WO2019019368A1

WO2019019368A1 - Method and device for selecting network account

Info

Publication number: WO2019019368A1
Application number: PCT/CN2017/104504
Authority: WO
Inventors: 王健宗; 吴天博; 黄章成; 肖京
Original assignee: 平安科技（深圳）有限公司
Priority date: 2017-07-24
Filing date: 2017-09-29
Publication date: 2019-01-31
Also published as: CN107566244B; CN107566244A

Abstract

Disclosed are a method and device for selecting a network account, applicable to the technical field of networks. The method comprises: acquiring, in a network platform, a user entity connection corresponding to each candidate account (S101); based on an out-degree vector in the network platform where each candidate account is located, and the user entity connection, determining a propagation path corresponding to each candidate account (S102); by means of a pre-set propagation probability calculation algorithm, obtaining the propagation probability corresponding to each propagation path (S103); according to the propagation path corresponding to each candidate account and the propagation probability corresponding to the propagation path, determining a radiation measurement value of each candidate account (S104); and selecting N candidate accounts with maximum radiation measurement values as selected accounts (S105). By the method, the problem of inaccurate selection results of existing account selection methods is solved.

Description

Method for selecting network account and device thereof

This application claims the priority of the Chinese Patent Application entitled "A Method for Selecting a Network Account and Its Equipment", filed on July 27, 2017, with the application number of 201710605542.5, the entire contents of which are incorporated by reference. In this application.

Technical field

The present application belongs to the field of network technologies, and in particular, to a method for selecting a network account and a device thereof.

Background technique

With the rapid development of the network platform, each network platform contains a large number of user accounts, and information exchange and information dissemination between the account and the account through the network platform. For example, an account forwards a piece of information through the network platform, and the fan of the account can receive the information posted by the account through the network platform because the fan of the account pays attention to the account, and if the fan of the user forwards the message again, attention is paid to The other accounts of the user's fans can also receive the information through the forwarding operation of the fan of the account, thereby realizing the dissemination of information. It can be seen that each user account has a certain influence range, that is, radiation capability, due to the network social relationship in the network platform, such as concern and attention. Therefore, each user account can be regarded as a propagation node. How to select an account with strong radiation ability as the propagation node will affect the efficiency and scope of information dissemination.

The existing account selection mainly takes the radiation capacity of the user account in a specific network platform as the basis for selection. However, most users have independent accounts in multiple network platforms, and the results of the existing account selection methods are selected. Not accurate enough.

technical problem

In view of this, the embodiment of the present application provides a method for selecting a network account and a device thereof, so as to solve the problem that the selection result of the existing account selection manner is not accurate enough.

Technical solution

A first aspect of the embodiment of the present application provides a method for selecting a network account, where the method for selecting a network account includes:

Obtaining, in the network platform, a user entity connection corresponding to each candidate account; wherein the user entity connection is: if there is a user account in another network platform that is the same as the user corresponding to the candidate account, the user account and the user account There is one of the user entity connections between the candidate accounts;

Determining a propagation path corresponding to each of the candidate accounts based on an out-of-vector vector in the network platform where the candidate account is located and the user entity connection; wherein the degree-out vector is: information in the network platform The direction of propagation is directed to the vector of other user accounts by the candidate account;

Obtaining a propagation probability corresponding to each of the propagation paths by using a preset propagation probability calculation algorithm;

Determining a radiation metric value of each of the candidate accounts according to the propagation path corresponding to each of the candidate accounts and a propagation probability corresponding to the propagation path;

The N candidate accounts with the largest radiation metric value are selected as the selected account, and the N is a positive integer greater than or equal to 1.

Beneficial effect

A method for selecting a network account and a device thereof provided by embodiments of the present application have the following beneficial effects:

In this embodiment, the user entity connection corresponding to the candidate account is obtained, and according to the user entity connection and the outreach vector of each candidate account in the network platform, the propagation path included in each candidate account and the corresponding propagation probability are determined, and then each is obtained. The radiation metric of the candidate account. It can be seen that the radiation metric in the embodiment of the present application depends not only on the influence of the network platform where the candidate account is located, but also on the influence of the network platform where other accounts are the same as the entity user of the candidate account, thereby making the radiation metric more Accurately characterize the user's true radiation capabilities. For example, the information published by the user on the microblog can be simultaneously published on the WeChat friend circle, and the user's microblog account can have cross-platform information through the physical user in addition to the corresponding radiation capability in the microblog. Spread and radiate to users of other network platforms. Therefore, the embodiment of the present application is not limited to solving the problem of maximizing the radiation capability in a single network platform, but selecting the candidate account with the largest radiation metric value as the selected account according to the comprehensive radiation capability of the candidate account in multiple platforms. , improve the accuracy of the results of account selection, and then improve the efficiency of information dissemination and the scope of dissemination.

DRAWINGS

FIG. 1 is a flowchart of implementing a method for selecting a network account according to an embodiment of the present application;

FIG. 2 is a flowchart of a specific implementation of a method for selecting a network account S102 according to another embodiment of the present application;

3 is a social topology diagram of a network platform user account provided by an embodiment of the present application;

4 is a flowchart of a specific implementation of a method for selecting a network account S103 according to another embodiment of the present application;

FIG. 5 is a structural block diagram of a device for selecting a network account according to an embodiment of the present application;

FIG. 6 is a schematic diagram of a terminal device according to an embodiment of the present application.

Embodiments of the invention

In order to make the objects, technical solutions and advantages of the present application more clear, the following is in conjunction with the accompanying drawings and embodiments. The application is further detailed. It is understood that the specific embodiments described herein are merely illustrative of the application and are not intended to be limiting.

