Social network user influence evaluation method, device, electronic device and medium

Abstract

The present invention provides a method, device, electronic device and medium for evaluating the influence of social network users, wherein the method includes: counting the social volume of the user to be evaluated in multiple social dimensions within a set time period; the social dimensions include at least individual influence and group influence; according to the social volume in each social dimension, respectively calculating the influence value of the user to be evaluated in each social dimension; according to the influence value of the user to be evaluated in each social dimension, drawing a relationship map; using the relationship map to evaluate the influence of the user to be evaluated in the social network. This solution can comprehensively evaluate the user's influence in multiple dimensions, thereby improving the evaluation accuracy.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of Internet technology, and in particular to a method, device, electronic device and medium for evaluating the influence of social network users. Background Art

[0002] Discovering influential individuals in social networks is a very important research branch in social network research and has important application value, such as microblog marketing, public opinion management, etc. At present, the influence of users is mainly evaluated by the number of their fans. The more fans a user has, the greater the influence of the user. However, some users have a large number of fans, but the number of fans who interact with the user is small. Therefore, the accuracy of evaluating user influence by the number of fans is poor. Summary of the invention

[0003] Based on the problem that the prior art uses the number of fans to evaluate user influence, but the evaluation accuracy is poor, the embodiments of the present invention provide a social network user influence evaluation method, device, electronic device and medium, which can comprehensively evaluate user influence in multiple dimensions and improve the evaluation accuracy.

[0004] In a first aspect, an embodiment of the present invention provides a method for evaluating the influence of social network users, comprising:

[0005] Counting the social volume of the user to be evaluated in multiple social dimensions within a set time period; the social dimensions at least include individual influence and group influence;

[0006] According to the social amount in each social dimension, respectively calculate the influence value of the user to be evaluated in each social dimension;

[0007] Draw a relationship map according to the influence value of the user to be evaluated in each social dimension;

[0008] The relationship graph is used to evaluate the influence of the user to be evaluated in the social network.

[0009] Preferably,

[0010] Statistics on the social volume of the user to be evaluated on the individual influence within a set time period, including:

[0011] Counting the number of posts by the user to be evaluated within the set time period that induce other users to perform a first interactive behavior; the first interactive behavior includes: at least one of reading, liking, commenting, forwarding, and collecting;

[0012] Calculating the influence value of the user to be evaluated on the individual influence includes:

[0013] Determining a set of other users that caused the first interactive behavior;

[0014] Determine the friendship relationship between each other user in the set and the user to be evaluated; the friendship relationship includes: non-friendship relationship, fan relationship of following the user to be evaluated, and mutual fan relationship;

[0015] Calculating a sub-influence value of the user to be evaluated on each other user according to the friend relationship and the first interactive behavior caused to other users;

[0016] The sum of the sub-influence values ​​is determined as the influence value of the to-be-evaluated user on the individual influence.

[0017] Preferably, the calculating the sub-influence value of the user to be evaluated on each other user according to the friend relationship and the first interactive behavior caused to other users includes:

[0018] Determine the relationship influence weight of the user to be evaluated on each other user according to the friendship relationship between each other user and the user to be evaluated;

[0019] Determine the behavior influence weights corresponding to different first interactive behaviors caused;

[0020] For each other user, the sum of the number of each first interactive behavior performed by the other user, the product of the corresponding behavior influence weight and the corresponding relationship influence weight is calculated, and the sum of the products is determined as the sub-influence value of the user to be evaluated on the other user.

[0021] Preferably,

[0022] Statistics on the social volume of the user to be evaluated on the group influence within a set time period, including:

[0023] Counting the number of second interactive behaviors performed by the user to be evaluated with members of the group to be joined within the set time period; the second interactive behavior is used to indicate that when any member of the group to be joined publishes information, other members can obtain the information;

[0024] Calculating the influence value of the user to be evaluated on the group influence includes:

[0025] Treat each member of the group as a node, and connect any two nodes to form a group topology;

[0026] Determine the connection edge value between any two nodes according to the number of second interactive behaviors performed between the two nodes;

[0027] According to each connection edge value in the group topology, the closeness centrality between the user to be evaluated and other members in the group is calculated, and the closeness centrality is determined as the influence value of the user to be evaluated on the group.

[0028] Preferably, determining the connection edge value between any two nodes according to the number of second interactive behaviors performed between the two nodes comprises:

[0029] The sum of the number of second interactive behaviors performed between the two nodes and the preset initial connection edge value between the two nodes is determined as the connection edge value between the two nodes.

