Method for determining intimacy in social network

Abstract

The invention provides a method for determining intimacy in a social network, and relates to the technical field of Internet, and the method comprises the steps: obtaining the number of associated users of a target creator from social network data, and converting the number of associated users into a relation score reflecting the influence and attention distraction degree of the target creator; based on the number of fans of the target creator and the number of common fans, determining a first network coefficient representing the connection strength of the target associated user in the fan network; determining a second network coefficient representing the influence of the target associated user in the concerned network based on the total concerned number and the concerned number of the target creator; correcting the relationship score by using the first network coefficient and the second network coefficient to determine a fan relationship score and an attention relationship score; and determining the intimacy based on the fan relationship score and the attention relationship score. By adopting the method for determining the intimacy in the social network, the accuracy of intimacy calculation is improved, and the complexity of data calculation is reduced.

Description

Technical Field

[0001] This application relates to the field of Internet technology, and more specifically, to a method for determining intimacy in a social network. Background Technology

[0002] With the rapid development of internet technology, numerous online social platforms have emerged, such as Weibo and Twitter, allowing users to build vast social networks. To promote the healthy development of these networks, these platforms typically analyze the intimacy between users, quantifying relationship value to optimize the platform ecosystem and understand users' social needs. Current technologies usually determine user intimacy based on dimensions such as interaction behavior, graph theory analysis, and semantic mining. For example, intimacy is calculated by statistically analyzing the frequency of user interactions (likes, comments, private messages) and shared activities.

[0003] However, existing methods for determining intimacy rely on interaction behaviors and specific behavioral data, but these behaviors and data mainly reflect the breadth and intensity of the interaction, and therefore cannot comprehensively and accurately measure the intimacy between users. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a method for determining intimacy in social networks to overcome at least one of the above-mentioned defects.

[0005] In a first aspect, embodiments of this application provide a method for determining intimacy in a social network, including: The number of associated users of a target creator is obtained from social network data. The number of associated users is converted into a relationship score that reflects the influence and attention diversion of the target creator. The number of associated users is the number of users who have a relationship with the target creator. Based on the total number of fans of the target creator and the number of fans in common, a first network coefficient is determined to represent the connection strength of the target associated user in the fan network. The number of fans in common is the number of users who are fans of both the target creator and the target associated user. Based on the total number of followers and the number of followers of the target creator, a second network coefficient is determined to represent the influence of the target associated user in the following network. The number of followers is the number of users who are followed by the target creator among the followers of the target associated user. The relationship score is corrected using the first network coefficient and the second network coefficient to determine the fan relationship score and the follower relationship score. Based on fan relationship scores and follower relationship scores, the intimacy between target users and target creators is determined.

[0006] In an optional implementation, the number of associated users includes the number of followers of the target creator and the number of followers of the target creator. The number of associated users is converted into a relationship score that reflects the influence and attention diversion of the target creator, including: converting the number of followers into a first relationship score that represents the influence of the target creator; and converting the number of followers into a second relationship score that represents the attention diversion of the target creator.

[0007] In an optional implementation, the intimacy between the target associated user and the target creator is determined based on the fan relationship score and the follower relationship score, including: determining the mutual follow score based on the fan relationship score and the follower relationship score; and determining the intimacy between the target associated user and the target creator based on the sum of the fan relationship score, the follower relationship score, and the mutual follow score.

[0008] In an optional implementation, a mutual follow score is determined based on the fan relationship score and the follower relationship score, including: determining a basic mutual follow score based on the geometric mean of the product of the fan relationship score and the follower relationship score; and determining a mutual follow score based on the product of the basic mutual follow score and a preset mutual follow coefficient.

[0009] In an optional implementation, the number of followers is converted into a first relationship score that characterizes the influence of the target creator, including: determining the increase in the number of followers based on the difference between the number of followers and a preset follower growth threshold; determining the initial influence based on the arctangent of the product of the increase in the number of followers and the preset influence slope; and determining the first relationship score based on the sum of the product of the initial influence and the preset influence coefficient and a set offset.

