CN109949172B - Social account influence evaluation method and device and storage medium - Google Patents
Social account influence evaluation method and device and storage medium Download PDFInfo
- Publication number
- CN109949172B CN109949172B CN201711349202.7A CN201711349202A CN109949172B CN 109949172 B CN109949172 B CN 109949172B CN 201711349202 A CN201711349202 A CN 201711349202A CN 109949172 B CN109949172 B CN 109949172B
- Authority
- CN
- China
- Prior art keywords
- social
- article
- social account
- influence
- account
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 128
- 238000000034 method Methods 0.000 claims description 58
- 238000012163 sequencing technique Methods 0.000 claims description 21
- 238000004458 analytical method Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 8
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 23
- 230000008569 process Effects 0.000 description 20
- 238000004422 calculation algorithm Methods 0.000 description 17
- 238000004364 calculation method Methods 0.000 description 16
- 238000004891 communication Methods 0.000 description 16
- 230000006870 function Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000010365 information processing Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 230000011664 signaling Effects 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 244000309464 bull Species 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000009193 crawling Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000011273 social behavior Effects 0.000 description 1
- 210000003813 thumb Anatomy 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention provides a social account influence evaluation method, a social account influence evaluation device and a storage medium, wherein a plurality of article incidence relations existing in a social application platform, namely incidence relations existing among articles issued by social accounts, such as forwarding relations, reference relations and the like, are obtained, so that influence propagation operation is performed on the social accounts, and influence evaluation parameters of corresponding social accounts are obtained and stored. Therefore, the form rate value of the social accounts having article association relations with the plurality of social accounts is considered, an artificial intelligence related article is taken as an example, weights of praise of the article by academic form rate people and praise of common users are distinguished, and accuracy and reliability of calculating influence of the social accounts are improved.
Description
Technical Field
The invention relates to the field of social influence propagation application, in particular to a method and a device for evaluating social account influence and a storage medium.
Background
In the internet era, users commonly use terminal devices such as mobile phones and notebook computers to achieve information acquisition and interaction, and accordingly various social application platforms are generated, and more convenient and effective services are provided for the users.
In practical application, a user can add other users with interests to be invested as friends by logging in a personal social account in a social application platform, share the latest published articles of the friends, and can also perform operations such as praise and comment on the published articles of the friends, so that communication among the users is facilitated. In addition, the user can pay attention to the social account number registered by the developer or the merchant or the individual according to the interest of the user and the like, so that articles of various contents published by the developer or the merchant or the individual through the social account number can be read, and more convenience and more fun are brought to the life and the work of the user.
For users of the type such as developers or merchants, it is often desirable that their social accounts can be paid attention to by more people, so that articles issued by the social accounts can be spread in time and widely; for users who select to pay attention to social accounts, it is generally desirable to pay attention to social accounts with a larger influence so as to know more valuable information through the concerned social accounts, and therefore, such users urgently need a social application platform to be capable of showing influence ranks of the social accounts and assisting the users in selecting social accounts to pay attention to.
In the prior art, influence of a social account is usually calculated based on the reading amount and the praise times of articles published by the social account, the obtained data channel is single, the table rate value of the social account is not considered, the accuracy and reliability of the calculation result of the influence of the social account are reduced, and further the selection efficiency of a user on the concerned social account is influenced.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method, an apparatus, and a storage medium for evaluating influence of a social account, which implement calculation of influence of the social account by using an association relationship between articles published by the social account, and improve accuracy and reliability of a calculation result of the influence of the social account in consideration of a table rate value of the social account, thereby improving selection efficiency of a user on a concerned social account.
In order to achieve the above object, the embodiments of the present invention provide the following technical solutions:
the embodiment of the invention provides a social account influence evaluation method, which comprises the following steps:
acquiring a plurality of article association relations existing in a social application platform, wherein the article association relations represent association relations among articles published by a plurality of social accounts in the social application platform;
carrying out influence propagation operation on the social account numbers by using the article association relations to obtain influence evaluation parameters of the corresponding social account numbers;
and storing the obtained influence evaluation parameters of the plurality of social account numbers.
The embodiment of the invention also provides a social account influence evaluation device, which comprises:
the article association relation acquisition module is used for acquiring a plurality of article association relations existing in a social application platform, wherein the article association relations represent association relations among articles published by a plurality of social accounts in the social application platform;
the influence propagation operation module is used for carrying out influence propagation operation on the plurality of social contact account numbers by utilizing the association relations of the articles to obtain influence evaluation parameters of the corresponding social contact account numbers;
and the influence evaluation parameter storage module is used for storing the obtained influence evaluation parameters of the plurality of social accounts.
The embodiment of the present invention further provides a storage medium, on which a computer program is stored, where the computer program is executed by a processor, and is configured to implement each step of the social account influence evaluation method described above.
Based on the technical scheme, the embodiment of the invention obtains the incidence relations of the articles existing in the social application platform, namely the incidence relations, such as forwarding relations, reference relations and the like, existing among the articles issued by the social accounts, so that the influence propagation operation is performed on the social accounts, and the influence evaluation parameters of the corresponding social accounts are obtained and stored. Therefore, the table rate value of the social accounts having article association relations with the social accounts is considered, an artificial intelligence related article is taken as an example, weights of the article praise by academic-table-rate people and praise by ordinary users are distinguished, accuracy and reliability of calculating influence of the social accounts are improved, ranking of the users based on the influence of the social accounts is further improved, and selection efficiency of the concerned social accounts is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 shows a structure diagram of a social account influence evaluation system according to an embodiment of the present invention;
fig. 2 is a hardware structure diagram of a server according to an embodiment of the present invention;
fig. 3 shows a flowchart of a social account influence evaluation method according to an embodiment of the present invention;
FIG. 4 is a diagram of an article citation network according to an embodiment of the present invention;
FIG. 5 illustrates another article citation network diagram provided by an embodiment of the present invention;
FIG. 6 is a flowchart illustrating another social account influence evaluation method according to an embodiment of the present invention;
fig. 7 is a flowchart illustrating a method for evaluating influence of a social account according to an embodiment of the present invention;
fig. 8 shows a signaling flowchart of a social account influence evaluation method according to an embodiment of the present invention;
FIG. 9 is a schematic diagram illustrating a social account ranking interface provided by an embodiment of the invention;
fig. 10 is a block diagram illustrating a structure of a social account influence evaluation apparatus according to an embodiment of the present invention;
fig. 11 is a block diagram illustrating a structure of another social account influence evaluation apparatus according to an embodiment of the present invention;
fig. 12 is a block diagram illustrating a structure of another social account influence evaluation apparatus according to an embodiment of the present invention.
Detailed Description
Nowadays, the social application platform becomes the communication tool widely used in daily life and work of people, and the user can also know interested relevant information through the information pushed by the social application platform, and can also post personal opinions and the like aiming at the information, which is very convenient and practical.
