A closeness evaluation method, device and electronic equipment in a social network

Abstract

The application provides a closeness evaluation method and device in a social network and electronic equipment, and relates to the technical field of Internet. The method comprises the following steps: determining a target user who produces an interactive behavior with a target creator based on social network data; evaluating a first interactive behavior from three dimensions of comment continuity, comment timeliness and comment influence to determine a first interactive score representing the interactive activity between the target user and the target creator; evaluating a second interactive behavior from two dimensions of forwarding timeliness and forwarding frequency to determine a second interactive score representing the propagation influence of the target user on user-generated content published by the target creator; and determining the closeness between the target user and the target creator based on the first interactive score and the second interactive score. By using the closeness evaluation method, device and electronic equipment in the social network, the accuracy and reliability of the closeness calculation result are improved.

Description

Technical Field

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

[0002] With the rapid development of internet technology, people's work and lives are increasingly intertwined with the internet, and social networks have become an indispensable part of people's lives. In practical applications, users can add other users with similar interests as friends through social application platforms, publish user-generated content such as tweets and videos, and interact with their friends' user-generated content by liking and commenting, greatly facilitating communication between users. How to effectively expand and maintain relationships between users and explore the intimacy between them is a core issue that every social networking platform must solve.

[0003] However, in existing technologies, the intimacy between users is usually calculated based on the number of views and likes of works posted on social media accounts, which reduces the accuracy and reliability of the intimacy calculation results. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a method, apparatus and electronic device for evaluating intimacy in social networks, so as to overcome at least one of the above-mentioned defects.

[0005] In a first aspect, embodiments of this application provide a method for evaluating intimacy in a social network, including:

[0006] Based on social network data, target users who interact with the target creators are identified. Interactions include the first interaction of commenting on user-generated content and the second interaction of forwarding user-generated content.

[0007] The first interaction behavior is evaluated from three dimensions: comment continuity, comment timeliness, and comment influence, to determine the first interaction score, which represents the level of interaction activity between the target user and the target creator.

[0008] The second interaction behavior is evaluated from two dimensions: forwarding timeliness and forwarding frequency, to determine the second interaction score, which represents the dissemination influence of target users on user-generated content published by target creators.

[0009] The intimacy between the target user and the target creator is determined based on the first interaction score and the second interaction score.

[0010] In an optional implementation, the first interactive behavior includes at least one comment on user-generated content, and the first interactive score includes the comment score corresponding to this comment. The first interactive behavior is evaluated in the following ways: for each comment, the continuity of the first interactive behavior under this comment is evaluated based on the number of consecutive comments up to this comment, to determine a continuity score; the timeliness of the first interactive behavior under this comment is evaluated based on the comment time interval between this comment and the previous comment and the proximity of this comment to the current time, to determine a timeliness score; the influence of the first interactive behavior under this comment is evaluated based on the number of likes and replies to this comment, to determine an influence score; and the comment score of the first interactive behavior under this comment is determined based on the continuity score, the timeliness score, and the influence score.

[0011] In an optional implementation, the second interactive behavior includes at least one forwarding of content generated by different users. The second interactive behavior is evaluated in the following ways: the forwarding timeliness of the second interactive behavior is evaluated based on the time interval between each forwarding and the current time to determine a forwarding timeliness score; the forwarding frequency of the second interactive behavior is evaluated based on the number of forwardings and the number of forwardings by all target users to determine a forwarding frequency score; and the second interactive score is determined based on the forwarding timeliness score and the forwarding frequency score.

[0012] In an optional implementation, a first interaction score, representing the level of interaction activity between the target user and the target creator, is determined by: summing the comment scores for the first interactive behavior under each comment to determine the total comment score; determining the popularity of user-generated content based on the total number of comments on user-generated content, and determining the first interaction score based on the popularity and the total comment score.

[0013] In an optional implementation, the comment score for the first interactive behavior under this comment is determined as follows: a base comment score is determined based on the total number of comments made by the target user on the user-generated content; the interaction timeliness score corresponding to the continuity score and comment timeliness score is compared with a set weight threshold to determine the interaction weight based on the comparison result; and the comment score for the first interactive behavior under this comment is determined based on the base comment score, the interaction weight, and the influence score.