[0010] In an optional implementation, the number of followers is converted into a second relationship score that characterizes the degree of distraction of the target creator, including: determining the second relationship score based on the logarithm of the sum of the number of followers and a preset relationship value.

[0011] In an optional implementation, a first network coefficient representing the connection strength of the target associated user in the fan network is determined based on the total number of fans of the target creator and the number of fans in common. This includes: determining the difference between the total number of fans of the target creator and the number of fans in common as a first difference; and determining the first network coefficient based on the sum of the first difference raised to the power of a first set parameter and a preset base value.

[0012] In an optional implementation, a second network coefficient representing the influence of the target associated user in the following network is determined based on the total number of followers and the number of followers of the target creator, including: determining the difference between the total number of followers and the number of followers of the target creator as a second difference; and determining the second network coefficient based on the sum of the second difference raised to the power of a second set parameter and a preset base value.

[0013] In an optional implementation, the relationship score is corrected using the first network coefficient and the second network coefficient to determine the fan relationship score and the follower relationship score, including: determining the first basic score corresponding to the first relationship score and the second basic score corresponding to the second relationship score based on the correspondence between the relationship score interval and the basic score interval; determining the fan relationship score based on the product of the first basic score, the second basic score and the first network coefficient; and determining the follower relationship score based on the product of the first basic score, the second basic score and the second network coefficient.

[0014] In an optional implementation, determining the first basic score corresponding to the first relationship score and the second basic score corresponding to the second relationship score based on the correspondence between the relationship score interval and the basic score interval includes: for a specified relationship score, selecting a target specified relationship score interval corresponding to the specified relationship score from multiple specified relationship score intervals, wherein the specified relationship score includes either the first relationship score or the second relationship score; determining a target specified basic score interval based on the correspondence between the specified relationship score interval and the specified basic score interval, wherein the specified relationship score interval and the specified basic score interval are numerical intervals corresponding to the specified relationship score; and determining the specified basic score corresponding to the position of the specified relationship score in the target specified relationship score interval using an interpolation algorithm based on the position of the specified relationship score in the target specified relationship score interval, wherein the specified basic score includes either the first basic score or the second basic score, and the specified basic score is the basic score corresponding to the specified relationship score.

[0015] The embodiments of this application bring the following beneficial effects: This application provides a method for determining intimacy in social networks. It measures a creator's relationship score in a social network from two dimensions: influence and attention dispersion. Then, it uses a first network coefficient and a second network coefficient to reflect the connection strength of the target related user in the fan network and its influence in the attention network, respectively. By combining the connection strength and influence of two users in the social network, the intimacy is determined, thereby improving the accuracy of intimacy calculation. Compared with existing methods for determining intimacy in social networks, this method solves the problem of low accuracy in intimacy calculation.

[0016] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart of the intimacy determination method in a social network provided in an embodiment of this application is shown; Figure 2 A flowchart illustrating the steps for determining the relationship score provided in an embodiment of this application is shown; Figure 3 A flowchart illustrating the steps for determining the first network coefficients provided in an embodiment of this application is shown; Figure 4 A flowchart illustrating the steps for determining the second network coefficients provided in an embodiment of this application is shown; Figure 5 A flowchart illustrating the steps for determining fan relationship score and follower relationship score provided in an embodiment of this application is shown; Figure 6 This invention provides a schematic diagram of the structure of a social network intimacy determination device according to an embodiment of the present application. Figure 7 A schematic diagram of the structure of the electronic device provided in the embodiments of this application is shown. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. Based on the embodiments of this application, every other embodiment obtained by those skilled in the art without inventive effort falls within the scope of protection of this application.

[0020] It is worth noting that prior to this application, with the rapid development of internet technology, numerous online social platforms emerged, such as Weibo and Twitter, allowing users to build vast social networks. To promote the healthy development of these networks, these platforms typically analyze the intimacy between users, quantifying relationship value to optimize the platform ecosystem and understand users' social needs. Existing technologies usually determine user intimacy based on dimensions such as interaction behavior, graph theory analysis, and semantic mining. For example, they calculate intimacy by statistically analyzing the frequency of user interactions (likes, comments, private messages) and shared activities. However, existing methods for determining intimacy rely on interaction behavior and specific behavioral data, which primarily reflect the breadth and intensity of interaction, thus failing to comprehensively and accurately measure the intimacy between users.