In this embodiment, the user entity connection corresponding to the candidate account is obtained, and according to the user entity connection and the outreach vector of each candidate account in the network platform, the propagation path included in each candidate account and the corresponding propagation probability are determined, and then each is obtained. The radiation metric of the candidate account solves the problem that the selection result of the existing account selection method is not accurate enough.

In the embodiment of the present application, the execution subject of the process is a device for selecting a network account. The selection device of the network account can be used as an independent selection device, and is connected to a plurality of network platform servers to obtain account information of the corresponding network platform; or can be used as a function module of a network platform server to perform an account selection operation. Directly retrieve relevant content in the network platform server, and obtain account information of other network platforms through the network platform server. It should be noted that, in this embodiment, the network account specifically refers to a user account registered in each network platform. FIG. 1 is a flowchart showing an implementation of a method for selecting a network account according to an embodiment of the present application, which is described in detail as follows:

In S101, a user entity connection corresponding to each candidate account is obtained in a network platform, where the user entity connection is: if there is a user account in another network platform that is the same as the user corresponding to the candidate account, There is one of the user entity connections between the user account and the candidate account.

In this embodiment, the selection device of the network account may determine the rule by using a preset user entity connection, and obtain the user entity connection corresponding to each candidate account in the network platform. It should be noted that the candidate account is any user account included in the network platform.

In this embodiment, different users can use the physical user as the information transmission medium to spread the information of the respective platforms through the physical user through the platform. If the two accounts have the same physical users, the two accounts are between the two accounts. It can be considered that there is a message propagation channel, that is, the above-mentioned user entity connection. Therefore, before determining the radiation metrics for each candidate account, it is necessary to determine their corresponding user entity connections, correlating the radiation capabilities of each platform.

Optionally, in this embodiment, the preset user entity connection determining rule includes: performing matching according to registration information and/or account information of each account; if the matching degree between the two accounts is greater than a preset threshold And determining that there is a user entity connection between the two accounts. Since the registration information of the user will have certain similarity when the user registers on the network platform, by matching the registration information and/or the account information between each network account, it can be determined whether the physical users corresponding to the two accounts are the same. The registration information includes but is not limited to the following one or a combination of at least two: a registration name, a registration password, a registered email address, a registered mobile phone number, etc.; the account information includes but is not limited to the following one or a combination of at least two: an account name , nickname, login password, login gesture, avatar, friend information, location information, etc.

For example, User A's registration habit is that the account username contains: David, so the account name in the WeChat is: David1, and the account name in Weibo is David9, therefore, the network account selection device In In the process of identifying the connection of the user entity, the matching degree of the two account usernames is high, so it is determined that the entity users corresponding to the two accounts are the same, and there is a user entity connection between the two. Of course, in the matching operation, in order to improve the accuracy of the recognition, the matching degree of the plurality of information will be considered, and the matching degree between each user account is determined according to the matching degree of the plurality of pieces of information.

Optionally, in this embodiment, the preset user entity connection determining rule includes: determining, according to the IP address logged in by each user account, whether there is a user entity connection between the two accounts. Specifically, the IP address registered by the user account is the IP address with the highest frequency of use when the user account logs in. Since the login using the same IP address means that the login is performed through the same network port or the same mobile terminal, the probability that both belong to the same user is also high. Therefore, the IP address registered by the user can be used as a judgment condition for the connection of the user entity.

Optionally, in this embodiment, the preset user entity connection determining rule includes: acquiring an avatar image of each user account, and determining a similarity of the avatar image according to a preset image recognition algorithm.

Optionally, before the step S101, the method further includes: the selecting device of the network account receiving the selection range determining information sent by the user, wherein the selecting range determining information includes at least one network platform identifier. Before the network account selection operation is performed, the selection device first needs to determine the network platform for which the selection operation is directed. For example, a user needs to select three user accounts with the highest radiation capacity in Weibo, Douban, and three network platforms as the selected account. At this time, the user will send a selection range to the selected device of the network account. Determining information, wherein the selection range determining information will include Weibo, Douban, and three network platform identifiers. After receiving the determination information of the selected range, the network account selection device uses the user accounts included in the three network platforms as the candidate accounts, and performs the related operations of S101.

It should be noted that if the user has defined the account selection range, that is, the network platform for the current selection operation, when the user entity connection identification is performed, only the network platform that needs to be considered includes other user accounts that are the same as the candidate account user. Therefore, the calculation amount of the selection device of the network account is reduced, and the selection efficiency is improved.

In S102, determining, according to an out-of-vector vector in each network platform where the candidate account is located, and the user entity connection, determining a propagation path corresponding to each of the candidate accounts; wherein the degree-out vector is: The information dissemination direction in the network platform is directed to the vector of other user accounts by the candidate account.

In this embodiment, because the user entity connection and the combination of the out-of-vectors can form a channel for information dissemination, that is, the propagation path in this embodiment, the device for selecting the network account will be based on the user acquired in S101. The physical connection, and the out-of-vector vector in the network platform, determine the propagation path corresponding to each candidate account, and determine the radiation range of the network user according to the propagation path. In theory, if there is a propagation path between account A and account B, it means that account A can transmit the published information to account B through the propagation path, that is, the radiation range of account A will cover account B, so the propagation path The amount of the path and the length of the path can be used to characterize the radiation capability of the candidate account.

It should be noted that the propagation path in this embodiment is a vector, that is, has a propagation direction. If Account A has a propagation path radiating to Account B, it cannot be determined that Account B also has a propagation path to Account A. The user entity connection is a two-way vector, that is, if there is a user entity connection between the account A1 and the account A2, it means that the account A1 can transmit information to the account A2, and can also accept the information sent by the account A2.

