CN112861015A

CN112861015A - Account associated information acquisition method and device in application program and electronic equipment

Info

Publication number: CN112861015A
Application number: CN201911185771.1A
Authority: CN
Inventors: 朱顺; 李鑫; 郑东
Original assignee: Beijing Dajia Internet Information Technology Co Ltd
Current assignee: Beijing Dajia Internet Information Technology Co Ltd
Priority date: 2019-11-27
Filing date: 2019-11-27
Publication date: 2021-05-28

Abstract

The disclosure relates to a method and a device for acquiring account associated information in an application program and electronic equipment, wherein the method comprises the following steps: generating a directed graph according to the concern relationship among the accounts in the application program; acquiring a social relation chain of each account in the application program according to the attention relation and the social closeness degree among the accounts recorded by the directed information, wherein the social relation chain is used for expressing: account information for accounts having a social association with a corresponding account; determining the social association degree between the accounts in the application program based on the obtained social relationship chain of the accounts; and screening out the associated accounts of the accounts from other accounts of the application program based on the determined social association degree between the accounts. Therefore, by the technical scheme provided by the embodiment of the disclosure, the incidence relation among the accounts of the application program can be determined, so that an operator of the application program can recommend content with rich types for the accounts according to the incidence relation among the accounts in the application program.

Description

Account associated information acquisition method and device in application program and electronic equipment

Technical Field

The present application relates to the field of multimedia technologies, and in particular, to a method and an apparatus for acquiring account association information in an application program, and an electronic device.

Background

With the development of computer technology and network technology, a large number of applications are continuously available, and users can register accounts in the applications and log in. After the user logs in the application program through the registered account, the operator of the application program can analyze the basic information filled when the user registers the account and the user behavior data corresponding to the account to obtain the behavior habit of the user, and recommend the content meeting the user requirement for the account so as to be convenient for the user to check.

In the process of implementing the invention, the inventor finds that at least the following problems exist in the related art:

when an operator of an application recommends content for a user, the content is generally recommended for the account only according to behavior habits of the user, but not according to social attributes of the user, that is, association relations among the accounts, so that in the related art, the content recommended for the account by the operator of the application is single in type.

Disclosure of Invention

In order to solve the technical problem that the content type recommended by an operator of an application program for an account is single in the related art, the disclosure provides a method and a device for acquiring account associated information in the application program and electronic equipment, and 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 method for acquiring account association information in an application program, including:

generating a directed graph according to an attention relation between accounts in an application program, wherein the attention relation is used for representing an actively or passively established social association relation between the accounts, the directed graph has directed information used for marking the attention relation, and the directed information is also used for recording the social closeness degree of the two accounts with the attention relation;

and acquiring a social relation chain of each account in the application program according to the attention relation and the social closeness degree among the accounts of the directed information record, wherein the social relation chain is used for representing: account information for accounts having a social association with a corresponding account;

determining the social association degree between the accounts in the application program based on the obtained social relationship chain of the accounts;

and screening out the associated accounts of the accounts from other accounts of the application program based on the determined social association degree between the accounts.

Optionally, the obtaining a social relationship chain of each account in the application program according to the concern relationship and the social closeness degree between the accounts of the directional information record includes:

for any account in the application program, determining a random walk sequence set corresponding to the account by using a random walk mode according to the attention relationship and the social contact degree between the account and other accounts recorded by the directed information, wherein the random walk sequence set obtained by determining the random walk mode comprises: a plurality of random walk sequences composed of account information, each random walk sequence being: determining a random walk sequence formed by the next account information corresponding to the previous account information according to the attention relationship and the social contact degree among the accounts, wherein the account corresponding to the next account information is as follows: a socially close account corresponding to the previous account information;

for any account in the application program, determining a random walk sequence in a random walk sequence set corresponding to the account as a social relation chain of the account.