[0021] Based on this, embodiments of this application provide a method for determining intimacy in social networks to improve the accuracy of intimacy calculation.

[0022] To facilitate understanding of this embodiment, the exemplary steps provided in this application embodiment will be described below.

[0023] Please see Figure 1 , Figure 1 This is a flowchart illustrating a method for determining intimacy in a social network, provided as an embodiment of this application. Figure 1 As shown in the embodiments of this application, the method for determining intimacy in a social network includes: Step S101: Obtain the number of associated users of the target creator from social network data, and convert the number of associated users into a relationship score that reflects the influence and attention diversion of the target creator; Step S102: Based on the total number of fans of the target creator and the number of fans in common, determine the first network coefficient that represents the connection strength of the target associated user in the fan network. Step S103: Based on the total number of followers and the number of followers of the target creator, determine the second network coefficient that represents the influence of the target associated user in the following network. Step S104: The relationship score is corrected using the first network coefficient and the second network coefficient respectively to determine the fan relationship score and the follower relationship score. Step S105: Determine the intimacy between the target related user and the target creator based on fan relationship score and follower relationship score.

[0024] Among them, the number of associated users is the number of users who are associated with the target creator, the number of shared fans is the number of users who are fans of both the target creator and the target associated users, and the number of followers is the number of fans of the target associated users who are followed by the target creator.

[0025] The method for determining intimacy in social networks provided in this application can measure the relationship score of creators in social networks from two dimensions: influence and attention dispersion. Then, the first network coefficient and the second network coefficient reflect the connection strength of the target related user in the fan network and its influence in the attention network, respectively. The connection strength and influence of two users in social networks are combined to determine intimacy, thereby improving the accuracy of intimacy calculation. Compared with the intimacy determination method in social networks in the prior art, it solves the problem of low accuracy in intimacy calculation.

[0026] To facilitate understanding of this embodiment, the following description uses the example of applying the social network intimacy determination method provided in this application embodiment to a server to illustrate the above exemplary steps provided in this application embodiment.

[0027] In step S101, the number of associated users of the target creator is obtained from social network data, and the number of associated users is converted into a relationship score that reflects the influence and attention diversion of the target creator.

[0028] In this step, the number of associated users refers to the number of users who have a connection with the target creator. The number of associated users includes the number of users who follow the target creator and the number of users who are followed by the target creator. The number of users who follow the target creator is called the target creator's number of followers, and the number of users who are followed by the target creator is called the target creator's number of followers.

[0029] Social network data refers to social data obtained from social network platforms. Social network data includes content data, the following list and follower list of each creator on the social network platform. For example, on the Twitter platform, content data refers to all tweets.

[0030] The relationship score includes a first relationship score that represents the target creator's influence and a second relationship score that represents the target creator's degree of distraction.

[0031] In this embodiment of the application, in order to determine the intimacy between each associated user of the target creator and the target creator, after obtaining the social network data, the creator information of the target creator, the associated user information of the target creator, the number of fans of the target creator, and the number of followers of the target creator can be extracted from the social network data.

[0032] Creator information refers to information used to describe a creator, including the number of the creator's followers, the number of followers the creator follows, the creator's user ID, the creator's user nickname, and the creator's platform account.

[0033] Related user information refers to information used to describe a creator's fans and followers. For a target creator, related user information includes the user ID of each related user, the number of fans each related user has, the number of followers each related user is following, the fan tag for each related user, and the followed tag for each related user. The fan tag indicates whether the related user is a fan of the creator (i.e., a fan identifier), and the followed tag indicates whether the related user is followed by the creator (i.e., a followed identifier).