In this embodiment, each network platform has a corresponding account social relationship topology, and the account social relationship topology is composed of information propagation vectors between users, wherein the information propagation vector can be divided into an outgoing vector and an input. Degree vector. The exit vector of account A refers to the vector whose information is transmitted from account A to account B. In this case, account A is the publisher of the information, account B is the recipient of the information, and the entry degree vector of account A is Refers to the vector in which the direction of information dissemination is directed from account B to account A. In this case, account A is the recipient of the information and account B is the publisher of the information. Since it is necessary to determine the radiation capability of each candidate account in the embodiment of the present application, that is, when the candidate account is the publisher of the information, its influence range in each network platform, therefore, the candidate account will be determined according to the outreach vector of the network platform. The propagation path.

For example, if a Weibo account has 30 fans and the Weibo account focuses on 100 other users, the Weibo account will have 30 out-of-vectors pointing to 30 fan accounts and 100 in-degree vectors respectively. From 100 other users who are concerned about it.

In S103, a propagation probability corresponding to each of the propagation paths is obtained by a preset propagation probability calculation algorithm.

In this embodiment, the selection device of the network account indicates the radiation capability of each propagation path by the magnitude of the propagation probability of the propagation path. The propagation probability corresponding to each propagation path refers to the probability that the information published by the origin account of the propagation path can be delivered to the end account of the propagation path. The selection device of the network account determines the propagation probability corresponding to each propagation path by using a preset propagation probability calculation algorithm.

Optionally, in this embodiment, the preset propagation probability calculation algorithm may be: determining a corresponding propagation probability according to the number of propagation nodes included in the propagation path. For example, if a propagation path passes through 5 propagation nodes, the propagation probability corresponding to the propagation path is 1/5=20%; if another propagation path passes through 3 propagation nodes, the propagation probability corresponding to the propagation path It is 1/3.

Optionally, in this embodiment, the preset propagation probability calculation algorithm may be: determining a corresponding propagation probability according to a propagation probability of each propagation sub-path included in the propagation path.

In S104, a radiation metric value of each of the candidate accounts is determined according to the propagation path corresponding to each of the candidate accounts and a propagation probability corresponding to the propagation path.

In this embodiment, after obtaining the propagation probability corresponding to each propagation path, the selection device of the network account determines the radiation metric value of each candidate account according to the propagation path corresponding to each candidate account and its corresponding propagation probability.

In this embodiment, when the selection means of the network account determines the radiation metric value of each candidate account, it will execute Related operations of S105.

In this embodiment, the network account selection device may superimpose the propagation probabilities of the respective propagation paths, and use the superimposed values as the radiation metric values; or determine each of the propagation paths according to the propagation length of the propagation path and the corresponding propagation probability. The radiation metric of the propagation path, and then the radiation metric of the candidate account is determined according to the radiation metric of each propagation path.

Optionally, in this embodiment, the corresponding weighting coefficient may be determined according to the number of propagation paths corresponding to each candidate account, and the radiation metric value of the candidate account is determined according to the weighting coefficient and the propagation probability of each path. For example, when the candidate path corresponds to a propagation path less than 30, the weighting coefficient is 1, and when the candidate account corresponds to a propagation path greater than 30, the weighting coefficient is 2. At this time, if a candidate account corresponds to 20 propagation paths, the corresponding weighting coefficient is 1, and the radiation metric value of the candidate account is determined according to the weighting coefficient and the propagation probability of the 20 propagation paths. Since the number of propagation paths is large, it indicates that the candidate account can radiate a wider range. Conversely, a candidate account with fewer propagation paths has a smaller radiation range. Therefore, according to the number of different propagation paths, the corresponding weighting coefficient is determined. It can more accurately reflect the true radiation ability of different candidates. It should be noted that the correspondence relationship of the weighting coefficients may be set by the user, or may be set according to the default configuration of the selected device of the network account.

In S105, the N candidate accounts with the largest radiation metric value are selected as the selected account, and the N is a positive integer greater than or equal to 1.

In this embodiment, the network account selection device selects N candidate accounts with the largest radiation metric value as the selected account according to the radiation metric values of the respective candidate accounts, wherein the N value can be set according to the user's needs.

It can be seen that the method for selecting a network account provided by the embodiment of the present application determines the user entity connection corresponding to the candidate account, and determines each candidate account according to the user entity connection and the outreach vector of each candidate account in the network platform. The included propagation paths and corresponding propagation probabilities, which in turn are derived from the radiation metrics for each candidate account. It can be seen that the radiation metric in the embodiment of the present application depends not only on the influence of the network platform where the candidate account is located, but also on the influence of the network platform where other accounts are the same as the entity user of the candidate account, thereby making the radiation metric more Accurately characterize the user's true radiation capabilities. For example, the information published by the user on the microblog can be simultaneously published on the WeChat friend circle, and the user's microblog account can have cross-platform information through the physical user in addition to the corresponding radiation capability in the microblog. Spread and radiate to users of other network platforms. Therefore, the embodiment of the present application is not limited to solving the problem of maximizing the radiation capability in a single network platform, but selecting the candidate account with the largest radiation metric value as the selected account according to the comprehensive radiation capability of the candidate account in multiple platforms. , improve the accuracy of the results of account selection, and then improve the efficiency of information dissemination and the scope of dissemination.