[0014] In an optional implementation, the forwarding frequency of the second interactive behavior is evaluated based on the number of forwards and the number of forwards by all target users to determine the forwarding frequency score, including: selecting the number of forwards with the largest value from the total number of forwards by candidate users as the target forwarding number, where candidate users are users who have forwarded user-generated content published by the target creator; and determining the forwarding frequency score based on the number of forwards by the target users and the target forwarding number.

[0015] In an optional implementation, the forwarding timeliness of the second interaction behavior is evaluated based on the time interval between each forward and the current time to determine a forwarding timeliness score, including: determining a single forwarding timeliness score based on the time interval raised to the power of the natural constant; and determining a forwarding timeliness score based on the mean of all single forwarding timeliness scores.

[0016] In an optional implementation, the target users include multiple users, and the method further includes: sorting the multiple target users in descending order of intimacy to determine the intimacy level of different target users with the target creator.

[0017] Secondly, embodiments of this application also provide a device for evaluating intimacy in a social network, the device comprising:

[0018] The selection module is used to identify target users who interact with the target creator based on social network data. The interaction behaviors include the first interaction behavior of commenting on user-generated content and the second interaction behavior of forwarding user-generated content.

[0019] The first evaluation module is used to evaluate the first interactive behavior from three dimensions: comment continuity, comment timeliness, and comment influence, and to determine the first interaction score, which represents the level of interaction activity between the target user and the target creator.

[0020] The second evaluation module is used to evaluate the second interaction behavior from two dimensions: forwarding timeliness and forwarding frequency, and to determine the second interaction score, which represents the dissemination influence of the target user on the user-generated content published by the target creator.

[0021] The comprehensive evaluation module is used to determine the intimacy between the target user and the target creator based on the first interaction score and the second interaction score.

[0022] Thirdly, embodiments of this application also provide an electronic device, including: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, they perform steps of the intimacy evaluation method in the social network described above.

[0023] The embodiments of this application bring the following beneficial effects:

[0024] This application provides a method, apparatus, and electronic device for evaluating intimacy in social networks. It can evaluate the interactive activity between users from three dimensions: comment continuity, comment timeliness, and comment influence. It also evaluates the dissemination impact of user-generated content published by a target creator from two dimensions: forwarding timeliness and forwarding frequency. This achieves a comprehensive evaluation of user intimacy from multiple dimensions, improving the accuracy and reliability of intimacy calculation results. Compared with existing intimacy evaluation methods in social networks, it solves the problem of low accuracy and reliability in intimacy calculation results.

[0025] 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

[0026] 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.

[0027] Figure 1 A flowchart of the intimacy evaluation method in a social network provided in an embodiment of this application is shown;

[0028] Figure 2 A flowchart illustrating the steps for determining review scores provided in an embodiment of this application is shown;

[0029] Figure 3 A flowchart illustrating the steps for determining the second interactive score provided in an embodiment of this application is shown;

[0030] Figure 4 This invention provides a schematic diagram of the structure of a social network intimacy evaluation device according to an embodiment of the present application.

[0031] Figure 5 A schematic diagram of the structure of the electronic device provided in the embodiments of this application is shown. Detailed Implementation

[0032] 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.

[0033] It is worth noting that prior to this application, with the rapid development of internet technology, people's work and life have become increasingly intertwined with the internet, and social networks have become an indispensable part of people's lives. In practical applications, users can add other users with similar interests as friends through social application platforms, publish user-generated content such as tweets and videos, and also interact with their friends' user-generated content by liking and commenting, greatly facilitating communication between users. How to effectively expand and maintain relationships between users and explore the intimacy between users is a core issue that every social network platform must solve. However, in existing technologies, the intimacy between users is usually calculated based on the number of views and likes of works published by social accounts, resulting in low accuracy and reliability of the intimacy calculation results.

[0034] Based on this, embodiments of this application provide a method for evaluating intimacy in social networks to improve the accuracy and reliability of intimacy calculation.

[0035] To facilitate understanding of this embodiment, the exemplary steps provided in this application embodiment will be described below.