[0034] Next, a rating table corresponding to the target creator is created and initialized. This rating table includes multiple fields such as user identifier, fan relationship rating, follower relationship rating, mutual follower rating, and total score, with each associated user's rating initialized to 0. Specifically, the user identifier field records the user identifier of each associated user related to the target creator; the fan relationship rating represents the intimacy between the associated user and the target creator in the fan relationship dimension; the follower relationship rating represents the intimacy between the associated user and the target creator in the follower relationship dimension; the mutual follower rating represents the intimacy between the associated user and the target creator in the mutual follower relationship dimension; and the total score represents the weighted sum of the fan relationship rating, follower relationship rating, and mutual follower rating.

[0035] The following reference Figure 2 This section will introduce the specific process for determining relationship scores.

[0036] Figure 2 A flowchart illustrating the steps for determining the relationship score provided in an embodiment of this application is shown, as follows: Figure 2 As shown, the steps for determining relationship scores include: Step S1011: Convert the number of followers into a first relationship score that represents the influence of the target creator.

[0037] Since the contribution of fan growth to influence is usually curvilinear, it is necessary to simulate this non-linear relationship in order to evaluate the influence of a target creator by the number of fans.

[0038] In one example, the increase in the number of followers is determined based on the difference between the number of followers and the preset follower growth rate threshold; the initial influence is determined based on the arctangent of the product of the increase in the number of followers and the preset influence slope; and the first relationship score is determined based on the sum of the product of the initial influence and the preset influence coefficient and the set offset.

[0039] For example: the first relationship score is denoted as fan_score, the target creator's number of followers is denoted as F, the maximum influence value is denoted as L, the preset follower growth threshold is denoted as M, and the preset influence slope is denoted as: The offset is denoted as b. With the preset influence coefficient being L / π, the increase in the number of followers can be expressed as: The initial influence can be expressed as: The first relation score, fan_score, can be represented as: Where L, M, k, and b are all set values.

[0040] Step S1012: Convert the number of followers into a second relation score that represents the degree of distraction of the target creator.

[0041] The attention of a target creator decreases as the number of users they follow increases; this attention decay effect can be simulated using a curve.

[0042] In one example, the second relationship score is determined based on the logarithm of the sum of the number of followers and the preset relationship value.

[0043] For example: the second relationship score is denoted as follow_score, the default relationship value is denoted as val, and the number of followers of the target creator is denoted as A. Then the second relationship score follow_score can be represented as: For example, the value of val can be 1.

[0044] It should be noted that there is no distinction between the execution order of steps S1011 and S1012. Step S1011 can be executed first and then step S1012, or step S1012 can be executed first and then step S1011, or steps S1011 and S1012 can be executed simultaneously.

[0045] In step S102, based on the total number of fans of the target creator and the number of fans in common, a first network coefficient representing the connection strength of the target associated user in the fan network is determined.

[0046] In this step, the target associated user can refer to one of several associated users who have a relationship with the target creator.

[0047] A fan network refers to the network formed by the fans of a target creator. The larger the first network coefficient, the greater the influence of the target-related users on the target creator's fan base; the smaller the first network coefficient, the smaller the influence of the target-related users on the target creator's fan base.

[0048] To accurately calculate the intimacy between a target associated user and a target creator, the connection strength of the target associated user within the fan network can be quantified to calculate the intimacy between the two through the quantified connection strength.

[0049] The following reference Figure 3 This section will introduce the specific process for determining the first network coefficients.

[0050] Figure 3 A flowchart illustrating the steps for determining the first network coefficients provided in an embodiment of this application is shown, as follows: Figure 3 As shown, the steps for determining the first network coefficients include: Step S1021: Determine the first difference between the total number of fans of the target creator and the number of fans in common.

[0051] The total number of followers of a target creator can refer to the number of users who follow the target creator. The total number of followers of a target creator is denoted as n.

[0052] For the target creator's fan base, iterate through all user accounts within that fan base and check if each user account also follows the target-related user. If the user account follows the target-related user, increment the co-following count by one, until all the target creator's fan accounts have been iterated through to determine the final co-following count. Here, the co-following count can refer to the number of users who follow both the target creator and the target-related user, denoted as x1_follow. The first difference can then be expressed as: .