[0030] Preferably, the relationship map is a radar map;

[0031] Drawing a relationship map according to the influence value of the user to be evaluated in each social dimension includes:

[0032] Based on the corresponding relationship between the influence value interval and the influence level constructed for each social dimension, and the influence value on each social dimension, determine the influence level of the user to be evaluated on each social dimension;

[0033] Convert the influence level on each social dimension into a label value on the corresponding social dimension;

[0034] Draw radar charts using multiple label values;

[0035] The using the relationship graph to evaluate the influence of the user to be evaluated on the social network includes:

[0036] The influence of the user to be evaluated in the social network is evaluated by using at least one parameter of the area, radius, center of gravity and shape in the radar chart.

[0037] Preferably, the number of influence levels included in the corresponding relationship constructed for each social dimension is the same; and the label values ​​corresponding to the same influence level of different social dimensions are equal.

[0038] In a second aspect, an embodiment of the present invention further provides a device for evaluating the influence of social network users, including:

[0039] A statistical unit, used to count the social amount of the user to be evaluated in multiple social dimensions within a set time period; the social dimensions at least include individual influence and group influence;

[0040] A calculation unit, used to calculate the influence value of the user to be evaluated in each social dimension according to the social amount in each social dimension;

[0041] A drawing unit, used for drawing a relationship map according to the influence value of the user to be evaluated in each social dimension;

[0042] An evaluation unit is used to evaluate the influence of the user to be evaluated in the social network by using the relationship map.

[0043] In a third aspect, an embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method described in any embodiment of this specification is implemented.

[0044] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, enables the computer to execute the method described in any embodiment of this specification.

[0045] The embodiment of the present invention provides a method, device, electronic device and medium for evaluating the influence of social network users. In addition to the dimension of individual influence, the group influence of users on social networks needs to be considered. The influence value of the user to be evaluated is calculated through multiple social dimensions, and a relationship map is drawn using the influence value on each social dimension. Then, the influence values ​​on multiple social dimensions in the relationship map can be used to comprehensively evaluate the influence of the user on the social network. It can be seen that this solution can comprehensively evaluate the influence of users in multiple dimensions, thereby improving the accuracy of the evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0047] Figure 1 This is a flow chart of a method for evaluating the influence of social network users provided by one embodiment of the present invention;

[0048] Figure 2 is a flow chart of an individual influence calculation method provided by an embodiment of the present invention;

[0049] Figure 3 is a flow chart of a group influence calculation method provided by an embodiment of the present invention;

[0050] Figure 4 is a hardware architecture diagram of an electronic device provided by an embodiment of the present invention;

[0051] Figure 5This is a structural diagram of a device for evaluating the influence of social network users provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0053] As mentioned above, the accuracy of evaluating user influence by the number of fans is poor. After analysis, the number of fans is only one aspect of the user's influence in social networks, and the user's influence is more reflected in social dimensions such as individual influence and group influence. Therefore, it is possible to consider using multiple social dimensions to comprehensively evaluate the user's influence.

[0054] The specific implementation of the above concept is described below.

[0055] Please refer to Figure 1 The embodiment of the present invention provides a method for evaluating the influence of social network users, the method comprising:

[0056] Step 100, counting the social volume of the user to be evaluated in multiple social dimensions within a set time period; the social dimensions at least include individual influence and group influence;

[0057] Step 102, calculating the influence value of the user to be evaluated in each social dimension according to the social amount in each social dimension;

[0058] Step 104, drawing a relationship map according to the influence value of the user to be evaluated in each social dimension;

[0059] Step 106: Use the relationship graph to evaluate the influence of the user to be evaluated in the social network.

[0060] In the embodiment of the present invention, in addition to the dimension of individual influence, the group influence of users on social networks needs to be considered. The influence values ​​of the users to be evaluated are calculated through multiple social dimensions, and a relationship map is drawn using the influence values ​​on each social dimension. Then, the influence values ​​on multiple social dimensions in the relationship map can be used to comprehensively evaluate the influence of users on social networks. It can be seen that this solution can comprehensively evaluate the influence of users in multiple dimensions, thereby improving the accuracy of the evaluation.

[0061] Described below Figure 1How the various steps are performed.

[0062] First, with respect to step 100, statistics are collected on the social volume of the user to be evaluated in multiple social dimensions within a set time period; the social dimensions at least include individual influence and group influence.

[0063] Evaluate the user's influence in a social network, which can be one social platform or multiple social platforms, such as Sina Weibo, Tik Tok, WeChat and other social platforms.

[0064] In social networks, each user can follow other users that he or she is interested in, and users can also follow each other. When a user posts information in a social network, other users who follow the user can browse the information and interact with it. Therefore, in social networks, users have a social dimension of individual influence.

[0065] Furthermore, users can also join groups of their interest, such as WeChat groups, super chats, and forums. When a user posts information in a group, other members of the group can browse the information and interact with it. Since members of a group join the group with a common goal, when a user posts relevant information in a group, it is easier to attract the attention and interaction of other members than individual influence. Therefore, in social networks, users have a social dimension of group influence.

[0066] In addition, since any two members in a group can be regarded as a mutual following relationship, that is, members in the group follow each other. However, in individual influence, there is no mutual following relationship between two members. Therefore, individual influence and group influence need to be analyzed separately.

[0067] In the embodiment of the present invention, the social dimension may include dimensions such as topic participation and user activity in addition to individual influence and group influence.

[0068] The amount of social interaction of a user in each social dimension is the basis for evaluating the user's influence, and the influence will change in different time periods. Therefore, when evaluating the user's influence, it is necessary to evaluate it for a certain time period. For example, evaluate the amount of social interaction in the past 30 days.

[0069] The following mainly explains this step from the four social dimensions of individual influence, group influence, topic participation, and user activity.

[0070] 1. Individual influence

[0071] In an embodiment of the present invention, when the social dimension is individual influence, this step 100 may include: counting the number of posts made by the user to be evaluated within the set time period, which induce other users to perform a first interactive behavior; the first interactive behavior includes: at least one of reading, liking, commenting, forwarding and collecting.

[0072] Among them, the post is a post published by the user on the personal site. For example, the number of posts published in the past 30 days is 10, and each post corresponds to the first interactive behavior of other users. Therefore, the total number of first interactive behaviors corresponding to these 10 posts can be counted, as well as the number of first interactive behaviors of each type. For example, the number of reads is 1 million, the number of likes is 300,000, the number of comments is 80,000, the number of reposts is 30,000, and the number of collections is 5,000, then the total number is 1.415 million. The number of the first interactive behavior is determined as the social volume of the user to be evaluated in the social dimension of individual influence within the set time period.

[0073] 2. Group influence

[0074] In an embodiment of the present invention, when the social dimension is group influence, this step 100 may include: counting the number of second interactive behaviors performed by the user to be evaluated with members of the joined group within the set time period; the second interactive behavior is used to characterize that when any member of the joined group publishes information, other members can obtain the information.

[0075] In a group, any two members in the group can be regarded as following each other. When any member in the group posts information, other members in the group can also read the information. The information posted can be the first information sent by a member in the group, or it can be a response to information posted by other members. For example, the information can be posted in the form of chat, call, email, etc.

[0076] It should be noted that when counting the social volume of group influence, the number of interactions between members needs to be considered. Taking a certain super topic as an example, the number of second interactive behaviors between the user to be evaluated and the members in the super topic may include: the number of interactions in which the super topic posts published by the user to be evaluated in the super topic are commented, liked, forwarded and collected by other members.

[0077] Taking a chat group as an example, the number of second interactive behaviors between the user to be evaluated and the members in the chat group may include: the number of messages posted by each member in the chat group. The posted messages may be parsed, and the posted messages correspond to different topics. The members who posted messages to the chat group during the discussion period of each topic are regarded as the members who performed the second interactive behavior.

[0078] 3. Topic participation

[0079] Since the higher the topic participation, the greater the influence it will generate, topic participation can be analyzed as a social dimension.

[0080] In this embodiment, topic participation is correlated with individual influence and / or group influence. For example, the number of posts participating in the topic among the number of posts of individual influence can be counted, and the number of messages published for participating in the topic discussion among the number of messages of group influence can also be counted. The number of posts participating in the topic and / or the number of messages participating in the topic discussion counted are determined as the social quantity of the social dimension of topic participation.

[0081] 4. Activity level

[0082] To a certain extent, the more active a user is on a social network, the greater the influence he or she will have, so the level of activity can be analyzed as a social dimension.

[0083] In this embodiment, when counting the social volume of the social dimension of activity level, the online time of the user within a set time can be counted, and the online time can be determined as the social volume of the user in the social dimension of activity level.

[0084] Then, for step 102, the influence value of the user to be evaluated in each social dimension is calculated respectively according to the social amount in each social dimension.

[0085] When calculating the influence value on each social dimension, different social dimensions may be calculated in different ways. The following describes the calculation methods of the influence values ​​for the four social dimensions in step 100 .

[0086] 1. Individual influence

[0087] In one embodiment of the present invention, when calculating the influence value for the social dimension of individual influence, please refer to Figure 2 , which can be achieved in at least one of the following ways:

[0088] Step 200: Determine a set of other users that cause the first interactive behavior;

[0089] Step 202: Determine the friendship relationship between each other user in the set and the user to be evaluated; the friendship relationship includes: non-friendship relationship, fan relationship of following the user to be evaluated, and mutual follower relationship;

[0090] Step 204: Calculate the sub-influence value of the user to be evaluated on each other user according to the friend relationship and the first interactive behavior caused to other users;

[0091] Step 206: Determine the sum of the sub-influence values ​​as the influence value of the user to be evaluated on the individual influence.

[0092] Since there are other users in the set who have multiple first interactions with the user to be evaluated, and have different friendship relationships with the user to be evaluated, the influence on other users is different. For example, users will pay more attention to other users with whom they have mutual followers, but pay almost no attention to other users with whom they are not friends. Therefore, it is necessary to analyze the influence value based on the friendship relationship between other users and the user to be evaluated.

[0093] In step 204, specifically, different correction factors can be configured for different friend relationships, the correction factor for the mutual fan relationship is greater than the correction factor for the fan relationship that follows the user to be evaluated, and the correction factor for the fan relationship that follows the user to be evaluated is greater than the correction factor for the non-friend relationship. The correction factor of the friend relationship is used to correct the number of first interactive behaviors caused by other users to calculate the sub-influence value of the user to be evaluated on each other user. For example, the correction factor for the friend relationship is 1.5, the correction factor for the fan relationship that follows the user to be evaluated is 1.2, and the correction factor for the non-friend relationship is 0.8. Among them, the correction factor can be a relationship influence weight.

[0094] Furthermore, in step 204, different behavior influence weights can be assigned to different first interactive behaviors. For example, the behavior influence weights of different types of first interactive behaviors such as reading, liking, commenting, forwarding and collecting gradually increase. That is, if the first interactive behavior of other users is collecting, it indicates that the user to be evaluated has a greater influence on the other users.

[0095] Specifically, step 204 may include: determining the relationship influence weight of the user to be evaluated on each other user based on the friendship relationship between each other user and the user to be evaluated; determining the behavior influence weights corresponding to different first interactive behaviors caused; for each other user, calculating the sum of the product of the number of each first interactive behavior performed by the other user and the corresponding behavior influence weight and the corresponding relationship influence weight, and determining the sum of the products as the sub-influence value of the user to be evaluated on the other user.

[0096] Specifically, in step 205, the influence value P1 of the individual influence of the user to be evaluated can be calculated using the following formula:

[0097]

[0098] Where n is the total number of other users in the set, m is the number of types of the first interactive behavior, and g iis the influence weight of the relationship between the user to be evaluated and the i-th user, k j The first interactive behavior caused is the behavior influence weight corresponding to the jth type, N ij is the number of first interactive behaviors of the jth type induced by the ith user.

[0099] It should be noted that in this embodiment, when calculating the influence value for the social dimension of individual influence, in addition to using the above Figure 2 In addition to the implementation method shown, other implementation methods may also be used, for example, directly determining the social volume as the influence value.

[0100] 2. Group influence

[0101] In one embodiment of the present invention, when calculating the influence value for the social dimension of group influence, please refer to Figure 3 , which can be achieved in at least one of the following ways:

[0102] Step 300: treat each member of the group as a node, and connect any two nodes to form a group topology;

[0103] Step 302: determining a connection edge value between any two nodes according to the number of second interactive behaviors performed between the two nodes;

[0104] Step 304: Calculate the closeness centrality between the user to be evaluated and other members of the group according to each connection edge value in the group topology, and determine the closeness centrality as the influence value of the user to be evaluated on the group influence.

[0105] Since any two members in a group follow each other, any two nodes in the group topology have a connection relationship.

[0106] In step 302, the connection edge between any two nodes in the initially formed community topology may be preset with an initial connection edge value. When there is a second interactive behavior between the two nodes, the connection edge value between the two nodes is updated.

[0107] Specifically, step 302 may include: determining the sum of the number of second interactive behaviors performed between the two nodes and a preset initial connection edge value between the two nodes as the connection edge value between the two nodes.

[0108] Taking the super topic as an example, assuming that the initial connection edge value is 0, and when it is determined through step 100 that the number of second interactive behaviors between the two nodes is 20, the connection edge value between the two nodes is updated to 20.

[0109] It should be noted that the calculation method of the closeness centrality can be implemented by using any closeness centrality calculation method disclosed in the prior art, which will not be described in detail here.

[0110] In this embodiment, when determining the influence value for individual influence, the social volume is used as the influence value after weighted processing, and when determining the influence value for group influence, the social volume is used as the connection edge value, and then the closeness centrality calculated by using the connection edge value is used as the influence value of the group influence. This is because the relationship between other users involved in the individual influence and the user to be evaluated is complex and does not have the nature of a group. Therefore, directly using the social volume after weighted processing as the influence value can represent the role of the user to be evaluated in the individual influence; and in a group, members follow each other in pairs, and any member who posts information will affect other members. Therefore, only using the influence value after weighted processing of the social volume cannot more accurately reflect the role of the user to be evaluated in the group. Choosing to use the number of the second interactive behaviors as the connection edge value and then calculating the closeness centrality, and using the closeness centrality as the influence value of the user to be evaluated on the group influence can better reflect the role of the user to be evaluated in the group.

[0111] 3. Topic participation

[0112] In this embodiment, the social volume corresponding to the topic participation degree can be directly determined as the influence value of the social dimension of the topic participation degree.

[0113] 4. Activity level

[0114] Similarly, in this embodiment, the social amount corresponding to the activity level can be directly determined as the influence value of the social dimension of the activity level.

[0115] Finally, step 104 “drawing a relationship map according to the influence value of the user to be evaluated in each social dimension” and step 106 “using the relationship map to evaluate the influence of the user to be evaluated in the social network” are explained at the same time.

[0116] In this embodiment, the relationship map is used to represent the relationship between the influence values ​​of the user to be evaluated in each social dimension. The relationship map can be a radar chart, a pie chart, a bar chart, etc.

[0117] Preferably, in order to be able to use the relationship graph to visually evaluate the influence of the user to be evaluated on the social network, the relationship graph is a radar graph.

[0118] Then step 104 may include: determining the influence level of the user to be evaluated in each social dimension based on the correspondence between the influence value interval and the influence level constructed for each social dimension, and the influence value on each social dimension; converting the influence level on each social dimension into a label value on the corresponding social dimension; and drawing a radar chart using multiple label values.

[0119] For example, assuming that the time period is set to one week, the following corresponding relationships exist for the above four social dimensions:

[0120] The impact levels of individual effects are: very low (0,5], low (5,25], medium (25,125], high (125,625], and very high (625,∞);

[0121] The impact levels of group influence are: very low (0,2], low (2,3], medium (3,4], high (4,5], and very high (5,∞);

[0122] The influence levels of topic participation are: very low (0,5], low (5,25], medium (25,125], high (125,625], and very high (625,∞);

[0123] The impact levels of activity are: very low (0,7], low (7,14], medium (14,21], high (21,28], and very high (28,168].

[0124] Among them, for each social dimension, a label value can be mapped to each of its influence levels, and then after the influence level on the social dimension is determined, the corresponding label value can be obtained.

[0125] In one embodiment of the present invention, in order to make the drawn radar chart more balanced and beautiful, and thus to clearly and intuitively show the difference in influence of different users, the number of influence levels contained in the corresponding relationship constructed for each social dimension is the same; the label values ​​corresponding to different social dimensions at the same influence level are equal.

[0126] For example, each social dimension is divided into five influence levels, and the label values ​​mapped to the five influence levels from extremely low to extremely high are 0, 25, 50, 75, and 100 respectively.

[0127] Furthermore, when using the relationship map to evaluate the influence of the user to be evaluated in the social network, the evaluation can be directly performed separately in different social dimensions. In order to evaluate the influence of different users, step 106 may include: using at least one parameter of the area, radius, center of gravity and shape in the radar map to evaluate the influence of the user to be evaluated in the social network.

[0128] In the geometric figure formed by connecting the tag values ​​end to end in the radar chart, the larger the area / radius, the greater the influence; the closer the center of gravity is to the origin, or the fuller and more symmetrical the shape is, the more balanced the social influence is in all social dimensions. When the area / or radius are equal, you can consider using the center of gravity or shape for further evaluation.

[0129] like Figure 4 , Figure 5 As shown, an embodiment of the present invention provides a device for evaluating the influence of social network users. The device embodiment can be implemented by software, or by hardware or a combination of software and hardware. From the hardware level, Figure 4 As shown, it is a hardware architecture diagram of an electronic device where a social network user influence evaluation device provided by an embodiment of the present invention is located, except Figure 4 In addition to the processor, memory, network interface, and non-volatile memory shown, the electronic device in the embodiment may also include other hardware, such as a forwarding chip responsible for processing messages, etc. Taking software implementation as an example, Figure 5 As shown, as a device in a logical sense, the CPU of the electronic device in which it is located reads the corresponding computer program in the non-volatile memory into the memory and runs it. This embodiment provides a social network user influence evaluation device, including:

[0130] A statistical unit 501 is used to count the social amount of the user to be evaluated in multiple social dimensions within a set time period; the social dimensions at least include individual influence and group influence;

[0131] A calculation unit 502 is used to calculate the influence value of the user to be evaluated in each social dimension according to the social amount in each social dimension;

[0132] A drawing unit 503, used to draw a relationship map according to the influence value of the user to be evaluated in each social dimension;

[0133] The evaluation unit 504 is used to evaluate the influence of the user to be evaluated in the social network by using the relationship graph.