Optionally, for any account in the application program, constructing a random walk sequence set corresponding to the account by using random walks according to the attention relationship and the social affinity between the account and other accounts recorded by the directed information record, where the method includes:

determining a second account which is socially close to a first account according to the attention relationship and the social close degree between the first account and other accounts, and sequentially placing account information of the first account and account information of the second account into an empty account information sequence, wherein the first account is any account in the application program;

determining a third account socially close to the second account according to the social close degree between the second account and the other updated accounts, and putting the account information of the third account into the account information sequence, wherein the other updated accounts are: the accounts except the account corresponding to the account information in the account information sequence;

correspondingly, according to the sequence of the account information put into the account information sequence, sequentially determining: the account corresponding to the last account information put into the account information sequence and the account with close social contact are obtained until the number of the account information put into the account information sequence is a first preset number;

and determining a second preset number of account information sequences as a random walk sequence set corresponding to the first account.

Optionally, the determining, based on the obtained social relationship chain of the account, a social association degree between the accounts in the application program includes:

converting each account information in a first social relationship chain of the first account into a first sub-vector, and converting each account information in a second social relationship chain of other accounts in the application program into a second sub-vector;

forming a first vector by using first sub-vectors corresponding to each account information in the first social relation chain; forming a second vector by using second sub-vectors corresponding to the account information in the second social relation chain;

and calculating the distance between the first vector and each second vector to obtain the social association degree of the first account and each other account.

Optionally, the method further includes:

recommending videos related to a fourth account for each account, wherein the fourth account is: the account other than the account with direct social association relation with the account in the corresponding association account;

alternatively, the first and second electrodes may be,

recommending videos related to a fifth account for each account, wherein the fifth account is as follows: and the account currently in live broadcast is selected from the corresponding associated accounts.

Optionally, each vertex in the directed graph corresponds to account information of one account, and each edge in the directed graph is used to characterize: two accounts corresponding to the account information corresponding to the two vertexes of the edge have an attention relationship, each edge in the directed graph has an edge weight, and the edge weights are used for representing: and the social closeness degree between the two accounts corresponding to the account information corresponding to the two vertexes of the edge.

According to a second aspect of the embodiments of the present disclosure, there is provided an apparatus for acquiring account related information in an application, including:

the directed graph generating module is configured to execute generating a directed graph according to an attention relation between accounts in an application program, wherein the attention relation is used for representing an actively or passively established social association relation between the accounts, the directed graph has directed information used for marking the attention relation, and the directed information is also used for recording the social closeness degree of the two accounts with the attention relation;

a social relationship chain obtaining module configured to perform obtaining of a social relationship chain of each account in the application program according to the attention relationship and the social closeness degree between the accounts recorded with the directional information, where the social relationship chain is used to represent: account information for accounts having a social association with a corresponding account;

the social association degree determining module is configured to execute determining the social association degree between the accounts in the application program based on the obtained social association chain of the accounts;

and the associated account determining module is configured to execute screening of associated accounts of the accounts from other accounts of the application program based on the determined social association degree between the accounts.

Optionally, the social relationship chain obtaining module includes:

a random walk sequence set determining unit, configured to execute, for any account in the application program, determining a random walk sequence set corresponding to the account by using a random walk manner according to the attention relationship and social closeness between the account and another account recorded by the directed information, where the random walk sequence set determined by the random walk manner includes: a plurality of random walk sequences composed of account information, each random walk sequence being: determining a random walk sequence formed by the next account information corresponding to the previous account information according to the attention relationship and the social contact degree among the accounts, wherein the account corresponding to the next account information is as follows: a socially close account corresponding to the previous account information;

and the social relation chain determining unit is configured to execute that for any account in the application program, the random walk sequence in the random walk sequence set corresponding to the account is determined as the social relation chain of the account.

Optionally, the random walk sequence set determining unit is configured to perform:

Optionally, the social association degree determining module is configured to perform:

Optionally, the apparatus further comprises:

a video recommendation module configured to perform recommendation of a video related to a fourth account for each account, the fourth account being: the account other than the account with direct social association relation with the account in the corresponding association account; or recommending videos related to a fifth account for each account, wherein the fifth account is as follows: and the account currently in live broadcast is selected from the corresponding associated accounts.

According to a third aspect of the 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 implement the method for acquiring account association information in an application program according to the first aspect.

According to a fourth aspect of the embodiments of the present disclosure, there is provided a storage medium, where instructions executed by a processor of an electronic device enable the electronic device to execute the method for acquiring account association information in an application program according to the first aspect.

