Intimacy measuring and calculating method based on network community behaviors, medium and equipment

Abstract

The invention discloses a network community behavior-based intimacy measuring and calculating method, which comprises the following steps of: acquiring friend behavior data of users in a network community, including like timeliness data, comment content depth data and common friend interaction condition data; classifying the collected like giving timeliness data, and respectively setting corresponding weights for various like giving behaviors; by means of a natural language processing technology, deeply analyzing comment contents, classifying the comment contents, and endowing various comments with different weights; counting and analyzing the interaction frequency data of the common friends between the user and the friends thereof, and endowing corresponding weights according to the interaction frequency; and in combination with the weight scores of the various behaviors, obtaining the intimacy scores between the user and the friends through comprehensive calculation and evaluation, and dividing different intimacy levels according to the intimacy scores. A powerful tool is provided for mining potential clues and monitoring and analyzing suspicious activities in a social network for users.

Description

Technical Field

[0001] The present invention belongs to the technical field of data analysis, and particularly relates to a method, medium, and device for measuring intimacy based on network community behavior. Background Art

[0002] In today's era of popular digital social networking, instant messaging tools have become essential for people's daily communication, and the friend circle has become a key platform for sharing life and expressing emotions. However, there are significant limitations in existing methods for evaluating the intimacy of friend relationships in network communities. Currently, some methods simply rely on simple interaction counts, such as the number of likes and comments, as the criterion for measuring intimacy. But this approach is too simplistic and cannot deeply reflect the true quality and depth of interactions. For example, the mere number of likes cannot accurately show the degree of attention and emotional investment of the liker in the content. At the same time, there is also a significant lack of in-depth analysis of comment content, making it difficult to determine whether it is due to sincere in-depth communication or superficial perfunctory responses. In addition, the factor of the activity level of mutual friends in both parties' friend circles, although it may imply potential connections and intimacy between the two, is often overlooked in the existing technology. The one-sidedness and inaccuracy of this evaluation method not only fail to meet users' needs for in-depth understanding of friend relationships in network communities but also are not conducive to our exploration and analysis of potential correlation clues.

[0003] Therefore, how to overcome the deficiencies of existing intimacy evaluation methods, achieve a comprehensive and accurate evaluation of friend relationships in network communities, meet users' needs for in-depth understanding of friend relationships in network communities, and facilitate the exploration and analysis of potential clues is the problem to be solved by the present invention. Summary of the Invention

[0004] In view of the problems existing in the existing intimacy evaluation methods, the present invention proposes an innovative solution. By comprehensively considering multiple dimensions such as interaction quality, in-depth analysis of comment content, and activity level of mutual friends, and using advanced algorithm models for data processing and analysis, the accuracy and comprehensiveness of the evaluation of friend relationships in network communities are solved.

[0005] According to one aspect of the present invention, a method for measuring intimacy based on network community behavior includes the following steps:

[0006] S1: Collect the friend behavior data of users in the network community, including but not limited to like timeliness data, comment content depth data, and mutual friend interaction situation data;

[0007] S2: Classify the collected like timeliness data, clearly distinguish between timely likes, relatively timely likes, and delayed likes, and set corresponding weights for each type of like behavior;

[0008] S3: By means of natural language processing technology, deeply analyze the comment content, classify it into positive in-depth comments, general communication comments, and perfunctory response comments, and assign different weights to each type of comment;

[0009] S4: Statistically analyze the data of the number of interactions between common friends in the interactions between the user and their friends, and assign corresponding weights according to the frequency of interaction;

[0010] S5: Combine the weight scores of the above various behaviors, and through comprehensive calculation and evaluation, obtain the intimacy score between the user and their friends, and divide different intimacy levels accordingly.

[0011] The above method for calculating intimacy based on online community behaviors further includes: in step S2, the weights of timely likes, relatively timely likes, and delayed likes are set to decrease gradually.

[0012] The above method for calculating intimacy based on online community behaviors further includes: in step S3, the weight of positive in-depth comments is set to be higher than that of general communication comments, and the weight of general communication comments is set to be higher than that of perfunctory response comments.