[0036] Please see Figure 1 , Figure 1 This is a flowchart illustrating a method for evaluating 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 evaluating intimacy in a social network includes:

[0037] Step S101: Based on social network data, identify target users who have interacted with the target creator;

[0038] Step S102: Evaluate the first interactive behavior from three dimensions: comment continuity, comment timeliness, and comment influence, and determine the first interaction score that represents the level of interaction activity between the target user and the target creator.

[0039] Step S103: Evaluate the second interactive behavior from two dimensions: forwarding timeliness and forwarding frequency, and determine the second interactive score that represents the dissemination influence of the target user on the user-generated content published by the target creator.

[0040] Step S104: Determine the intimacy between the target user and the target creator based on the first interaction score and the second interaction score.

[0041] Interactive behaviors include the first interactive behavior of commenting on user-generated content and the second interactive behavior of forwarding user-generated content.

[0042] The intimacy evaluation method in social networks provided in this application can evaluate the interaction activity between users from three dimensions: comment continuity, comment timeliness, and comment influence. It can also evaluate the dissemination influence of tweets published by target creators from two dimensions: forwarding timeliness and forwarding frequency. This achieves a comprehensive evaluation of the intimacy between users from multiple dimensions, improves the accuracy and reliability of intimacy calculation results, and solves the problem of low accuracy and reliability of intimacy calculation results.

[0043] To facilitate understanding of this embodiment, the following description uses the application of the information processing method in the game provided in this application to a server of a social network platform as an example to illustrate the exemplary steps provided in this application embodiment.

[0044] In step S101, target users who interact with the target creator are identified based on social network data.

[0045] In this step, social network data refers to user social data obtained from social network platforms, such as Weibo and Twitter. Social network data includes user information and tweet data for each creator, user information of users followed by each target creator, and user information of each target creator's followers.

[0046] The following section describes the process of determining the intimacy between a target creator and their corresponding target users on a social networking platform.

[0047] Target users refer to users who interact with target creators. These interactions are between target users and target creators, including the first interaction of commenting on user-generated content and the second interaction of sharing user-generated content. User-generated content can refer to UGC (User-Generated Content), for example, tweets posted by creators.

[0048] In an optional embodiment, the interactive behavior also includes following behavior and being followed behavior, wherein following behavior refers to following the behavior followed by the target creator, and being followed behavior refers to being followed by the target creator. That is, fans who follow the target creator and users who are followed by the target creator are also target users.

[0049] For example, extract the target creator's fans, the users followed by the target creator, and the users who comment on or share the user-generated content posted by the target creator from social network data, and use the extracted fans, users who follow, and users who participate in commenting on or sharing user-generated content as target users.

[0050] Taking user-generated content (Tweets) as an example, the algorithm extracts all Tweets posted by the target creator and the comment information for each Tweets from social network data, and uses a disjoint-set data structure algorithm to associate the comments with the original Tweets. Tweets include, but are not limited to: Tweets ID, Tweets content, and posting time; comment information includes, but is not limited to: Tweets ID of the original Tweets, Tweets ID of the replies, whether it is a retweet, number of likes, and number of replies.

[0051] The original tweet identifier refers to the unique identifier of the original tweet to which the current comment or reply belongs, used to associate it with the main content being commented on; the reply tweet identifier refers to the tweet identifier of another comment that the current comment directly replies to (not the original tweet).

[0052] In one alternative embodiment, when extracting comment information from each tweet of a target creator, it is necessary to filter the comment content to remove comments that are irrelevant to the tweet's topic, such as advertising.

[0053] For example, a large language model can be used to determine the semantic relevance between comments and tweets. Comments with a relevance greater than a set relevance threshold can be retained, while comments with a relevance less than or equal to the set relevance threshold can be filtered out. The first interaction score can be calculated based on the retained comments.

[0054] In step S102, the first interactive behavior is evaluated from three dimensions: comment continuity, comment timeliness, and comment influence, to determine the first interaction score, which represents the level of interaction activity between the target user and the target creator.

[0055] In this step, when determining the intimacy between the target user and the target creator, the first interaction score between the target user and the target creator is calculated. The first interaction score includes the comment score corresponding to each comment. The first interaction score can be determined based on the comment score corresponding to each comment, and the comment score of the same comment will change over time.