In this regard, many developers or merchants recognize the function of the social application platform, and usually register a social account (i.e., an account for implementing network information propagation) on the social application platform, so that the embodiment of the present invention does not limit the type of the social account, and determines the social account based on the social application platform where the social account is located, so as to promote products or brands, etc., and attract more users to know the promotion content of the users through a network, thereby exploiting the market through the internet. Certainly, the user can also realize publicity or popularization of information such as texts, pictures, videos and the like by registering the social account, and especially for users with certain identity status in the field, the popularization of knowledge in the field can be realized more effectively by the mode.
In practical applications, the greater the reading amount or the number of praise times of contents such as articles and videos published through a social account, the greater the propagation capacity of the social account, that is, the greater the influence of the social account, when a user selects a social account to pay attention to, the social account with a larger influence is often selected to pay attention to. The social application platform can usually show the influence of each social account, for example, by ranking, to assist the user in selecting a social account to be focused on. Therefore, how to evaluate the influence of each social account in the social application platform has become one of important development directions of the social application platform.
In the prior art, when influence calculation is performed on any social account on a social application platform, the influence calculation often depends completely on the read number and the praise number of the published content obtained through statistics, so that some linear models, such as a qingbo Index model and a New Rank Index (NRI) model, are generated to obtain an influence evaluation parameter representing the influence of the social account.
If the Qingbo index model is used for calculating the influence of the social account, the number of readings and the number of praise times of articles published by the social account in the social application platform generally need to be counted, and a statistical manner shown in the following table 1 may be generated. Also, the various indicators used to characterize the social account impact may be divided into a primary indicator and a secondary indicator, as shown in table 1 below.
TABLE 1
Based on the method, a Qingbo index model shown in the formula (1) can be constructed by using the WCI algorithm:
the calculation result obtained by the WCI algorithm can represent the propagation degree, the coverage degree, the maturity degree and the influence of the social account number for pushing the article through the social account number so as to reflect the overall popularity of the social application platform and the development trend of the social account number. Therefore, when the influence of a certain social account needs to be calculated, the social application platform may count the social account number associated with R, R/n, R shown in table 1 max Z, Z/n and Z max And (3) waiting for data, and then performing operation as an input parameter of the Qingbo index model shown in the formula (1), wherein the output result can represent the influence of the social account.
Similarly, if a new list index model is constructed by using the NRI algorithm, when the influence of the social account in the social application platform is calculated, the data shown in table 2 below may be collected, but the data is not limited to the data content shown in table 2. The NRI algorithm may be a calculation method shown in the following formula (2), but is not limited thereto.
TABLE 2
Based on this, when an NRI model is constructed using the NRI algorithm, a model shown by the following formula (2) can be obtained:
in summary, the two methods for calculating the influence of the social account are known, because the methods completely depend on the number of readings and the number of praise of the contents such as the published articles, a single data channel for calculating the influence of the social account is caused, the situation that each dimension of the social account is complex cannot be reflected, and the table rate value of the social account cannot be reflected, if the praise of the published articles by experts recognized in the field cannot be reflected, the difference from the praise of common users cannot be reflected, and the influence of the social account obtained by the conventional calculation is not accurate enough.
In order to solve the above problems, the inventor of the present invention proposes a new method for calculating influence of a social account by using a link analysis algorithm, and may calculate an influence score parameter of the social account by combining an association relationship of articles published by each social account in a social application platform.
Based on the above description of the inventive concept of the solution provided by the present invention, the technical solution in the embodiment of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiment of the present invention, however, the embodiment described herein is only a part of the embodiment of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a structure diagram of a social account influence evaluation system for implementing a social account influence evaluation method according to an embodiment of the present invention is provided, where the system may include: a server 11, a database 12 and a plurality of clients 13.
The server 11 may be a service device that provides a service for a user on a network side, and may be a server cluster formed by a plurality of servers, or may be a single server.
In practical applications, the server 11 may be a service server corresponding to the client 13, and provides data required by the operation for the client, so as to ensure the normal operation of the client. Moreover, in the embodiment of the present invention, the server 11 may implement a social account information processing method, which may be specifically used to calculate influence of each social account in a social application platform (that is, influence evaluation parameters of each social account are calculated to represent influence thereof), and when receiving a query request sent by a client, obtain influence evaluation parameters of a plurality of social accounts that satisfy the query request, and then, may feed back the obtained influence ranking and influence index data of each social account to the client for display, so as to assist a user in knowing influence conditions of each social account in the social application platform at the current stage, and accurately select a social account to be concerned as needed, and so on.
The database 12 may be a repository that organizes, stores, and manages data in a data structure.
In the embodiment of the present invention, the database 12 may be a database matched with the client 13 and the server 11, such as a cloud database or a local database, and may be specifically used to store various data generated during the operation of the client, various data and various calculation results generated during the execution of the social account information processing method by the server 11, a query result of the server 11 responding to a query request of the client, and a program code for ensuring the realization of various functions of the client, and the like.
The client 13 may be an application program loaded on a user device such as a mobile phone, a tablet computer, a notebook computer, or the like, or may be a web application program set in a browser, and in practical applications, a communication connection is established with the server 11, so that a user accesses the server 11 through the client 13, and various service functions of the client 13 are implemented.
In this embodiment of the present invention, the client may be an application program capable of presenting influence rankings of multiple social accounts in various social application platforms (or the present social application platform), so that a user may select an interested social account with reference to the rankings, and the like.
Optionally, referring to fig. 2, a hardware structure diagram of a server provided in the embodiment of the present invention is provided, where the server may include: a communication interface 21, a memory 22, and a processor 23.
The number of the communication interface 21, the memory 22 and the processor 23 may be at least one, and the communication interface 21, the memory 22 and the processor 23 may complete communication with each other through a communication bus.
In the embodiment of the present invention, the communication interface 21 may be an interface of a wireless communication module, such as an interface of a WIFI module, and can communicate with at least one client to provide a service for each client.
Of course, in the embodiment of the present invention, the server 11 may also perform data interaction with the database 12 through a communication interface, may also perform communication with other servers through a communication interface, and the like, which may be determined specifically according to actual requirements, and this embodiment is not described in detail herein.
The memory 22 may include a high-speed RAM memory, or may also include a nonvolatile memory, and the like, and is used to store a program for implementing the social account influence evaluation method provided in the embodiment of the present invention, and the program is loaded and executed by the processor 23, so as to implement the social account influence evaluation method provided in the embodiment of the present invention.
The processor 23 may be a central processing unit CPU, or a specific integrated circuit ASIC, etc., the present invention does not limit the composition structure of the processor 33, in the embodiment of the present invention, the processor 23 loads and executes the program stored in the memory 22, and each step of implementing the social account influence evaluation method may refer to the following description of the corresponding embodiment, which is not described in detail herein.
With reference to fig. 1 and fig. 2, an embodiment of the present invention provides a social account influence evaluation method, which is mainly described from the perspective of a server, and with reference to a flowchart of the social account influence evaluation method shown in fig. 3, the method may include:
step S301, obtaining a plurality of article association relations existing in a social application platform;
the article association relationship may represent an association relationship between articles published by a plurality of social accounts in the social application platform, such as a reference relationship between the articles, a relationship of class references, and the like.