[0013] The above method for calculating intimacy based on online community behaviors further includes: in step S4, the data of the number of interactions of common friends includes the number of likes and comments within a specific time period. When these interactions exceed a preset threshold, a higher weight will be assigned.

[0014] The above method for calculating intimacy based on online community behaviors further includes: in step S5, the process of calculating and evaluating the intimacy score includes adding up the weight scores of various behaviors to obtain the total score, and judging the specific intimacy level between the user and their friends according to the preset intimacy level threshold.

[0015] The above method for calculating intimacy based on online community behaviors further includes: among them, the weight of timely likes is set to 1, the weight of relatively timely likes is set to 0.8, and the weight of delayed likes is set to 0.5.

[0016] The above method for calculating intimacy based on online community behaviors further includes: among them, the weight of positive in-depth comments is set to 3, the weight of general communication comments is set to 2, and the weight of perfunctory response comments is set to 1.

[0017] The above method for calculating intimacy based on online community behaviors further includes: when the number of interactions between common friends in the past 30 days exceeds 10 times for the two people, the assigned weight is 0.4.

[0018] According to another aspect of the present invention, there is provided a computer-readable storage medium, on which a computer program is stored, wherein when the computer program is executed, the method according to any one of claims 1 to 8 is implemented.

[0019] According to another aspect of the present invention, a computer device is provided, comprising a processor, a memory and a computer program stored in the memory, wherein the processor implements the method according to any one of claims 1 to 8 when executing the computer program.

[0020] The present invention implements a friend intimacy measurement method based on the interactive behavior of the circle of friends in the network community, and realizes an in-depth analysis of the user's network social relationship. The method finely collects and analyzes multi-dimensional data such as the timeliness of the likes of friends in the circle of friends in the network community, the depth of the comment content, and the interaction of common friends. Specifically, the present invention subdivides the like behavior into timely, relatively timely and delayed likes, and assigns corresponding weights according to the different degrees of their influence on intimacy; at the same time, the comment content is thoroughly classified and weighted into active and in-depth, general communication and perfunctory response, which further improves the meticulousness of the evaluation. In addition, by counting the number of interactions of common friends and assigning corresponding weights, the present invention incorporates a wider social background when evaluating friend relationships. After comprehensive calculation and evaluation, the present invention can derive an accurate friend intimacy score, and divide the intimacy level accordingly, thereby providing users with a more scientific and insightful network community friend relationship measurement standard. This not only helps users understand their social networks more clearly and optimize social strategies, but also provides users with a powerful tool for mining potential clues, monitoring and analyzing suspicious activities in social networks. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings, which are incorporated into the specification and constitute a part of the specification, illustrate embodiments of the present invention and are used to explain the principles of the present invention together with the relevant text description. In these drawings, similar reference numerals are used to represent similar elements. The drawings described below are some embodiments of the present invention, but not all embodiments. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 A schematic diagram of a flow chart of a method for calculating intimacy based on network community behavior provided by an embodiment of the present invention is shown.

[0023] Figure 2 A schematic diagram of a network community behavior data analysis interface of a method for calculating intimacy based on network community behavior provided by an embodiment of the present invention is shown.

[0024] Figure 3 The invention is a block diagram of a computer device according to an exemplary embodiment. DETAILED DESCRIPTION

[0025] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention. It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other arbitrarily.

[0026] In current social interaction assessment technologies, traditional methods for measuring the intimacy of friends generally have problems such as simplified assessment criteria, insufficient reflection of interaction quality, and neglect of the influence of common friends. These methods not only fail to comprehensively show the true quality and depth of interactions, but also are difficult to meet the needs of users to deeply understand online friend relationships. At the same time, the neglect of factors such as the depth of comment content and the activity level of common friends in both parties' friend circles also leads to one-sidedness and inaccuracy of the assessment results, which is not conducive to the mining and analysis of potential association clues. To solve the limitations of traditional methods in friend intimacy assessment, this embodiment proposes an innovative solution. By comprehensively considering multiple dimensions such as interaction quality, in-depth analysis of comment content, and activity level of common friends, and using advanced algorithm models for data processing and analysis, the accuracy and comprehensiveness of the assessment of the intimacy of friend relationships in online communities are solved. To more intuitively show the technical features and implementation methods of the present invention, the following will describe the present invention in detail with reference to the accompanying drawings. In the accompanying drawings, Figure 1 A flowchart showing the method for calculating intimacy based on network community behavior is presented. Through the accompanying drawings, it can be clearly seen that an embodiment of the present invention provides a method for calculating intimacy based on network community behavior, including the following steps:

[0027] Step 1: Collect the friend behavior data of users in the network community, including but not limited to data on the timeliness of liking, data on the depth of comment content, and data on the interaction of common friends.

[0028] Network communities can be divided into various types, including friend circles, forums, blogs, instant messaging, and SNS, etc. In a specific embodiment, the friend behavior data of users in the network community can be crawled in real time or regularly through web crawler technology or by using the API interface provided by the network community. For example Figure 2As shown, through compliant electronic data forensics means or other legal channels, comprehensively obtain various types of data of users on the Moments platform, covering the content information posted, the posting timestamp, the identity information and the like of the likers and the liking time, the total number of likes, the profiles and comment times of the commentators, the specific comment content, and the friendship network among users, etc. Then, further evaluate the timeliness of likes based on the timestamp information of friends' likes; analyze the depth and sentiment of comments through natural language processing technology according to the specific comment content of friends; in addition, it is also possible to obtain the interaction data between users and common friends, such as information on discussions participated in together, activities attended together, etc., to further obtain the data on the interaction situation of common friends. These data will serve as an important cornerstone for in-depth analysis and provide detailed and accurate information support for subsequent research. The implementation of this step provides a rich and accurate data basis for the subsequent calculation of friend intimacy, and can more comprehensively reflect the interaction situation and the degree of closeness between users and their friends.

[0029] Step 2: Classify the collected like timeliness data, clearly distinguish timely likes, relatively timely likes, and delayed likes, and set corresponding weights for each type of like behavior. For example, it can be set that a like within 1 hour after the content is posted is a "timely like", a like within 1 to 3 hours is a "relatively timely like", and a like after more than 3 hours is a "delayed like". Subsequently, set corresponding weights for each type of like behavior to reflect their different impacts on the interaction situation of users' friends.

[0030] Preferably, the weights of timely likes, relatively timely likes, and delayed likes can be set to decrease gradually. The purpose of such a design is to more accurately reflect the real-time nature and interactivity of users' friend behaviors. By setting different weights for different types of like behaviors, it is possible to better analyze the activity of users' Moments and the popularity of the content. The setting of gradually decreasing weights means that the more timely the like, the greater the contribution to the user's social influence, which also conforms to the timeliness characteristics of information dissemination in the social network.

[0031] Serial number Liking type Liking rule Score weight 1 Timely like Within 1 hour after publication 1 2 Relatively timely like Within 1 - 3 hours 0.8 3 Delayed like More than 3 hours 0.5

[0032] Preferably, referring to the above like rule comparison table, the weight of timely likes can be set to 1, the weight of relatively timely likes can be set to 0.8, and the weight of delayed likes can be set to 0.5. Subsequently, multiply these numbers by their respective corresponding weights respectively, aiming to quantify different types of like behaviors into specific values for more intuitive comparison and analysis. By adding up the obtained results, the total score of likes is obtained. Analyzing the like timeliness in this way not only considers the number of likes, but also takes into account the timeliness and quality of likes, so as to more accurately measure the degree of attention and enthusiasm of friends for the Moments dynamics.

[0033] Suppose user A actively updated 20 Moments within a month, showing his life details and mental journey. During this period, friend B showed varying degrees of attention and interaction with A's Moments. Specifically, B quickly liked 8 of A's Moments within 30 minutes after they were posted. This timely feedback can be called "timely like"; for another 5 Moments, B gave affirmation within 2 hours, which is defined as "relatively timely like"; for the other 2 Moments, B liked them within 4 hours. Although it was a bit delayed, it still reflected attention and recognition, which is called "delayed like". Of course, there were also 5 Moments that B did not like.