FIG. 2 is a flowchart of a specific implementation of a method for selecting a network account S102 according to an embodiment of the present application. As shown in FIG. 2, in the method for selecting a network account provided in this embodiment, S102 includes The following steps are detailed below:

Further, as another embodiment of the present application, the determining, according to the egress vector in the topology of the network platform where the candidate account is located, and the user entity connection, determining that the propagation path corresponding to each candidate account is specifically :

In S201, the candidate account is used as a starting point of a propagation path, a user account other than the candidate account is used as a termination point of the propagation path, and the propagation path propagation node, and the outreach vector and The user entity is connected as a propagation subpath, and the propagation path corresponding to the candidate account is determined.

In this embodiment, the propagation path will be composed of a starting point, a terminating point, a propagating node, and a propagating sub-path. It is to be said that the propagation node does not include the propagating node for the propagation path between the two user accounts. Wherein, the starting point of the propagation path is a candidate account, the propagation sub-path included in the propagation path is an out-of-vector vector and a user entity connection, and other user accounts are used as a termination point of the propagation path and a propagation node, and the above-mentioned various elements are combined to obtain The propagation path corresponding to the candidate account.

For example, FIG. 3 shows a social topology diagram of a network platform user account provided by this embodiment. Wherein, T1, T2, and T3 are user accounts in the network platform 1, and F1, F2, and F3 are user accounts in the network platform 2. In this embodiment, the candidate accounts are T1, T2, T3, F1, F2, and F3. Taking T1 as a candidate account as an example, since there is a user entity connection between T1 and F1, T1 has an out-of-order vector pointing to T2 and T3, and F1 has an out-of-order vector pointing to F2 and F3. Therefore, for T1, the corresponding propagation path is six, namely: T1-T2; T1-T3; T1-F1; T1-F1-F3; T1-F1-F2 and T1-F1-F2-F3 . Therefore, by traversing and combining the various elements included above, all propagation paths of the candidate account can be obtained.

In the embodiment of the present application, the propagation path not only includes each channel in the propagation process, but also includes each propagation node, thereby facilitating determination of the radiated account information of the propagation path. On the other hand, in addition to the out-of-vector vector in the network platform, the propagation sub-path also considers the connection of user entities, which can more accurately reflect the actual information interaction between platforms and improve the accuracy of the propagation path.

FIG. 4 is a flowchart of a specific implementation of a method for selecting a network account S103 according to another embodiment of the present application. As shown in FIG. 4, with respect to the previous embodiment, a method for selecting a network account S103 provided in this embodiment includes the following steps, which are as follows:

Further, as another embodiment of the present application, the propagation path includes at least one of the propagation sub-paths;

The obtaining, by using a preset propagation probability calculation algorithm, the propagation probability corresponding to each of the propagation paths specifically includes:

In S401, if the propagation sub-path is the out-degree vector, the propagation probability of the propagation sub-path is determined according to the degree of the degree of the corresponding degree of the out-of-range vector.

In this embodiment, the propagation path will include at least one propagation sub-path. Since the propagation sub-path includes two cases, namely, an out-of-vector vector and a user entity connection, it will be based on two different types of propagation sub-paths. Count Calculate its corresponding propagation probability. If the propagation sub-path is an out-of-vector, the related operation of S401 is performed; if the propagation sub-path is a user entity connection, the related operation of S402 is performed.

In this embodiment, if the propagation sub-path is an out-degree vector, the propagation probability of the propagation path may be determined according to the degree of the degree of the degree corresponding to the out-of-degree vector. Because each user has a social relationship with the network, such as attention and attention, each social relationship has a certain degree of adhesion, and the degree of adhesion is the degree of degree of engagement and the degree of penetration. For example, the microblog user A and the microblog user B are fans of the microblog user C, and the microblog user C has two outgoing vectors pointing to the microblog user A and the microblog user B respectively. Weibo user A often posts, comments, or likes under the information posted by Weibo user C, while Weibo user B rarely performs the above-mentioned interactive operations. It can be seen that Weibo user C points to Weibo user A. The degree of degree is higher, that is, the adhesion between Weibo user A and Weibo user C is higher, and information dissemination is easier; relatively, Weibo user B and Weibo user C have lower adhesion, Although the microblog user C is concerned, the information released may be ignored, so that the purpose of information dissemination cannot be achieved. At this time, the probability of the spread vector of the microblog user C pointing to the microblog user B is low. It can be seen that the propagation probability of the propagation sub-path can be determined according to the degree of the out-of-range vector.

In this embodiment, the selection device of the network account may determine the propagation probability of the propagation sub-path as the out-of-vector vector according to the degree of the degree of the out-of-degree vector and the scaling algorithm of the degree of the pre-existing degree and the propagation probability. For example, the scaling algorithm is a correspondence conversion table, and each degree of extent range corresponds to a propagation probability.

In S402, if the propagation sub-path is connected to the user entity, the matching probability of the candidate account and the user account corresponding to the user entity connection is used as a propagation probability of the connection of the user entity.

In this embodiment, if the propagation sub-path is a user entity connection, the determination rule of the user entity connection propagation probability is adopted, and the propagation probability of the propagation sub-path is determined. Specifically, in this embodiment, the propagation probability of the propagation sub-path is the matching degree between the candidate account corresponding to the entity connection and the user account. Since the user entity connection is a network account selection device according to the preset user entity connection determination rule, and the candidate account and other user accounts correspond to the same entity user, it is also determined according to the matching degree of the two. Therefore, whether the information of one account can be transmitted to another account of another platform is whether the judgment of the connection with the user entity is accurately related. Since the physical users are the same, whether each account receives information and what kind of information is received is determined by the physical user. If the user obtains the information on a certain platform, it will affect the account transmitted to other platforms. Therefore, if the matching degree between the candidate account and the user account of another network platform is 100%, it means that the corresponding entity users are definitely the same, and the probability of being propagated to the user account with which the user entity is connected should also be 100%. That is, the propagation probability of the propagation sub-path is 100%.