[0053] Step S1022: Determine the first network coefficient based on the sum of the first power of the first difference of the first set parameter and the preset base value.

[0054] The first network coefficient is denoted as: fan_struct_coeff, and the first set parameter is denoted as: Let the default base value be denoted as c. Then the first network coefficient fan_struct_coeff can be expressed as: As an example, , .

[0055] The scoring table also includes a first network coefficient field. After determining the first network coefficient, the first network coefficient is recorded in the data item corresponding to the target associated user under the first network coefficient field.

[0056] It should be noted that, if If the first network coefficient is 1, then the first network coefficient is 1.

[0057] In step S103, a second network coefficient representing the influence of the target creator in the following network is determined based on the total number of followers and the number of followers.

[0058] In this step, in order to accurately calculate the intimacy between the target associated user and the target creator, the influence of the target associated user in the attention network can be quantified, so as to calculate the intimacy between the two through the quantified influence.

[0059] The second network refers to the network formed by the users followed by the target creator. The larger the second network coefficient, the greater the influence of the target associated users on the user group followed by the target creator. The smaller the second network coefficient, the smaller the influence of the target associated users on the user group followed by the target creator.

[0060] The following reference Figure 4 This section will introduce the specific process for determining the second network coefficients.

[0061] Figure 4 A flowchart illustrating the steps for determining the first network coefficients provided in an embodiment of this application is shown, as follows: Figure 4 As shown, the steps for determining the second network coefficients include: Step S1031: Determine the difference between the total number of followers and the number of followers of the target creator as the second difference.

[0062] The total number of followers of a target creator can refer to the number of users followed by the target creator. The target creator is a fan of these users. The total number of followers of a target creator is denoted as w.

[0063] For the target associated user, iterate through all user accounts that follow that user, checking if each user account is also followed by the target creator (i.e., the target creator is a follower of that user account). If the user account's follower list includes the target creator (i.e., checking if the user account is also followed by the target creator), increment the number of followers in the community by one. Continue this process until all user accounts have been iterated through to determine the final number of followers in the community. The number of followers refers to the number of followers of the target associated user who are followed by the target creator. This number is denoted as x2_follow. The second difference can then be expressed as: .

[0064] Step S1032: Determine the second network coefficient based on the sum of the second power of the second difference of the second set parameter and the preset base value.

[0065] The second network coefficient is denoted as: follow_struct_coeff, and the second parameter setting is denoted as: Let the default base value be denoted as c. Then the second network coefficient follow_struct_coeff can be expressed as: As an example, , .

[0066] The scoring table also includes a second network coefficient field. After the second network coefficient is determined, it is recorded in the data item corresponding to the target associated user under the second network coefficient field.

[0067] It should be noted that, if If the second network coefficient is 1, then the value of the second network coefficient is 1.

[0068] In step S104, the relationship score is corrected using the first network coefficient and the second network coefficient to determine the fan relationship score and the follower relationship score.

[0069] In this step, since the first network coefficient represents the connection strength of the target associated user in the fan network, the greater the connection strength of the target associated user in the fan network, the more the target associated user can influence more fans, and the more likely the target associated user is to interact with the target creator. Therefore, the first network coefficient will affect the intimacy between the target associated user and the target creator, and the first network coefficient is positively correlated with the intimacy between the target associated user and the target creator.

[0070] Similarly, since the second network coefficient represents the influence of the target associated user in the attention network, the greater the influence of the target associated user in the attention network, the more followers the target associated user can influence, and the more likely the target associated user is to interact with the target creator. Therefore, the second network coefficient also affects the intimacy between followers and target creators.

[0071] Therefore, the first network coefficient can be used to correct the score of the first relationship, and the second network coefficient can be used to correct the score of the second relationship.