Optionally, in the embodiment of the present invention, the page data of each article published in the social application platform may be crawled by using a crawler system, so that the page data is analyzed to determine the association relationship of multiple articles possibly existing in the social application platform at the current time, and a specific implementation process is not limited.
In the embodiment of the invention, after at least one article page data issued by any one social account is captured by using a crawler system, URL data contained in the article page data can be analyzed, so that the source of the article, namely other social accounts quoted by the article, is determined by using the URL of the social account contained in the URL data, then unique identifiers such as names of other social accounts can be obtained, and the article association relationship between the social accounts is determined by using the social account identifiers.
At this time, an article reference relationship pair between two social accounts having an article reference relationship (such as a direct reference relationship or an indirect reference relationship) may be generated, thereby representing an article association relationship between the corresponding social accounts, but is not limited thereto.
In practical application, after analyzing the articles of the other referenced social account, the crawler system can be directly triggered to directly download the article contents of the other referenced social account, and can also continue to crawl the article page data of the other social account according to the scheme, analyze whether the article published by the crawler system references the article of the third social account, and so on, determine all article reference relations among a plurality of social accounts in the social application platform.
As another embodiment of the invention, a crawler system may be further used to actively capture all article page data published by each social account in the social application platform, so that the captured article page data is analyzed to determine the source of the article published by the social account and whether the article is referred by other social accounts, that is, the article reference relationship between the social accounts is used to determine the article association relationship between the social accounts.
It should be noted that, the method for how the crawler system obtains the article association relationship between social account numbers is not limited to the two implementation methods described above, and the embodiments of the present invention are not described in detail herein.
In practical application of the embodiment of the invention, the crawler system can be arranged in a server of the social account influence evaluation system, page data of an article published by each social account is captured by monitoring a preset communication interface of the server, and other social account identifications having an article reference relationship with the social account are further analyzed to determine a corresponding article association relationship.
Certainly, the crawler system may also be disposed in a client of the social account influence evaluation system, and similar to the crawling process, the crawler system may monitor a communication interface of the client and extract article page data that meets the above requirements, so as to obtain a plurality of article association relationships.
In addition, the crawler system in the embodiment of the present invention may also be used as an application program of a third-party independent application platform, and capture and analysis of the article page data are implemented by monitoring social behavior data of a social application platform, so as to obtain a plurality of article association relationships between social account numbers.
Step S302, a plurality of social account numbers are used as nodes, and an incidence relation graph of a social application platform is constructed by utilizing the incidence relations of the articles;
in the embodiment of the invention, the concept of a link analysis algorithm, namely PageRank, can be utilized to realize the calculation of the influence of the social account, and for the application of the PageRank algorithm, the more the number of webpages linked to the webpage A is, the more important the webpage A is (or the higher the quality of the webpage A is), the more high-quality webpages point to the webpage A, and the more important the webpage A is.
Based on this, the idea can be applied to the social account influence calculation of the social application platform, that is, an article is forwarded for many times, and the article is considered to be important, that is, the social account influence for publishing the article is high; if an article is forwarded for a short time, but the social account number for forwarding the article contains a social account number with high influence, the article is considered to be important, and the influence of the social account number for publishing the article is high.
Moreover, the article a of the social account 1 "refers to" the article B published by the social account 2, and is similar to the Web page a "vote" Web page B, so that the embodiment of the present invention may generate an association relationship graph of a social application platform similar to a Web graph model by using the article association relationship. For example, a social account reference relationship graph shown in fig. 4 may be specifically formed by taking a plurality of social accounts in a social application platform as nodes according to an article reference relationship between any two social accounts, circles a to E represent the social accounts a to E, arrows represent articles in which the social accounts reference another social account, such as C → E, and represent that an article issued by the social account C references an article of the social account E, but the association relationship graph of the social application platform constructed in the embodiment of the present invention is not limited to the graph structure shown in fig. 4.
Step S303, carrying out influence propagation operation on a plurality of social account numbers based on the incidence relation graph of the social application platform to obtain influence evaluation parameters of the corresponding social account numbers;
in the embodiment of the invention, the influence evaluation parameters of the social accounts can be used for representing the influence of the corresponding social accounts, and generally, the larger the influence evaluation parameter of the social account is, the larger the influence of the published or forwarded article is.
Optionally, in practical application, after the association relationship graph of the social application platform is generated, the association relationship graph may be initialized, for example, an initial evaluation parameter of influence of each node in the association relationship graph is determined, that is, each social account is given an initial value representing the influence thereof, and then, according to the number of association relationships included in each node in the association relationship graph and a specific association manner of each association relationship, influence propagation operation of the initial evaluation parameter of influence of each node is performed, so as to obtain the evaluation parameter of influence of the corresponding social account.
Taking the article reference network graph (i.e., an association relationship graph of a social application platform) shown in fig. 4 as an example, a logical vector between two corresponding social accounts, that is, a directed edge in the reference relationship graph, may be determined by using the article reference relationship, so that propagation operation is performed by using the number of directed edges included in each node and the direction of each directed edge to obtain an influence evaluation parameter of each social account.
Through the influence propagation operation, the weights of the nodes in the association relationship graph of the social application platform (namely, the influence evaluation parameters of the social accounts) are continuously updated, and a file reference network graph as shown in fig. 5 can be obtained, wherein the size of a circle can represent the size of the current influence evaluation parameter of the social account, namely the influence of the social account, so that it can be seen that the state of the node E, namely the social account E, indicates that the more other social accounts which refer to the published articles, the more important the social account E is, namely the larger the influence thereof is; the status of the social account a indicates that although the number of other social accounts referencing the article published by the social account a is not too large, the article published by the social account a is referenced by a social account having a higher influence, and the influence of the social account a can also be considered to be larger.
It should be noted that, in the embodiment of the present invention, an implementation method for performing influence propagation operation on a plurality of social accounts by using a plurality of article association relations currently existing in a social application platform to obtain influence evaluation parameters of the corresponding social accounts is not limited to the above-described manner for constructing an association relation graph of the social application platform, and when constructing the association relation graph, the implementation method is not limited to the reference network graph of the social accounts as shown in fig. 4 and 5, and other logical topological graphs may also be constructed, where the implementation process is similar to the construction of the reference network graph and the influence propagation operation, and details of the embodiment of the present invention are not described here.
And step S304, storing the obtained influence evaluation parameters of the plurality of social account numbers.
In the embodiment of the present invention, after obtaining the influence evaluation parameters corresponding to the multiple social account numbers in the social application platform by the server, the server may store the influence of each social account number, specifically, may send the influence to the database for storage, or may store the influence in the memory of the server.
In practical application, when a user starts a client corresponding to a social application platform, hopes to select some social accounts with large influence for attention, and can generally query influence ranking lists of various social accounts, such as a week list, a month list and the like, the server can specifically send corresponding query requests to the server, so that the server obtains query conditions contained in the query requests by analyzing the query requests, thereby querying influence evaluation parameters of a plurality of social accounts conforming to the query conditions, and obtaining influence ranking of the social accounts according to the size of the queried influence evaluation parameters of the plurality of social accounts, so that the ranking results and index data (such as the number of thumbs and the number of headlines and the like) corresponding to the influence of each social account are fed back to the client, the client displays the influence index data of the corresponding social accounts in a social account influence ranking window of the current display interface according to the ranking results, helps the user select the social accounts meeting the needs of the user, and the social account ranking is very convenient.