According to a fifth aspect of the embodiments of the present disclosure, there is provided a computer program product containing instructions, which when run on a computer, causes the computer to implement the method for acquiring account association information in an application program according to the first aspect.

According to the technical scheme provided by the embodiment of the disclosure, when the account association information in the application program is acquired, the directed graph is generated according to the concern relationship among the accounts in the application program; acquiring a social relationship chain of each account in the application program according to the attention relationship and the social closeness degree among the accounts with directed information records in the directed graph; and determining the social association degree between the accounts in the application program based on the obtained social association chain of the accounts, and finally screening the associated accounts of the accounts from other accounts of the application program based on the determined social association degree between the accounts.

Therefore, according to the technical scheme provided by the embodiment of the disclosure, when the associated account of one account in the application program is determined, the social relationship chain of the account can be accurately determined according to the attention relationship and the social closeness degree of the account and other accounts in the application program, and further the social relationship degree of the account and other accounts is determined according to the social relationship chain of the account, so that the associated account associated with the account can be accurately screened out. After the association account of each account in the application program is determined, the association relationship between each account of the application program is determined, so that an operator of the application program can recommend content with rich types for each account according to the association relationship of each account in the application program.

Drawings

FIG. 1 is a flow diagram illustrating a method for obtaining account association information in an application according to an example embodiment;

FIG. 2 is a flowchart illustrating one embodiment of step S12 in the embodiment of FIG. 1;

FIG. 3 is a flowchart of an embodiment of step S121 in the embodiment shown in FIG. 2;

FIG. 4 is a flowchart illustrating one embodiment of step S13 in the embodiment of FIG. 1;

FIG. 5 is a flow diagram illustrating another method for obtaining account association information in an application according to an illustrative embodiment;

FIG. 6 is a block diagram illustrating an account associated information obtaining apparatus in an application according to an example embodiment;

FIG. 7 is a block diagram illustrating an electronic device in accordance with an exemplary embodiment;

fig. 8 is a block diagram illustrating an account associated information acquiring apparatus in an application according to an exemplary 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.

In order to solve the technical problem that the content type recommended by an operator of an application program for an account is single in the related art, the disclosure provides a method and a device for acquiring account associated information in the application program and electronic equipment.

First, a method for acquiring account related information in an application provided by the embodiment of the present disclosure is described in detail below.

It should be noted that an execution subject of the method for acquiring account related information in an application provided by the embodiment of the present disclosure is an apparatus for acquiring account related information in an application, where the apparatus for acquiring account related information in an application runs in an electronic device, and the electronic device may be a server.

Fig. 1 is a flowchart illustrating a method for acquiring account association information in an application according to an exemplary embodiment, and as shown in fig. 1, the method may include the following steps.

In step S11, a directed graph is generated from the attention relationship between the accounts in the application.

The concern relationship is used for representing a social association relationship actively or passively established between the accounts, the directed graph has directed information used for marking the concern relationship, and the directed information is also used for recording the social closeness degree of the two accounts with the concern relationship.

Specifically, any two accounts in the application program can concern each other. When one of the two accounts is interested in the other account, the two accounts have an interest relationship, so that a social association relationship is established between the two accounts. For an account actively paying attention to another account, the account actively establishes a social association relationship; likewise, for another account that is of interest, the other account has a social relationship established passively.

The electronic device may generate a directed graph according to attention relationships between accounts in the application. In a directed graph, directed information can be used to record the attention relationship between any two accounts, as well as the social closeness of two accounts with an attention relationship. Wherein the social closeness may be used to represent the degree of attention of two accounts having an attention relationship.

For example, two accounts with an attention relationship are: account a and account B. The social closeness of account a and account B may be used as: utilizing the click times of the video published by the account A to the account B to account; or, the watching duration of the video published by the account A to the account B is measured by the ratio and the like. It is understood that a higher ratio of the number of clicks or a higher ratio of the viewing time indicates a higher degree of social contact between the account a and the account B.

For clarity of description of the scheme, the directed graph will be explained in detail in the following embodiments.

In step S12, a social relationship chain of each account in the application is obtained according to the attention relationship and the social closeness degree between the accounts recorded with the directional information.