[0034] To more intuitively quantify the degree of B's attention and interaction with A's Moments, the present invention sets a corresponding scoring mechanism for different types of likes. Timely like reflects the highest degree of attention and interactivity, so each is given a weight of 1 point. Therefore, the total score of timely likes is 8×1 = 8 points. Although relatively timely like is slightly inferior, it still reflects a relatively high degree of attention. Each is given a weight of 0.8 points. The total score of relatively timely likes is 5×0.8 = 4 points. The degree of attention of delayed like is relatively low, and each is given a weight of 0.5 points. The total score of delayed likes is 2×0.5 = 1 point. By combining the scores of various types of likes above, the total like score of B for A's Moments can be calculated as 8 + 4 + 1 = 13 points.

[0035] Step 3: With the help of natural language processing technology, deeply analyze the comment content, classify it into positive in-depth comments, general communication comments, and perfunctory response comments, and assign different weights to each type of comment.

[0036] In a specific embodiment, with the help of advanced natural language processing technology, the collected comment content is deeply analyzed to extract the deep information and emotional tendency contained in the comments. By comprehensively analyzing the vocabulary, grammar, and semantic structure of the comments, the true thoughts and needs of friends can be grasped more accurately. By constructing and optimizing the classification model, the embodiments of the present invention accurately classify the comments into positive in-depth comments, general communication comments, and perfunctory response comments. In implementation, domestic large language models such as Tongyi Qianwen and ERNIE Bot, which have excellent performance in understanding complex contexts and capturing emotional tendencies, as well as high efficiency and accuracy in processing large amounts of text data, can be used for in-depth analysis and accurate classification of comment content. Preferably, to ensure the accuracy of classification, the model can be continuously trained and adjusted to adapt to various comment styles and contexts.

[0037] After classification, different weights are assigned to various types of comments according to the type and quality of the comments. Specifically, positive and in-depth comments often reflect a relatively high frequency of interaction and emotional investment among users. Such exchanges will be assigned a higher weight in the calculation. On the contrary, general communication comments and perfunctory responses or simple confirmation messages contribute less to the intimacy of friends due to the lack of in-depth interaction. Therefore, they will be assigned a lower weight in the calculation process. Through this weight assignment mechanism, the intimacy between friends can be more accurately quantified, providing valuable reference data for the calculation of intimacy.

[0038]

[0039] Preferably, in order to quantify this evaluation, referring to the above comment rule comparison table, the weight of positive and in-depth comments is set to 3, the weight of general communication comments is set to 2, and the weight of perfunctory response comments is set to 1. Still taking the comments of friend B on user A's Moments as an example, within one month, B commented on A's Moments 15 times. Among them, there were 5 positive and in-depth comments, showing that B has a strong interest and deep concern for A's content; there were 6 general communication comments, indicating that both sides have a stable interaction; and there were 4 perfunctory response comments, which may be short responses during busyness. Then, multiply these numbers by their respective corresponding weights to obtain the scores of various types of comments. Finally, add up these scores to get the total score of the comments. According to the following scoring mechanism:

[0040] Score of positive and in-depth comments = 5 × 3 = 15 points

[0041] Score of general communication comments = 6 × 2 = 12 points

[0042] Score of perfunctory response comments = 4 × 1 = 4 points

[0043] Therefore, the total score of friend B's comments on user A's Moments is: 15 + 12 + 4 = 31 points. This score objectively reflects B's attention and interaction depth with A's Moments, effectively differentiates the quality and depth of the comments, and more truly reflects the degree of communication between friends.

[0044] Step 4: Statistically analyze the data on the number of interactions of mutual friends between the user and their friends, and assign corresponding weights according to the frequency of interaction. The interaction behavior of mutual friends can often indirectly reflect the strength of the relationship and potential similarity between the two. For example, within a 30-day time range, if the total number of interactions of this mutual friend exceeds a set specific threshold (such as 10 times), it is determined that there is a strong relationship between the two.

[0045] Specifically, in this embodiment, it is necessary to obtain the interaction records between the user and all their friends, which can include various forms of interactions such as chat messages, likes, and comments. Then, identify which interactions occur between the user and their mutual friends, and count these interactions. To analyze the frequency of interactions more precisely, a certain time window can be adopted, such as the interaction data within the past month or three months. Calculate the number of interactions between each mutual friend and the user within this time window, and then assign corresponding weights to each mutual friend according to the frequency of interactions. For example, several weight levels can be set, such as "high", "medium", and "low", or a more detailed quantitative scoring system can be used. The assignment of weights can be based on preset rules or algorithms, or can be dynamically adjusted in combination with machine learning methods to improve accuracy and flexibility.

[0046] Taking friends A, C and their mutual friend B as an example, assume that within one month, mutual friend B liked and commented on the Moments of friends A and C respectively, for a total of 48 times. According to the analysis rules, this means that there is a strong association between user A and friend C. To quantify this association, a weight value is assigned, which is set to 0.4 in this example. When calculating the mutual friend interaction score, a simple and effective method can be adopted, which is to directly multiply the total number of interactions by the weight. Therefore, according to our calculation method, the mutual friend interaction score is equal to 48 interactions multiplied by the weight of 0.4, that is, 18 points.

[0047] This scoring mechanism helps to capture the indirect associations and potential similarities in the friend relationship, thus providing a richer dimension for the intimacy assessment and also providing strong data support for subsequent functions such as social network analysis.

[0048] Step 5: Combine the weight scores of various behaviors in the above steps, and through comprehensive calculation and evaluation, obtain the intimacy score between the user and the friend, and divide different intimacy levels accordingly. That is to say, in Step 5, add up the total like score, the total comment score, and the mutual friend interaction score. Through this rigorous calculation process, obtain the comprehensive intimacy score between the user and the friend.

[0049] Specifically, first sum up the scores of the user in each dimension, including like behavior, comment quality, and the interaction of mutual friends. Next, according to the pre-set scientific score range, accurately divide the comprehensive score into intimacy levels.

[0050] Serial number Score range Intimacy level 1 0-20 Low intimacy 2 21-50 Medium intimacy 3 51-80 High intimacy 3 Above 81 points Extremely high intimacy

[0051] Referring to the above intimacy level rule comparison table, the intimacy status between the user and his friends can be comprehensively evaluated based on the scores of each item. Taking user A and his friends as an example, after detailed statistics and analysis, the following scores were obtained: the total score for likes is 13 points, the total score for comments is 31 points, and the score for mutual friend interaction is 18 points. Then add these three scores together, that is, the comprehensive score = total score for likes + total score for comments + score for mutual friend interaction = 13+31+18=62 points. According to the pre-set scientific score range, a comprehensive score between 51-80 points is judged to be a high intimacy state. Therefore, this method can clearly determine that user A and his friend B are in a high intimacy state.

[0052] This comprehensive calculation and grading method not only provides objective and quantitative evaluation results, but also helps users better understand and manage their interpersonal networks. Users can adopt different communication strategies for different friends based on the intimacy level, thereby optimizing their social experience. It also provides users with a clear reference to help them mine and analyze potential clues.

[0053] In general, through the comprehensive calculation and evaluation in step 5, a comprehensive and accurate intimacy evaluation system is provided for users. This system not only takes into account direct interaction behaviors, but also incorporates the interaction of common friends, making the evaluation results more comprehensive and in-depth.

[0054] It is worth mentioning that the intimacy measurement method based on network community behavior proposed in this invention has been widely used in the field of network security and has been highly praised and recognized by industry experts in operation. This method can not only process target data quickly and stably, but also substantially optimize the work efficiency of professionals. It can be foreseen that the efficiency and reliability of this technology will provide strong support for the rapid execution and analysis of more important tasks in the future, provide more powerful data support for the field of network security, and further highlight its practical application value and social significance in maintaining network security.

[0055] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed, the steps of the intimacy measurement method based on network community behavior provided by the embodiment of the present invention are implemented.