[0072] Before determining the analysis relationship score and the attention relationship score, first determine the minimum and maximum basic score values. Based on the minimum and maximum basic score values, divide the basic score into multiple basic score intervals. Simultaneously, divide the relationship score into multiple relationship score intervals and determine the correspondence between the relationship score intervals and the basic score intervals.

[0073] The following reference Figure 5 This section will explain the process of determining fan relationship score and follower relationship score.

[0074] Figure 5A flowchart illustrating the steps for determining fan relationship scoring and follower relationship scoring provided in an embodiment of this application is shown, such as... Figure 5 As shown, the steps for determining fan relationship score and follower relationship score include: Step S1041: Based on the correspondence between the relationship scoring interval and the basic scoring interval, determine the first basic score corresponding to the first relationship score and the second basic score corresponding to the second relationship score.

[0075] The relationship scoring interval includes the first relationship scoring interval corresponding to the first relationship score and the second relationship scoring interval corresponding to the second relationship score. The basic scoring interval includes the first basic scoring interval corresponding to the first basic score and the second basic scoring interval corresponding to the second basic score.

[0076] The correspondence between the first relational scoring interval and the first basic scoring interval is described in Table 1 below.

[0077]

[0078] As shown in Table 1, the numerical range corresponding to the first starting value and the first ending value is the first relationship scoring range, and the numerical range corresponding to the first starting base score and the first ending base score is the first base score range. When the first relationship score is 200, the target first relationship scoring range is [100, 500), and the target first base score range is [16, 14].

[0079]

[0080] As shown in Table 2, the numerical range corresponding to the second starting value and the second ending value is the second relationship scoring range, and the numerical range corresponding to the second starting base score and the second ending base score is the second base score range. When the second relationship score is 20, the target second relationship scoring range is [10, 50), and the target second base score range is [1, 0.9].

[0081] The following example of a specified relationship score illustrates the process of determining the basic score.

[0082] The first step is to select the target specified relationship score interval from multiple specified relationship score intervals for the specified relationship score.

[0083] The specified relationship score includes either the first relationship score or the second relationship score, and the specified base score includes either the first base score or the second base score. The specified base score is the base score corresponding to the specified relationship score.

[0084] The specified relationship score can be either the first relationship score or the second relationship score. The specified base score can be either the first base score or the second base score. If the specified relationship score is the first relationship score, then the specified base score is the first base score; if the specified relationship score is the second relationship score, then the specified base score is the second base score.

[0085] The specified relationship scoring interval and the specified basic scoring interval are the numerical intervals corresponding to the specified relationship score. When the specified relationship score is the first relationship score, the target first relationship scoring interval is the target specified relationship scoring interval, and the target first basic scoring interval is the target specified basic scoring interval.

[0086] Assuming the specified relationship score is the first relationship score, then the target first relationship score interval corresponding to the first relationship score is selected from multiple first relationship score intervals. Taking the above example, if the first relationship score is 200, then the target first relationship score interval corresponding to the first relationship score selected from Table 1 is [100, 500).

[0087] The second step is to determine the target specified basic score interval based on the correspondence between the specified relational score interval and the specified basic score interval.

[0088] As shown in Table 1, the target first relational score interval [100, 500) corresponds to the first basic score interval [16, 14). Therefore, the first basic score interval [16, 14) is the target first basic score interval, which is also the target specified basic score interval.

[0089] The third step is to use an interpolation algorithm to determine the specified basic score corresponding to the position in the specified basic score interval of the target based on the position of the specified relationship score.

[0090] Since the first relationship score 200 is at the 25th percentile in the target first relationship score interval [100, 500), the value at the 25th percentile in the specified basic score interval is also selected as the specified basic score. At this time, a linear interpolation algorithm can be used to determine that the first basic score corresponding to the first relationship score 200 is 15.5.

[0091] The second basic score is determined in the same way as the first basic score, except that when determining the second basic score, Table 2 is used to determine the target-specified basic score interval, and a linear interpolation algorithm is used to calculate the second basic score within the target-specified basic score interval in Table 2.