In S403, a propagation probability corresponding to the propagation path is obtained based on propagation probabilities of all the propagation sub-paths included in the propagation path.

In this embodiment, since the radiation capability of each propagation path will be propagated by the propagation path and constitutes the The out-of-vector vector of the path is determined by the propagation capability of the user entity connection. Therefore, the propagation probability corresponding to the propagation path is determined based on the propagation probability of each propagation sub-path included in the propagation path.

Optionally, in this embodiment, the method for selecting a network account may set a maximum number of effective propagation sub-paths. For a propagation path containing more propagation sub-paths, the subsequent propagation probability will be less after the accumulation, that is, the probability of actual propagation is also low, negligible. Therefore, when calculating the propagation probability of the propagation path, only the propagation probability of the first K propagation sub-paths will be considered, where K is the set maximum effective propagation sub-path number.

In the embodiment of the present application, by propagating the propagation probability corresponding to different types of propagation sub-paths, the propagation determination of the propagation path is obtained, and the accuracy of the propagation probability is improved.

Further, as another embodiment of the present application, the S401 is specifically:

And importing the degree of degree corresponding to the degree of the vector into a preset propagation probability conversion function to determine a propagation probability of the propagation subpath; the preset propagation probability conversion function is:

Where u is the starting node of the out-of-degree vector; v is the terminating node of the out-of-vector vector; P(u,v) is the propagation probability of the propagating sub-path; the N(u) is the The extent to which the starting node is out of the terminating node.

In the present embodiment, the degree of degree of exit N(u) is used to indicate the adhesion between the starting point u and the ending point v, and the higher the degree of adhesion, that is, the shorter the information propagation distance of the two, the closer to 1; The smaller the adhesion, that is, the farther the distance between the two information propagation distances is, the larger the value of N(u) will be. Therefore, in the present embodiment, the reciprocal of N(u) is taken as the propagation probability of the propagation sub-path.

In this embodiment, the network account selection device imports the degree of the degree of the propagation sub-path of each type of the out-of-vector vector into the above function, and determines the corresponding propagation probability.

In the embodiment of the present application, according to the reciprocal of the degree of outdegree as the propagation probability of the propagation sub-path, the algorithm is simple, thereby improving the calculation speed of the propagation probability of the propagation sub-path, and then improving the selection efficiency.

Further, as another embodiment of the present application, the S403 is specifically:

And inputting a propagation probability of all the propagation sub-paths included in the propagation path into a path probability determination model, and determining a propagation probability corresponding to the propagation path; the path probability determination model is:

Where L is the propagation path; PP(L) is the propagation probability corresponding to the propagation path; n ₁ is the starting point of the propagation path; n _m is the termination point of the propagation path; n _i is the Propagation node of the propagation path; said P(n _i , n _i+1 ) is the propagation probability of the propagation sub-path of n _i to n _i+1 .

In this embodiment, the product of all propagation sub-paths included in the propagation path is used as the propagation probability of the propagation path. Since information propagation is a process of forwarding through each propagation node, the previous node needs to receive the information. After that, it can be advanced to the next node, which is similar to the product of the propagation probability. Therefore, the product of the propagation probability of all the propagation sub-paths included in the propagation path can be calculated as the propagation probability of the propagation path.

In the embodiment of the present application, the propagation probability of the propagation path is determined by the product model, and the algorithm is simple, thereby improving the calculation speed of the propagation probability of the propagation sub-path, and then improving the selection efficiency.

It should be understood that the size of the sequence of the steps in the above embodiments does not mean that the order of execution is performed. The order of execution of each process should be determined by its function and internal logic, and should not be construed as limiting the implementation process of the embodiments of the present application.

FIG. 5 is a structural block diagram of a device for selecting a network account according to an embodiment of the present application. Each unit included in the device for selecting a network account is used to execute each step in the embodiment corresponding to FIG. 1. For details, please refer to the related description in the embodiment corresponding to FIG. 1 and FIG. For the convenience of explanation, only the parts related to the present embodiment are shown.

Referring to FIG. 5, the device for selecting a network account includes:

The user entity connection determining unit 51 is configured to obtain a user entity connection corresponding to each candidate account in the network platform, where the user entity connection is: if there is a user account corresponding to the candidate account in another network platform The same, the user account and the candidate account have one of the user entity connections;

The propagation path determining unit 52 is configured to determine a propagation path corresponding to each of the candidate accounts based on an out-degree vector in each network platform where the candidate account is located and the user entity connection; wherein the out-of-degree vector is : a vector in the network platform in which the direction of information propagation is directed by the candidate account to other user accounts;

The propagation probability determining unit 53 is configured to obtain a propagation probability corresponding to each of the propagation paths by using a preset propagation probability calculation algorithm;

The radiation metric calculation unit 54 is configured to determine a radiation metric value of each of the candidate accounts according to the propagation path corresponding to each of the candidate accounts and a propagation probability corresponding to the propagation path;

The account selection unit 55 is configured to select the N candidate accounts with the largest radiation metric value as the selected account, and the N is a positive integer greater than or equal to 1.

Optionally, the propagation path determining unit 52 specifically includes:

a propagation path connecting unit, configured to use the candidate account as a starting point of a propagation path, a user account other than the candidate account as a termination point of the propagation path, and the propagation path propagation node to The degree vector and the user entity are connected as a propagation subpath, and a propagation path corresponding to the candidate account is determined.

Optionally, the propagation path includes at least one of the propagation sub-paths;

The propagation probability determining unit 53 specifically includes:

An out-of-vector probability determining unit, configured to determine a propagation probability of the propagation sub-path according to an out-degree degree corresponding to the out-of-degree vector if the propagation sub-path is the out-of-range vector;

a user entity connection probability determining unit, configured to connect, according to the user entity, the matching account corresponding to the user entity and the matching degree of the user account as the user entity if the propagating sub-path is connected to the user entity Probability of propagation;

And a propagation probability calculation unit, configured to obtain a propagation probability corresponding to the propagation path based on propagation probabilities of all the propagation sub-paths included in the propagation path.

Therefore, the device for selecting a network account provided by the embodiment of the present application may also be not limited to solving the problem of maximizing the radiation capability in a single network platform, but selecting the radiation metric according to the comprehensive radiation capability of the candidate account in multiple platforms. The largest candidate account is selected as the selected account, which improves the accuracy of the account selection result, and then improves the efficiency of information dissemination and the scope of dissemination.

FIG. 6 is a schematic diagram of a terminal device according to another embodiment of the present application. As shown in FIG. 6, the terminal device 6 of this embodiment includes a processor 60, a memory 61, and computer readable instructions 62 stored in the memory 61 and operable on the processor 60, such as a network account. Select the program. The processor 60 executes the computer readable instructions 62 to implement the steps in the above-described embodiments of the protection methods of the respective batteries, such as S101 to S105 shown in FIG. 1. Alternatively, the processor 60, when executing the computer readable instructions 62, implements the functions of the various units in the various apparatus embodiments described above, such as the functions of the units 51 through 55 shown in FIG.

Illustratively, the computer readable instructions 62 may be partitioned into one or more modules, the one or more modules being stored in the memory 61 and executed by the processor 60 to complete the application. . The one or more modules may be a series of computer readable instruction instructions segments capable of performing a particular function, the instruction segments being used to describe the execution of the computer readable instructions 62 in the terminal device 6. For example, the computer readable instructions 62 may be partitioned into a user entity connection determination module, a propagation path determination module, a propagation probability determination module, a radiation metric calculation module, and an account selection module, each module having a specific function as described above.

The memory 61 may be an internal storage unit of the terminal device 6, such as a hard disk or a memory of the terminal device 6. The memory 61 may also be an external storage device of the terminal device 6, for example, a plug-in hard disk equipped on the terminal device 6, a smart memory card (SMC), and a secure digital (SD). Card, flash card, etc. Further, the memory 61 may also include both an internal storage unit of the terminal device 6 and an external storage device. The memory 61 is configured to store the computer readable instructions and other programs and data required by the terminal device. The memory 61 can also be used to temporarily store data that has been output or is about to be output.

It will be apparent to those skilled in the art that for the convenience and brevity of the description, only the above function lists are The division of the element and the module is exemplified. In the actual application, the function distribution may be completed by different functional units and modules according to requirements, that is, the internal structure of the device is divided into different functional units or modules to complete the above description. All or part of the function. Each functional unit and module in the embodiment may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit, and the integrated unit may be implemented by hardware. Formal implementation can also be implemented in the form of software functional units. In addition, the specific names of the respective functional units and modules are only for the purpose of facilitating mutual differentiation, and are not intended to limit the scope of protection of the present application. For the specific working process of the unit and the module in the foregoing system, reference may be made to the corresponding process in the foregoing method embodiment, and details are not described herein again.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

The above-mentioned embodiments are only used to explain the technical solutions of the present application, and are not limited thereto; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still implement the foregoing embodiments. The technical solutions described in the examples are modified or equivalently replaced with some of the technical features; and the modifications or substitutions do not deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in Within the scope of protection of this application.

Claims

A method for selecting a network account, which is characterized by comprising:

Obtaining, in the network platform, a user entity connection corresponding to each candidate account; wherein the user entity connection is: if there is a user account in another network platform that is the same as the user corresponding to the candidate account, the user account and the user account There is one of the user entity connections between the candidate accounts;

Determining a propagation path corresponding to each of the candidate accounts based on an out-of-vector vector in the network platform where the candidate account is located and the user entity connection; wherein the degree-out vector is: information in the network platform The direction of propagation is directed to the vector of other user accounts by the candidate account;

Obtaining a propagation probability corresponding to each of the propagation paths by using a preset propagation probability calculation algorithm;

Determining a radiation metric value of each of the candidate accounts according to the propagation path corresponding to each of the candidate accounts and a propagation probability corresponding to the propagation path;

The N candidate accounts with the largest radiation metric value are selected as the selected account, and the N is a positive integer greater than or equal to 1.
The method according to claim 1, wherein the determining the propagation of each candidate account based on the outgoing vector in the topology of the network platform where each candidate account is located and the user entity connection The path is specifically:

Using the candidate account as a starting point of a propagation path, using a user account other than the candidate account as a termination point of the propagation path, and the propagation path propagation node, the outgoing vector, and the user entity The connection is a propagation sub-path, and the propagation path corresponding to the candidate account is determined.
The method according to claim 2, wherein the propagation path comprises at least one of the propagation sub-paths;

The obtaining, by using a preset propagation probability calculation algorithm, the propagation probability corresponding to each of the propagation paths specifically includes:

If the propagation sub-path is the out-of-range vector, determining a propagation probability of the propagation sub-path according to the degree of the degree of the corresponding degree of the out-of-degree vector;

If the propagation sub-path is the user entity connection, the matching probability of the candidate account and the user account corresponding to the user entity connection is used as a propagation probability of the connection of the user entity;

And obtaining a propagation probability corresponding to the propagation path based on propagation probabilities of all the propagation sub-paths included in the propagation path.
The method of selecting according to claim 3, wherein the outreach according to the out-degree vector To determine the propagation probability of the propagation sub-path, specifically:

And importing the degree of degree corresponding to the degree of the vector into a preset propagation probability conversion function to determine a propagation probability of the propagation subpath; the preset propagation probability conversion function is:

Where u is the starting node of the out-of-degree vector; v is the terminating node of the out-of-vector vector; P(u,v) is the propagation probability of the propagating sub-path; the N(u) is the The extent to which the starting node is out of the terminating node.
The selection method according to claim 3 or 4, wherein the propagation probability corresponding to the propagation path is obtained based on the propagation probability of all the propagation sub-paths included in the propagation path:

And inputting a propagation probability of all the propagation sub-paths included in the propagation path into a path probability determination model, and determining a propagation probability corresponding to the propagation path; the path probability determination model is:

Where L is the propagation path; PP(L) is the propagation probability corresponding to the propagation path; n 1 is the starting point of the propagation path; n m is the termination point of the propagation path; n i is the Propagation node of the propagation path; said P(n i , n i+1 ) is the propagation probability of the propagation sub-path of n i to n i+1 .
A device for selecting a network account, comprising:

a user entity connection determining unit, configured to obtain a user entity connection corresponding to each candidate account in the network platform, where the user entity connection is: if another user network account exists in the other network platform, the user corresponding to the candidate account is the same a user entity connection exists between the user account and the candidate account;

a propagation path determining unit, configured to determine a propagation path corresponding to each of the candidate accounts based on an out-of-vector vector in each of the network platforms in which the candidate account is located and the user entity connection; wherein the out-of-service vector is: a vector in the network platform that is directed by the candidate account to other user accounts;

a propagation probability determining unit, configured to obtain a propagation probability corresponding to each of the propagation paths by using a preset propagation probability calculation algorithm;

a radiation metric calculation unit, configured to determine a radiation metric value of each of the candidate accounts according to the propagation path corresponding to each of the candidate accounts and a propagation probability corresponding to the propagation path;

And an account selecting unit, configured to select the N candidate accounts with the largest radiation metric value as the selected account, where the N is a positive integer greater than or equal to 1.
The selecting device according to claim 6, wherein the propagation path determining unit specifically comprises:

a propagation path connecting unit, configured to use the candidate account as a starting point of a propagation path, a user account other than the candidate account as a termination point of the propagation path, and the propagation path propagation node to The degree vector and the user entity are connected as a propagation subpath, and a propagation path corresponding to the candidate account is determined.
The selection device according to claim 7, wherein the propagation path includes at least one of the propagation sub-paths;

The propagation probability determining unit specifically includes:

An out-of-vector probability determining unit, configured to determine a propagation probability of the propagation sub-path according to an out-degree degree corresponding to the out-of-degree vector if the propagation sub-path is the out-of-range vector;

a user entity connection probability determining unit, configured to connect, according to the user entity, the matching account corresponding to the user entity and the matching degree of the user account as the user entity if the propagating sub-path is connected to the user entity Probability of propagation;

And a propagation probability calculation unit, configured to obtain a propagation probability corresponding to the propagation path based on propagation probabilities of all the propagation sub-paths included in the propagation path.
The selecting terminal according to claim 3, wherein the out-of-vector probability determining unit is specifically configured to:

And importing the degree of degree corresponding to the degree of the vector into a preset propagation probability conversion function to determine a propagation probability of the propagation subpath; the preset propagation probability conversion function is:

Where u is the starting node of the out-of-degree vector; v is the terminating node of the out-of-vector vector; P(u,v) is the propagation probability of the propagating sub-path; the N(u) is the The extent to which the starting node is out of the terminating node.
The selection method according to claim 8 or 9, wherein the propagation probability calculation unit is specifically configured to:

And inputting a propagation probability of all the propagation sub-paths included in the propagation path into a path probability determination model, and determining a propagation probability corresponding to the propagation path; the path probability determination model is:

Where L is the propagation path; PP(L) is the propagation probability corresponding to the propagation path; n 1 is the starting point of the propagation path; n m is the termination point of the propagation path; n i is the Propagation node of the propagation path; said P(n i , n i+1 ) is the propagation probability of the propagation sub-path of n i to n i+1 .
A terminal device, comprising: a memory, a processor, and computer readable instructions stored on the memory and executable on the processor, the processor executing the computer readable The following steps are implemented when the instruction is executed:

Obtaining, in the network platform, a user entity connection corresponding to each candidate account; wherein the user entity connection is: if there is a user account in another network platform that is the same as the user corresponding to the candidate account, the user account and the user account There is one of the user entity connections between the candidate accounts;

Determining a propagation path corresponding to each of the candidate accounts based on an out-of-vector vector in the network platform where the candidate account is located and the user entity connection; wherein the degree-out vector is: information in the network platform The direction of propagation is directed to the vector of other user accounts by the candidate account;

Obtaining a propagation probability corresponding to each of the propagation paths by using a preset propagation probability calculation algorithm;

Determining a radiation metric value of each of the candidate accounts according to the propagation path corresponding to each of the candidate accounts and a propagation probability corresponding to the propagation path;

The N candidate accounts with the largest radiation metric value are selected as the selected account, and the N is a positive integer greater than or equal to 1.
The terminal device according to claim 11, wherein the determining, according to an out-of-vector vector in each network platform where the candidate account is located, and the user entity connection, determining a propagation path corresponding to each of the candidate accounts The steps specifically include:

Using the candidate account as a starting point of a propagation path, using a user account other than the candidate account as a termination point of the propagation path, and the propagation path propagation node, the outgoing vector, and the user entity The connection is a propagation sub-path, and the propagation path corresponding to the candidate account is determined.
The terminal device according to claim 12, wherein the propagation path includes at least one of the propagation sub-paths;

And the step of obtaining a propagation probability corresponding to each of the propagation paths by using a preset propagation probability calculation algorithm, specifically:

If the propagation sub-path is the out-of-range vector, determining a propagation probability of the propagation sub-path according to the degree of the degree of the corresponding degree of the out-of-degree vector;

If the propagation sub-path is the user entity connection, the matching probability of the candidate account and the user account corresponding to the user entity connection is used as a propagation probability of the connection of the user entity;

And obtaining a propagation probability corresponding to the propagation path based on propagation probabilities of all the propagation sub-paths included in the propagation path.
The terminal device according to claim 13, wherein the corresponding output according to the degree of exit vector The degree of the degree, the step of determining the propagation probability of the propagation sub-path, specifically includes:

And importing the degree of degree corresponding to the degree of the vector into a preset propagation probability conversion function to determine a propagation probability of the propagation subpath; the preset propagation probability conversion function is:

Where u is the starting node of the out-of-degree vector; v is the terminating node of the out-of-vector vector; P(u,v) is the propagation probability of the propagating sub-path; the N(u) is the The extent to which the starting node is out of the terminating node.
The terminal device according to claim 13 or 14, wherein the propagation probability corresponding to the propagation path is obtained based on a propagation probability of all the propagation sub-paths included in the propagation path:

And inputting a propagation probability of all the propagation sub-paths included in the propagation path into a path probability determination model, and determining a propagation probability corresponding to the propagation path; the path probability determination model is:

Where L is the propagation path; PP(L) is the propagation probability corresponding to the propagation path; n 1 is the starting point of the propagation path; n m is the termination point of the propagation path; n i is the Propagation node of the propagation path; said P(n i , n i+1 ) is the propagation probability of the propagation sub-path of n i to n i+1 .
A computer readable storage medium storing computer readable instructions, wherein the computer readable instructions, when executed by a processor, implement the following steps:

Obtaining, in the network platform, a user entity connection corresponding to each candidate account; wherein the user entity connection is: if there is a user account in another network platform that is the same as the user corresponding to the candidate account, the user account and the user account There is one of the user entity connections between the candidate accounts;

Determining a propagation path corresponding to each of the candidate accounts based on an out-of-vector vector in the network platform where the candidate account is located and the user entity connection; wherein the degree-out vector is: information in the network platform The direction of propagation is directed to the vector of other user accounts by the candidate account;

Obtaining a propagation probability corresponding to each of the propagation paths by using a preset propagation probability calculation algorithm;

Determining a radiation metric value of each of the candidate accounts according to the propagation path corresponding to each of the candidate accounts and a propagation probability corresponding to the propagation path;

The N candidate accounts with the largest radiation metric value are selected as the selected account, and the N is a positive integer greater than or equal to 1.
A computer readable storage medium according to claim 16, wherein said said said The step of selecting an out-of-vector vector in the network platform where the account is located and the user entity connection, and determining a propagation path corresponding to each of the candidate accounts, specifically includes:

Using the candidate account as a starting point of a propagation path, using a user account other than the candidate account as a termination point of the propagation path, and the propagation path propagation node, the outgoing vector, and the user entity The connection is a propagation sub-path, and the propagation path corresponding to the candidate account is determined.
The computer readable storage medium of claim 17, wherein the propagation path comprises at least one of the propagation sub-paths;

And the step of obtaining a propagation probability corresponding to each of the propagation paths by using a preset propagation probability calculation algorithm, specifically:

If the propagation sub-path is the out-of-range vector, determining a propagation probability of the propagation sub-path according to the degree of the degree of the corresponding degree of the out-of-degree vector;

If the propagation sub-path is the user entity connection, the matching probability of the candidate account and the user account corresponding to the user entity connection is used as a propagation probability of the connection of the user entity;

And obtaining a propagation probability corresponding to the propagation path based on propagation probabilities of all the propagation sub-paths included in the propagation path.
The computer-readable storage medium according to claim 18, wherein the step of determining a propagation probability of the propagation sub-path according to the degree of the degree of the corresponding degree of the out-of-range vector comprises:

And importing the degree of degree corresponding to the degree of the vector into a preset propagation probability conversion function to determine a propagation probability of the propagation subpath; the preset propagation probability conversion function is:

Where u is the starting node of the out-of-degree vector; v is the terminating node of the out-of-vector vector; P(u,v) is the propagation probability of the propagating sub-path; the N(u) is the The extent to which the starting node is out of the terminating node.
The computer readable storage medium according to claim 18 or claim 19, wherein the propagation probability corresponding to the propagation path is obtained based on a propagation probability of all the propagation sub-paths included in the propagation path:

And inputting a propagation probability of all the propagation sub-paths included in the propagation path into a path probability determination model, and determining a propagation probability corresponding to the propagation path; the path probability determination model is:

Where L is the propagation path; PP(L) is the propagation probability corresponding to the propagation path; n 1 is the starting point of the propagation path; n m is the termination point of the propagation path; n i is the Propagation node of the propagation path; said P(n i , n i+1 ) is the propagation probability of the propagation sub-path of n i to n i+1 .