CN112612949B

CN112612949B - Method and device for establishing recommended data set

Info

Publication number: CN112612949B
Application number: CN202011477718.1A
Authority: CN
Inventors: 郜姝妮
Original assignee: Beijing Dajia Internet Information Technology Co Ltd
Current assignee: Beijing Dajia Internet Information Technology Co Ltd
Priority date: 2020-12-15
Filing date: 2020-12-15
Publication date: 2024-06-11
Anticipated expiration: 2040-12-15
Also published as: CN112612949A

Abstract

The disclosure provides a method and a device for establishing a recommended data set, a recommendation method and a device, an electronic device and a computer storage medium, wherein the method comprises the following steps: by acquiring content tags of published multimedia content corresponding to an author account; and determining the author labels corresponding to the author accounts according to the content labels, sequencing the author accounts with the same author label to obtain an author account sequence corresponding to each author label, and establishing a recommendation data set according to the corresponding relation between the author labels and the author account sequence. In the method, the matching degree between the recommended content and the recommended content producer is improved, so that the account of a high-quality author which can learn and reference in the same field can be accurately provided for equipment corresponding to the account of the first author, and the content creator using the equipment can be assisted to grow.

Description

Method and device for establishing recommended data set

Technical Field

The embodiment of the disclosure relates to the technical field of computers, in particular to a method and a device for establishing a recommended data set, a recommendation method, a recommendation device, electronic equipment and a computer storage medium.

Background

With the continuous development of internet technology, recommendation systems are also continuously developed and mature, and the recommendation systems focus on how to provide more accurate and diversified recommended contents to users.

At present, in a wide application scene of a recommendation system, the recommendation system has two roles of a content consumer and a content producer, and the recommendation system is usually focused on the content consumer, obtains interests and demands of the content consumer through records such as browsing, clicking and the like generated by the content consumer, recommends personalized content for the content consumer, and improves the viscosity of the content consumer. Common methods for recommendation systems are content-based recommendation, collaborative filtering recommendation, association rule-based recommendation, and the like.

However, in the current scheme, when content recommendation is performed for a content producer, the matching degree between the recommended content and the content producer is not high, and the recommendation accuracy is reduced.

Disclosure of Invention

The embodiment of the disclosure provides a method, a device, a recommendation method, a device, electronic equipment and a computer storage medium for establishing a recommendation data set, so as to solve the problems that in the related art, the matching degree of recommendation content and a content producer is not high and the recommendation accuracy is reduced.

In a first aspect, an embodiment of the present disclosure provides a method for establishing a recommended data set, where the method includes:

acquiring content tags of the released multimedia content corresponding to the author account; the content tag is used for reflecting the category to which the issued multimedia content belongs;

Determining an author label corresponding to the author account according to the content label, wherein the author label is used for reflecting the category to which the author account belongs;

and ordering the author accounts with the same author labels to obtain an author account sequence corresponding to each author label, and establishing a recommendation data set according to the corresponding relation between the author labels and the author account sequence.

In an alternative embodiment, the sorting the author accounts with the same author tag to obtain the author account sequence corresponding to each author tag includes:

acquiring associated information of the published multimedia content corresponding to the author account, wherein the associated information is interaction information associated with the multimedia content;

And sorting the author accounts with the same author labels according to the association information to obtain an author account sequence corresponding to each author label.

In an alternative embodiment, the sorting the author accounts with the same author label according to the association information to obtain an author account sequence corresponding to each author label includes:

Determining a first score of the published multimedia content corresponding to the author account according to the associated information of the published multimedia content corresponding to the author account aiming at the author account with the same author label;

determining a second score of the author account according to the first score of the published multimedia content corresponding to the author account;

And according to the second scores, sorting the author accounts corresponding to each author label to obtain an author account sequence corresponding to each author label.

In an alternative embodiment, the associated information includes one or more of praise number, comment number, forwarding number and vermicelli number increment of the multimedia content;

The determining a first score of the published multimedia content corresponding to the author account according to the associated information of the published multimedia content corresponding to the author account comprises:

weighting and summing the associated information of the multimedia content according to the weight values corresponding to the praise number, the comment number, the forwarding number and the vermicelli number increment respectively to obtain a first score of the multimedia content;

The determining the second score of the author account according to the first score of the published multimedia content corresponding to the author account comprises the following steps:

And taking the average value of the first scores of the published multimedia contents corresponding to the author account as the second score of the author account.

In an alternative embodiment, the author account is an author account that publishes the multimedia content in a preset time range with a number greater than or equal to a preset threshold.

In an optional embodiment, the determining, according to the content tag, an author tag corresponding to the author account includes:

Determining the category corresponding to the content label;

determining a parent category of a category corresponding to the content tag in a category relation set of a tree structure;

and determining an author label corresponding to the author account according to the parent category.

In a second aspect, embodiments of the present disclosure provide a recommendation method, the method including:

Acquiring an author label of a first author account;

Determining an author account sequence to be recommended corresponding to the author label in a recommendation data set, and selecting a second author account from the author account sequence to be recommended; the recommended data set comprises a corresponding relation between an author label and an author account sequence;

and recommending the second author account to equipment corresponding to the first author account.

In an alternative embodiment, the selecting a second author account from the sequence of author accounts to be recommended includes:

acquiring a vermicelli identification set of each author account in the to-be-recommended author account sequence and a vermicelli identification set of the first author account;

Determining the association degree of each author account in the to-be-recommended author account sequence and the first author account according to the vermicelli identification set of the first author account and the vermicelli identification set of the author account in the to-be-recommended author account sequence;

And in the to-be-recommended author account sequence, taking the author account with the association degree larger than or equal to a preset association degree threshold as the second author account.

In an optional implementation manner, the determining the association degree between each author account in the to-be-recommended author account sequence and the first author account according to the vermicelli identification set of the first author account and the vermicelli identification set of the author accounts in the to-be-recommended author account sequence includes:

For each author account in the sequence of author accounts to be recommended, determining an intersection and a union between the vermicelli identification set of the author account and the vermicelli identification set of the first author account;

and taking the ratio of the intersection set and the union set as the association degree of the author account and the first author account.