[0092] Step S1042: Determine the fan relationship score based on the product of the first basic score, the second basic score, and the first network coefficient.

[0093] Fan relationship score is denoted as: Fa_score, first basic score is denoted as: fan_bascore, second basic score is denoted as: follow_bascore, fan tag is denoted as: fan_sign, fan relationship score is: .

[0094] Step S1043: Determine the attention relationship score based on the product of the first basic score, the second basic score, and the second network coefficient.

[0095] The follow relationship score is denoted as Fo_score, the first basic score is denoted as fan_bascore, the second basic score is denoted as follow_bascore, the followed flag is denoted as fo_sign, and the follow relationship score is: .

[0096] In step S105, the intimacy between the target associated user and the target creator is determined based on the fan relationship score and the follower relationship score.

[0097] In this step, in order to reflect the impact of fan networks and follower networks on intimacy, mutual follower ratings need to be included in the intimacy calculation.

[0098] In one example, a mutual follow score is determined based on fan relationship score and follower relationship score, and the intimacy between the target associated user and the target creator is determined based on the sum of the fan relationship score, follower relationship score and mutual follow score.

[0099] For example: A basic mutual follow score is determined based on the geometric mean of the product of the fan relationship score and the follower relationship score. The final mutual follow score is determined by multiplying this basic score by a preset mutual follow coefficient. Intimacy is denoted as Intimacy, and the basic mutual follow score is denoted as Fm_score. In the above formula, .

[0100] In this way, the intimacy between each associated user and the target creator can be calculated, and then the associated users can be sorted in descending order of intimacy to determine the ranking of intimacy between the associated users and the target creator.

[0101] Based on the same inventive concept, this application also provides a device for determining intimacy in a social network, which corresponds to the method for determining intimacy in a social network. Since the principle of the device in this application is similar to the method for determining intimacy in a social network described above, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0102] Please see Figure 6 , Figure 6This is a schematic diagram of a device for determining intimacy in a social network, provided as an embodiment of this application. Figure 6 As shown, the intimacy determination device 200 in the social network includes: The scoring determination module 201 is used to obtain the number of associated users of the target creator from social network data, and convert the number of associated users into a relationship score that reflects the influence and attention diversion of the target creator. The number of associated users is the number of users who have a relationship with the target creator. The first coefficient determination module 202 is used to determine a first network coefficient representing the connection strength of the target associated user in the fan network based on the total number of fans of the target creator and the number of common fans. The number of common fans is the number of users who are fans of both the target creator and the target associated user. The second coefficient determination module 203 is used to determine the second network coefficient representing the influence of the target associated user in the following network based on the total number of followers and the number of followers of the target creator. The rating correction module 204 is used to correct the relationship rating using the first network coefficient and the second network coefficient respectively, so as to determine the fan relationship rating and the follower relationship rating. The intimacy determination module 205 is used to determine the intimacy between the target associated user and the target creator based on fan relationship score and follower relationship score.

[0103] Please see Figure 7 , Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 7 As shown, the electronic device 300 includes a processor 310, a memory 320, and a bus 330.

[0104] The memory 320 stores machine-readable instructions executable by the processor 310. When the electronic device 300 is running, the processor 310 and the memory 320 communicate via the bus 330. When the machine-readable instructions are executed by the processor 310, they can perform the operations described above. Figure 1 The steps of the method for determining intimacy in a social network in the method embodiment shown are described in detail in the method embodiment, and will not be repeated here.

[0105] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can perform the above-described actions. Figure 1 The steps of the method for determining intimacy in a social network in the method embodiment shown are described in detail in the method embodiment, and will not be repeated here.