Wherein the social relationship chain is used to represent: account information for accounts having a social association with a corresponding account;

specifically, because the directed information records the attention relationship and the social contact degree between the accounts in the application program, for any account in the application program, the social relationship chain of the account can be acquired according to the attention relationship and the social contact degree between the account and other accounts.

The social relationship chain of an account may be: account information for accounts having a direct social relationship or an indirect social relationship with the account. It will be appreciated that an account having a direct social relationship with the account may be: an account having a direct attention relationship with the account; an account having an indirect social relationship with the account may be: an account having an indirect focus relationship with the account.

For clarity of description of the solution, a detailed description will be given in the following embodiments of "obtaining a social relationship chain of each account in an application according to a concern relationship and a social closeness degree between accounts with directional information records".

In step S13, based on the obtained social relationship chain of the accounts, a social association degree between the accounts in the application program is determined.

It will be appreciated that for any two accounts in an application, if the social relationship of the two accounts is more similar, this indicates that the social relationship of the two accounts is higher. If the social relationship chains of two accounts are more dissimilar, i.e., the gap is larger, the social relationship between the two accounts is lower. Therefore, after obtaining the social relationship chain of each account in the application program, the social relationship degree between each account in the application program can be determined based on the obtained social relationship chain of the account.

For clarity of the description of the solution, in the following embodiments, a specific implementation manner of determining the social association degree between the accounts in the application program based on the obtained social relationship chain of the accounts is described in detail.

In step S14, the associated accounts of the accounts are screened from the other accounts of the application based on the determined social association degree between the accounts.

If the social association degree between the two accounts is higher, the probability that the two accounts are the associated accounts is higher; similarly, a lower degree of social association between two accounts indicates a lower probability that the two accounts are associated accounts. Thus, after determining the social association degree between the accounts, the associated accounts of the accounts may be determined based on the determined social association degree between the accounts.

Specifically, for any account in the application, an account having a social association degree with the account greater than a preset social association degree may be determined as an associated account of the account. The preset association degree can be determined according to actual conditions, and the size of the preset association degree is not specifically limited in the embodiment of the invention.

On the basis of the embodiment shown in fig. 1, a directed graph will be explained in detail in the following embodiment for clarity of the description of the scheme.

In one embodiment, each vertex in the directed graph corresponds to account information of one account, and each edge in the directed graph is used for characterizing: two accounts corresponding to the account information corresponding to the two vertexes of the edge have an attention relationship, each edge in the directed graph has an edge weight, and the edge weight is used for representing: and the social closeness degree between the two accounts corresponding to the account information corresponding to the two vertexes of the edge.

In this embodiment, each vertex in the directed graph may have a vertex identifier for identifying an account, that is, the vertex identifier may be account information, and the account information may be an ID number or a name of the account. The embodiment of the present disclosure does not specifically limit the account information.

Assuming that there is a concern relationship between two accounts, an edge may be used to connect two vertices corresponding to the two accounts; instead, the two vertices are not connected. It is understood that the edges may or may not be directional.

In practical application, an account with account information a is assumed, and an account with account information B is concerned, so that a directed edge from a vertex corresponding to account information a to a vertex corresponding to account information B may be formed in a directed graph.

If the account information is B and the account information is a is concerned, a directed edge from a vertex corresponding to the account information B to a vertex corresponding to the account information a may be formed in the directed graph.

If the account with account information a pays attention to the account with account information B and the account with account information B pays attention to the account with account information a, that is, the account with account information a and the account with account information B pay attention to each other, at this time, the edge connecting the vertex corresponding to account information a and the vertex corresponding to account information B may be an edge without direction.

And, each edge in the directed graph has an edge weight that characterizes: account information corresponding to two vertexes of the edge, and social closeness degree between the two corresponding accounts.

For example, assume that account information a focuses on account information B.

As an optional implementation manner, the edge weight of the edge connecting the vertex corresponding to the account information a and the vertex corresponding to the account information B may be: the account information is the account of A, and the number of clicks of the video released by the account of which the account information is B is smaller than that of the video released by the account of which the account information is B.

As another optional implementation manner, the edge weight of the edge connecting the vertex corresponding to the account information a and the vertex corresponding to the account information B may be: the account information is the account A, and the watching time length of the video published by the account with the account information B is in proportion.