[0134] In one embodiment of the present invention, the statistical unit 501, when counting the social amount of the user to be evaluated on the individual influence within a set time period, specifically includes: counting the number of posts by the user to be evaluated within the set time period that induce other users to perform a first interactive behavior; the first interactive behavior includes: at least one of reading, liking, commenting, forwarding and collecting;

[0135] The calculation unit 502, when calculating the influence value of the to-be-evaluated user on the individual influence, specifically includes:

[0136] Determine a set of other users who cause the first interactive behavior; determine the friendship relationship between each other user in the set and the user to be evaluated; the friendship relationship includes: non-friendship relationship, fan relationship of following the user to be evaluated, and mutual fan relationship;

[0137] Calculating a sub-influence value of the user to be evaluated on each other user according to the friend relationship and the first interactive behavior caused to other users;

[0138] The sum of the sub-influence values ​​is determined as the influence value of the to-be-evaluated user on the individual influence.

[0139] In one embodiment of the present invention, when the calculation unit 502 calculates the sub-influence value of the user to be evaluated on each other user according to the friend relationship and the first interactive behavior caused to other users, the calculation unit 502 specifically includes:

[0140] Determine the relationship influence weight of the user to be evaluated on each other user according to the friendship relationship between each other user and the user to be evaluated;

[0141] Determine the behavior influence weights corresponding to different first interactive behaviors caused;

[0142] For each other user, the sum of the number of each first interactive behavior performed by the other user, the product of the corresponding behavior influence weight and the corresponding relationship influence weight is calculated, and the sum of the products is determined as the sub-influence value of the user to be evaluated on the other user.

[0143] In one embodiment of the present invention, the statistical unit 501, when counting the social amount of the user to be evaluated on the group influence within a set time period, specifically includes: counting the number of second interactive behaviors performed by the user to be evaluated with members of the group joined within the set time period; the second interactive behavior is used to represent that when any member of the group joined releases information, other members can know the information;

[0144] When calculating the influence value of the to-be-evaluated user on the group influence, the calculation unit 502 specifically includes:

[0145] Treat each member of the group as a node, and connect any two nodes to form a group topology;

[0146] Determine the connection edge value between any two nodes according to the number of second interactive behaviors performed between the two nodes;

[0147] According to each connection edge value in the group topology, the closeness centrality between the user to be evaluated and other members in the group is calculated, and the closeness centrality is determined as the influence value of the user to be evaluated on the group.

[0148] In one embodiment of the present invention, when the calculation unit 502 determines the connection edge value between any two nodes based on the number of second interactive behaviors performed between the two nodes, it specifically includes: determining the sum of the number of second interactive behaviors performed between the two nodes and the preset initial connection edge value between the two nodes as the connection edge value between the two nodes.

[0149] In one embodiment of the present invention, the relationship map is a radar map;

[0150] The drawing unit 503 specifically includes:

[0151] Based on the corresponding relationship between the influence value interval and the influence level constructed for each social dimension, and the influence value on each social dimension, determine the influence level of the user to be evaluated on each social dimension;

[0152] Convert the influence level on each social dimension into a label value on the corresponding social dimension;

[0153] Draw radar charts using multiple label values;

[0154] The evaluation unit 504 specifically includes: using at least one parameter of the area, radius, center of gravity and shape in the radar chart to evaluate the influence of the user to be evaluated in the social network.

[0155] In one embodiment of the present invention, the number of influence levels included in the corresponding relationship constructed for each social dimension is the same; and the label values ​​corresponding to the same influence level of different social dimensions are equal.

[0156] It is understood that the structure illustrated in the embodiment of the present invention does not constitute a specific limitation on a social network user influence evaluation device. In other embodiments of the present invention, a social network user influence evaluation device may include more or fewer components than shown in the figure, or combine some components, or split some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0157] The information interaction, execution process and other contents between the modules in the above-mentioned device are based on the same concept as the embodiment of the method of the present invention. For the specific contents, please refer to the description in the embodiment of the method of the present invention, and no further description is given here.

[0158] An embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, a method for evaluating the influence of social network users in any embodiment of the present invention is implemented.

[0159] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the processor executes a method for evaluating the influence of social network users in any embodiment of the present invention.

[0160] Specifically, a system or device equipped with a storage medium can be provided, on which software program code that implements the functions of any of the above-mentioned embodiments is stored, and a computer (or CPU or MPU) of the system or device can be enabled to read and execute the program code stored in the storage medium.

[0161] In this case, the program code itself read from the storage medium can realize the function of any one of the above-mentioned embodiments, and thus the program code and the storage medium storing the program code constitute a part of the present invention.

[0162] The storage medium embodiments for providing the program code include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), a magnetic tape, a non-volatile memory card, and a ROM. Alternatively, the program code can be downloaded from a server computer by a communication network.

[0163] In addition, it should be clear that the functions of any of the above embodiments can be implemented not only by executing the program code read by the computer, but also by enabling an operating system operating on the computer to complete part or all of the actual operations based on instructions from the program code.