[0056] Taking a single target user as an example, the target user may comment multiple times on a tweet from a target creator. All the interactive behaviors under these multiple comments are considered as first interactive behaviors. That is, the first interactive behaviors include at least one comment on the user-generated content of the target creator.

[0057] The following reference Figure 2 This section will explain the process of determining the rating for a single comment.

[0058] Figure 2 A flowchart illustrating the steps for determining review scores provided in an embodiment of this application is shown, as follows: Figure 2 As shown, the steps for determining review ratings include:

[0059] Step S1021: For each comment, based on the number of consecutive comments up to the current comment, evaluate the continuity of the first interactive behavior under this comment to determine the continuity score.

[0060] For example: For each comment from a single target user, determine the number of consecutive comments up to that comment, and determine the continuity score based on the number of consecutive comments. Here, the number of consecutive comments is denoted as k, the continuity score is denoted as continuity_score, and the formula for calculating the continuity score is:

[0061] ;

[0062] In the above formula, The continuity enhancement parameter is a setting used to define the exponential growth rate of continuous comments.

[0063] In one example, when determining the number of consecutive comments, all comments from a single target user on the tweet are sorted chronologically. Starting from the current comment, each comment is traversed backward in reverse order. The current comment is taken as the current comment, and it is determined whether the time interval between the current comment and the previous comment of the target user preceding the current comment is less than a duration threshold. If the time interval is less than the duration threshold, the number of consecutive comments k is incremented by one, and the previous comment is selected as the latest current comment. The time interval between the latest current comment and the previous comment of the target user preceding the latest current comment is determined whether it is less than the duration threshold, until the time interval is greater than or equal to the duration threshold. The value of k at this point is then determined as the number of consecutive comments corresponding to the current comment.

[0064] Step S1022: Based on the comment time interval between this comment and the previous comment, and the distance of this comment from the current time, evaluate the timeliness of the first interactive behavior under this comment to determine the comment timeliness score.

[0065] For example: Determine the number of hours between this comment and the previous comment posted by another user that could create interaction. The number of hours is denoted as: At the same time, determine the number of days since this comment was posted, which is denoted as: The timeliness score for comments is denoted as Timeliness_score, and the formula for calculating the timeliness score is:

[0066] ;

[0067] In the above formula, This represents the first-time decay parameter. Used to characterize the time decay strength of interaction intervals within a tweet; This represents the second time decay parameter. Used to characterize the global temporal decay intensity of comments; and These are all set parameter values.

[0068] It should be noted that when calculating the number of hours between intervals... If a target creator initiates an interaction with a target user, for example, by tagging the target user and expressing gratitude, then the interaction initiated by the target creator is also considered as a comment made by another user that could form an interaction in the previous context.

[0069] Interval hours And the number of days since this comment was posted. Substitute these values ​​into the formula for calculating the timeliness score of the review to determine the timeliness score. The length of the interaction reflects the enthusiasm of the target users. The smaller the value, the higher the level of engagement and the higher the timeliness score of the comment. The higher the value, the lower the level of engagement and the lower the timeliness score for comments. The length of the interval represents the intensity of the decline in the popularity of this comment over natural time. The smaller the value, the closer the comment is to the current moment, the stronger its dissemination potential, and the higher the comment's timeliness score. The larger the value, the further away the comment is from the current moment, the weaker its dissemination potential, and the lower the comment's timeliness score.

[0070] Step S1023: Based on the number of likes and replies to this comment, evaluate the comment influence of the first interactive behavior under this comment to determine the influence score.

[0071] For example: To count the number of likes and replies to this comment, the number of likes is denoted as LKs, and the number of replies is the number of sub-comments of this comment, denoted as RC. The sum of the weights of the number of likes and the number of replies is then determined as the influence score, denoted as comment_influence.

[0072] Step S1024: Based on the continuity score, comment timeliness score, and influence score, determine the comment score of the first interactive behavior under this comment.

[0073] For example, a base comment score is determined based on the total number of comments a target user makes on user-generated content. This base comment score is denoted as `base_score`. For instance, the base comment score can be determined by summing the reciprocal of the total number of comments a target user makes on the tweet with a preset base value. This dilutes the base comment score and helps prevent spamming.