[0106] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0107] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the shown or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0108] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0109] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0110] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0111] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The scope of protection of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this application. Such modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for determining closeness in a social network, the method comprising: The method comprises the following steps: obtaining the number of associated users of a target author from social network data, and converting the number of associated users into a relationship score reflecting the influence and attention dispersion degree of the target author, wherein the number of associated users is the number of users having an association relationship with the target author; determining a first network coefficient representing the connection strength of the target associated user in the fan network based on the total number of fans of the target author and the number of common fans, wherein the number of common fans is the number of users who are fans of both the target author and the target associated user; determining a second network coefficient representing the influence of the target associated user in the attention network based on the total number of attention of the target author and the number of attention, wherein the number of attention is the number of users who are fans of the target associated user and are followed by the target author; correcting the relationship score by using the first network coefficient and the second network coefficient respectively to determine a fan relationship score and an attention relationship score; determining the closeness between the target associated user and the target author based on the fan relationship score and the attention relationship score.

2. The method of claim 1, wherein, The number of associated users includes the number of fans following the target author and the number of attention followed by the target author, and the conversion of the number of associated users into a relationship score reflecting the influence and attention dispersion degree of the target author comprises: converting the number of fans into a first relationship score representing the influence of the target author; converting the number of attention into a second relationship score representing the attention dispersion degree of the target author.

3. The method of claim 1, wherein, The determination of the closeness between the target associated user and the target author based on the fan relationship score and the attention relationship score comprises: determining a mutual relationship score based on the fan relationship score and the attention relationship score; determining the closeness between the target associated user and the target author based on the sum of the fan relationship score, the attention relationship score and the mutual relationship score.

4. The method of claim 3, wherein, The determination of the mutual relationship score based on the fan relationship score and the attention relationship score comprises: determining a mutual relationship basic score based on the geometric mean of the product of the fan relationship score and the attention relationship score; determining a mutual relationship score based on the product of the mutual relationship basic score and a preset mutual relationship number.

5. The method of claim 2, wherein, The conversion of the number of fans into a first relationship score representing the influence of the target author comprises: determining a fan number increment based on the difference between the number of fans and a preset fan growth threshold; determining an initial influence based on the arctangent value of the product of the fan number increment and a preset influence slope; determining a first relationship score based on the sum of the product of the initial influence and a preset influence coefficient and a set offset.

6. The method of claim 2, wherein, The conversion of the number of attention into a second relationship score representing the attention dispersion degree of the target author comprises: determining a second relationship score based on the logarithm of the sum of the number of attention and a preset relationship value.

7. The method of claim 1, wherein, The determination of a first network coefficient representing the connection strength of the target associated user in the fan network based on the total number of fans of the target author and the number of common fans comprises: Determine a first difference value between the total number of fans of the target creator and the number of common fans; Determine a first network coefficient based on a sum of a first difference value power of the first set parameter and a preset base value.

8. The method of claim 1, wherein, Determine a second network coefficient representing influence of the target associated user in a following network based on the total number of followers of the target creator and the number of followed users, including: Determine a second difference value between the total number of followers of the target creator and the number of followed users; Determine a second network coefficient based on a sum of a second difference value power of the second set parameter and a preset base value.

9. The method of claim 2, wherein, Determine a fan relationship score and a following relationship score by respectively correcting the relationship score using the first network coefficient and the second network coefficient, including: Determine a first base score corresponding to the first relationship score and a second base score corresponding to the second relationship score based on a corresponding relationship between a relationship score interval and a base score interval; Determine a fan relationship score based on a product of the first base score, the second base score and the first network coefficient; Determine a following relationship score based on a product of the first base score, the second base score and the second network coefficient.

10. The method of claim 9, wherein, Determine a first base score corresponding to the first relationship score and a second base score corresponding to the second relationship score based on a corresponding relationship between a relationship score interval and a base score interval, including: For a specified relationship score, select a target specified relationship score interval corresponding to the specified relationship score from a plurality of specified relationship score intervals, the specified relationship score including the first relationship score or the second relationship score; Determine a target specified base score interval based on a corresponding relationship between a specified relationship score interval and a specified base score interval, the specified relationship score interval and the specified base score interval being a numerical interval corresponding to the specified relationship score; Determine a specified base score corresponding to a position of the specified relationship score in the target specified relationship score interval using an interpolation algorithm, the specified base score including the first base score or the second base score, the specified base score being a base score corresponding to the specified relationship score.

Images