In an alternative embodiment, in the recommendation data set, each author account included in the sequence of author accounts to be recommended has a corresponding second score, and the author accounts included in the sequence of author accounts to be recommended are ordered according to the second score;

The selecting a second author account from the sequence of author accounts to be recommended comprises the following steps:

And selecting an author account with a second score larger than or equal to a preset score value from the author account sequence to be recommended as the second author account.

In a third aspect, an embodiment of the present disclosure provides an apparatus for establishing a recommended data set, including:

a first acquisition module configured to acquire a content tag of the published multimedia content corresponding to the author account; the content tag is used for reflecting the category to which the issued multimedia content belongs;

The tag determining module is configured to determine an author tag corresponding to the author account according to the content tag, wherein the author tag is used for reflecting the category to which the author account belongs;

the establishing module is configured to sort the author accounts with the same author labels to obtain an author account sequence corresponding to each author label, and establish a recommendation data set according to the corresponding relation between the author labels and the author account sequence.

In an alternative embodiment, the establishing module includes:

The first acquisition sub-module is configured to acquire associated information of the published multimedia content corresponding to the author account, wherein the associated information is interaction information associated with the multimedia content;

And the sorting sub-module is configured to sort the author accounts with the same author labels according to the association information to obtain an author account sequence corresponding to each author label.

In an alternative embodiment, the sorting sub-module includes:

a first scoring unit configured to determine, for an author account having the same author tag, a first score of a published multimedia content corresponding to the author account according to associated information of the published multimedia content corresponding to the author account;

a second scoring unit configured to determine a second score of the author account according to the first score of the published multimedia content corresponding to the author account;

and the ordering unit is configured to order the author accounts corresponding to each author label according to the second score to obtain an author account sequence corresponding to each author label.

In an alternative embodiment, the associated information includes one or more of praise number, comment number, forwarding number and vermicelli number increment of the multimedia content; the first scoring unit includes:

The weighting calculation subunit is configured to carry out weighted summation on the associated information of the multimedia content according to the weight values corresponding to the praise number, the comment number, the forwarding number and the vermicelli number increment respectively to obtain a first score of the multimedia content;

the second scoring unit includes:

And the average calculation subunit is configured to take the average value of the first scores of the published multimedia contents corresponding to the author account as the second score of the author account.

In an alternative embodiment, the tag determination module includes:

A first category determination submodule, configured to determine a category corresponding to the content tag;

A second category determining sub-module, configured to determine, in a category relation set of a tree structure, a parent category of a category corresponding to the content tag;

And establishing a sub-module for determining an author label corresponding to the author account according to the father category.

In a fourth aspect, an embodiment of the present disclosure further provides a recommendation apparatus, including:

A second acquisition module configured to acquire an author tag of the first author account;

the second determining module is configured to determine a sequence of to-be-recommended author accounts corresponding to the author labels in the recommendation data set, and select a second author account from the sequence of to-be-recommended author accounts; the recommended data set comprises a corresponding relation between an author label and an author account sequence;

and the recommending module is configured to recommend the second author account to the device corresponding to the first author account.

In an alternative embodiment, the second determining module includes:

The second obtaining submodule is configured to obtain a vermicelli identification set of each author account in the to-be-recommended author account sequence and a vermicelli identification set of the first author account;

the association degree sub-module is configured to determine association degree between each author account in the to-be-recommended author account sequence and the first author account according to the vermicelli identification set of the first author account and the vermicelli identification set of the author accounts in the to-be-recommended author account sequence;

And the selecting sub-module is configured to take the author account with the association degree larger than or equal to a preset association degree threshold value as the second author account in the to-be-recommended author account sequence.

In an alternative embodiment, the association degree submodule includes:

A set calculation unit configured to determine, for each author account in the sequence of author accounts to be recommended, an intersection and a union between a fan-identified set of the author account and a fan-identified set of the first author account;

And the ratio calculating unit is configured to take the ratio of the intersection set and the union set as the association degree of the author account and the first author account.

the selecting sub-module comprises:

And the selecting sub-module is configured to select an author account with a second score being greater than or equal to a preset score value from the author account sequence to be recommended as the second author account.

In a fifth aspect, embodiments of the present disclosure further provide an electronic device, including a processor;

A memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the method of establishing a recommended data set and the steps of the recommendation method provided by the present disclosure.

In a sixth aspect, the embodiments of the present disclosure further provide a computer storage medium, which when executed by a processor of an electronic device, enables the electronic device to perform the method for creating and the method for recommending a recommended data set provided by the present disclosure.

In a seventh aspect, the disclosed embodiments also provide a computer program product comprising a computer program/instruction which, when executed by a processor, implements the method of establishing a recommended data set and the steps of the recommendation method provided by the present disclosure.

In the embodiment of the disclosure, the content label of the released multimedia content corresponding to the account of the author is obtained; determining an author label corresponding to the author account according to the content label, wherein the author label is used for reflecting the category to which the author account belongs; and ordering the author accounts with the same author labels to obtain an author account sequence corresponding to each author label, and establishing a recommendation data set according to the corresponding relation between the author labels and the author account sequence. In the embodiment of the disclosure, the author accounts with the same author label can be determined to belong to the same domain, and when the recommendation operation is specifically performed, a second author account belonging to the same domain as the first author account can be selected from the recommendation data set and recommended to the device corresponding to the first author account.

The foregoing description is merely an overview of the technical solutions of the present disclosure, and may be implemented according to the content of the specification in order to make the technical means of the present disclosure more clearly understood, and in order to make the above and other objects, features and advantages of the present disclosure more clearly understood, the following specific embodiments of the present disclosure are specifically described.

Drawings

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

FIG. 1 is a flowchart illustrating steps of a method for establishing a recommended data set according to an embodiment of the present disclosure;

FIG. 2 is a flow chart of steps of a recommendation method provided by an embodiment of the present disclosure;

FIG. 3 is a flowchart illustrating specific steps of a method for creating a recommended data set according to an embodiment of the present disclosure;

FIG. 4 is a flowchart illustrating specific steps of a recommendation method provided by an embodiment of the present disclosure;

FIG. 5 is a block diagram of an apparatus for establishing a recommendation data set provided by an embodiment of the present disclosure;

FIG. 6 is a block diagram of a recommendation device provided by an embodiment of the present disclosure;

FIG. 7 is a logical block diagram of an electronic device of one embodiment of the present disclosure;

Fig. 8 is a logic block diagram of an electronic device of another embodiment of the present disclosure.

Detailed Description

In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the technical solutions of 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 foregoing figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the disclosure described herein may be capable of operation in sequences other than those illustrated or described herein. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as detailed in the accompanying claims.

Fig. 1 is a flowchart of steps of a method for establishing a recommendation data set, which is applied to a recommendation server performing a recommendation operation and is shown in fig. 1, and the method may include steps 101-103.

Step 101, obtaining content labels of published multimedia content corresponding to an author account; the content tag is used for reflecting the category to which the released multimedia content belongs.

In one application scenario provided by the embodiments of the present disclosure, a content creator may create a corresponding author account on a multimedia content operation platform by using a device, and create and publish a multimedia content by logging in the device of the author account, where the multimedia content operation platform may display the multimedia content for viewing by a content consumer.

It should be noted that the multimedia content includes, but is not limited to, images, audio, video, text.

In particular, the multimedia content may have a corresponding content tag for reflecting the category to which the content of the multimedia content belongs. For example, the content of one video includes: running, playing football, and lifting dumbbell, a content label of 'sports' can be added for the video; in addition, based on the diversity of the multimedia content, a plurality of content tags may also be added to one multimedia content, for example, the content of one video includes: sports, cooking, singing, content tags "sports", "cooking", "show" can be added to the video, respectively.

Further, the determination of the content tag of the multimedia content may be performed manually, or may be performed by machine learning, for example, the determination may be performed by using a deep learning model, a classifier, or other models to input the multimedia content as a model, and output the content tag of the multimedia content as a model.

And 102, determining an author label corresponding to the author account according to the content label, wherein the author label is used for reflecting the category to which the author account belongs.

In an embodiment of the disclosure, a device logging in an author account may publish one or more multimedia contents, and in order to more accurately reflect the attribute of the author account, an author tag for reflecting a category to which the author account belongs may be determined based on a content tag of the published multimedia contents corresponding to the author account.

For example, an author account publishes 3 pieces of multimedia content, and content labels of the 3 pieces of multimedia content are respectively: "football", "basketball", "marathon", then the author tag "sports" may be added to the author account according to the category to which the 3 tags correspond.

Step 103, sorting the author accounts with the same author labels to obtain an author account sequence corresponding to each author label, and establishing a recommendation data set according to the corresponding relation between the author labels and the author account sequence.

In the embodiment of the disclosure, in the recommendation scenario facing the content creator, the field consistency of the multimedia content authored and released by the device of the recommender and the multimedia content authored and released by the device of the recommender needs to be considered, so that the author accounts with the same author label can be determined to be in the same field. Taking the recommendation of the content creator of the short video as an example, a content creator of the short video in the sports field is frequently released, and in order to ensure the recommendation effect on the content creator, the content creator in the sports field can be recommended. In addition, the multimedia content authored and released by the recommender and the multimedia content authored and released by the recommender can belong to the same-drop field, wherein the drop field refers to a field tree established according to the relationship between fields, for example, a content creator frequently releasing short videos in the football field and a content creator frequently releasing short videos in the basketball field can belong to the same-drop field, because the basketball field and the football field are sub-fields of the sports field, and a field tree is established in the three fields.

Therefore, the embodiment of the disclosure can determine the author accounts with the same author label as belonging to the same field and divide the author accounts into the same sequence, so as to obtain the corresponding relation between the author label and the author account sequence, and based on the corresponding relation, a recommendation data set can be established.

When the recommendation operation is specifically performed, a sequence of to-be-recommended author accounts corresponding to the author labels of the first author accounts can be selected from the recommendation data set, one or more author accounts are selected from the sequence of to-be-recommended author accounts, multimedia content issued by equipment logging in the selected author accounts is recommended to equipment corresponding to the first author accounts, and because the author accounts in the sequence of to-be-recommended author accounts and the first author accounts belong to the same field, equipment corresponding to the first author accounts can be provided with high-quality author accounts which can be learned and referred in the same field, and content authors using the equipment can be assisted to grow. The device corresponding to the first author account may be a device that logs in to the first author account. In addition, the recommendation server can automatically output the recommendation result to the equipment corresponding to the account of the creator by utilizing the recommendation data set, so that the manpower is greatly released, and the recommendation efficiency is improved.

To sum up, in the embodiments of the present disclosure, by acquiring content tags of published multimedia content corresponding to an author account; determining an author label corresponding to the author account according to the content label, wherein the author label is used for reflecting the category to which the author account belongs; and ordering the author accounts with the same author labels to obtain an author account sequence corresponding to each author label, and establishing a recommendation data set according to the corresponding relation between the author labels and the author account sequence. In the embodiment of the disclosure, the author accounts with the same author label can be determined to belong to the same domain, and when the recommendation operation is specifically performed, a second author account belonging to the same domain as the first author account can be selected from the recommendation data set and recommended to the device corresponding to the first author account.

Fig. 2 is a flowchart of steps of a recommendation method provided in an embodiment of the present disclosure, as shown in fig. 2, applied to a recommendation server performing recommendation operations, the method may include steps 201-203.

In step 201, an author tag of a first author account is obtained.

In the embodiment of the disclosure, a corresponding second author account may be selected from the recommendation data set to be recommended to the first author account, and the second author account and the first author account should belong to the same domain, so as to provide a learnable and borrowable account of a high-quality author in the same domain for a device logged in with the first author account, and assist content creators using the first author account to grow.

Specifically, in performing the recommendation operation, an author tag of the first author account may be first obtained, where the author tag determines a category to reflect the first author account.