[0074] Then, the interaction timeliness score corresponding to the continuity score and comment timeliness score is compared with a set weight threshold to determine the interaction weight based on the comparison result. For example, the set weight threshold includes a minimum interaction weight and a maximum interaction weight, denoted as Min_weight, Max_weight, and interaction weight as interact_weight. The interaction timeliness score is determined by multiplying the continuity score and comment timeliness score, denoted as interact_time. The interaction timeliness score is then compared with the set weight threshold using the following formula to determine the interaction weight:

[0075] .

[0076] The score for the first interaction under this comment is determined based on the base comment score, interaction weight, and influence score. For example, the base comment score (base_score) and interaction weight are... The score for the first interactive action under this comment is determined by multiplying the comment score by the influence score (comment_influence).

[0077] In one example, after determining the comment score for the first interaction under each comment, a total comment score is determined based on the sum of the comment scores for the first interaction under each comment. For example, the total comment score is determined by summing the comment scores of all comments from the target user regarding the tweet, denoted as "score". Then, the popularity of user-generated content is determined based on the total number of comments, and the first interaction score is determined based on the popularity and the total comment score. For example, the logarithm of the sum of the total number of comments and a preset value is determined as the popularity, and the product of the popularity and the total comment score is determined as the first interaction score.

[0078] The total number of comments refers to all comments related to the tweet, not just those from the target user. The total number of comments is positively correlated with the popularity of the user-generated content; a higher total number of comments indicates greater popularity, and a lower total number of comments indicates lower popularity. The total number of comments is denoted as v, and popularity is denoted as log_weight, with a default value of 1. Popularity can be calculated using the following formula: .

[0079] The first interaction score determined by the above calculation process is the score corresponding to the interaction behavior between the target user and a user-generated content published by the target creator. The user-generated content published by the target creator can be multiple, such as multiple tweets. The target user may comment on and / or retweet multiple tweets published by the target creator. Then, the first interaction score between the target user and each tweet can be determined, and the sum of all the first interaction scores is determined as the first interaction score between the target user and the target creator.

[0080] In step S103, the second interactive behavior is evaluated from two dimensions: forwarding timeliness and forwarding frequency, to determine the second interactive score, which represents the dissemination influence of the target user on the user-generated content published by the target creator.

[0081] In this step, when determining the intimacy between the target user and the target creator, a second interaction score is calculated between the target user and the target creator. The second interaction score is generated based on the second interaction behavior, which includes at least one retweet of content generated by different users. For example, the target user can retweet a tweet from the target creator multiple times, or retweet different tweets from the target creator multiple times.

[0082] The following reference Figure 3 Let me introduce the process of determining the second interactive score.

[0083] Figure 3 A flowchart illustrating the steps for determining the second interactive score provided in an embodiment of this application is shown, as follows: Figure 3 As shown, the steps for determining the second interactive rating include:

[0084] Step S1031: Based on the time interval between each forwarding and the current time, evaluate the forwarding timeliness of the second interactive behavior to determine the forwarding timeliness score.

[0085] For example: record the forwarding time of each forward, calculate the forwarding time interval between the forwarding time of each forward and the current time, and denot the forwarding time interval corresponding to the i-th forward as: Then, based on the time interval raised to the power of the natural constant, a single forwarding timeliness score is determined. For example, the timeliness score of the i-th forwarding is denoted as time_score_i. Based on the average of all single-forward timeliness scores, the forwarding timeliness score corresponding to multiple forwards is determined. This forwarding timeliness score is denoted as `time_score`. The formula for calculating the forwarding timeliness score is as follows:

[0086] ;

[0087] In the above formula, This represents the forwarding time decay coefficient. It is a set value, such as 0.001; n represents the total number of forwards.

[0088] Step S1032: Based on the number of forwards and the number of forwards by all target users, evaluate the forwarding frequency of the second interaction behavior to determine the forwarding frequency score.

[0089] For example: For each candidate user who has forwarded user-generated content posted by the target creator, the total number of times the candidate user forwarded all user-generated content posted by the target creator is counted. The forwarding count with the largest value among the candidate users' total forwarding counts is selected as the target forwarding count. Then, based on the target user's forwarding count and the target forwarding count, a forwarding frequency score is determined. For example, the ratio of the target user's forwarding count to the target forwarding count is determined as the forwarding frequency score.