As another optional implementation manner, the edge weight of the edge connecting the vertex corresponding to the account information a and the vertex corresponding to the account information B may be: and the weighted value obtained by weighted calculation of the click number ratio and the watching time length ratio.

It will be appreciated that edge weights are typically numbers between 0 and 1. In order to improve the accuracy of the edge weight, the edge weight may be calculated in a normalized manner. For example, if an account with account information a pays attention to three accounts, namely an account with account information B, an account with account information C, and an account with account information D, the edge weight of the edge connecting the vertex corresponding to account information a and the vertex corresponding to account information B may be: the number of clicks of videos released by an account with account information A on an account with account information B is divided by the total number of clicks of videos released by three accounts, namely the account with account information A on the account with account information B, the account with account information C and the account with account information D.

Of course, the edge weight may also be estimated by a model, and the calculation method of the edge weight in the embodiment of the present invention is not particularly limited.

Therefore, the directed graph provided by the embodiment can accurately record the attention relationship among the accounts and the social closeness degree of the two accounts with the attention relationship.

In an alternative embodiment, a specific implementation manner of obtaining the social relationship chain of each account in the application program according to the attention relationship and the social closeness degree between the accounts with the directional information records is as follows.

Specifically, step S12 in the embodiment shown in fig. 1 may include the following two steps, as shown in fig. 2, which are respectively: s121 and S122.

And S121, for any account in the application program, determining a random walk sequence set corresponding to the account by using a random walk mode according to the attention relationship and the social contact degree between the account and other accounts recorded by the directed information.

The random walk sequence set determined by the random walk mode comprises: a plurality of random walk sequences composed of account information, each random walk sequence being: according to the attention relationship and the social contact degree among the accounts, determining the subsequent account information corresponding to the previous account information to form a random walk sequence, wherein the account corresponding to the subsequent account information is as follows: a socially close account corresponding to the previous account information.

Random walk (random walk) is also called random walk, and the core concept means that conservation quantities carried by any irregular walker correspond to a diffusion transport law respectively, are close to Brownian motion, and are ideal mathematical states of the Brownian motion. For any account in the application program, according to the attention relationship and the social contact degree between the account and other accounts recorded by the directed information, a plurality of random walk sequences can be generated in a random walk mode, and the plurality of random walk sequences form a random walk sequence set. The number of random walk sequences included in the random walk sequence set may be determined according to an actual situation, and the length of each random walk sequence may also be determined according to the actual situation.

As an implementation manner of the embodiment of the present disclosure, S121 may include the following 4 steps, as shown in fig. 3, respectively: s1211 to S1214.

S1211, according to the attention relationship and the social contact degree between the first account and other accounts, determining a second account which is in social contact with the first account, and sequentially placing account information of the first account and account information of the second account into an empty account information sequence, wherein the first account is any account in the application program.

Specifically, the first account may have an attention relationship with one account or a plurality of accounts, and when the first account has an attention relationship with only one account, the second account is: an account having an attention relationship with the first account. When the first account and the plurality of accounts have the attention relationship, one account is randomly selected from the plurality of accounts according to the social contact degree of the first account and the plurality of accounts, and the account is determined to be the second account.

After determining the first account and the second account, the account information of the first account and the account information of the second account may be sequentially placed in the empty account information sequence.

S1212, according to the social contact degree between the second account and the other updated accounts, determining a third account which is socially close to the second account, and putting the account information of the third account into the account information sequence, wherein the other updated accounts are: and accounts except the account corresponding to the account information in the account information sequence.

Specifically, the second account may have an attention relationship with one account or a plurality of accounts other than the first account, and when the second account has an attention relationship with only one account, the third account is: an account having an attention relationship with the second account. When the second account has concern relations with the plurality of accounts, one account is randomly selected from the plurality of accounts according to the social contact degree of the second account and the plurality of accounts, and the second account is determined to be a third account. After determining as the third account, the account information of the third account may be placed into the sequence of account information.

S1213, correspondingly, according to the order of the account information put into the account information sequence, sequentially determining: and the account corresponding to the account information placed in the account information sequence last, namely the account with close social contact, is added until the number of the account information placed in the account information sequence is a first preset number.