[0056] Figure 3 is a block diagram of a computer device 300 showing a method for calculating intimacy based on network community behavior according to an exemplary embodiment. For example, the computer device 300 may be provided as a server. Figure 3, the computer device 300 includes a processor 301, and the number of processors can be set to one or more according to needs. The computer device 300 further includes a memory 302 for storing instructions executable by the processor 301, such as application programs. The number of memories can be set to one or more according to needs. The application programs stored therein can be one or more. The processor 301 is configured to execute instructions to perform the above-mentioned method for calculating intimacy based on network community behavior.

[0057] Those skilled in the art should understand that the embodiments herein can be provided as a method, an apparatus (device), or a computer program product. Therefore, the embodiments herein can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments herein can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code. Computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable instructions, data structures, program modules, or other data, including but not limited to RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cassette, tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, as is well known to those of ordinary skill in the art, communication media typically includes computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transmission mechanism, and can include any information delivery medium.

[0058] This article is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (devices), and computer program products according to the embodiments herein. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the function specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0059] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device that implements the function in the process Figure 1One or more processes and / or blocks Figure 1 The functions specified in one or more blocks.

[0060] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operations S are performed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide S for implementing the functions specified in one Figure 1 One or more processes and / or blocks Figure 1 S for the functions specified in one or more blocks.

[0061] In this document, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that an article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such article or device. Without further limitation, the elements defined by the statement "comprising..." do not exclude the presence of additional identical elements in the article or device comprising said elements.

[0062] Although the preferred embodiments of this document have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of this document.

[0063] Obviously, those skilled in the art can make various changes and modifications to this document without departing from the spirit and scope of this document. Thus, if these modifications and variations of this document fall within the scope of the claims of this document and their equivalent technologies, the intention of this document also includes these modifications and variations.

Claims

1. A method for calculating intimacy based on online community behavior, comprising the following steps: S1: Collect friend behavior data of users in the online community, including but not limited to the timeliness of likes, the depth of comment content and the interaction data of common friends; S2: classifying the collected like timeliness data, clearly distinguishing timely likes, relatively timely likes and delayed likes, and setting corresponding weights for each type of like behavior; S3: With the help of natural language processing technology, the comments are deeply analyzed and classified into active and in-depth comments, general communication comments and perfunctory response comments, and different weights are assigned to each type of comments; S4: Count and analyze the number of interactions between the user and his friends, and assign corresponding weights according to the frequency of interactions; S5: Combining the weighted scores of the above-mentioned various behaviors, through comprehensive calculation and evaluation, the intimacy score between the user and the friend is obtained, and different intimacy levels are divided accordingly.

2. According to the method of claim 1, in step S2, the weights of timely likes, relatively timely likes and delayed likes are set to decrease step by step.

3. According to the method of claim 1 or 2, in step S3, the weight of active and in-depth comments is set higher than that of general communication comments, and the weight of general communication comments is set higher than that of perfunctory response comments.

4. According to the method described in claims 1-3, in step S4, the interaction data of common friends includes the number of likes and comments in a specific time period. When these interactions exceed a preset threshold, they will be given a higher weight.

5. According to the method described in claims 1-3, the calculation and evaluation process of the intimacy score in step S5 includes accumulating the weighted scores of various behaviors to obtain a total score, and judging the specific intimacy level between the user and the friend based on a preset intimacy level threshold.

6. The method according to claim 2, wherein: The weight of timely likes is set to 1, the weight of relatively timely likes is set to 0.8, and the weight of delayed likes is set to 0.

5.

7. The method according to claim 3, wherein: Set the weight of active and in-depth comments to 3, the weight of general communication comments to 2, and the weight of perfunctory response comments to 1.

8. According to the method of claim 4, when the number of interactions between two people by a common friend exceeds 10 times in the past 30 days, the weight assigned is 0.

4.

9. A computer-readable storage medium having a computer program stored thereon, wherein: When the computer program is executed, the method according to any one of claims 1 to 8 is implemented.

10. A computer device comprising a processor, a memory and a computer program stored in the memory, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

Images