Step 202, determining a sequence of to-be-recommended author accounts corresponding to the author labels in the recommendation data set, and selecting a second author account from the sequence of to-be-recommended author accounts.

The recommended data set comprises a corresponding relation between an author label and an author account sequence.

And step 203, recommending the second author account to the equipment corresponding to the first author account.

The device corresponding to the first author account may be a device that logs in to the first author account, and when there are multiple devices that log in to the first author account, the multiple devices may be referred to as devices corresponding to the first author account.

When the recommendation operation is specifically performed, a sequence of to-be-recommended author accounts corresponding to the author labels of the first author accounts can be selected from the recommendation data set, one or more author accounts are selected from the sequence of to-be-recommended author accounts, and the selected author accounts and the multimedia content released by the selected author accounts are recommended to the equipment corresponding to the first author accounts. The relevant description of the recommended data set may refer to steps 101 to 103, which are not repeated herein.

For example, assuming that the recommended data set includes an author account sequence 1 corresponding to an author tag "sports", an author account sequence 2 corresponding to an author tag "movie", and an author account sequence 3 corresponding to an author tag "travel", in the case that the author tag of the current first author account is "travel", one or more author accounts may be selected from the author account sequence 3 as second author accounts and recommended to the device corresponding to the first author account.

It should be noted that the plurality of author accounts in the author account sequence may be ordered (e.g., importance, priority, etc.) according to a certain rule, so as to select the second author account according to the ordering order.

To sum up, in the embodiments of the present disclosure, an author tag of a first author account is obtained; determining a sequence of to-be-recommended author accounts corresponding to the author label in the recommendation data set, and selecting a second author account from the sequence of to-be-recommended author accounts; and recommending the second author account to the device corresponding to the first author account. In the method, the writer accounts with the same writer labels can be determined to belong to the same field, when the recommendation operation is specifically performed, a second writer account belonging to the same field as the first writer account can be selected from the recommendation data set and recommended to the device corresponding to the first writer account, and as the second writer account and the first writer account belong to the same field, the matching degree between recommended content and a recommended content producer is improved, so that the device corresponding to the first writer account can be provided with a high-quality writer account which can be learned and referred in the same field more accurately, and the content creator using the device can be assisted to grow.

Fig. 3 is a flowchart of specific steps of a method for establishing a recommendation data set, applied to a recommendation server performing a recommendation operation, provided in an embodiment of the present disclosure, the method may include steps 301-306.

Step 301, obtaining content tags of published multimedia content corresponding to an author account; the content tag is used for reflecting the category to which the released multimedia content belongs.

The implementation of this step is similar to the implementation of step 101 described above, and embodiments of the present disclosure are not described in detail herein.

Step 302, determining an author label corresponding to the author account according to the content label, where the author label is used to reflect a category to which the author account belongs.

The implementation of this step is similar to the implementation of step 102 described above, and embodiments of the present disclosure are not described in detail herein.

Optionally, step 302 may also include steps 3021 to 3023.

Step 3021, determining a category corresponding to the content tag.

In this step, since the content tag is used to reflect the category to which the published multimedia content belongs, the category to which the content tag corresponds may be determined according to the content tag of the multimedia content.

Step 3022, determining a parent category of the category corresponding to the content tag in the category relation set of the tree structure.

And 3023, determining an author label corresponding to the author account according to the parent category.

Specifically, in the tree-structured category relation set, there is a relation between categories, and when one first category belongs to another second category, the first category may be considered as a sub-category of the second category, that is, the second category is a parent category of the first category.

For determining the relationship of the father category and the sub-category in the category relationship set, a Knowledge Graph (knowledgegraph/module) can be referred to, namely, the relationship of all or part of categories in the Knowledge Graph is added into the category relationship set, the Knowledge Graph is a series of various graphs for displaying the Knowledge development process and the structural relationship, the feature information corresponding to the Knowledge resource is described through a visualization technology, the feature information and the interrelation between the feature information are mined, analyzed, constructed, drawn and displayed, and the Knowledge Graph comprises the association between the categories corresponding to each field. For example, for the recommendation of the sports field, the category relation between categories of the sports field in the knowledge graph can be selected and added into the category relation set.

And constructing a category relation set of the tree structure according to the knowledge graph, and determining a parent category of the category corresponding to the content label.

For example, an author account publishes 3 multimedia contents, and content tags of the 3 multimedia contents are respectively: in the category relation set constructed according to the knowledge graph, the author label "sports" can be added for the author account according to the relation that the categories corresponding to the 3 labels all belong to the category of "sports".

Step 303, deleting the account of the author, which is issued in the preset time range and the quantity of the multimedia content is smaller than the preset threshold value.

In the disclosed embodiments, the author account may be defined as: and publishing the author accounts with the quantity of the multimedia contents larger than or equal to a preset threshold value in a preset time range.

In actual production, the device logged in with a certain account stably distributes a large amount of multimedia content for a long time, which indicates that the output of the device corresponding to the account is stable, and the recommended value of the account is higher.

The equipment corresponding to the author account stored in the recommended data set has the characteristic of stable output, particularly, the equipment corresponding to the author account frequently distributes multimedia content within a certain time period, the quantity of the distributed multimedia content is more, the equipment corresponding to the author account meeting the condition has stable multimedia content output, and the recommendation value of the multimedia content is higher.

For this purpose, an author account whose number of released multimedia contents within a preset history time range is less than or equal to a preset threshold value may be determined as an author account whose production is unstable and deleted. Alternatively, in the short video platform, the preset time range may be set to be within approximately 14 days, and the preset threshold may be set to be 4, that is, when the number of multimedia contents published by the device logged in with the author account is less than or equal to 4 in approximately 14 days, it is determined that the author account is unstable in output, and the author account needs to be deleted.

Step 304, obtaining the associated information of the published multimedia content corresponding to the author account.

Wherein the associated information is interactive information associated with the multimedia content.