Specifically, after the account information of the third account is placed in the account information sequence, an account that is socially close to the third account is determined according to the third account and the updated other accounts, and the determined account information of the account is placed in the account information sequence. Until the amount of the account information put into the account information sequence is a first preset amount, the first preset amount may be determined according to an actual situation, which is not specifically limited by the present disclosure.

And S1214, determining the account information sequences with the second preset number as a random walk sequence set corresponding to the first account.

Specifically, a second preset number of account information sequences may be determined in a random walk manner, and the second preset number of account information sequences may be determined as a random walk set corresponding to the first account.

For example, in the directed graph, a first vertex corresponding to first account information of a first account is x, and when a random walk sequence set is generated for the first account, starting from the first vertex x, a second vertex y connected to the first vertex x by an edge is selected at random with an edge weight of the edge including the first vertex x as a probability, and starting from the second vertex y, a third vertex z connected to the second vertex y by an edge is selected at random with an edge weight of the edge including the second vertex y as a probability, and repeating the steps to obtain a random walk sequence x → y → z → … having a length of a predetermined length L. Repeating the process for a preset number of r times to obtain a random walk sequence set of the first account, wherein the random walk sequence set comprises: r random walk sequences of length L.

It can be understood that, for an account corresponding to each vertex in the directed graph, the random walk sequence set corresponding to the account may be generated by using the above method, so as to obtain the random walk sequence set corresponding to each account in the application program.

S122, for any account in the application program, determining a random walk sequence in the random walk sequence set corresponding to the account as a social relation chain of the account.

In step S121, the random walk sequence set corresponding to each account is determined, and for the random walk sequence set corresponding to each account, the random walk sequence in the random walk sequence set is determined according to the attention relationship and the social association degree between the account and another account, so that the random walk sequence in the random walk sequence set can be determined as the social relationship chain of the account.

Therefore, by the technical scheme provided by the embodiment, the social relationship chain of each account in the application program can be accurately determined according to the attention relationship and the social closeness degree among the accounts recorded by the directed information.

In an optional embodiment, a specific implementation manner of determining the social association degree between the accounts in the application program based on the obtained social relationship chain of the accounts is as follows.

Specifically, S13 in the embodiment shown in fig. 1 may include the following three steps, as shown in fig. 4, which are S131 to S133, respectively.

S131, converting each account information in the first social relationship chain of the first account into a first sub-vector, and converting each account information in the second social relationship chain of other accounts in the application program into a second sub-vector.

Wherein, the word2vec algorithm can be used to map each word to a vector, and can be used to represent the relation between words and words. In order to accurately determine the social association degree between different accounts in the subsequent steps, each account information in the first social association chain can be converted into a first sub-vector by using a word2vec algorithm; and converting each account information in the second social relationship chain of the other accounts in the application program into a second sub-vector. In the word2vec algorithm, except for dimension, window size (how large window is used to construct training samples), and skip _ gram (a mode of predicting construction samples of other words in a window by using a central word), parallel numbers need to be specified, other word2vec algorithm parameters such as learning rate learning _ rate and the like can all be default values of the word2vec algorithm. As can be seen, the dimension of the vector converted from each account information in the first social relationship chain may be preset. The present disclosure is not particularly limited thereto.

S132, forming a first vector by using first sub-vectors corresponding to each account information in the first social relation chain; and forming a second vector by using the second sub-vectors corresponding to the account information in the second social relation chain.

Specifically, since the first social relationship chain includes a plurality of account information, after each account information included in the first social relationship chain is converted into the first sub-vector, a plurality of first sub-vectors corresponding to the plurality of account information may form the first vector. Similarly, since the second social relationship chain also includes a plurality of account information, after each account information included in the second social relationship chain is converted into the second sub-vector, a plurality of second sub-vectors corresponding to the plurality of account information may form the second vector.

And S133, calculating the distance between the first vector and each second vector to obtain the social association degree between the first account and each other account.

By calculating the distance between the first vector and each second vector, the distance between the first social relationship chain of the first account and the second social relationship chain of each other account can be determined, and the distance between the first social relationship chain and the second social relationship chain of each other account can reflect the social relevance of the first account and each other account. It is understood that the smaller the distance between a first vector and a second vector is, the higher the social association degree between the first account and the account corresponding to the second vector is, otherwise, the lower the social association degree between the first account and the account corresponding to the vector is.