In summary, in the embodiment of the present invention, a corresponding article association relationship is determined for a social account having an article association relationship in a social application platform, so that according to a large number of determined article association relationships, a table rate social account in a plurality of social accounts is determined (for example, a published article of the social account is associated with an article published by a plurality of social accounts, or a published article of the social account is associated with an article published by other table rate social accounts, which may be regarded as a social account having a large influence), so as to distinguish the influence weight of the influence of the article on the social account publishing the article associated with a common social account, and the influence of the article associated with the table rate social account publishing article, that is, when the influence propagation operation of the social account is performed, the influence of the social account associated with the article is considered, and the accuracy and reliability of the influence evaluation parameter of the social account are greatly improved.
Optionally, as described above, in the embodiment of the present invention, an association relationship graph of the social application platform is constructed by using an article association relationship, so that the association relationship graph can show whether an article published by each social account is referred by other social accounts (or other association relationships and is limited to the referred relationship), how many articles published by the social accounts are referred, whether the published article is an article published by referring to other social accounts, and the like.
Optionally, with reference to fig. 6, a flowchart of another social account influence evaluation method provided in an embodiment of the present invention is mainly illustrated in an iterative operation manner, where the process of implementing propagation operation of multiple social account influences is implemented based on a constructed association relationship diagram of a social application platform, and the embodiment mainly uses the association relationship diagram specifically as an article reference network diagram, that is, an article reference network diagram constructed by using multiple article reference relationships is used as an example for explanation, but is not limited to the implementation method described in the embodiment, and specifically, the method may include:
step S601, capturing page data of at least one article published by any social account in a social application platform;
in practical application, the page data captured by the crawler system may include content such as URL data of a corresponding social account, a nickname of a user, a head portrait of the user, reading numbers of all articles to be published, numbers of praise times, numbers of forwarding times, numbers of comments, numbers of concerns, publication time of each article, article content, and attributes of publishing devices.
Step S602, analyzing Uniform Resource Locator (URL) data contained in the page data of the at least one article, and determining that the first article refers to a second article published by a second social account;
the first article may be any one of the at least one article, and the first article and the article have at least partial same content, or may be completely the same content, and specifically may be determined according to a second article posted by a second social account referred by a first social account, and content input when the first article is posted. For example, when the user posts the first article through the first social account, the user may input or forward other content in addition to forwarding the second article, or may directly forward the second article, and so on.
It should be noted that, in the embodiment of the present invention, an implementation method for analyzing whether an article published by another social account is cited or not through page data of a captured article is not limited. In addition, in order to clearly illustrate the determination process of the article reference relationship, in the embodiment of the present invention, an article posted by a social account captured this time may be referred to as a first article, the social account is referred to as a first social account, articles of other social accounts to which the determined first article applies are referred to as a second article, and a social account posting the second article is referred to as a second social account, where the first social account is different from the second social account.
Step S603, capturing page data of a second article, and analyzing the page data of the first article and the page data of the second article to obtain a first social contact account identifier and a second social contact account identifier;
the first social account identifier and the second social account identifier may be names or IDs of corresponding social accounts, or the like.
Step S604, determining an article reference relation between the first social contact account and the second social contact account by using the first social contact account identifier and the second social contact account identifier;
as analyzed above, the first social account and the second social account have an article reference relationship therebetween, and therefore, an article reference relationship pair may be established between the two social accounts to represent the article reference relationship between the two social accounts, so as to determine a direction of a directed edge between the two social accounts when the article reference network graph is subsequently constructed.
Step S605, continuing to analyze URL data contained in the page data of the second article, and determining whether the second article refers to articles published by other social accounts or not until it is determined that the currently analyzed article does not refer to articles published by other social accounts, so as to obtain a plurality of article reference relations existing in the social application platform;
in the embodiment of the present invention, whether the second article has an application relationship with other social accounts (social accounts other than the first social account) may be continuously analyzed according to the analysis process of the first article reference relationship, which is similar to the above-described process, and this embodiment is not described in detail here one by one, so that a plurality of article reference relationships of the social application platform may be obtained, that is, it is determined that article reference relationship pairs between all social accounts having article reference relationships in the social application platform are present.
It should be noted that, the method for capturing page data by the crawler system and determining the reference relationships of multiple articles is not limited to the implementation method described in this embodiment.
Step S606, constructing an article reference network graph of the social application platform by using the obtained article reference relations;
step S606 is the same as the implementation process of step S302, and the embodiment of the present invention is not described in detail herein.
Step S607, determining the initial evaluation parameter of the influence of each social account in the article citation network diagram;
in the embodiment of the invention, the social account influence propagation operation of the social account forwarding dimension can be realized by using a PageRank algorithm, before iteration is started, an article quote network graph can be initialized, namely under the condition that the iteration time t =0, the initial values of various nodes of the article quote network graph, namely the influence initial evaluation parameters of various social accounts, are determined, and then iteration is performed on the basis of the initial values.
Optionally, when the article reference network graph is initialized, the initial values of the nodes may be set to be the same, that is, in the initial state, the influence of each social account in the social application platform may be considered to be the same, and then iteration is performed on the basis.
Of course, in the embodiment of the present invention, the influence of each node may be calculated according to index data such as the number of times of articles being praised, the number of times of being commented, and the number of times of being forwarded, which are published by the social account, for example, the influence of each node may be calculated by using a qingbo index model similar to the above formula (1) or a new bang index model shown in the formula (2) in combination with the index data, and the model output data may be used as an initial value of the node. According to actual needs, model parameters can be properly adjusted, influence of a maximum value can be optimized by combining logarithmic operation, and accuracy of model output data is improved.
It should be noted that, in the embodiment of the present invention, a method for determining an initial value of each node (that is, an influence initial parameter of each social account) in an article reference network diagram, and a specific numerical value of the initial value of each node are not limited.
Step S608, carrying out iterative operation on the influence initial parameters of the social account numbers until a first preset condition is reached to obtain influence evaluation parameters of the corresponding social account numbers;
the first preset condition may be a condition that the influence evaluation parameter of a social account is shown to be convergent (i.e., tends to be stable), that is, the influence evaluation parameter before and after updating is not changed or the variable is smaller than a preset threshold, or the number of iterations reaches a preset number, and the like.
Optionally, the embodiment of the present invention may use a PageRank algorithm to perform iterative operations, which is to actually calculate a weighted sum of impact evaluation parameter transmissions of other social accounts having a direct or indirect reference relationship with the social account, where a specific iterative process is not described in detail, and the impact evaluation parameter of each social account may be updated once each iteration is completed under a normal condition. Moreover, each time iteration is completed, whether the influence evaluation parameter or the iteration frequency after the iteration meets a first preset condition can be judged, and if not, the social account influence evaluation parameter is continuously updated in an iteration mode; if so, the influence evaluation parameter obtained by the iteration (namely the most iteration) can be used as the influence evaluation parameter of the corresponding social account.