[0164] In addition, it can be understood that the program code read from the storage medium is written to a memory provided in an expansion board inserted into the computer or to a memory provided in an expansion module connected to the computer, and then based on the instructions of the program code, a CPU installed on the expansion board or expansion module is enabled to perform part or all of the actual operations, thereby realizing the functions of any of the above-mentioned embodiments.

[0165] Each embodiment of the present invention has at least the following beneficial effects:

[0166] 1. In one embodiment of the present invention, in addition to the individual influence of users on social networks, it is also necessary to consider the group influence of users. The influence values ​​of the users to be evaluated are calculated through multiple social dimensions, and a relationship map is drawn using the influence values ​​on each social dimension. Then, the influence values ​​on multiple social dimensions in the relationship map can be used to comprehensively evaluate the influence of users on social networks. It can be seen that this solution can comprehensively evaluate the influence of users in multiple dimensions, thereby improving the accuracy of the evaluation.

[0167] 2. In one embodiment of the present invention, any two members in a group can be regarded as mutual followers, that is, members in the group follow each other. However, in individual influence, there is no mutual following relationship. Therefore, individual influence and group influence need to be analyzed separately to improve the accuracy of the evaluation results.

[0168] 3. In one embodiment of the present invention, among the other users included in the set, there are other users who have multiple first interactive behaviors with the user to be evaluated, and when they have different friendship relationships with the user to be evaluated, the strength of the influence on other users is different. For example, users will pay more attention to other users with whom they have mutual followers, and pay almost no attention to other users with whom they are not friends. Therefore, it is necessary to analyze the influence value based on the friendship relationship between other users and the user to be evaluated.

[0169] 4. In one embodiment of the present invention, when determining the influence value for individual influence, the social amount is used as the influence value after weighted processing, and when determining the influence value for group influence, the social amount is used as the connection edge value, and then the close centrality calculated by using the connection edge value is used as the influence value of the group influence. This is because the relationship between other users involved in the individual influence and the user to be evaluated is complex and does not have the nature of a group. Therefore, directly using the social amount after weighted processing as the influence value can represent the role of the user to be evaluated in the individual influence; and in the group, members follow each other in pairs, and any member who releases information will affect other members. Therefore, only using the influence value after weighted processing of the social amount cannot more accurately reflect the role of the user to be evaluated in the group. Choosing to use the number of the second interactive behaviors as the connection edge value and then calculating the close centrality, and using the close centrality as the influence value of the user to be evaluated on the group influence can better reflect the role of the user to be evaluated in the group.

[0170] It should be noted that, in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprise a ..." do not exclude the presence of other identical factors in the process, method, article or device including the elements.

[0171] A person of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk, etc., various media that can store program codes.

[0172] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for evaluating the influence of social network users, characterized in that: include: Count the social activities of the user to be evaluated in multiple social dimensions within a set time period; The social dimension includes at least individual influence and group influence; According to the social amount in each social dimension, respectively calculate the influence value of the user to be evaluated in each social dimension; Draw a relationship map according to the influence value of the user to be evaluated in each social dimension; Using the relationship graph to evaluate the influence of the user to be evaluated in the social network; Counting the social volume of the user to be evaluated on the individual influence within a set time period, including: counting the number of posts by the user to be evaluated within the set time period that induce other users to perform a first interactive behavior; the first interactive behavior includes: at least one of reading, liking, commenting, forwarding and collecting; Calculating the influence value of the user to be evaluated on the individual influence, including: determining a set of other users that cause the first interactive behavior; determining the friendship relationship between each other user in the set and the user to be evaluated; the friendship relationship includes: non-friendship relationship, fan relationship following the user to be evaluated, and mutual fan relationship; determining the relationship influence weight of the user to be evaluated on each other user according to the friendship relationship between each other user and the user to be evaluated; determining the behavior influence weights corresponding to different first interactive behaviors caused; for each other user, calculating the sum of the product of the number of each first interactive behavior performed by the other user and the corresponding behavior influence weight and the corresponding relationship influence weight, and determining the sum of the products as the sub-influence value of the user to be evaluated on the other user; determining the sum of the sub-influence values ​​as the influence value of the user to be evaluated on the individual influence; Counting the social amount of the user to be evaluated on the group within a set time period, including: counting the number of second interactive behaviors performed by the user to be evaluated with members of the group to be joined within the set time period; the second interactive behavior is used to indicate that when any member of the group to be joined publishes information, other members can learn about the information; Calculating the influence value of the user to be evaluated on the group influence, including: taking the members of the group to be added as a node respectively, and connecting any two nodes to form a group topology; determining the connection edge value between any two nodes according to the number of second interactive behaviors performed between the two nodes; calculating the closeness centrality between the user to be evaluated and other members of the group to be added according to each connection edge value in the group topology, and determining the closeness centrality as the influence value of the user to be evaluated on the group influence.