Specifically, there are various ways to calculate the distance between the first vector and the second vector.

The first mode is as follows: and calculating cosine values of the first vector and the second vector, wherein the larger the cosine values of the two vectors are, the closer the distance between the two vectors is.

The second way is: and calculating Euclidean distance between the first vector and the second vector, and determining the calculated Euclidean distance as the distance between the first vector and the second vector.

The third mode is as follows: and calculating the distance between the first vector and the second vector by utilizing a distributed calculation framework Hadoop, or obtaining the distance between the first vector and the second vector by adopting an algorithm with the complexity of O (n).

Of course, the manner of calculating the distance between the first vector and the second vector is not limited to the above three manners, and this disclosure does not specifically limit this.

Therefore, by the technical scheme provided by the embodiment, the social association degree between the accounts in the application program can be accurately determined through the social relationship chain of each account.

In order to recommend videos with rich types to accounts, an embodiment of the present disclosure further provides a method for acquiring account association information in an application program, as shown in fig. 5, the method includes the following steps:

in step S51, a directed graph is generated from the attention relationship between the accounts in the application.

In step S52, a social relationship chain of each account in the application is obtained according to the attention relationship and the social closeness degree between the accounts recorded with the directional information.

In step S53, based on the obtained social relationship chain of the accounts, a social association degree between the accounts in the application program is determined.

In step S54, the associated accounts of the accounts are screened from the other accounts of the application based on the determined social association degree between the accounts.

Since steps S51 to S54 are the same as steps S11 to S14, in the embodiment shown in fig. 1, steps S11 to S14 have been described in detail, and thus, steps S51 to S54 are not described again.

In step S55, a video related to the fourth account is recommended for each account, or a video related to the fifth account is recommended for each account.

Wherein the fourth account is: the account other than the account with the direct social association relation with the account in the corresponding association account; the five accounts are: and corresponding to the account currently live in the associated accounts.

It will be appreciated that if two accounts are associated accounts, then there is a high probability that one of the two accounts will like to see a video associated with the other account, and therefore, when a video is recommended for an account, the account associated with that account may be used. For example, the first account and the second account are associated accounts, and if the first account generally likes watching idol dramas and the second account recently watches basketball games, the basketball games can be recommended to the first account, so that the types of videos watched by the first account are more comprehensive.

In addition, in one embodiment, in the process of recommending videos, it is considered that an account with a direct social relationship exists in the accounts associated with one account, that is, since videos published by the accounts directly concerned by the account can be directly viewed by the account, in order to recommend more diversified videos to the account, videos related to other accounts except the account with the direct social relationship with the account in the associated accounts can be recommended to the account.

In another embodiment, in order to enable the account to view the latest video being live, the real-time index of the recommendation system may determine which accounts are live and recommend the video live in the account currently being live in the associated accounts for the account.

Therefore, according to the technical scheme provided by the embodiment of the disclosure, when the associated account of one account in the application program is determined, the social relationship chain of the account can be accurately determined according to the attention relationship and the social closeness degree of the account and other accounts in the application program, and further the social relationship degree of the account and other accounts is determined according to the social relationship chain of the account, so that the associated account associated with the account can be accurately screened out. After the association account of each account in the application program is determined, the association relationship between each account of the application program is determined, so that an operator of the application program can recommend videos with rich types for each account according to the association relationship of each account in the application program.

According to a second aspect of the embodiments of the present disclosure, there is provided an apparatus for acquiring account related information in an application program, as shown in fig. 6, including:

the directed graph generating module 610 is configured to execute generating a directed graph according to an attention relationship between accounts in an application program, where the attention relationship is used to represent an actively or passively established social association relationship between the accounts, the directed graph has directed information used to label the attention relationship, and the directed information is also used to record the social closeness degree of two accounts having the attention relationship.