It should be noted that, in the embodiment of the present invention, other iterative algorithms may also be used to perform iterative operations, so as to update the initial evaluation parameter of the influence of each social account, so as to obtain the evaluation parameter of the influence of each social account, which is not limited to the PageRank algorithm described in the above embodiment, but may also be a HITS (hyper-Induced Topic Search) algorithm to obtain the evaluation parameter of the influence of each social account, and a specific implementation process may be determined by combining the principle of the HITS algorithm, which is not described in detail herein.
And step S609, sequencing the obtained influence evaluation parameters of the social accounts to obtain influence sequences of the social accounts in the social application platform, and storing the influence sequences of the social accounts.
In the embodiment of the present invention, when the ranking result is stored, the influence ranking serial numbers of the social account numbers are stored, and meanwhile, influence index data of the social account numbers may also be stored correspondingly, and a specific storage manner is not limited.
Optionally, in the embodiment of the present invention, a plurality of social account influence ranking results corresponding to the social application platform in a week, a month, or even a year before the current time may be obtained, so that when the user needs to obtain the latest social account influence ranking list, the server may obtain the corresponding ranking results in time and feed the ranking results back to the client for display, and of course, the server may also obtain query conditions (such as query start time, query end time, query subject content, and the like) carried by the user by analyzing the query request sent by the user, and then obtain influence evaluation parameters of a plurality of social accounts matching the query conditions, and obtain the plurality of social account influence ranking results in a corresponding time period as if it is, which is not limited in the embodiment of the present invention.
In practical application, influence sequencing of social accounts in the same social application platform may be changed in different time periods, so that the obtained influence sequencing of each social account in the social application platform can be updated periodically or in real time, and the influence sequencing of the social accounts obtained by a user is guaranteed to be the latest sequencing.
Optionally, when it is detected that a new article reference relationship occurs in the social application platform, the influence evaluation parameters of the social account numbers in the social application platform may be updated by using the new article reference relationship in the manner described above, so as to update the stored influence ranks of the social account numbers corresponding to the various query conditions. Therefore, in the embodiment of the invention, the article reference relations among the social account numbers are obtained by capturing the page data of the articles published by the social account numbers in the social application platform and analyzing the page data, so that the article reference network diagram of the social application platform is constructed according to a large number of article reference relations, and the social account number influence propagation operation based on the article reference network diagram fully considers the factors of the forwarding times, forwarding sources, influence of the social account numbers and the like of the articles published by the social account numbers, so that the influence of the social account numbers can be accurately reflected by the evaluation parameters of the calculated social account number influence, and a more effective recommendation assistance effect is realized for users.
For example, referring to fig. 7, taking a social account specifically as a public number as an example for explanation, a crawler system may capture page data of an article a published by any one public number, extract URL data in the page data of the article a, filter out a public number URL, download the public number URL, determine that the article a refers to an article published by another public number, obtain page data of another referred public number article B, extract a public number name of the published article a and a public number name of the published article B, determine an article reference relationship between the two public numbers, and so on to obtain a large number of article reference relationships, generate a file reference network diagram of a social application platform, perform influence propagation operation on the article a by using a PageRank algorithm, obtain an influence evaluation parameter of each number, so as to represent the influence of the corresponding public number, and implement ordering of influences on multiple public numbers.
The method and the device have the advantages that the influence evaluation parameters of the public numbers are calculated by utilizing article citation relations among the public numbers, the difference that the article related to the artificial intelligence is praised by the public number of academic bulls and praised by the public number of the common user is considered, the table rate value of the public number user is reflected, and therefore the public number influence sequencing result displayed by the client side has more effective recommendation value.
Referring to fig. 8, which is a signaling flowchart of a social account influence evaluation method provided in an embodiment of the present invention, the method may include:
step S801, a client outputs a social account sequencing interface of a social application platform;
step S802, the client generates a corresponding query request based on the operation of the user on the social account ranking interface;
in practical application of the embodiment of the present invention, when a user wishes to query a social account influence ranking list of a certain social application platform, the corresponding client may be started to enter a social account ranking interface shown in fig. 9, but not limited to the interface content shown in fig. 9, the user may set, in the social account ranking interface, a social account influence ranking result in which time period needs to be displayed, for example, a "day list", a "week list", a "month list", and the like may be selected, the start time of statistical data will be changed correspondingly, and the deadline of statistical data is usually the current time.
Based on the operation of the user in the social account ranking interface, the client may generate a corresponding query request, and request the server to query the social account influence ranking result meeting the operation requirement, where the query request may carry query conditions, such as the determined start time of statistics, end time of statistics, and statistics topic, but is not limited thereto.
Step S803, the client sends the query request to the server;
step S804, the server analyzes the query request to obtain a query condition;
step S805, the server acquires influence evaluation parameters of a plurality of social account numbers corresponding to the query conditions;
taking the query condition including the statistics start time as an example, the influence evaluation parameters of the multiple social accounts acquired at this time may be obtained by analyzing page data from the statistics start time to the current time to obtain corresponding multiple article association relations existing in the social application platform at this time, and according to the operation method in the above embodiment, the influence evaluation parameters of the multiple social accounts in the social application platform at this time period are obtained.
The influence evaluation parameters of the social accounts in the social application platform change along with the change of time, so that the influence evaluation parameters of the social accounts can be updated along with the update of the incidence relation of the new article detected by the server.
Step S806, the server ranks the acquired influence evaluation parameters of the plurality of social contact accounts to obtain influence ranks of the plurality of social contact accounts;
step S807, the server feeds the influence ranks of the plurality of social account numbers and the influence index data of the corresponding social account numbers back to the client;
the influence index data of the social account may include the number of headlines, the average number of times of reading all articles in a day, the highest reading number, the total number of praise, and the like, and these index parameters may be captured by a crawler system, and the specific process is not described in detail.
Step S808, the client sorts according to the influence of the plurality of social accounts.
As shown in fig. 9, the influence ranks of multiple social account numbers in the social application platform in the last day may be displayed in a list manner, but are not limited to this, so that the user can intuitively know the social account number with higher influence in the social application platform in this time, and the user may select whether to join in a collection or directly pay attention to the corresponding social account number in combination with the corresponding influence index data, which is very convenient.
Optionally, when the client displays the ranking result, the display states of the n social account numbers with the highest influence may be adjusted, where n is a positive integer greater than 1, so that the n social account numbers are displayed more prominently, and a specific adjustment manner is not limited.
As another embodiment of the present invention, the client may be configured to present social account influence ranking lists in multiple social application platforms, and the social account influence calculation processes of different social application platforms are similar and may be calculated by a server of a corresponding social application platform according to the foregoing method. The user can switch to the social account ranking interface of other social application platforms as required, and query the date list, the week list or the month list of the social accounts according to the method.
Moreover, according to actual needs, a user can enter a corresponding setting menu through a self-defined list button set by the client, flexibly set lists and the like which are expected to be inquired, and the specific implementation process is not limited.