In the embodiment of the disclosure, the author accounts stored in the recommendation data set also have to have the characteristic of good quality of the content of the work, and in the embodiment of the disclosure, the judgment of whether one author account has the characteristic of good quality of the content of the work can be determined by analyzing the quality of the work of the multimedia content issued by the device corresponding to the author account. Firstly, the related information of the released multimedia content corresponding to the author account can be obtained, the quality of the work of the multimedia content is determined according to analysis of the related information, and whether the author account has the characteristic of high quality of the work content is further determined.

Specifically, the associated information may include post data generated after the multimedia content is published by the multimedia operation platform, where the post data includes, but is not limited to, praise number, comment number, forwarding number, vermicelli number increment, viewing number, downloading number, and collection number of the multimedia content. The associated information is used for reflecting posterior expression of the multimedia content, wherein the posterior expression is as follows: after the multimedia content is released by the multimedia operation platform, the multimedia content faces to the approved value of the platform user and the recommended value. By comprehensively analyzing the associated data of the multimedia content, the quality score of the work of the multimedia content can be obtained.

And 305, sorting the author accounts with the same author labels according to the association information to obtain an author account sequence corresponding to each author label.

In the embodiment of the disclosure, after the quality score of each piece of released multimedia content is determined by using the associated information of the released multimedia content corresponding to each author account, the author quality score of each author account can be obtained by comprehensively analyzing the quality scores of the pieces of released multimedia content according to the author accounts. The author quality score may reflect a recommended value for one author account and an approved value for a platform user, and by ordering author accounts with the same author labels according to the author quality score, an author account sequence corresponding to each author label may be obtained.

Optionally, step 305 may include:

Step 3051, determining a first score of the published multimedia content corresponding to the author account according to the associated information of the published multimedia content corresponding to the author account aiming at the author account with the same author label.

In the embodiment of the disclosure, the associated information may include post-data generated after the multimedia content is released by the multimedia operation platform, and the associated information may be used to analyze the approved value, the recommended value, and the post-approval value of the multimedia content for the platform user after the multimedia content is released by the multimedia operation platform. By comprehensively analyzing the associated information of the multimedia content, the quality score of the work of the multimedia content can be obtained. The quality score of the work is the first score and can reflect the recommended value of a piece of multimedia content.

Optionally, the associated information includes one or more of praise number, comment number, forwarding number and vermicelli number increment of the multimedia content;

The step 3051 may include:

And A1, carrying out weighted summation on the associated information of the multimedia content according to the weight values corresponding to the praise number, the comment number, the forwarding number and the vermicelli number increment, so as to obtain a first score of the multimedia content.

In the embodiment of the disclosure, the number of praise, the number of comments, the number of forwarding, the number of vermicelli increases and the like included in the associated information have corresponding weight values, and the first score of the multimedia content can be obtained by carrying out weighted summation on the associated information of the multimedia content.

Specifically, each weight value can be set according to the actual requirement, or a principal component analysis algorithm (PCA, PRINCIPAL COMPONENT ANALYSIS) can be utilized, the PCA is a parameter-free data dimension reduction method, multiple indexes are converted into a few comprehensive indexes, and the PCA can realize the dimension reduction and principal component analysis of input data by inputting a large amount of associated information such as praise, comment number, forwarding number, vermicelli number increment and the like of sample multimedia content so as to obtain principal components of each associated information, and the principal components can be converted into the weight values of the associated information.

Step 3052, determining a second score of the author account according to the first score of the published multimedia content corresponding to the author account.

After the quality scores of the published works of each multimedia content are determined, the quality scores of the authors of each author account can be obtained by comprehensively analyzing the quality scores of the published works of the multimedia content corresponding to the author account. The author quality score is the second score, and may reflect the recommended value of an author account.

Alternatively, step 3052 may be implemented by taking the average value of the first score of the published multimedia content corresponding to the author account as the second score of the author account.

In an embodiment of the present disclosure, an average value of the first scores of the published multimedia contents corresponding to the author account may be used as the second score of the author account. Of course, a corresponding weight value may be set for each of the published multimedia contents corresponding to the author account according to the actual situation, so that a weighted average of the first scores of the published multimedia contents corresponding to the author account is used as the second score of the author account. For example, the published multimedia content corresponding to the author account includes: multimedia content 1, multimedia content 2, multimedia content 3, the weight value of multimedia content 1 is 0.4, the weight value of multimedia content 2 is 0.5, the first score is 70, the weight value of multimedia content 3 is 0.2, the first score is 90, the weighted average value of the first scores of the published multimedia content corresponding to the author account=0.4×80+0.5×70+0.2×90=85.

And step 3053, sorting the author accounts corresponding to each author label according to the second score to obtain an author account sequence corresponding to each author label.

In the embodiment of the disclosure, the author accounts corresponding to each author label may be ordered according to the order of the second score from low to high or from high to low, so as to obtain an author account sequence corresponding to each author label.

Step 306, establishing a recommended data set according to the corresponding relation between the author label and the author account sequence.

The implementation of this step is similar to the implementation of step 103 described above, and embodiments of the present disclosure are not described in detail herein.

In summary, the method for establishing a recommendation data set according to the embodiments of the present disclosure obtains content tags of published multimedia content corresponding to an author account; the content tag is used for reflecting the category of the content of the multimedia content; determining an author label corresponding to the author account according to the content label, wherein the author label is used for reflecting the category to which the author account belongs; and ordering the author accounts with the same author labels to obtain an author account sequence corresponding to each author label, and establishing a recommendation data set according to the corresponding relation between the author labels and the author account sequence. The author accounts with the same author labels can be determined to belong to the same field, and when the recommendation operation is specifically performed, a second author account belonging to the same field as the first author account can be selected from the recommendation data set and recommended to the equipment corresponding to the first author account.

Fig. 4 is a flowchart illustrating specific steps of a recommendation method provided in an embodiment of the present disclosure, as shown in fig. 4, applied to a recommendation server performing a recommendation operation, and the method may include steps 401-404.

Step 401, obtaining a content tag of the published multimedia content corresponding to the first author account.