In an optional implementation manner, each vertex in the directed graph corresponds to account information of one account, and each edge in the directed graph is used for characterizing: two accounts corresponding to the account information corresponding to the two vertexes of the edge have an attention relationship, each edge in the directed graph has an edge weight, and the edge weights are used for representing: and the social closeness degree between the two accounts corresponding to the account information corresponding to the two vertexes of the edge.

Therefore, the directed graph provided by the embodiment can accurately record the attention relationship among the accounts and the social contact degree of the two accounts with the attention relationship.

A social relationship chain obtaining module 620, configured to perform obtaining, according to the attention relationship and the social closeness degree between the accounts recorded by the directional information, a social relationship chain of each account in the application program, where the social relationship chain is used to represent: account information for accounts having a social association with a corresponding account;

a social association degree determining module 630, configured to execute determining a social association degree between the accounts in the application program based on the obtained social association chain of the accounts;

and the associated account determining module 640 is configured to execute screening out associated accounts of the accounts from other accounts of the application program based on the determined social association degree between the accounts.

In an alternative embodiment, the social relationship chain obtaining module 620 may include:

In an optional embodiment, the random walk sequence set determination unit is configured to perform:

In an alternative embodiment, the social relevance degree determining module is configured to perform:

In an alternative embodiment, the apparatus may further comprise:

Therefore, according to the technical scheme provided by the embodiment of the disclosure, when the associated account of one account in the application program is determined, the social relationship chain of the account can be accurately determined according to the attention relationship and the social closeness degree of the account and other accounts in the application program, and further the social relationship degree of the account and other accounts is determined according to the social relationship chain of the account, so that the associated account associated with the account can be accurately screened out. After the association account of each account in the application program is determined, the association relationship between each account of the application program is determined, so that an operator of the application program can recommend content with rich types to each account according to the association relationship of each account in the application program, and the content can be a video.

According to a third aspect of the embodiments of the present disclosure, there is provided an electronic apparatus, as shown in fig. 7, including:

a processor 710;

a memory 720 for storing the processor-executable instructions;

Fig. 8 is a block diagram illustrating an apparatus 800 for acquiring account-related information in an application according to an exemplary embodiment. For example, the apparatus 800 may be provided as a server. Referring to FIG. 8, the apparatus 800 includes a processing component 822, which further includes one or more processors, and memory resources, represented by memory 832, for storing instructions, such as applications, that are executable by the processing component 822. The application programs stored in memory 832 may include one or more modules that each correspond to a set of instructions. Further, the processing component 822 is configured to execute the instructions to execute the account associated information obtaining method in any of the application programs described in the first aspect.

The device 800 may also include a power component 826 configured to perform power management of the device 800, a wired or wireless network interface 850 configured to connect the device 800 to a network, and an input/output (I/O) interface 858. The apparatus 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.

It should be noted that the account or user information referred to in the present application is collected by the user or account authorization and analyzed by subsequent processing.

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. An account associated information acquisition method in an application program is characterized by comprising the following steps:

2. The method according to claim 1, wherein the obtaining a social relationship chain of each account in the application according to the attention relationship and the social closeness degree between the accounts of the directed information record comprises:

3. The method according to claim 2, wherein for any account in the application, constructing a random walk sequence set corresponding to the account by using random walks according to the attention relationship and social closeness between the account and other accounts recorded by the directed information record comprises:

4. The method of claim 3, wherein determining the social association degree between the accounts in the application program based on the obtained social association chain of the accounts comprises:

5. The method according to any one of claims 1 to 4, further comprising:

alternatively, the first and second electrodes may be,

6. The method of any of claims 1 to 4, wherein each vertex in the directed graph corresponds to account information for one account, and wherein each edge in the directed graph is used to characterize: two accounts corresponding to the account information corresponding to the two vertexes of the edge have an attention relationship, each edge in the directed graph has an edge weight, and the edge weights are used for representing: and the social closeness degree between the two accounts corresponding to the account information corresponding to the two vertexes of the edge.

7. An apparatus for acquiring account related information in an application, comprising:

8. The apparatus of claim 7, wherein the social relationship chain obtaining module comprises:

9. 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 account association information acquisition method in the application program according to any one of claims 1 to 6.

10. A storage medium in which instructions, when executed by a processor of an electronic device, enable the electronic device to execute the method of acquiring account association information in an application program according to any one of claims 1 to 6.