In addition, the influence ranking results of the social accounts on a certain aspect, such as one or more combinations of current affairs, science and technology, automobiles, education, food and the like, can be queried, and the server is informed of the results through a query request, so that the crawler system can crawl page data of articles in a targeted manner, social account influence evaluation parameters capable of showing the required influence on one or more aspects are obtained according to the method, and the obtained ranking results are fed back to the client to be displayed.
Referring to fig. 10, which is a block diagram of an apparatus for processing social account information according to an embodiment of the present invention, the apparatus may include:
an article association obtaining module 1010, configured to obtain a plurality of article associations existing in the social application platform;
in an actual application, the article association relationship may be an article reference relationship or an article type reference relationship, for example, the article association relationship is determined based on operations such as article forwarding and approval between social accounts, but is not limited thereto.
Optionally, the article association obtaining module 1010 may include:
the first grabbing unit is used for grabbing page data of at least one article published by any one social account in the social application platform;
the first analysis unit is used for analyzing Uniform Resource Locator (URL) data contained in page data of the at least one article and determining that the first article refers to a second article published by a second social account, wherein the first article is any one of the at least one article;
the second capturing unit is used for capturing page data of the second article, analyzing the page data of the first article and the page data of the second article to obtain a first social account identifier and a second social account identifier, wherein the first social account is a social account for publishing the first article;
a first determining unit, configured to determine an article association relationship between the first social account and the second social account by using the first social account identifier and the second social account identifier;
and then, the first analysis unit can be triggered to continuously analyze URL data contained in the page data of the second article, and whether the second article refers to articles published by other social accounts is determined until the currently analyzed article does not refer to the articles published by other social accounts, so that a plurality of article association relations existing in the social application platform are obtained.
As yet another embodiment of the present invention. The article association obtaining module 1010 may include:
the third capturing unit is used for capturing page data of all articles published by a plurality of social accounts in the social application platform;
the second analysis unit is used for analyzing all the captured page data to obtain an analysis result;
and a second determining unit, configured to determine, by using the analysis result, a plurality of article association relations existing in the plurality of social account numbers.
It should be noted that, with respect to the process of obtaining the article association relationship between the social account numbers by using the crawler system, reference may be made to the description of the corresponding part of the foregoing method embodiment, and this embodiment is not described herein again.
An influence propagation operation module 1020, configured to perform influence propagation operation on the multiple social account numbers by using the multiple article association relationships to obtain influence evaluation parameters of the corresponding social account numbers;
optionally, referring to fig. 11, the influence propagation operation module 1020 may include:
an association relationship graph building unit 1021, configured to build an association relationship graph of the social application platform by using the multiple social account numbers as nodes and using the obtained association relationships of the multiple articles; the influence propagation operation unit 1022 is configured to perform influence propagation operation on the multiple social account numbers based on the association relationship diagram of the social application platform to obtain influence evaluation parameters of the corresponding social account numbers;
in the embodiment of the invention, the influence evaluation parameter of the social account is used for representing the influence of the corresponding social account, and generally, the larger the influence evaluation parameter of the social account is, the larger the influence of the social account is, the more important the user of the social account is, and the more important the published article is.
Optionally, the influence propagation operation unit 1022 may include:
the first determining unit is used for determining an influence initial evaluation parameter of each social account in an association relation graph of the social application platform;
and the iterative operation unit is used for performing iterative operation on the influence initial evaluation parameters of the social account numbers until a first preset condition is reached to obtain the influence evaluation parameters of the corresponding social account numbers.
It should be noted that, with regard to the process of iterating the initial evaluation parameter of influence of each social account in the association relationship diagram of the social application platform, reference may be made to the description of the corresponding part of the foregoing method embodiment, which is not described herein again.
And an influence evaluation parameter storage module 1030, configured to store the obtained influence evaluation parameters of the multiple social account numbers.
The embodiment of the invention does not limit the storage mode of the obtained influence evaluation parameters of the plurality of social account numbers, and in practical application, the stored influence evaluation parameters of the social account numbers are dynamically updated, and the specific implementation process can refer to the description of the corresponding part of the embodiment of the method.
As another embodiment of the present invention, referring to fig. 12, the apparatus may further include:
the query request receiving module 1040 is configured to receive a query request sent by a client;
the query request is generated based on the operation of a user on a social account sequencing interface, and the query request carries query conditions;
a query condition determining module 1050, configured to parse the query request to obtain a query condition;
the query module 1060 is configured to obtain influence evaluation parameters of the multiple social account numbers matching the query condition;
the ranking module 1070 is configured to rank the acquired influence evaluation parameters of the multiple social contact accounts to obtain influence rankings of the multiple social contact accounts;
and the data transmission module 1080 is configured to feed back the influence ranking of the multiple social accounts and the influence index data of the corresponding social accounts to the client for ranking and displaying.
Optionally, the apparatus may further include:
the detection module is used for detecting that a new article citation relation appears on the social application platform;
and the updating module is used for updating the influence evaluation parameters of the social account numbers in the social application platform by using the new article reference relationship.
In summary, in the embodiment of the invention, the incidence relation graph of the social application platform is generated by analyzing the article incidence relation among the social account numbers in the social application platform, and then the social account number influence propagation operation is performed on the incidence relation graph to obtain the influence evaluation parameters representing the influence of the social account numbers, so that the user social account numbers with higher values have the higher influence evaluation parameters, the table rate values of the social account numbers are reflected, and the accuracy of the obtained influence evaluation parameters of the social account numbers is improved.
The article association relationship between the social accounts can be determined through various relationships such as whether the articles are forwarded, whether the articles are praised, whether the articles are commented, whether the articles are read and the like, so that the social account scores obtained through calculation in the embodiment of the invention can reflect complex requests of multiple dimensions of the social accounts, and the problems that the existing influence calculation method is completely realized by depending on article reading/praise data, so that the data channel is single and the obtained calculation result cannot comprehensively reflect the condition of each dimension of the social accounts are solved.
The structure of the virtual device for implementing the social account influence evaluation method is described above from the perspective of a functional module, and the constituent structure of the device for implementing the method will be described below from the perspective of a hardware structure.
Referring to fig. 2, an embodiment of the present invention further provides a hardware structure diagram of a server, where the server may include:
a communication interface 21;
a memory 22 for storing a program for implementing the social account influence evaluation method;
in the embodiment of the present invention, the memory may further store a plurality of article association relationships obtained by the server, a generated association relationship graph of the social application platform, finally obtained influence evaluation parameters of each social account, and the like, and may further include page data of each article captured by the crawler system, and the like, which may be specifically determined according to actual needs, and specific contents stored in the embodiment of the present invention are not limited.
The article reference relation pair acquisition module, the influence propagation operation module, the influence evaluation parameter storage module, the query request receiving module, the query condition determination module, the ranking module and the like can be program modules stored in a memory, and the processor executes the program modules stored in the memory to realize corresponding functions.
Alternatively, the memory may include volatile memory in a computer readable medium, random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM).