[0090] Step S1033: Determine the second interaction score based on the forwarding timeliness score and the forwarding frequency score.

[0091] For example, the weighted sum of the forwarding timeliness score and the forwarding frequency score is determined as the second interaction score.

[0092] In step S104, the intimacy between the target user and the target creator is determined based on the first interaction score and the second interaction score.

[0093] In this step, the first weight corresponding to the first interaction score and the second weight corresponding to the second interaction score are determined. The first weight and the second weight are used to determine the sum of the weights of the first interaction score and the second interaction score. The sum of the weights is determined as the intimacy between the target user and the target creator.

[0094] In one example, if there are continuous high-quality interactions between the target user and the target creator, the first interaction score may be too high, so the first interaction score needs to be normalized.

[0095] For example: Based on the popularity of each user-generated content published by the target creator, determine the reference value corresponding to the first interaction score. For instance, the popularity of the j-th user-generated content is denoted as: Then the formula for calculating the popularity of the j-th user-generated content is: , If the total number of comments for the j-th user-generated content is given, then the first interaction score is divided by the sum of the popularity of all user-generated content published by the target creator for normalization.

[0096] In an optional embodiment, the target users include multiple users, which can be sorted in descending order of intimacy to determine the level of intimacy between different target users and the target creator.

[0097] Based on the same inventive concept, this application also provides a device for evaluating intimacy in a social network, which corresponds to the intimacy evaluation method in a social network. Since the principle of the device in this application is similar to the intimacy evaluation method 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.

[0098] Please see Figure 4 , Figure 4 This is a schematic diagram of the structure of a social network intimacy evaluation device provided in an embodiment of this application. Figure 4 As shown, the intimacy evaluation device 200 in the social network includes:

[0099] Module 201 is used to identify target users who interact with the target creator based on social network data. The interaction behaviors include the first interaction behavior of commenting on user-generated content and the second interaction behavior of forwarding user-generated content.

[0100] The first evaluation module 202 is used to evaluate the first interactive behavior from three dimensions: comment continuity, comment timeliness, and comment influence, and to determine the first interaction score, which represents the level of interaction activity between the target user and the target creator.

[0101] The second evaluation module 203 is used to evaluate the second interactive behavior from two dimensions: forwarding timeliness and forwarding frequency, and to determine the second interactive score that represents the dissemination influence of the target user on the user-generated content published by the target creator.

[0102] The comprehensive evaluation module 204 is used to determine the intimacy between the target user and the target creator based on the first interaction score and the second interaction score.

[0103] Please see Figure 5 , Figure 5This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 5 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 intimacy evaluation method in the social network shown in the method embodiment can be found in the method embodiment for specific implementation, 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 intimacy evaluation method in the social network shown in the method embodiment can be found in the method embodiment for specific implementation, 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 evaluating intimacy in social networks, characterized in that, include: Based on social network data, target users who interact with target creators are identified. These interactions include first interactions such as commenting on user-generated content and second interactions such as forwarding user-generated content. The first interactive behavior is evaluated from three dimensions: comment continuity, comment timeliness, and comment influence, to determine a first interaction score that represents the level of interaction activity between the target user and the target creator. The second interactive behavior is evaluated from two dimensions: forwarding timeliness and forwarding frequency, to determine a second interactive score that represents the dissemination influence of the target user on the user-generated content published by the target creator. Based on the first interaction score and the second interaction score, the intimacy between the target user and the target creator is determined; The first interactive behavior includes at least one comment on the user-generated content, and the first interactive score includes the comment score corresponding to this comment. The first interactive behavior is evaluated in the following ways: For each comment, the continuity of the first interactive behavior under the current comment is evaluated based on the number of consecutive comments up to the current comment, in order to determine a continuity score; Based on the time interval between the current comment and the previous comment, and the distance of the current comment from the current time, the timeliness of the first interactive behavior under the current comment is evaluated to determine the timeliness score of the comment; Based on the number of likes and replies to this comment, the comment influence of the first interactive behavior under this comment is evaluated to determine the influence score; Based on the continuity score, the timeliness score, and the influence score, the comment score for the first interactive behavior under this comment is determined; The second interactive behavior includes at least one forwarding of content generated by different users, and the second interactive behavior is evaluated in the following ways: The forwarding timeliness of the second interaction behavior is evaluated based on the time interval between each forward and the current time to determine the forwarding timeliness score; The forwarding frequency of the second interaction behavior is evaluated based on the number of forwards and the number of forwards by all target users to determine the forwarding frequency score; A second interaction score is determined based on the forwarding timeliness score and the forwarding frequency score.