Step 402, determining an author label corresponding to the first author account according to the content label.

The implementation of steps 401-402 is similar to the implementation of steps 101-102 described above, and embodiments of the present disclosure are not described in detail herein.

Step 403, determining an author account sequence to be recommended corresponding to the author label in the recommendation data set, and selecting a second author account from the author account sequence to be recommended.

The implementation of this step is similar to the implementation of step 202 described above, and embodiments of the present disclosure are not described in detail herein.

Optionally, in a specific implementation, step 403 may include:

Step 4031, obtaining a vermicelli identification set of each author account in the to-be-recommended author account sequence and a vermicelli identification set of the first author account, wherein the vermicelli identification set comprises at least one vermicelli identification.

In one implementation manner of the embodiment of the disclosure, the vermicelli set of the recommender's author account has high similarity with the vermicelli set of the recommenders' author accounts, that is, the recommender's accounts and the recommenders' accounts all have a large number of same vermicelli, so that the recommenders can perceive which other authors the recommenders like recently.

For this reason, based on the characteristic of the high similarity of the vermicelli sets, the embodiments of the present disclosure may obtain a vermicelli identification set of each author account in the sequence of author accounts to be recommended, and obtain a vermicelli identification set of the first author account, where the vermicelli identification set includes identifications (IDs, identity document) of all the vermicelli of the author account.

Specifically, all vermicelli IDs in a vermicelli list of an author account can be imported into a vermicelli identification set, and the vermicelli identification set is established.

Step 4032, determining the association degree between each author account in the to-be-recommended author account sequence and the first author account according to the vermicelli identification set of the first author account and the vermicelli identification set of the author accounts in the to-be-recommended author account sequence.

After the vermicelli identification sets are obtained, the vermicelli association degree between each author account in the sequence of the author accounts to be recommended and the first author account can be obtained by calculating the set distance between the vermicelli identification set of each author account in the sequence of the author accounts to be recommended and the vermicelli identification set of the first author account.

Optionally, step 4032 may include:

And C1, determining an intersection and a union between the vermicelli identification set of the author account and the vermicelli identification set of the first author account for each author account in the to-be-recommended author account sequence.

And C2, taking the ratio of the intersection set to the union set as the association degree of the author account and the first author account.

Specifically, the vermicelli identification set can be regarded as a character string group, and the set distance between the vermicelli identification set of each author account and the vermicelli identification set of the first author account in the to-be-recommended author account sequence can be determined by calculating the character string group distance between the two vermicelli identification sets and the vermicelli identification set of the first author account.

Specifically, each vermicelli identifier in the vermicelli identifier set may be in a character string form, and the disclosure may calculate a character string distance by using a Jaccard similarity coefficient algorithm, that is, determine an intersection and a union between the vermicelli identifier set of the author account in the to-be-recommended author account sequence and the vermicelli identifier set of the first author account, and use a ratio of the intersection and the union as a degree of association between the author account and the first author account in the to-be-recommended author account sequence. For example, if the set of fan-identifications of one author account in the sequence of author accounts to be recommended is A and the set of fan-identifications of the first author account is B, then thisWherein, the numerator represents the length of the intersection of the vermicelli identification set A and the vermicelli identification set B, and the denominator represents the length of the union of the vermicelli identification set A and the vermicelli identification set B.

It should be noted that, the method for calculating the association degree is not limited to the Jaccard similarity coefficient algorithm, and a string group similarity calculation method such as a hamming distance calculation algorithm, a Dice distance calculation algorithm, an edit distance calculation algorithm, and the like may be adopted.

Step 4033, in the to-be-recommended author account sequence, using the author account with the association degree greater than or equal to the preset association degree threshold as the second author account.

When the recommendation is specifically performed, a preset association threshold value can be set according to actual requirements, and in the to-be-recommended author account sequence, the author accounts with association degree larger than or equal to the preset association threshold value are determined to be accounts with higher vermicelli similarity with the first author account, and the author accounts are used as the second author account for recommendation.

Optionally, in another specific implementation manner, in the recommendation data set, each author account included in the author account sequence has a corresponding second score, and the author accounts included in the author account sequence are ordered according to the second score, and step 403 may also be implemented by selecting, from the to-be-recommended author account sequence, an author account with a second score greater than or equal to a preset score value as the second author account.

In another implementation manner of the embodiment of the disclosure, in the recommendation data set, each of the author accounts included in the author account sequence has a corresponding second score for reflecting the quality of the content of the work, and the author accounts included in the author account sequence are ordered according to the second score, when the recommendation is specifically performed, a preset score value can be set according to actual requirements, in the to-be-recommended author account sequence, the author accounts with the second score being greater than or equal to the preset score value are determined to be accounts with higher quality of the content of the work than the first author account, and the author accounts are recommended as the second author accounts.

Step 404, recommending the second author account to the device corresponding to the first author account.

Specifically, the embodiment of the disclosure may recommend the information of the ID, the access link, the published multimedia content, etc. of the second author account to the device corresponding to the first author account.

To sum up, in the embodiments of the present disclosure, an author tag of a first author account is obtained; determining a sequence of to-be-recommended author accounts corresponding to the author label in the recommendation data set, and selecting a second author account from the sequence of to-be-recommended author accounts; and recommending the second author account to the device corresponding to the first author account. According to the method and the device for recommending the content, the author accounts with the same author labels can be determined to belong to the same field, when the recommending operation is specifically carried out, the second author account which belongs to the same field as the first author account can be selected from the recommending data set and recommended to the device corresponding to the first author account, and as the second author account and the first author account belong to the same field, the matching degree between recommended content and a recommended content producer is improved, so that the device corresponding to the first author account can be provided with the account of a high-quality author which can be learned and referred in the same field more accurately, and the content creator using the device can be assisted to grow.