2. The method according to claim 1, characterized in that Determining the connection edge value between any two nodes according to the number of second interactive behaviors performed between the two nodes includes: The sum of the number of second interactive behaviors performed between the two nodes and the preset initial connection edge value between the two nodes is determined as the connection edge value between the two nodes.

3. The method according to any one of claims 1-2, characterized in that: The relationship map is a radar map; Drawing a relationship map according to the influence value of the user to be evaluated in each social dimension includes: Based on the corresponding relationship between the influence value interval and the influence level constructed for each social dimension, and the influence value on each social dimension, determine the influence level of the user to be evaluated on each social dimension; Convert the influence level on each social dimension into a label value on the corresponding social dimension; Draw radar charts using multiple label values; The using the relationship graph to evaluate the influence of the user to be evaluated on the social network includes: The influence of the user to be evaluated in the social network is evaluated by using at least one parameter of the area, radius, center of gravity and shape in the radar chart.

4. The method according to claim 3, characterized in that The number of influence levels included in the corresponding relationship constructed for each social dimension is the same; the label values ​​corresponding to different social dimensions at the same influence level are equal.

5. A device for evaluating the influence of social network users, characterized in that: include: A statistical unit, used to count the social activities of the user to be evaluated in multiple social dimensions within a set time period; The social dimension includes at least individual influence and group influence; A calculation unit, used to calculate the influence value of the user to be evaluated in each social dimension according to the social amount in each social dimension; A drawing unit, used for drawing a relationship map according to the influence value of the user to be evaluated in each social dimension; An evaluation unit, configured to evaluate the influence of the user to be evaluated on the social network by using the relationship graph; The statistical unit, when counting the social amount of the user to be evaluated on the individual influence within a set time period, specifically includes: counting the number of posts by the user to be evaluated within the set time period that induce other users to perform a first interactive behavior; the first interactive behavior includes: at least one of reading, liking, commenting, forwarding and collecting; The calculation unit, when calculating the influence value of the user to be evaluated on the individual influence, specifically includes: determining a set of other users that cause the first interactive behavior; determining the friendship relationship between each other user in the set and the user to be evaluated; the friendship relationship includes: non-friendship relationship, fan relationship following the user to be evaluated, and mutual fan relationship; determining the relationship influence weight of the user to be evaluated on each other user according to the friendship relationship between each other user and the user to be evaluated; determining the behavior influence weights corresponding to different first interactive behaviors caused; for each other user, calculating the sum of the product of the number of each first interactive behavior performed by the other user and the corresponding behavior influence weight and the corresponding relationship influence weight, and determining the sum of the products as the sub-influence value of the user to be evaluated on the other user; determining the sum of the sub-influence values ​​as the influence value of the user to be evaluated on the individual influence; The statistical unit, when counting the social amount of the user to be evaluated on the group influence within a set time period, specifically includes: counting the number of second interactive behaviors performed by the user to be evaluated with members of the group joined within the set time period; the second interactive behavior is used to indicate that when any member of the group joins releases information, other members can learn about the information; When the calculation unit calculates the influence value of the user to be evaluated on the group influence, it specifically includes: taking the members of the joined group as a node respectively, and connecting any two nodes to form a group topology; determining the connection edge value between any two nodes according to the number of second interactive behaviors performed between the two nodes; according to each connection edge value in the group topology, calculating the closeness centrality between the user to be evaluated and other members of the joined group, and determining the closeness centrality as the influence value of the user to be evaluated on the group influence.

6. The device according to claim 5, characterized in that When the calculation unit determines the connection edge value between any two nodes based on the number of second interactive behaviors performed between the two nodes, it specifically includes: determining the sum of the number of second interactive behaviors performed between the two nodes and the preset initial connection edge value between the two nodes as the connection edge value between the two nodes.

7. The device according to any one of claims 5-6, characterized in that: The relationship map is a radar map; The drawing unit specifically includes: determining the influence level of the user to be evaluated in each social dimension based on the corresponding relationship between the influence value interval and the influence level constructed for each social dimension and the influence value on each social dimension; converting the influence level on each social dimension into a label value on the corresponding social dimension; and drawing a radar map using multiple label values; The evaluation unit specifically includes: using at least one parameter of the area, radius, center of gravity and shape in the radar map to evaluate the influence of the user to be evaluated in the social network.

8. The device according to claim 7, characterized in that The number of influence levels included in the corresponding relationship constructed for each social dimension is the same; the label values ​​corresponding to different social dimensions at the same influence level are equal.

9. An electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method according to any one of claims 1 to 4 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to execute the method according to any one of claims 1 to 4.

Images