2. The method according to claim 1, characterized in that, A first interaction score, representing the level of interaction activity between the target user and the target creator, is determined using the following method: The total comment score is determined by summing the comment scores for the first interactive behavior under each comment. The popularity of the user-generated content is determined based on the total number of comments, and a first interaction score is determined based on the popularity and the total comment score.

3. The method according to claim 1, characterized in that, The comment score for the first interactive action under this comment is determined by the following method: A basic comment score is determined based on the total number of comments made by the target user on the content generated by the user. The interaction timeliness score corresponding to the continuity score and the comment timeliness score is compared with a set weight threshold to determine the interaction weight based on the comparison result; Based on the basic comment score, the interaction weight, and the influence score, the comment score for the first interactive behavior under this comment is determined.

4. The method according to claim 1, characterized in that, The evaluation of the forwarding frequency of the second interaction behavior based on the number of forwards and the number of forwards by all target users to determine the forwarding frequency score includes: The target forwarding count is selected from the total forwarding counts of candidate users, where the candidate users are those who have forwarded user-generated content published by the target creator. The forwarding frequency score is determined based on the number of forwards by the target user and the target number of forwards.

5. The method according to claim 1, characterized in that, The evaluation of the forwarding timeliness of the second interaction behavior based on the time interval between each forward and the current time, to determine the forwarding timeliness score, includes: The timeliness score for a single forwarding is determined by raising the time interval to the power of the natural constant. The forwarding timeliness score is determined based on the average of all single forwarding timeliness scores.

6. The method according to claim 1, characterized in that, The target users include multiple users, and the method further includes: Multiple target users are sorted in descending order of intimacy to determine the level of intimacy between different target users and the target creator.

7. A device for evaluating intimacy in a social network, characterized in that, include: The selection module is used to identify target users who interact with the target creator based on social network data. The interaction includes a first interaction of commenting on user-generated content and a second interaction of forwarding the user-generated content. The first evaluation module is used to evaluate the first interactive behavior from three dimensions: comment continuity, comment timeliness, and comment influence, and to determine a first interaction score that represents the level of interaction activity between the target user and the target creator. The second evaluation module is used to evaluate the second interactive behavior from two dimensions: forwarding timeliness and forwarding frequency, and to determine the second interactive score, which represents the dissemination influence of the target user on the user-generated content published by the target creator. The comprehensive evaluation module is used to determine the intimacy between the target user and the target creator based on the first interaction score and the second interaction score; The first interactive behavior includes at least one comment on the user-generated content, the first interactive score includes the comment score corresponding to this comment, and the first evaluation module is specifically used for: For each comment, the continuity of the first interactive behavior under the current comment is evaluated based on the number of consecutive comments up to the current comment, in order to determine a continuity score; Based on the time interval between the current comment and the previous comment, and the distance of the current comment from the current time, the timeliness of the first interactive behavior under the current comment is evaluated to determine the timeliness score of the comment; Based on the number of likes and replies to this comment, the comment influence of the first interactive behavior under this comment is evaluated to determine the influence score; Based on the continuity score, the timeliness score, and the influence score, the comment score for the first interactive behavior under this comment is determined; The second interactive behavior includes at least one forwarding of content generated by different users, and the second evaluation module is specifically used for: The forwarding timeliness of the second interaction behavior is evaluated based on the time interval between each forward and the current time to determine the forwarding timeliness score; The forwarding frequency of the second interaction behavior is evaluated based on the number of forwards and the number of forwards by all target users to determine the forwarding frequency score; A second interaction score is determined based on the forwarding timeliness score and the forwarding frequency score.

8. An electronic device, characterized in that, include: The device includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus, and the processor executes the machine-readable instructions to perform the steps of the intimacy evaluation method in a social network as claimed in any one of claims 1 to 6.

Images