Fig. 5 is a block diagram of an apparatus for establishing a recommended data set according to an embodiment of the disclosure, as shown in fig. 5, including:

a first obtaining module 501 configured to obtain a content tag of the published multimedia content corresponding to an author account; the content tag is used for reflecting the category to which the issued multimedia content belongs;

A tag determination module 502, configured to determine, according to the content tag, an author tag corresponding to the author account, where the author tag is used to reflect a category to which the author account belongs;

the establishing module 503 is configured to sort the author accounts with the same author label, obtain an author account sequence corresponding to each author label, and establish a recommendation data set according to the corresponding relationship between the author label and the author account sequence.

Optionally, the establishing module 503 includes:

Optionally, the sorting sub-module includes:

Optionally, the associated information includes one or more of praise number, comment number, forwarding number and vermicelli number increment of the multimedia content; the first scoring unit includes:

the second scoring unit includes:

Optionally, the author account is an author account that publishes the multimedia content in a preset time range, wherein the number of the multimedia content is greater than or equal to a preset threshold.

Optionally, the tag determining module includes:

In summary, the device for establishing a recommendation data set provided in the embodiments of the present disclosure obtains content tags of published multimedia content corresponding to an author account; determining an author label corresponding to the author account according to the content label, wherein the author label is used for reflecting the category to which the author account belongs; and ordering the author accounts with the same author labels to obtain an author account sequence corresponding to each author label, and establishing a recommendation data set according to the corresponding relation between the author labels and the author account sequence. In the embodiment of the disclosure, the author accounts with the same author label can be determined to belong to the same domain, and when the recommendation operation is specifically performed, a second author account belonging to the same domain as the first author account can be selected from the recommendation data set and recommended to the device corresponding to the first author account.

Fig. 6 is a block diagram of a recommendation device according to an embodiment of the present disclosure, as shown in fig. 6, including:

A second obtaining module 601 configured to obtain a target author tag of the first author account;

A second determining module 602 configured to determine a sequence of to-be-recommended author accounts corresponding to the author tag in the recommendation data set, and select a second author account from the sequence of to-be-recommended author accounts; the recommended data set comprises a corresponding relation between an author label and an author account sequence;

optionally, the second determining module 602 includes:

optionally, the association degree submodule includes:

Optionally, in the recommendation data set, each author account included in the sequence of author accounts to be recommended has a corresponding second score, and the author accounts included in the sequence of author accounts to be recommended are ordered according to the second scores;

the selecting sub-module comprises:

And a recommending module 603 configured to recommend the second author account to a device corresponding to the first author account.

In summary, the recommending device provided in the embodiment of the present disclosure obtains the author tag of the first author account; determining a sequence of to-be-recommended author accounts corresponding to the author label in the recommendation data set, and selecting a second author account from the sequence of to-be-recommended author accounts; and recommending the second author account to the device corresponding to the first author account. According to the method and the device for recommending the content, the author accounts with the same author labels can be determined to belong to the same field, when the recommending operation is specifically carried out, the second author account which belongs to the same field as the first author account can be selected from the recommending data set and recommended to the device corresponding to the first author account, and as the second author account and the first author account belong to the same field, the matching degree between recommended content and a recommended content producer is improved, so that the device corresponding to the first author account can be provided with the account of a high-quality author which can be learned and referred in the same field more accurately, and the content creator using the device can be assisted to grow.

Fig. 7 is a block diagram of an electronic device 700, according to an example embodiment. For example, the electronic device 700 may be a mobile phone, computer, digital broadcast terminal, messaging device, game console, tablet device, medical device, exercise device, personal digital assistant, or the like.

Referring to fig. 7, an electronic device 700 may include one or more of the following components: a processing component 702, a memory 704, a power component 706, a multimedia component 708, an audio component 710, an input/output (I/O) interface 712, a sensor component 714, and a communication component 716.

The processing component 702 generally controls overall operation of the electronic device 700, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 702 may include one or more processors 720 to execute instructions to perform all or part of the steps of the methods described above. Further, the processing component 702 can include one or more modules that facilitate interaction between the processing component 702 and other components. For example, the processing component 702 may include a multimedia module to facilitate interaction between the multimedia component 708 and the processing component 702.

The memory 704 is used to store various types of data to support operations at the electronic device 700. Examples of such data include instructions for any application or method operating on the electronic device 700, contact data, phonebook data, messages, pictures, multimedia content, and so forth. The memory 704 may be implemented by any type or combination of volatile or nonvolatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.

The power supply component 706 provides power to the various components of the electronic device 700. Power supply components 706 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for electronic device 700.

The multimedia component 708 includes a screen between the electronic device 700 and the user that provides 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 input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only the boundary of a touch or slide action, but also the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 708 includes a front-facing camera and/or a rear-facing camera. When the electronic device 700 is in an operational mode, such as a shooting mode or a multimedia content 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 focal length and optical zoom capabilities.

The audio component 710 is for outputting and/or inputting audio signals. For example, the audio component 710 includes a Microphone (MIC) for receiving external audio signals when the electronic device 700 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may be further stored in the memory 704 or transmitted via the communication component 716. In some embodiments, the audio component 710 further includes a speaker for outputting audio signals.

The I/O interface 712 provides an interface between the processing component 702 and peripheral interface modules, which may be a keyboard, click wheel, buttons, etc. These buttons may include, but are not limited to: homepage button, volume button, start button, and lock button.

The sensor assembly 714 includes one or more sensors for providing status assessment of various aspects of the electronic device 700. For example, the sensor assembly 714 may detect an on/off state of the electronic device 700, a relative positioning of the components, such as a display and keypad of the electronic device 700, a change in position of the electronic device 700 or a component of the electronic device 700, the presence or absence of a user's contact with the electronic device 700, an orientation or acceleration/deceleration of the electronic device 700, and a change in temperature of the electronic device 700. The sensor assembly 714 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 714 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 714 may also include an acceleration sensor, a gyroscopic sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 716 is employed to facilitate communication between the electronic device 700 and other devices, either wired or wireless. The electronic device 700 may access a wireless network based on a communication standard, such as WiFi, an operator network (e.g., 2G, 3G, 4G, or 5G), or a combination thereof. In one exemplary embodiment, the communication component 716 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 716 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 electronic device 700 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, microcontrollers, microprocessors, or other electronic elements for implementing the methods provided by the embodiments of the disclosure.