The processor 23 includes a kernel, the kernel calls corresponding program modules from the memory, the kernel may set one or more than one, the calculation of the score representing the influence of the social account and the ranking of the influence of the social account are realized by adjusting parameters of the kernel, and the program stored in the memory is specifically used for loading and executing, and includes:
acquiring a plurality of article association relations existing in a social application platform, wherein the article association relations represent association relations among articles published by a plurality of social accounts in the social application platform;
carrying out influence propagation operation on the social contact account numbers by utilizing the article association relations to obtain influence evaluation parameters of the corresponding social contact account numbers;
and storing the obtained influence evaluation parameters of the plurality of social account numbers.
For the step implementation process of the processor 23 executing the program, reference may be made to the description of the corresponding part of the above method embodiment, which is not described herein again.
Optionally, the executing the program by the processor 23 may further include:
receiving a query request sent by a client, wherein the query request is generated based on an operation of a user on a social account sorting interface and carries query conditions;
analyzing the query request to obtain the query condition;
acquiring influence evaluation parameters of a plurality of social account numbers matched with the query conditions;
sequencing the acquired influence evaluation parameters of the plurality of social contact accounts to obtain influence sequencing of the plurality of social contact accounts;
and feeding the influence sequencing of the social accounts and the influence index data of the corresponding social accounts back to the client for sequencing display.
Optionally, the processor 23 may further execute a program for implementing the following steps:
establishing an association relationship graph of the social application platform by using the obtained article association relationships with the social account numbers as nodes;
and carrying out influence propagation operation on the plurality of social account numbers based on the incidence relation graph of the social application platform to obtain influence evaluation parameters of the corresponding social account numbers.
Optionally, the processor 23 may further execute a program for implementing the following steps:
determining initial evaluation parameters of the influence of each social account in an association relation graph of the social application platform;
and carrying out iterative operation on the initial evaluation parameter of the influence of the social account number until a first preset condition is reached to obtain the evaluation parameter of the influence of the corresponding social account number.
Optionally, the processor 23 may further execute a program for implementing the following steps:
detecting that a new article reference relationship appears on the social application platform;
and updating the influence evaluation parameters of the plurality of social accounts in the social application platform by using the new article reference relationship.
Optionally, the processor 23 may further execute a program for implementing the following steps:
page data of at least one article published by any social account number in the social application platform is captured;
analyzing Uniform Resource Locator (URL) data contained in page data of the at least one article, and determining that a first article is a second article which refers to a second social account and is published, wherein the first article is any one of the at least one article;
capturing page data of the second article, and analyzing the page data of the first article and the page data of the second article to obtain a first social account identifier and a second social account identifier, wherein the first social account is a social account for publishing the first article;
determining an article association relationship between the first social account and the second social account by using the first social account identifier and the second social account identifier;
and continuously analyzing URL data contained in the page data of the second article, and determining whether the second article refers to articles published by other social accounts or not until the currently analyzed article does not refer to the articles published by other social accounts, so as to obtain a plurality of article association relations existing in the social application platform.
Optionally, the processor 23 may further execute a program for implementing the following steps:
capturing page data of all articles published by a plurality of social accounts in a social application platform;
analyzing all captured page data to obtain an analysis result;
and determining a plurality of article association relations existing in the plurality of social account numbers by using the analysis result.
The embodiment of the present application further provides a storage medium, where a computer program is stored, and the computer program is executed by a processor to implement each step of the social account influence evaluation method, where a specific execution process may refer to the description of the corresponding part in the above embodiment, and this embodiment is not described herein again.
The embodiment of the present application further provides a computer program product, which, when executed on an electronic device, can implement the computer program in the steps of the social account influence evaluation method described above, and specific contents may refer to descriptions of corresponding parts in the above method embodiments, which are not described herein again.
Finally, it should be noted that, in the embodiments, relational terms such as first, second and the like are only used for distinguishing one operation, unit or module from another operation, unit or module, and do not necessarily require or imply any actual relation or order between the units, the units or modules. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, apparatus, product, or system. Without further limitation, an element defined by the phrases "comprising a," "8230," "8230," or "comprising" does not exclude the presence of additional like elements in a process, method, or system comprising the element.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device and the server disclosed by the embodiment correspond to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the description of the method part.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the technical solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (6)
1. A social account influence evaluation method is characterized by comprising the following steps:
page data of at least one article published by any social account number in the social application platform is captured;
analyzing Uniform Resource Locator (URL) data contained in page data of the at least one article, and determining that a first article refers to a second article published by a second social account, wherein the first article is any one of the at least one article;
capturing page data of the second article, analyzing the page data of the first article and the page data of the second article to obtain a first social account identifier and a second social account identifier, and generating an article reference relationship pair between a first social account and the second social account, wherein the first social account is a social account for publishing the first article, and the first social account is different from the second social account;
determining an article association relationship between the first social account and the second social account according to an article reference relationship pair between the first social account and the second social account by using the first social account identifier and the second social account identifier;
continuing to analyze URL data contained in page data of the second article, and detecting whether the second article refers to articles published by other social accounts or not until the currently analyzed article does not refer to articles published by other social accounts, so as to obtain a plurality of article association relations existing in the social application platform, wherein the article association relations represent association relations among the articles published by the social accounts in the social application platform;
establishing an association relationship graph of the social application platform by using the obtained article association relationships with the social account numbers as nodes;
determining initial evaluation parameters of the influence of each social account in an association relationship graph of the social application platform;
performing iterative operation on the initial evaluation parameter of the influence of the social account until a first preset condition is reached to obtain the evaluation parameter of the influence of the corresponding social account, wherein if the number of times of forwarding articles issued by the social account is more, the influence of the social account is determined to be higher; if the article published by the social account is forwarded by other social accounts with high influence, determining that the influence of the social account is higher;
and storing the obtained influence evaluation parameters of the plurality of social account numbers.
2. The method of claim 1, further comprising:
receiving a query request sent by a client, wherein the query request is generated based on the operation of a user on a social account sorting interface and carries query conditions;
analyzing the query request to obtain the query condition;
acquiring influence evaluation parameters of a plurality of social account numbers matched with the query conditions;
sequencing the acquired influence evaluation parameters of the plurality of social contact accounts to obtain influence sequencing of the plurality of social contact accounts;
and feeding the influence sequencing of the social accounts and the influence index data of the corresponding social accounts back to the client for sequencing display.
3. The method of claim 1, further comprising:
detecting that a new article reference relationship appears on the social application platform;
and updating the influence evaluation parameters of the plurality of social accounts in the social application platform by using the new article reference relationship.
