the target multimedia resource, or the operation of the target multimedia resource or the recommended multimedia resource, etc. can be directly realized through the resource interaction control displayed in the resource playing stop page.

In an exemplary embodiment, as shown in fig. 2, the determining the resource interaction control specifically includes the following steps:

in step 210, historical behavior data for the target user account is obtained.

The historical behavior data comprises historical operation records of a target user account on a preset resource interaction control, and the preset resource interaction control refers to a functional component provided by a client for man-machine interactive information communication and comprises but is not limited to a collection control, a praise control, an attention control, a reward control and the like. The historical operation records refer to the relevant data of the historical operation behaviors of the target user account on the collection control, the approval control, the attention control, the reward control and the like. In this embodiment, after the client receives the play stop operation performed by the target user account on the currently played target multimedia resource, the client acquires the historical behavior data of the target user account.

In step 220, according to the historical operation record of the target user account on the preset resource interaction control, the target resource interaction control preferred by the target user account is obtained, and the target resource interaction control is determined as the resource interaction control.

The target resource interaction control preferred by the target user account refers to the target resource interaction control most interested by the target user account, and the target resource interaction control with higher operation frequency of the target user account is generally determined as the target resource interaction control preferred by the target user account. Specifically, the operation times of the target user account on the preset resource interaction controls can be counted according to the historical behavior data of the target user account, the preset resource interaction controls with the highest operation times and the target quantity are selected as the target resource interaction controls preferred by the target user account, and the target resource interaction controls are displayed in the resource playing stop page as the resource interaction controls, so that the resource interaction controls displayed in the resource playing stop page are more suitable for the interests of the user, and personalized display is achieved.

In an exemplary embodiment, in step 220, obtaining a target resource interaction control preferred by a target user account according to a historical operating record of the target user account on a preset resource interaction control includes: acquiring the operation times of each preset resource interaction control by a target user account according to the historical operation record of the target user account on the preset resource interaction controls; and acquiring the preset resource interaction control with the highest operation frequency and the target quantity as the target resource interaction control preferred by the target user account. The target number refers to the number of preset resource interaction controls displayed in the resource playing stop page. In this embodiment, the operation times of the target user account on each preset resource interaction control are counted according to the historical operation records of the target user account on the preset resource interaction controls, and then the preset resource interaction controls with the target number of the highest operation times are extracted as the target resource interaction controls preferred by the target user account. Specifically, when the target resource interaction control preferred by the target user account is determined, the preset resource interaction controls can be sorted according to the operation times of each preset resource interaction control, and then the preset resource interaction controls with the target quantity in the top sorting order are intercepted from the sorting result and serve as the target resource interaction control preferred by the target user account. Because the capability of displaying the resource interaction controls in the resource playing stop page is limited, and all the resource interaction controls may not be displayed under the condition of considering the aesthetic appearance of the page, the target number of the resource interaction controls displayed in the resource playing stop page is preset, and the interest of the target user account is also considered, so that the target resource interaction controls with the target number preferred by the target user account are determined according to the operation times of the target user account on each preset resource interaction control and displayed, and the accuracy of the displayed information is improved on the basis of ensuring the aesthetic appearance of the displayed page.

In an exemplary embodiment, as shown in fig. 3, the determining of the corresponding recommended multimedia resource may specifically include the following steps:

in step 310, a set of preferred multimedia resources for a target user account is obtained.

The preference multimedia resource set of the target user account refers to a set of multimedia resources most interested by the target user account, and can be obtained by analyzing historical operation behavior data of the target user account. In this embodiment, when multimedia resource recommendation is to be performed on a target user account, a preferred multimedia resource set of the target user account needs to be determined first, and then a subsequent method is used to determine multimedia related to the preferred multimedia resource set for recommendation, so that recommended multimedia is matched with the target user account, and accuracy of multimedia recommendation is improved.

In step 320, a first eigenvector matrix corresponding to the preference multimedia resource set and a second eigenvector matrix corresponding to the candidate recommendation multimedia resource set are generated according to the set content tags.

The content tag is preset keyword information with different dimensions, and specifically may include keyword information such as a character attribute, an activity state, background content, and the like corresponding to the multimedia content. The set of candidate recommended multimedia resources is a set selected from a library of multimedia resources for extracting recommended multimedia resources. The first eigenvector matrix is obtained by performing feature extraction and vectorization on the preference multimedia resource set based on the set content tag, and is used for representing the eigenvector of the multimedia content in the preference multimedia resource set. In this embodiment, feature extraction is performed on the preferred multimedia resource set and the candidate recommended multimedia resource set according to the set content tag, so as to obtain a first feature vector matrix corresponding to the preferred multimedia resource set and a second feature vector matrix corresponding to the candidate recommended multimedia resource set.

In step 330, according to the feature similarity between the first feature vector matrix and the second feature vector matrix, the matched candidate multimedia resources are selected from the candidate recommended multimedia resource set as the corresponding recommended multimedia resources.

The matched candidate multimedia resources refer to a certain number of candidate recommended multimedia resources in the set of candidate recommended multimedia resources with the highest feature similarity with the preferred multimedia in the set of preferred multimedia resources. The recommended multimedia resource is a collection of multimedia that can be recommended to the target user account. Specifically, according to the feature similarity between a first feature vector matrix of the preference multimedia resource set and a second feature vector matrix of the candidate recommendation multimedia resource set, matched candidate multimedia is selected from the candidate recommendation multimedia resource set, and accordingly, recommended multimedia resources recommended to the target user account are generated.

In this embodiment, a preferred multimedia resource set of a target user account is determined, a first eigenvector matrix corresponding to the preferred multimedia resource set and a second eigenvector matrix of a candidate recommended multimedia resource set are generated according to a set content tag, and then matched candidate multimedia is selected from the candidate recommended multimedia resource set according to a feature similarity between the first eigenvector matrix and the second eigenvector matrix, so as to generate recommended multimedia resources for the target user account. When the recommended multimedia resources are generated, the set content tags are used for carrying out feature extraction and vectorization on the preference multimedia resource set and the candidate recommended multimedia resource set of the target user account, and then matched candidate multimedia is selected from the candidate recommended multimedia resource set according to the feature similarity between the preference multimedia resource set and the candidate recommended multimedia resource set, so that personalized recommendation for the target user account can be realized, and the accuracy of recommending the multimedia resources to the target user account is improved.

In an exemplary embodiment, in step 310, the preferred multimedia resource set of the target user account is obtained, which may specifically be implemented by the following steps: generating an original multimedia list according to historical operation behavior data of a target user account; and selecting a first target amount of original multimedia from the original multimedia list as a preference multimedia resource set of the target user account. The historical operation behavior data of the target user account refers to all recorded historical operation behaviors of the target user account operated through the client and relevant data corresponding to the historical operation behaviors. For example, taking the multimedia resource as a video, the video includes, but is not limited to, an operation behavior of browsing the video in history by the target user account and a corresponding video record, an operation behavior of approving the video in history by the target user account and a corresponding video record, an operation behavior of collecting the video in history by the target user account and a corresponding video record, and the like. The original multimedia list is generated according to the historical operation behavior data of the target user account. For example, an original multimedia list is generated according to the operation behavior of the historical video approval of the target user account and the corresponding video record, and the original multimedia list can be understood as the video record corresponding to the operation behavior of the historical video approval of the target user account. The first target number may be the number of preference videos preset for the preference multimedia resource set, and may be specifically set according to an actual scene, which is not limited in this embodiment.

Specifically, when a user (i.e., a target user account) logs in a backend server through a multimedia client installed on a terminal or the user refreshes an application program, the client may obtain historical operation behavior data of the target user account and generate an original multimedia list. When the data in the original multimedia list is less, the original multimedia list can be used as a preference multimedia resource set of the target user account, so that the preference multimedia resource set can fully embody the operation behavior of the target user account. When the data in the original multimedia list is large, a first target amount of recent original multimedia can be extracted from the original multimedia list as a preferred multimedia resource set of the target user account, considering that the user interest may change over time. For example, the original multimedia in the original multimedia list can be sorted in a reverse order according to the time of the occurrence of the historical operation behavior, and then the original multimedia with the first target quantity in the top sorting is extracted as the preference multimedia resource set of the target user account, so that the recent interests of the preference multimedia resource set and the target user account are more fitted, further, the recommended multimedia resources recalled through the preference multimedia resource set are more in line with the recent interests of the user, and the accuracy of the recommended multimedia resources is further improved.

In an exemplary embodiment, when determining the set of preferred multimedia resources for the target user account, it may also be considered whether the target user account is interested in the currently viewed target multimedia resource, so as to determine whether to add the currently viewed target multimedia resource to the set of preferred multimedia resources. Specifically, if the watching duration of the target multimedia resource currently watched by the target user account is longer than the set duration, the target user account is shown to be interested in the currently watched target multimedia resource, so that the target multimedia resource and a first target number of original multimedia selected from the original multimedia list are jointly used as a preference multimedia resource set of the target user account, a recommendation factor is fully considered, and more accurate recommendation is provided for the user.

In an exemplary embodiment, in order to prevent over-fitting the user interests and avoid the problem of over-concentration of the user interests, a corresponding number of original multimedia may be randomly selected from the original multimedia list as a preferred multimedia resource set of the target user account according to the first target number.

In an exemplary embodiment, before generating the first eigenvector matrix corresponding to the preferred multimedia resource set and the second eigenvector matrix of the candidate recommended multimedia resource set according to the set content tag, the method further includes: and randomly selecting candidate multimedia resources with a second target quantity from the multimedia resource library to generate a candidate recommended multimedia resource set. The multimedia resource library is a resource database for providing multimedia services for users by clients. The second target number is the number of candidate multimedia set for the candidate recommended multimedia resource set in advance, and may be specifically set according to an actual scene. Specifically, since the resource database providing the multimedia service has a large amount of multimedia, if all of the multimedia resources are used as candidate recommended multimedia resource sets, the amount of subsequently processed data will be large, and the processing speed will be affected.

In an exemplary embodiment, as shown in fig. 4, in step 320, a first eigenvector matrix corresponding to the preferred multimedia resource set and a second eigenvector matrix corresponding to the candidate recommended multimedia resource set are generated according to the set content tag, which may be specifically implemented by the following steps:

in step 321, the multimedia contents of the preferred multimedia resources in the preferred multimedia resource set and the multimedia contents of the candidate multimedia resources in the candidate recommended multimedia resource set are respectively identified according to the preset content tags, so as to obtain a first content feature vector of the preferred multimedia resources and a second content feature vector of the candidate multimedia resources corresponding to the content tags.

Wherein the content tags may include different dimensions of keyword information. For example, the method may include 5 actions such as [ cooking, singing, dancing, running, and drawing ] set according to the character action attribute, and after the video is identified based on the set character action attribute tag, the result is that the action with the corresponding dimension is set to 1, and the action without the corresponding dimension is set to 0, so as to obtain the content feature vector corresponding to the character action attribute tag. For example, if a video content includes singing and dancing actions, the content feature vector identified by the video content to obtain the character action attribute tag results in [0,1,1,0,0 ]. If the content tags also comprise character gender tags [ male, female ], if a certain video is male, identifying the male to obtain a content feature vector result corresponding to the character gender tags as [1,0 ]; if the female is identified, the result of the content feature vector corresponding to the character gender label is [0,1] after the female is identified; if there is no person, the result of identifying the person to obtain the content feature vector corresponding to the gender label of the person is [0,0 ].

Therefore, in this embodiment, the multimedia content of each preferred multimedia in the preferred multimedia resource set is respectively identified according to the preset content tag, so as to obtain the first content feature vector of each preferred multimedia corresponding to the content tag; and respectively identifying the multimedia content of each candidate multimedia in the candidate recommended multimedia resource set according to a preset content tag, thereby obtaining a second content feature vector of each candidate multimedia corresponding to the content tag.

In step 322, feature fusion and normalization are performed on the first content feature vector and the second content feature vector, respectively, to obtain a first target feature vector corresponding to the preferred multimedia resource and a second target feature vector corresponding to the candidate multimedia resource.

The feature fusion is to generate new features from content feature vectors extracted through content tags of different dimensions by a certain method, so that the new features are more effective for classification. And the normalization is a processing form for mapping the new features subjected to feature fusion to a range of 0-1 for the convenience of data processing and more benefit for feature classification. In this embodiment, a first target feature vector corresponding to each preferred multimedia resource is obtained by performing feature fusion and normalization processing on the first content feature vector; and performing feature fusion and normalization processing on the second content feature vector to obtain a second target feature vector corresponding to the candidate multimedia resource. Specifically, the trained neural network may be used to perform feature fusion processing on the first content feature vector and the second content feature vector respectively. The neural network can set a corresponding full connection layer based on the dimensionality of the content label, so that the content feature vectors corresponding to the content labels with different dimensionalities are subjected to feature fusion through the full connection layer to obtain new features.

In step 323, a first eigenvector matrix of the set of preferred multimedia resources is generated from the first target eigenvector of each preferred multimedia resource in the set of preferred multimedia resources, and a second eigenvector matrix of the set of candidate recommended multimedia resources is generated from the second target eigenvector of each candidate multimedia resource in the set of candidate recommended multimedia resources.

For example, if there are M preferred multimedia resources in the preferred multimedia resource set, the multimedia content of each preferred multimedia resource is identified through the above steps, so as to obtain a first content feature vector of each preferred multimedia resource, and then feature fusion and normalization processing are performed on the first content feature vector of each preferred multimedia resource, so as to obtain a first target feature vector of each preferred multimedia resource, a first feature vector matrix of the preferred multimedia resource set is generated based on the first target feature vector of each preferred multimedia resource, and for convenience of subsequent feature similarity calculation, the number of rows of the first feature vector matrix is the number of preferred multimedia resources in the preferred multimedia resource set. If N candidate multimedia resources exist in the candidate recommended multimedia resource set, identifying the multimedia content of each candidate multimedia resource through the steps to obtain a second content feature vector of each candidate multimedia resource, further performing feature fusion and normalization processing on the second content feature vector of each candidate multimedia resource to obtain a second target feature vector of each candidate multimedia resource, generating a second feature vector matrix of the candidate recommended multimedia resource set based on the second target feature vector of each candidate multimedia resource, and facilitating subsequent feature similarity calculation, wherein the number of columns of the second feature vector matrix is the number of candidate multimedia resources in the candidate recommended multimedia resource set.

For example, if the predetermined content tags include P tags, such as a character attribute tag, an activity status tag, background content, etc., the tag may be used₁,tag₂…tag_pRepresenting the P tags, and selecting the content tags for multimedia (such as preferred multimedia resources or candidate multimedia resources)Source), vectorizing each label to obtain corresponding x₁,x₂…x_pWith x ═ x₁,x₂…x_p]A tag vector (i.e., a content feature vector) representing the entire multimedia. Inputting x into the trained neural network to obtain new feature vector, normalizing the output result of the network to obtain final feature vector for calculating similarity between multimedia

(i.e., the target feature vector for the corresponding multimedia).

If the preference multimedia resource set comprises M preference multimedia resources and the candidate recommendation multimedia resource set comprises N candidate multimedia resources, after the preference multimedia resources and the candidate multimedia resources are processed, a corresponding first eigenvector matrix A and a corresponding second eigenvector matrix B are respectively obtained, wherein,

wherein, P represents the number of the set content labels, M represents the number of the preferred multimedia resources in the preferred multimedia resource set, and N represents the number of the candidate multimedia resources in the candidate recommended multimedia resource set.

In the above embodiment, the set content tags are used to respectively identify the multimedia content of the preferred multimedia resource in the preferred multimedia resource set and the multimedia content of the candidate multimedia resource in the candidate recommended multimedia resource set, so as to obtain the first content feature vector of the preferred multimedia resource and the second content feature vector of the candidate multimedia resource, and obtain the corresponding first target feature vector and second target feature vector through feature fusion and normalization processing, so as to generate the first feature vector matrix of the preferred multimedia resource set and the second feature vector matrix of the candidate recommended multimedia resource set, thereby improving the accuracy of the recommended content according to the content tags, so as to solve the problem that the conventional floating layer advertisement recommendation method is generally obtained only through the interest tag of the user or the content tag of the multimedia currently played by the user, without fully considering the recommendation factors, resulting in a problem of low accuracy of recommended content.

In an exemplary embodiment, as shown in fig. 5, in step 330, according to the feature similarity between the first feature vector matrix and the second feature vector matrix, the matched candidate multimedia resources are selected from the candidate recommended multimedia resource set as corresponding recommended multimedia resources, which may specifically be implemented by the following steps:

in step 331, a feature similarity matrix between the first feature vector matrix and the second feature vector matrix is obtained.

The feature similarity can be calculated by using a cosine similarity evaluation index. After the first eigenvector matrix A of the preference multimedia resource set and the second eigenvector matrix B of the candidate recommendation multimedia resource set are obtained through the steps, a cosine similarity calculation method can be adopted to obtain the eigenvector matrixes of the preference multimedia resource set and the candidate recommendation multimedia resource set. Specifically, if the feature similarity matrix is represented by C, then C is a × B, where C in C is C_ijRepresenting the similarity of the ith preferred multimedia asset in a and the jth candidate multimedia asset in B.

In step 332, candidate multimedia resources with similarity greater than the similarity threshold are screened from the candidate recommended multimedia resource set according to the feature similarity matrix.

The similarity threshold may be a value preset according to an actual usage scenario. Specifically, according to a preset similarity threshold value alpha, C larger than alpha is selected from C_ijThe ith preferred multimedia resource in the representation A is more similar to the jth candidate multimedia resource in the representation B, so that the corresponding candidate multimedia resource is selected from the candidate recommended multimedia resource set.

In step 333, a set of recommended multimedia resources is generated according to the candidate multimedia resources with the similarity greater than the similarity threshold.

Specifically, the recommended multimedia resource set may be generated according to the candidate multimedia resources whose similarity is greater than the similarity threshold, that is, all the candidate multimedia resources whose similarity is greater than the similarity threshold are determined as recommended multimedia resources. And selecting candidate multimedia resources with a third target number from the candidate multimedia resources with the similarity larger than the similarity threshold value to generate a recommended multimedia resource set. And the third target quantity is the quantity of recommended multimedia resources in a preset recommended multimedia resource set. In this embodiment, the recommended multimedia resource set may be generated by selecting the candidate multimedia resources with the maximum similarity from the candidate multimedia resources with the similarity greater than the similarity threshold, or by randomly selecting the candidate multimedia resources with the third target number from the candidate multimedia resources with the similarity greater than the similarity threshold, which is not limited in this embodiment.

In the above embodiment, the accuracy of recommending the multimedia resource set to the target user account is improved by obtaining the feature similarity matrix between the first feature vector matrix and the second feature vector matrix, screening the candidate multimedia resources with the similarity greater than the similarity threshold from the candidate recommended multimedia resource set according to the feature similarity matrix, and generating the recommended multimedia resource set according to the candidate multimedia resources with the similarity greater than the similarity threshold.

In an exemplary embodiment, the determination of the corresponding recommended multimedia resource and the resource interaction control can also be realized through interaction with a server. Specifically, after receiving a play stop operation performed on a currently played target multimedia resource, the client sends a corresponding information acquisition request to the server, so as to trigger the server to return a corresponding recommended multimedia resource and a resource interaction control, thereby reducing resource consumption of the client for processing data and further improving processing performance of the client.

In an exemplary embodiment, as shown in fig. 6, a page display method is provided, and this embodiment takes the application of the method to a server as an example for description, and specifically includes the following steps:

in step 610, an information acquisition request is received from a client.

The information acquisition request is a request sent by a client for acquiring information from a server, and the information acquisition request is generated by a target user account through a play stop operation carried out by the client for a currently played target multimedia resource. Specifically, when the target user account performs a play stop operation on the currently played target multimedia resource through the client, the client generates an information acquisition request and sends the information acquisition request to the server.

In step 620, according to the information acquisition request, the corresponding recommended multimedia resource and resource interaction control are determined, and returned to the client for the client to display to the target user account.

Specifically, the server determines the corresponding recommended multimedia resource and resource interaction control according to the received information acquisition request, and returns the recommended multimedia resource and resource interaction control to the client for the client to display to the target user account.

According to the page display method, the server receives the information acquisition request from the client, determines the corresponding recommended multimedia resource and resource interaction control according to the information acquisition request, returns the recommended multimedia resource and resource interaction control to the client for the client to display to the target user account, so that the target user account can interact with the user account providing the target multimedia resource through the resource interaction control displayed by the client, or operate the target multimedia resource or the recommended multimedia resource, more interaction meeting the information requirement of the client is realized, and the client acquires information from the server and directly displays the information, so that the resource consumption of the client for processing data is reduced, and the processing performance of the client is improved.

In an exemplary embodiment, determining a resource interaction control comprises: acquiring historical behavior data of a target user account, wherein the historical behavior data comprises historical operation records of the target user account on a preset resource interaction control; and acquiring a target resource interaction control preferred by the target user account according to the historical operating record of the target user account on the preset resource interaction control, and determining the target resource interaction control as the resource interaction control.

In an exemplary embodiment, the obtaining of the target resource interaction control preferred by the target user account according to the historical operation record of the target user account on the preset resource interaction control includes: acquiring the operation times of each preset resource interaction control by a target user account according to the historical operation record of the target user account on the preset resource interaction controls; and acquiring the preset resource interaction control with the highest operation frequency and the target quantity as the target resource interaction control preferred by the target user account.

In an exemplary embodiment, the obtaining of the preset resource interaction control with the highest target number of operation times as the target resource interaction control preferred by the target user account includes: sequencing each preset resource interaction control according to the operation times of each preset resource interaction control; and taking the preset resource interaction control with the top-ranked target quantity as a target resource interaction control preferred by the target user account.

In an exemplary embodiment, determining the corresponding recommended multimedia resource includes: acquiring a preference multimedia resource set of a target user account; generating a first eigenvector matrix corresponding to the preference multimedia resource set and a second eigenvector matrix of the candidate recommendation multimedia resource set according to the set content tag; and selecting the matched candidate multimedia resources from the candidate recommended multimedia resource set as corresponding recommended multimedia resources according to the feature similarity between the first feature vector matrix and the second feature vector matrix.

In an exemplary embodiment, obtaining the set of preferred multimedia resources for the target user account comprises: generating an original multimedia resource list according to historical operation behavior data of a target user account; and selecting a first target number of original multimedia resources from the original multimedia resource list as a preference multimedia resource set of the target user account.

In an exemplary embodiment, obtaining the set of preferred multimedia resources for the target user account further comprises: acquiring a target multimedia resource currently played by a target user account; and if the playing time length of the target multimedia resource is longer than the set time length, taking the target multimedia resource and the original multimedia resources with the first target quantity selected from the original multimedia resource list as a preference multimedia resource set of the target user account.

In an exemplary embodiment, the method further comprises: and randomly selecting candidate multimedia resources with a second target quantity from the multimedia resource library to generate a candidate recommended multimedia resource set.

In an exemplary embodiment, generating a first eigenvector matrix corresponding to the preferred multimedia resource set and a second eigenvector matrix of the candidate recommended multimedia resource set according to the set content tag includes: respectively identifying the multimedia contents of the preference multimedia resources in the preference multimedia resource set and the multimedia contents of the candidate multimedia resources in the candidate recommendation multimedia resource set according to the set content tags to obtain a first content feature vector of the preference multimedia resources and a second content feature vector of the candidate multimedia resources corresponding to the content tags; respectively carrying out feature fusion and normalization processing on the first content feature vector and the second content feature vector to obtain a first target feature vector corresponding to the preference multimedia resource and a second target feature vector corresponding to the candidate multimedia resource; and generating a first eigenvector matrix of the preference multimedia resource set according to the first target eigenvector of each preference multimedia resource in the preference multimedia resource set, and generating a second eigenvector matrix of the candidate recommendation multimedia resource set according to the second target eigenvector of each candidate multimedia resource in the candidate recommendation multimedia resource set.

In an exemplary embodiment, selecting a matched candidate multimedia resource from the candidate recommended multimedia resource set as a corresponding recommended multimedia resource according to the feature similarity between the first feature vector matrix and the second feature vector matrix includes: acquiring a feature similarity matrix between the first feature vector matrix and the second feature vector matrix; screening candidate multimedia resources with similarity larger than a similarity threshold value from the candidate recommended multimedia resource set according to the characteristic similarity matrix; and generating a recommended multimedia resource set according to the candidate multimedia resources with the similarity greater than the similarity threshold value.

In an exemplary embodiment, generating a set of recommended multimedia resources based on candidate multimedia resources having a similarity greater than a similarity threshold comprises: and selecting candidate multimedia resources with a third target quantity from the candidate multimedia resources with the similarity larger than the similarity threshold value to generate a recommended multimedia resource set.

In a specific embodiment, as shown in fig. 7, the method for implementing the page display by the interaction between the terminal and the server includes:

in step 701, the terminal receives a play stop operation performed by the target user account on the currently played target multimedia resource.

In step 702, the terminal sends an information acquisition request to the server.

And 703, the server determines the corresponding recommended multimedia resource and the resource interaction control according to the information acquisition request.

Step 704, the server returns the corresponding recommended multimedia resource and resource interaction control to the terminal.

In step 705, the terminal responds to the play stop operation, sets the target multimedia resource to stop playing,

step 706, the terminal displays the recommended multimedia resource and the resource interaction control in the corresponding resource playing stop page.

The specific implementation method of the page display method applied to the server is the same as the specific implementation method of the page display method applied to the terminal, and is not described herein again.

It should be understood that although the various steps in the flow charts of fig. 1-7 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 1-7 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed in turn or alternately with other steps or at least some of the other steps.

FIG. 8 is a block diagram illustrating a page presentation apparatus according to an exemplary embodiment. Referring to fig. 8, the apparatus includes a play stop operation receiving module 801, an information determining module 802, and a play stop operation responding module 803.

A play stop operation receiving module 801 configured to execute a play stop operation performed on a currently played target multimedia resource by receiving a target user account;

an information determining module 802 configured to determine, for a target user account and a target multimedia resource, a corresponding recommended multimedia resource and a resource interaction control;

and the play stop operation response module 803 is configured to execute a response to the play stop operation, set the target multimedia resource to stop playing, and display the recommended multimedia resource and the resource interaction control in the corresponding resource play stop page.

In an exemplary embodiment, the information determination module includes a resource interaction control determination unit configured to perform determining a resource interaction control; the resource interaction control determining unit comprises: the historical behavior data acquisition subunit is configured to execute acquisition of historical behavior data of a target user account, wherein the historical behavior data comprises a historical operation record of the target user account on a preset resource interaction control; and the target resource interaction control acquiring subunit is configured to execute the historical operation record of the preset resource interaction control according to the target user account, acquire the target resource interaction control preferred by the target user account, and determine the target resource interaction control as the resource interaction control.

In an exemplary embodiment, the target resource interaction control acquisition subunit is configured to perform: acquiring the operation times of each preset resource interaction control by a target user account according to the historical operation record of the target user account on the preset resource interaction controls; and acquiring the preset resource interaction control with the highest operation frequency and the target quantity as the target resource interaction control preferred by the target user account.

In an exemplary embodiment, the target resource interaction control acquisition subunit is configured to perform: sequencing each preset resource interaction control according to the operation times of each preset resource interaction control; and taking the preset resource interaction control with the top-ranked target quantity as a target resource interaction control preferred by the target user account.

In an exemplary embodiment, the information determining module includes a recommended multimedia resource determining unit configured to perform determining a corresponding recommended multimedia resource; the recommended multimedia resource determining unit includes: a preference multimedia resource set acquisition subunit configured to perform acquisition of a preference multimedia resource set of a target user account; the characteristic vector matrix generation subunit is configured to generate a first characteristic vector matrix corresponding to the preference multimedia resource set and a second characteristic vector matrix of the candidate recommendation multimedia resource set according to the set content label; and the recommended multimedia resource determining subunit is configured to select the matched candidate multimedia resource from the candidate recommended multimedia resource set as the corresponding recommended multimedia resource according to the feature similarity between the first feature vector matrix and the second feature vector matrix.

In an exemplary embodiment, the preferred multimedia resource set acquiring subunit is configured to perform: generating an original multimedia resource list according to historical operation behavior data of a target user account; and selecting a first target number of original multimedia resources from the original multimedia resource list as a preference multimedia resource set of the target user account.

In an exemplary embodiment, the preferred multimedia resource set acquiring subunit is further configured to perform: acquiring a target multimedia resource currently played by a target user account; and if the playing time length of the target multimedia resource is longer than the set time length, taking the target multimedia resource and the original multimedia resources with the first target quantity selected from the original multimedia resource list as a preference multimedia resource set of the target user account.

In an exemplary embodiment, the recommended multimedia resource determining unit further includes a candidate recommended multimedia resource set generating subunit configured to perform: and randomly selecting candidate multimedia resources with a second target quantity from the multimedia resource library to generate a candidate recommended multimedia resource set.

In an exemplary embodiment, the feature vector matrix generating subunit is configured to perform: respectively identifying the multimedia contents of the preference multimedia resources in the preference multimedia resource set and the multimedia contents of the candidate multimedia resources in the candidate recommendation multimedia resource set according to the set content tags to obtain a first content feature vector of the preference multimedia resources and a second content feature vector of the candidate multimedia resources corresponding to the content tags; respectively carrying out feature fusion and normalization processing on the first content feature vector and the second content feature vector to obtain a first target feature vector corresponding to the preference multimedia resource and a second target feature vector corresponding to the candidate multimedia resource; and generating a first eigenvector matrix of the preference multimedia resource set according to the first target eigenvector of each preference multimedia resource in the preference multimedia resource set, and generating a second eigenvector matrix of the candidate recommendation multimedia resource set according to the second target eigenvector of each candidate multimedia resource in the candidate recommendation multimedia resource set.

In an exemplary embodiment, the recommended multimedia resource determining subunit is configured to perform: acquiring a feature similarity matrix between the first feature vector matrix and the second feature vector matrix; screening candidate multimedia resources with similarity larger than a similarity threshold value from the candidate recommended multimedia resource set according to the characteristic similarity matrix; and generating a recommended multimedia resource set according to the candidate multimedia resources with the similarity greater than the similarity threshold value.

In an exemplary embodiment, the recommended multimedia resource determining subunit is further configured to perform: and selecting candidate multimedia resources with a third target quantity from the candidate multimedia resources with the similarity larger than the similarity threshold value to generate a recommended multimedia resource set.

In an exemplary embodiment, the information determination module is configured to perform: and sending an information acquisition request to the server, and triggering the server to return the corresponding recommended multimedia resources and the resource interaction control.

FIG. 9 is a block diagram illustrating a page presentation apparatus according to an exemplary embodiment. Referring to fig. 9, the apparatus includes an information receiving module 901, an information determining module 902, and an information transmitting module 903.

An information receiving module 901 configured to perform receiving an information acquisition request from a client, where the information acquisition request is generated by a target user account through a play stop operation performed by the client for a currently played target multimedia resource;

an information determining module 902 configured to determine a corresponding recommended multimedia resource and a resource interaction control according to the information obtaining request;

and the information sending module 903 is configured to execute returning the corresponding recommended multimedia resource and resource interaction control to the client for the client to display to the target user account.

With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

In an exemplary embodiment, a page presentation system is provided, as shown in fig. 10, comprising a terminal 1002 and a server 1004. The following describes the terminal 1002 and the server 1004 with reference to fig. 11 and 12.

FIG. 11 is a block diagram illustrating an apparatus for page presentation Z00, according to an example embodiment. For example, device Z00 may be a mobile phone, computer, digital broadcast terminal, messaging device, game console, tablet device, medical device, fitness device, personal digital assistant, and the like.

Referring to fig. 11, device Z00 may include one or more of the following components: a processing component Z02, a memory Z04, a power component Z06, a multimedia component Z08, an audio component Z10, an interface to input/output (I/O) Z12, a sensor component Z14 and a communication component Z16.

The processing component Z02 generally controls the overall operation of the device Z00, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component Z02 may include one or more processors Z20 to execute instructions to perform all or part of the steps of the method described above. Further, the processing component Z02 may include one or more modules that facilitate interaction between the processing component Z02 and other components. For example, the processing component Z02 may include a multimedia module to facilitate interaction between the multimedia component Z08 and the processing component Z02.

The memory Z04 is configured to store various types of data to support operations at device Z00. Examples of such data include instructions for any application or method operating on device Z00, contact data, phonebook data, messages, pictures, videos, etc. The memory Z04 may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

The power supply component Z06 provides power to the various components of the device Z00. The power component Z06 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device Z00.

The multimedia component Z08 comprises a screen between the device Z00 and the user providing an output interface. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component Z08 includes a front facing camera and/or a rear facing camera. When device Z00 is in an operating mode, such as a capture mode or a video mode, the front-facing camera and/or the rear-facing camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

The audio component Z10 is configured to output and/or input an audio signal. For example, the audio component Z10 includes a Microphone (MIC) configured to receive external audio signals when the device Z00 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signal may further be stored in the memory Z04 or transmitted via the communication component Z16. In some embodiments, the audio component Z10 further includes a speaker for outputting audio signals.

The I/O interface Z12 provides an interface between the processing component Z02 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.

The sensor assembly Z14 includes one or more sensors for providing status assessment of various aspects to the device Z00. For example, sensor assembly Z14 may detect the open/closed state of device Z00, the relative positioning of the components, such as the display and keypad of device Z00, sensor assembly Z14 may also detect a change in the position of one component of device Z00 or device Z00, the presence or absence of user contact with device Z00, the orientation or acceleration/deceleration of device Z00, and a change in the temperature of device Z00. The sensor assembly Z14 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly Z14 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly Z14 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component Z16 is configured to facilitate wired or wireless communication between device Z00 and other devices. Device Z00 may access a wireless network based on a communication standard, such as WiFi, a carrier network (such as 2G, 3G, 4G, or 5G), or a combination thereof. In an exemplary embodiment, the communication component Z16 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component Z16 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the device Z00 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described methods.

In an exemplary embodiment, a non-transitory computer readable storage medium is also provided, such as the memory Z04, comprising instructions executable by the processor Z20 of the device Z00 to perform the above method. For example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

Fig. 12 is a block diagram illustrating an apparatus for page presentation S00 according to an example embodiment. For example, the device S00 may be a server. Referring to FIG. 12, device S00 includes a processing component S20 that further includes one or more processors and memory resources represented by memory S22 for storing instructions, e.g., applications, that are executable by processing component S20. The application program stored in the memory S22 may include one or more modules each corresponding to a set of instructions. Further, the processing component S20 is configured to execute instructions to perform the page presentation method described above.

The device S00 may also include a power supply component S24 configured to perform power management of the device S00, a wired or wireless network interface S26 configured to connect the device S00 to a network, and an input-output (I/O) interface S28. The device S00 may operate based on an operating system stored in the memory S22, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, or the like.

In an exemplary embodiment, there is also provided a storage medium comprising instructions, such as the memory S22 comprising instructions, executable by the processor of the device S00 to perform the above method. The storage medium may be a non-transitory computer readable storage medium, which may be, for example, a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A page display method is characterized by comprising the following steps:

determining corresponding recommended multimedia resources and resource interaction controls for the target user account and the target multimedia resources;

and responding to the play stop operation, setting the target multimedia resource to stop playing, and displaying the recommended multimedia resource and the resource interaction control in a corresponding resource play stop page.

2. The method of claim 1, wherein determining the resource interaction control comprises:

acquiring historical behavior data of the target user account, wherein the historical behavior data comprises historical operation records of the target user account on a preset resource interaction control;

and acquiring a target resource interaction control preferred by the target user account according to the historical operating record of the target user account on a preset resource interaction control, and determining the target resource interaction control as the resource interaction control.

3. A page display method is characterized by comprising the following steps:

receiving an information acquisition request from a client, wherein the information acquisition request is generated by a target user account through a play stop operation which is carried out by the client aiming at a currently played target multimedia resource;

and determining corresponding recommended multimedia resources and resource interaction controls according to the information acquisition request, returning to the client side, and displaying the recommended multimedia resources and the resource interaction controls to the target user account by the client side.

4. A page display apparatus, comprising:

the information determining module is configured to determine corresponding recommended multimedia resources and resource interaction controls aiming at the target user account and the target multimedia resources;

and the play stop operation response module is configured to execute a response to the play stop operation, set the target multimedia resource to stop playing, and display the recommended multimedia resource and the resource interaction control in a corresponding resource play stop page.

5. A page display apparatus, comprising:

an information receiving module configured to perform receiving an information acquisition request from a client, the information acquisition request being generated by a target user account through a play stop operation performed by the client for a currently played target multimedia resource;

the information determining module is configured to execute the steps of determining corresponding recommended multimedia resources and resource interaction controls according to the information obtaining request;

6. An electronic device, comprising:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the page presentation method of any one of claims 1 to 2.

7. A server, comprising:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the page presentation method of claim 3.

8. A page presentation system, comprising an electronic device according to claim 6 and a server according to claim 7.

9. A storage medium in which instructions, when executed by a processor of an electronic device, enable the electronic device to perform the page presentation method of any one of claims 1 to 2.

10. A storage medium in which instructions, when executed by a processor of a server, enable the server to perform the page presentation method of claim 3.