In an exemplary embodiment, a non-transitory computer storage medium is also provided, such as a memory 704 including instructions executable by the processor 720 of the electronic device 700 to perform the above-described method. For example, the non-transitory computer storage medium may be ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

Fig. 8 is a block diagram of an electronic device 800, according to an example embodiment. For example, the electronic device 800 may be provided as a server. Referring to fig. 8, the electronic device 800 includes a processing component 822 that further includes one or more processors and memory resources, represented by memory 832, for storing instructions, such as application programs, executable by the processing component 822. The application programs stored in memory 832 may include one or more modules each corresponding to a set of instructions. Further, the processing component 822 is configured to execute instructions to perform the methods provided by the embodiments of the present disclosure.

The electronic device 800 may also include a power component 826 configured to perform power management of the electronic device 800, a wired or wireless network interface 850 configured to connect the electronic device 800 to a network, and an input-output (I/O) interface 858. The electronic device 800 may operate based on an operating system stored in the memory 832, such as Windows Server, mac OS XTM, unixTM, linuxTM, freeBSDTM, or the like.

The disclosed embodiments also provide a computer program product comprising computer programs/instructions which, when executed by a processor, implement the methods as provided by the present disclosure.

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 disclosure is intended to cover any adaptations, uses, or adaptations of the disclosure following the general 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 is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method of establishing a recommended data set, the method comprising:

Ordering the author accounts with the same author labels to obtain an author account sequence corresponding to each author label, and establishing a recommendation data set according to the corresponding relation between the author labels and the author account sequence;

The ordering of the author accounts with the same author labels to obtain an author account sequence corresponding to each author label comprises the following steps:

Acquiring associated information of the published multimedia content corresponding to the author account, wherein the associated information is interaction information associated with the multimedia content; wherein, the associated information comprises post data generated after the multimedia content is released by the multimedia operation platform; the associated information comprises one or more of praise number, comment number, forwarding number and vermicelli number increment of the multimedia content;

according to the association information, sorting the author accounts with the same author labels to obtain an author account sequence corresponding to each author label;

And according to the association information, sorting the author accounts with the same author label to obtain an author account sequence corresponding to each author label, including:

2. The method of claim 1, wherein determining the first score of the published multimedia content corresponding to the author account based on the associated information of the published multimedia content corresponding to the author account comprises:

3. The method of claim 1, wherein the author account is an author account that publishes the multimedia content in a preset time frame by an amount greater than or equal to a preset threshold.

4. The method of claim 1, wherein determining the author tag corresponding to the author account based on the content tag comprises:

Determining the category corresponding to the content label;

5. A recommendation method, the method comprising:

Acquiring an author label of a first author account;

Recommending the second author account to equipment corresponding to the first author account;

In the to-be-recommended author account sequence, taking an author account with the association degree being greater than or equal to a preset association degree threshold value as the second author account;

In the recommendation data set, each author account included in the sequence of author accounts to be recommended has a corresponding second score, and the author accounts included in the sequence of author accounts to be recommended are ordered according to the second scores;

the author accounts included in the to-be-recommended author account sequence are ranked according to the second score, and the method comprises the following steps: determining a first score of the published multimedia content corresponding to the author account according to the associated information of the published multimedia content corresponding to the author account aiming at the author account with the same author label; determining a second score of the author account according to the first score of the published multimedia content corresponding to the author account; according to the second scores, the author accounts corresponding to each author label are sequenced, and an author account sequence corresponding to each author label is obtained; the associated information is interaction information associated with the multimedia content; wherein, the associated information comprises post data generated after the multimedia content is released by the multimedia operation platform; the associated information comprises one or more of praise number, comment number, forwarding number and vermicelli number increment of the multimedia content;

6. The method of claim 5, wherein determining the association of each author account in the sequence of author accounts to be recommended with the first author account based on the set of fan identifications of the first author account and the set of fan identifications of the author accounts in the sequence of author accounts to be recommended comprises:

7. A device for establishing a recommended data set, the device comprising:

The establishing module is configured to sort the author accounts with the same author labels to obtain an author account sequence corresponding to each author label, and establish a recommendation data set according to the corresponding relation between the author labels and the author account sequence;

Comprising the following steps:

the first acquisition sub-module is configured to acquire associated information of the published multimedia content corresponding to the author account, wherein the associated information is interaction information associated with the multimedia content; wherein the associated information comprises one or more of praise number, comment number, forwarding number and vermicelli number increment of the multimedia content;

the sorting sub-module is configured to sort the author accounts with the same author labels according to the association information to obtain an author account sequence corresponding to each author label;

the sequencing submodule comprises:

8. The apparatus of claim 7, wherein the first scoring unit comprises:

the second scoring unit includes:

9. The apparatus of claim 7, wherein the author account is an author account that publishes the multimedia content in a preset time frame by an amount greater than or equal to a preset threshold.

10. The apparatus of claim 7, wherein the tag determination module comprises:

11. A recommendation device, the device comprising:

a recommending module configured to recommend the second author account to a device corresponding to the first author account;

The second determining module includes:

The selecting submodule is configured to take the author account with the association degree larger than or equal to a preset association degree threshold value as the second author account in the author account sequence to be recommended;

the author accounts included in the author account sequence to be recommended are ranked according to the second score; comprising the following steps: a first scoring unit configured to determine, for an author account having the same author tag, a first score of a published multimedia content corresponding to the author account according to associated information of the published multimedia content corresponding to the author account;

The sorting unit is configured to sort the author accounts corresponding to each author label according to the second scores to obtain an author account sequence corresponding to each author label;

the selecting sub-module comprises:

12. The apparatus of claim 11, wherein the relevancy sub-module comprises:

13. 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 method of any one of claims 1 to 6.

14. A computer storage medium, characterized in that instructions in the computer storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the method of any one of claims 1 to 6.

15. A computer program product comprising computer programs/instructions which, when executed by a processor, implement the method of any of claims 1-6.