4. A social account influence evaluation device, the device comprising:
the article association relation acquisition module is used for acquiring a plurality of article association relations existing in a social application platform, wherein the article association relations represent association relations among articles published by a plurality of social account numbers in the social application platform;
the influence propagation operation module is used for carrying out influence propagation operation on the social account numbers by utilizing the article incidence relations to obtain influence evaluation parameters of the corresponding social account numbers;
the influence evaluation parameter storage module is used for storing the obtained influence evaluation parameters of the plurality of social account numbers;
wherein, the influence propagation operation module comprises:
the association relationship graph building unit is used for building an association relationship graph of the social application platform by taking the plurality of social account numbers as nodes and utilizing the obtained association relationships of the plurality of articles;
the first determining unit is used for determining an influence initial evaluation parameter of each social account in an association relationship graph of the social application platform;
the iterative operation unit is used for performing iterative operation on the initial evaluation parameters of the influence of each social account until a first preset condition is reached to obtain the evaluation parameters of the influence of the corresponding social account, wherein if the number of times that the article issued by the social account is forwarded is more, the influence of the social account is determined to be higher; if the article published by the social account number is forwarded by other social account numbers with high influence, determining that the influence of the social account number is higher;
the article association relation obtaining module comprises:
the first capturing unit is used for capturing page data of at least one article published by any social account in the social application platform;
the first analysis unit is used for analyzing Uniform Resource Locator (URL) data contained in page data of the at least one article and determining that the first article refers to a second article published by a second social account, wherein the first article is any one of the at least one article;
the second capturing unit is used for capturing page data of the second article, analyzing the page data of the first article and the page data of the second article to obtain a first social account identifier and a second social account identifier, and generating an article reference relationship pair between a first social account and the second social account, wherein the first social account is a social account for publishing the first article, and the first social account is different from the second social account;
a first determining unit, configured to determine, by using the first social account identifier and the second social account identifier, an article association relationship between the first social account and the second social account according to an article reference relationship pair between the first social account and the second social account;
the first analysis unit is further configured to continue to analyze URL data included in the page data of the second article, and detect whether the second article refers to an article published by another social account, until it is determined that the currently analyzed article does not refer to an article published by another social account, so as to obtain a plurality of article association relationships existing in the social application platform, where the article association relationships indicate association relationships among articles published by multiple social accounts in the social application platform.
5. The apparatus of claim 4, further comprising:
the system comprises a query request receiving module, a query request sending module and a query processing module, wherein the query request receiving module is used for receiving a query request sent by a client, the query request is generated based on the operation of a user on a social account ranking interface, and the query request carries query conditions;
the query condition determining module is used for analyzing the query request to obtain the query condition;
the query module is used for acquiring influence evaluation parameters of a plurality of social account numbers matched with the query conditions;
the sequencing module is used for sequencing the acquired influence evaluation parameters of the plurality of social contact accounts to obtain influence sequencing of the plurality of social contact accounts;
and the data transmission module is used for feeding the influence sequencing of the plurality of social account numbers and the influence index data of the corresponding social account numbers back to the client for sequencing display.
6. A storage medium having stored thereon a computer program, wherein the computer program is executed by a processor to implement the steps of the social account impact evaluation method according to any one of claims 1 to 3.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711349202.7A CN109949172B (en) | 2017-12-15 | 2017-12-15 | Social account influence evaluation method and device and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711349202.7A CN109949172B (en) | 2017-12-15 | 2017-12-15 | Social account influence evaluation method and device and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109949172A CN109949172A (en) | 2019-06-28 |
CN109949172B true CN109949172B (en) | 2022-12-27 |
Family
ID=67005583
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711349202.7A Active CN109949172B (en) | 2017-12-15 | 2017-12-15 | Social account influence evaluation method and device and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109949172B (en) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110457601B (en) * | 2019-08-15 | 2023-10-24 | 腾讯科技(武汉)有限公司 | Social account identification method and device, storage medium and electronic device |
CN111681120A (en) * | 2020-05-20 | 2020-09-18 | 卓尔智联(武汉)研究院有限公司 | Core user determination method, device and storage medium |
CN111931060B (en) * | 2020-08-25 | 2023-11-03 | 腾讯科技(深圳)有限公司 | Evaluation method of influence of release platform, related device and computer storage medium |
CN113807733A (en) * | 2021-09-28 | 2021-12-17 | 杭州网易云音乐科技有限公司 | User influence evaluation method, device, medium and electronic equipment |
CN116450757A (en) * | 2023-06-19 | 2023-07-18 | 深圳索信达数据技术有限公司 | Method, device, equipment and storage medium for determining evaluation index of data asset |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105260849A (en) * | 2015-10-21 | 2016-01-20 | 内蒙古科技大学 | Scientific researcher evaluation method across social networks |
CN106875277A (en) * | 2017-01-16 | 2017-06-20 | 星云纵横(北京)大数据信息技术有限公司 | A kind of determination methods of social media account influence power |
CN107391659A (en) * | 2017-07-18 | 2017-11-24 | 北京工业大学 | A kind of citation network academic evaluation sort method based on credit worthiness |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWI582617B (en) * | 2015-11-18 | 2017-05-11 | 財團法人資訊工業策進會 | Article influence prediction method and article influence prediction device using the same |
-
2017
- 2017-12-15 CN CN201711349202.7A patent/CN109949172B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105260849A (en) * | 2015-10-21 | 2016-01-20 | 内蒙古科技大学 | Scientific researcher evaluation method across social networks |
CN106875277A (en) * | 2017-01-16 | 2017-06-20 | 星云纵横(北京)大数据信息技术有限公司 | A kind of determination methods of social media account influence power |
CN107391659A (en) * | 2017-07-18 | 2017-11-24 | 北京工业大学 | A kind of citation network academic evaluation sort method based on credit worthiness |
Non-Patent Citations (1)
Title |
---|
SARank:一种学术社交网络用户影响力分析模型;顾瑞春等;《计算机技术与发展》;20171205(第03期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN109949172A (en) | 2019-06-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109949172B (en) | Social account influence evaluation method and device and storage medium | |
US11449719B2 (en) | Image evaluation | |
US11659050B2 (en) | Discovering signature of electronic social networks | |
CN108446410B (en) | Information recommendation method, device, system, equipment and readable storage medium | |
US9530160B2 (en) | System and method for an affinity capture, user feedback and affinity analysis | |
TWI618015B (en) | Method,computer-readable non-transitory storage medium,and system for mobile device-related measures of affinity | |
US20150227972A1 (en) | System and methods for identifying and promoting tagged commercial products | |
US20110173198A1 (en) | Recommendations based on relevant friend behaviors | |
US20090228397A1 (en) | Exchange for tagged user information with scarcity control | |
EP2048612A1 (en) | System and method for searching network users | |
US20130332385A1 (en) | Methods and systems for detecting and extracting product reviews | |
CN107644100B (en) | Information processing method, device and system and computer readable storage medium | |
CA2917140A1 (en) | Social network for employment search | |
US20150269606A1 (en) | Multi-source performance and exposure for analytics | |
CN112771564A (en) | Artificial intelligence engine that generates semantic directions for web sites to map identities for automated entity seeking | |
WO2018081966A1 (en) | User association method, terminal and server | |
KR101559719B1 (en) | Auto-learning system and method for derive effective marketing | |
CN108259638A (en) | Personal group list intelligent sorting method, intelligent terminal and storage medium | |
CN107798012B (en) | Reading resource comment pushing method and system | |
US20130275223A1 (en) | Future ad targeting | |
CN111447081A (en) | Data chain generation method, device, server and storage medium | |
CN111159575A (en) | Friend making method and device based on mobile banking | |
JP5762456B2 (en) | Advertisement providing device | |
US20160098773A1 (en) | Infusing product popularity insights into search results for product research queries | |
JP6353396B2 (en) | Advertisement providing apparatus and advertisement providing method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |