KR101540451B1 - Social network service system and method for recommending friend of friend based on intimateness between users - Google Patents

Abstract

A social network service system and method for recommending a friend of a friend based on an intimacy between users is disclosed.
A social network service system, comprising: an extractor for extracting communication information from a friend relationship of a user with a one-village friend and a friend relationship of a friend of a two-village friend; A calculation unit for calculating an intimacy degree of the friend relationship based on the extracted communication information; And a generating unit for generating a list of the two-dimensional buddies to be recommended based on the calculated intimacy.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a social network service system and method for recommending a friend of a friend based on intimacy between users,

Embodiments of the present invention relate to a social network service system and method for recommending a friend of a friend based on intimacy between users.

A friend recommendation function in a social network service (SNS) is a function for helping a user to make a new friend, and is a function useful for a user having a small number of friends having a friend relationship. In the prior art, when a friend of a specific user is defined as a friend of a particular village and a friend of a friend of the village is defined as a friend of a friend of the village (in terms of a particular user) ).

For example, assuming that the users A and B have a friend relationship (F (A, B) = True) and the mutual friend count of the users A and C is MFC (A, C) (A, B) = True and F (B, C) = True and F (A, C) = not True ). ≪ / RTI > In this case, in the prior art, the number of common friends of users A and C and the number of common friends of users A and C are sorted in descending order, (A, C) are set to a value equal to or greater than the set value.

However, in the friend recommendation method of the friend according to the related art, in recommending a friend of a friend who is a friend of a friend who is a second friend to a specific user, the recommendation priority is set such that the friend of the friend and the specific user have many common friends The number of common friends), so there is actually a problem that the relationship between two users (a specific user and a friend of a two-dimensional person) is not reflected. For example, even though a particular user and a second-class friend may have 100 common friends, the two users may not know each other at all. That is, there is a problem that the number of common friends can not indicate how much the two users are related to each other.

In this specification, a social network service system and method are provided that can more effectively recommend a friend in a social network service.
Korean Patent Laid-Open No. 10-2010-0130003 and Korean Laid-Open Patent Application No. 10-2010-0109847 are the background technologies of the present invention.

The intimacy degree between the users is calculated based on the communication information such as the number of the conversations and the number of the sympathies between the users and the like, and the friend's friend is recommended based on the calculated intimacy, And provides a social network service system and method for recommending a friend.

A social network service system for recommending a friend, the system comprising: an extracting unit for extracting communication information from a friend relationship of a first-person friend and a friend relationship of a second friend who is a friend relationship with the friend of the user; A calculation unit for calculating an intimacy degree of the friend relationship based on the extracted communication information; And a generation unit for generating a list of recommended two-dimensional buddies based on the calculated intimacy level.

In one example, the communication information extracted by the extraction unit includes at least one of interaction information such as number of comments and empathy, and friend duration, and the interaction information is an interaction occurring in a friend relationship, Based on

In another aspect, the calculation unit calculates the intimacy of the friendship of the user with the one-village friend, and the friend relationship of the one-village friend and the two-village friend.

In yet another aspect, the calculation unit calculates the intimacy by reflecting the equation (1).

Equation 1:

(Here, the user is referred to as a two-dimensional friend recommended for X, X is referred to as Z, and the mutual friend count of the two is referred to as MFC (X, Z). and, I (X, Y _i) is a numerical representation of the intimate index, that is, the traffic of user Z and 1 connection friend Y value, I (Yi, Z) is intimately in one village friend Y with his friend, 2 Village friend Z And the intimacy index is obtained by the number of common friends of X and Z.)

In yet another aspect, the intimacy calculated in the calculation unit is used after the estimation and verification process, and is fed back to the extraction unit to reflect the continuously changing communication information.

In another aspect, the generating unit leaves only a certain number of recommended 2-dimensional buddies based on the calculated intimacy, and removes the rest.

In another aspect, a social network service system performs a query method of a graph model for tracking desired reference data by tracking a reference pointer indicating a friend relationship between users.

According to another aspect of the present invention, a social network service system further includes a memory unit that stores related data, stores data exceeding a memory capacity of the memory unit in a solid state drive (SSD) Lt; / RTI >

In another aspect, a social network service system further comprises a memory unit for storing related data, wherein the memory of the memory unit is categorized to distribute and store data, and a remote cache cloud is included in the distributed memory Refer to it when data can not be found.

A method of providing a social network service for recommending a friend, comprising: extracting communication information from a friend relationship of a user with a one-village friend and a friend relationship of a friend of a two-village friend; Calculating an intimacy degree of the friend relationship based on the extracted communication information; And generating a list of the two-dimensional buddies to be recommended based on the calculated intimacy.

The degree of familiarity between users based on communication information such as the number of comments and the number of sympathies and the like, the duration of friends, etc., and recommends a friend of a friend based on the calculated familiarity, Can be recommended.

By constructing a data model having a faster response speed suitable for a social network system, data can be obtained more efficiently with respect to a social network service.

1 is a block diagram for explaining an internal configuration of a social network service system according to an embodiment of the present invention.
FIG. 2 is a diagram showing an example of calculating the intimacy between a user and a friend in an embodiment of the present invention. FIG.
FIG. 3 is a diagram showing an example for explaining a process of calculating an intimacy value in an embodiment of the present invention. FIG.
4 is a diagram illustrating a data model structure applicable to a social network service system according to an embodiment of the present invention.
5 is a diagram illustrating a data model structure applicable to a social network service system according to an embodiment of the present invention.
FIG. 6 is a table comparing performance of a relationship modeling structure and a graphic modeling structure in an embodiment of the present invention.
FIG. 7 is a table comparing performance of a graph modeling structure in a case of using a relationship modeling structure, a graph modeling structure, and a predetermined number of friends in an embodiment of the present invention.
FIG. 8 is a graph comparing the performance of a graph modeling structure that displays all recommended friends and a graph modeling structure that sets a recommended number of friends in an embodiment of the present invention.
9 is a diagram illustrating an example of a method for expanding a social network service system in an embodiment of the present invention.
10 is a diagram illustrating another example of a method for expanding a social network service system in an embodiment of the present invention.
11 is a flowchart illustrating a method of providing a social network service according to an exemplary embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

Embodiments of the present invention can be applied to a two-dimensional friend (i.e., a friend of a friend) who is a friend who has a friend relationship with a specific user in a social network service, Friend) as a one-man friend so that the user can extend the network.

At this time, in the social network service system and method according to the embodiment of the present invention, in order to recommend a two-dimensional friend to a specific user, basically, one-sided friend who has a high intimacy with a specific user, You can recommend a friend who is a high one person and a friend who is two people who are very close to each other.

If the friend recommendation method of the existing friend is determined only by the friend priority of the friend in recommending friend's friend and how many common friends the friend and the specific user have (i.e., the number of common friends) In the embodiments, the intimacy level is reflected in the friend relationship, so that it can be focused on the friend who is closer to the intimacy similar to the real life.

1 is a block diagram for explaining an internal configuration of a social network service system 100 according to an embodiment of the present invention. The social network service system 100 according to the present embodiment may include an extraction unit 110, a calculation unit 120, and a generation unit 130 as shown in FIG.

First, the extracting unit 110 extracts the communication information from the friend relationship of the user and the one-village friend, and the communication information from the friend relationship of the friend of the two villages which is the friend relationship with the user of the user.

The communication information may include at least one of interaction information such as the number of comments and empathy, and friend duration, and the interaction information may be determined based on the number of the at least one action as the interaction occurring in the friend relationship. For example, the interaction information can be determined on the basis of the number of times a comment is made, the number of times it is sympatrated, the number of times an action such as post embedding, or setting a friend of interest has occurred.

The calculation unit 120 calculates the intimacy of the friend relationship based on the extracted communication information. The intimacy calculated here is the intimacy of friendship between a user and a friend, and the intimacy of friendship between a user and a friend.

Referring to FIG. 2, in the embodiment of the present invention, a total of seven users from user A to user G are shown. User A corresponds to a user, users B, C and D are friends of a user A, and users E, F, and G are friends that can be recommended to the user A, that is, friends of two. In FIG. 2, the users connected with the double arrows may refer to users who have a friend relationship with each other, and the numbers on the arrows indicate familiarity between users who are connected to each other by double arrows.

Intimacy can be a measure of how much you have commented on and sympathized with your opponent. As you write a lot of comments and get a lot of sympathy, the intimacy is measured highly, and you can perform operations on the published posts.

Some friendship is formed shortly after the friendship is established, and as the friendship day passes, the intimacy can be reduced. The default value for indicating a friend relationship can be one.

In calculating the intimacy, the concept of being leveled can be introduced in order to reduce the deviation of one-sided familiarity, so that the value of the recent days can be calculated by leveling. Hereinafter, a friend recommendation algorithm according to an embodiment of the present invention will be described. First, when F (X, Y) = True, the mutual friend count of the users X and Z is MFC (X, Z) Assuming that the recommended friend set of user X is F (X, Y) and can be defined as a set of Z's with F (Y, Z). At this time, assuming that I (X, Y) is an intimacy of X → Y (that is, a value representing the traffic from X to Y), the intimacy of Z with respect to X is calculated as shown in Equation 1 below .

In Equation 1, X represents a user, Yi represents a user and a one-village friend, and Z represents a user and a two-dimensional friend. As an example using the above equation, the intimacy between the user A and the two-sided friend users E, F, and G shown in FIG. 2 can be obtained. The number of common friends of users A and E, that is, MFC (A, E) is '3', the number of common friends of users A and F, , That is, MFC (A, G) is '2'. Therefore, according to the existing technology, since the friend is recommended based on the number of common friends, the probability that the user E is recommended to the user A is the highest. However, according to the embodiment of the present invention, the familiarity of the user E, the user F, and the user G to the user A calculated using Equation (1) is 1 * 2 + 5 * 1 + 2 * 1 = 9 ',' 5 * 4 = 20 ', and' 5 * 2 + 2 * 3 = 16 ', the user F has the highest degree of familiarity with user A,

In addition, the intimacy calculated by the calculation unit 120 is used after being subjected to estimation and verification, and the feedback process is repeatedly performed by the extraction unit 110 to reflect the continuously changed communication information.

Fig. 3 is a diagram for explaining a process of calculating the intimacy in the embodiment of the present invention. Fig. Since the interest friend setting, commenting, sympathy, and friend duration extracted from the extracting unit 110 continuously change as a variable, the total statistics are aggregated and the numerical value is displayed in a predetermined range (Normalize or normalize), and the weight is applied to calculate the intimacy value. The calculated intimacy value can be calculated again through a predetermined method of verification, and the feedback process can be repeated to reflect the continuously changing numerical value.

In the process of calculating the intimacy, since there may be a bias of the intimacy value in the process of normalizing the intimacy value, one of the following two expressions can be selected and normalized.

In Equation (2), the above equation is the minimum-maximum normalization method using the maximum and minimum of the intimacy, and the following equation is an equation using the mean and standard deviation of the intimacy and intimacy before the normalization by the z-score normalization method. In Equation (2), I represents the intimacy original value, I 'represents the normalized intimate value, A represents the average of the intimacy, and б represents the standard deviation of the intimacy.

4 and 5 are diagrams illustrating a data modeling structure applicable to the social network service system 100. As shown in FIG. A data model suitable for a social network can be represented by a relational model and a graph model. Figure 4 illustrates the relationship model, and Figure 5 illustrates the modeling technique of the graph model.

The relationship model of FIG. 4 is a model for performing a join operation or a re-query method in which a user, a friend of a user and a friend of a friend are connected in a one-to- Is a model that forms a node based on a user of a social network service and performs a query method of obtaining desired data by tracking a reference pointer indicating a friend relationship between users.

When a friend of a user's friend is sought, the user's friend's data is fetched, the friend's friend's data is fetched in order, and the duplicate data or the friend's data is removed have.

In doing this, there is a join operation method and a re-query method. The two methods are substantially similar in processing within the system 100. If you re-query or combine operations, you will need to use additional pre- and post-processing to increase the amount of computation. In fact, faster data processing is possible when using the graph model. The reason for this is that the computation process is only possible with a memory operation. The fact that a reference pointer is connected means that the node has memory addresses of other nodes. That is, when moving from node to node, it is possible to do only memory operation.

For example, FIG. 6 can be referred to as a table comparing the performance of the relationship model and the graphic model structure described above. The embodiment of FIG. 6 shows the response speed when performing operations for obtaining two-dimensional buddies of a user having 250,000 friends for the relationship model structure and the graphic model structure, respectively. As a result, the number of friends in the two villages is 9,060,712, and the time required to extract two friends is 5.9 seconds. The graph model has a speed difference of about 40 times, which is 0.15 seconds. The response speed of the model shows a fast response speed.

In order to improve the validity of the system, it is necessary to perform response fail-over (see Fig. 2). In order to improve the validity of the system, Replication Failover) function. The response failover function allows data to be backed up to the alternate computer system so that the alternate system can be activated if the social network service system 100 fails and is not available.

In the social network service system 100, the generation unit 130 may remove only a certain number of recommended 2-way friends based on the calculated intimacy, and remove the rest. It is possible to reduce the performance of friend recommendation to the user and friend. In fact, as the number of users using the social network service increases, the number of users with a large number of friends is also increasing.

Therefore, in order to overcome the performance degradation caused by a large number of friends, a method of recommending only the number of friends set in order of intimacy can be used. This number may be based on the Dunbar's number. The Dunbar number is a number from the theory that Robin Dunbar, a professor of evolutionary anthropology at Oxford University, says that the number of people a human brain can remember as a close network is around 150, , And excluded friends may be excluded from the operation.

 As an example related to this, by expanding the embodiment shown above, a relationship model and a graph model for a user having 250,000 friends, and a graph model limited to 250 friends (150 for example) FIG. 7 shows a table comparing the performance when two-way buddies of a user are obtained in the three models.

As shown, the response time of the relationship model and the graph model is about 40 times better than that of the graph model, but the response time when the user's friend is reduced from 250,000 to 150 under the same conditions The performance of the same graph model can be 300 times as fast as the response speed of 0.0005 seconds.

The graph model is compared with the graph model in the case of using the number of friends set according to the intimacy. FIG. 8 shows the result count (result count, number of friends of the obtained friend), memory usage (Memory (memory), and the like) when a graph modeling technique using a graph model and the number of friends set according to the intimacy is used, ) And a load time (load time), respectively. As a result of comparison, the graph model in the case of setting the number of friends according to the intimacy improves the performance of the social network service system 100 by reducing the result count by about 99%, the memory by about 32%, and the load time by about 23% .

The social network service system 100 may not be able to store all the networking information according to the friend relationship through one server or one memory according to the rapid growth of the service. In fact, it is expected that the number of social network services in the world will reach 100 million subscribers and the amount of data will be huge.

Accordingly, in order to solve the scalability problem of data storage of the system, the social network service system 100 further includes a memory unit 140 for storing related data, and the memory unit 140 includes at least one memory 9, data exceeding the capacity of the memory of the memory unit 140 is stored in a solid state drive (SSD), which is a separate semiconductor storage medium, and data is maintained in the memory in accordance with a cache algorithm (Cache Algorithm) . The cache algorithm corresponds to Least Recently Used (LRU) or Least Frequently Used (LFU), and can hold data in the memory depending on the frequency of use of the memory or the recent use.

10, in order to solve the data extensibility problem of the system, the memory of the memory unit 140 is distributed and stored using a classification algorithm, and data is not found in the local memory, If not, you can refer to the data in the distributed memory via the Remote Cache Cloud.

11 is a flowchart illustrating a method of providing a social network service in an embodiment of the present invention. The social network service method according to the embodiment may be performed by the social network service system 100 described with reference to FIG.

In step 1110, the social network service system 100 determines whether a friend is in a friend relationship with a first-person friend, and a friend relationship with a second friend in a friend's first friend The communication information can be extracted. The communication information extracted in step 1110 may include at least one of interaction information such as number of comments and empathy, and friend duration, and the interaction information may include at least one number of actions Can be determined.

Also, in step 1120, the social network service system 100 may calculate the intimacy of the friend relationship based on the communication information extracted in step 1110.

Step 1120 can calculate the intimacy of the friend relationship of the user with the one-village friend and the friend relationship of the friend of the first village and the friend of the second village, and quantifies the traffic in the friend relationship, It uses the product of the quantified traffic to find the intimacy of the friend, and the intimacy can be obtained by the number of the common friends of the two friends who are recommended to the user and the user.

In addition, the calculated intimacy is used after evaluation and verification, and in order to reflect the continuously changing communication information, it is necessary to determine the degree of intimacy between the user and one of the two friends It is a step of extracting communication information from a friend relationship. The feedback process is performed. When the intimacy value is calculated through the feedback process and the verification is completed, a new intimacy value can be calculated by counting the communication information again.

After the intimacy has been calculated, the social network service system 100 may perform step 1130 of generating a list of recommended 2-party buddies based on the calculated intimacy through step 1120.

In step 1130, it is possible to leave only a certain number of recommendable 2-dimensional friends based on the calculated intimacy, and remove the rest. The recommended number of friends can be based on 150 persons, Limiting the number may be related to the problem of scalability of the social network service system 100, or to providing a concise system to the user by reducing unnecessary referral friend lists.

As described above, according to the embodiments of the present invention, an intimacy degree between users is calculated based on communication information such as the number of conversations and the number of empathes, such as the number of interactions and the friend duration, and the friend's friend is recommended based on the calculated intimacy , A friend of a friend can be recommended based on the intimacy between the actual users.

The methods according to embodiments of the present invention may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, and the like, alone or in combination. The program instructions recorded on the medium may be those specially designed and constructed for the present invention or may be available to those skilled in the art of computer software.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed embodiments, but, on the contrary, This is possible.

Therefore, the scope of the present invention should not be limited to the described embodiments, but should be determined by the equivalents of the claims, as well as the claims.

100: Social network service system
110:
120:
130:
140:

Claims (16)

1. A social network service system for recommending a friend,
The first communication information indicating the friend relationship between the user and the first-degree friend is extracted from the friend relationship of the first-degree friend, which is the friend of the user, and the first communication information indicating the relationship between the first friend and the friend An extracting unit for extracting second communication information indicating a friend relationship of a village friend;
Calculates a first intimacy of a friend relationship between the user and the first-degree friend based on the first communication information, and calculates a second intimacy of the friend relationship between the first-degree friend and the second-degree friend based on the second communication information ; And
A list of friends of two friends to be recommended based on the calculated first intimacy, the second intimacy, and the number of common friends between the user and two friends,
The social network service system comprising: The method according to claim 1,
Wherein the first and second communication information extracted by the extracting unit includes:
At least one of the number of comments or the number of emotions, and the friend duration,
Wherein the interaction information is determined based on at least one number of actions in an interaction occurring in a friend relationship
And a social network service system. The method according to claim 1,
The calculation unit may calculate,
Calculates the first intimacy for each friend relationship for the user and a plurality of one-village friends,
To calculate the second intimacy for friends of one village and friends of two villages by each friendship of friends of one village and friends of two villages
And a social network service system. 1. A social network service system for recommending a friend,
An extraction unit for extracting communication information from a friend relationship of a first-person friend who is a friend with a user, and a friend relationship of a friend who is a friend with the friend of the user;
A calculation unit for calculating an intimacy degree of a friend relationship based on the extracted communication information; And
And a generating unit for generating a list of the two-village friends to be recommended based on the calculated intimacy
Lt; / RTI >
The calculation unit
Calculating the intimacy of the friend relationship of the user with the one-village friend and the friendliness of the friend relationship of the one-village friend and the two-village friend to the expression (1)
And a social network service system.
Equation 1:

(Here, the user is referred to as a two-dimensional friend recommended for X, X is referred to as Z, and the mutual friend count thereof is referred to as MFC (X, Z). I (Yi, Z) represents the intimacy of friend 1 of friend 1 and friend 2 of friend Friend Z, and I (Xi, Yi) And the familiarity is obtained by the number of common friends of X and Z to obtain the familiarity degree of the user Z with respect to the user X.) The method according to claim 1,
The first and second intimates calculated by the calculation unit are used after a calculation and verification process,
A feedback process to the extracting unit to reflect the first and second communication information continuously changed
And a social network service system. The method according to claim 1,
Wherein the generation unit comprises:
Removing only a predetermined number of recommended 2-way friends based on the calculated first and second intimacy, and removing the rest
And a social network service system. The method according to claim 1,
The social network service system
Forming a node based on the user of the social network service,
Performing a query method of a graph model that obtains desired data by tracking a reference pointer indicating a friend relationship between users
And a social network service system. The method according to claim 1,
Wherein the social network service system further comprises a memory unit for storing related data,
Storing data exceeding the capacity of the memory of the memory unit in a solid state drive (SSD)
Maintaining said data in said memory in accordance with a Cache Algorithm
And a social network service system. The method according to claim 1,
Wherein the social network service system further comprises a memory unit for storing related data,
The memory of the memory unit is classified and the data is distributed and stored,
Including a remote cache cloud to refer to when the data is not found in the distributed memory
And a social network service system. A social network service method for recommending a friend performed by a social network service system including an extracting unit, a calculating unit, and a generating unit,
Extracting communication information from a friend relationship of a first-person friend who is a friend with a user, and a friend relationship of a second friend who is a friend relationship with the first-village friend of the user;
Calculating, in the calculation unit, an intimacy degree of a friend relationship based on the extracted communication information; And
Generating a list of the two-village friends to be recommended based on the calculated intimacy,
Lt; / RTI >
The step of extracting the communication information includes:
Extracting first communication information indicating a friend relationship between a user and a one-village friend in a friend relationship of the one-village friend with the user; And
Extracting second communication information indicating a friend relationship between a first-class friend and a second-class friend in a friend relationship of the two-village friend,
Lt; / RTI >
Wherein the step of calculating the affinity comprises:
Calculating a first affinity of a friend relationship between the user and the one-sided friend based on the extracted first communication information; And
Calculating a second intimacy of the friend relationship between the one-village friend and the two-village friend based on the second communication information
Lt; / RTI >
The step of generating the list of the two-
Generating a list of friends of the two communities based on the first intimacy, the second intimacy, and the number of common friends between the user and the two friends
Wherein the social network service method comprises the steps of: 11. The method of claim 10,
The communication information extracted in the step of extracting the communication information from the friend relationship of the user with the one-village friend and the friend relationship of the friend of the two villages,
At least one of the number of comments or the number of emotions, and the friend duration,
Wherein the interaction information is determined based on at least one number of actions in an interaction occurring in a friend relationship
Wherein the social network service method comprises the steps of: 11. The method of claim 10,
Wherein the step of calculating the intimacy of the friend relationship based on the extracted communication information comprises:
Calculates the first intimacy for each friend relationship for the user and a plurality of one-village friends,
To calculate the second intimacy for friends of one village and friends of two villages by each friendship of friends of one village and friends of two villages
Wherein the social network service method comprises the steps of: A social network service method for recommending a friend performed by a social network service system including an extracting unit, a calculating unit, and a generating unit,
Extracting communication information from a friend relationship of a first-person friend who is a friend with a user, and a friend relationship of a second friend who is a friend relationship with the first-village friend of the user;
Calculating, in the calculation unit, an intimacy degree of a friend relationship based on the extracted communication information; And
And generating, in the generation unit, a list of the two-dimensional buddies to be recommended based on the calculated intimacy,
The step of calculating the intimacy degree of the friend relationship based on the extracted communication information
And calculating the intimacy of the friend relationship of the user with the one-village friend and the friendliness of the friend relationship of the one-village friend and the two-village friend to the expression (2)
Wherein the social network service method comprises the steps of:
Equation 2:

(Here, the user is referred to as a two-dimensional friend recommended for X, X is referred to as Z, and the mutual friend count thereof is referred to as MFC (X, Z). I (Yi, Z) represents the intimacy of friend 1 of friend 1 and friend 2 of friend Friend Z, and I (Xi, Yi) And the familiarity is obtained by the number of common friends of X and Z to obtain the familiarity degree of the user Z with respect to the user X.) 11. The method of claim 10,
The intimacy calculated in the step of calculating the intimacy of the friend relationship based on the extracted communication information is used after a calculation process and a verification process,
In order to reflect the communication information continuously changing,
A step of extracting communication information from the friendship relationship between the user and the one-village friend, and the friend relationship of the friend of the two villages, that is, the friend relationship with the one-village friend of the user
Wherein the social network service method comprises the steps of: 11. The method of claim 10,
Wherein the step of generating a list of recommendable two-dimensional buddies based on the calculated intimacy,
Removing only the recommended number of 2-way friends based on the calculated intimacy and remainder
Wherein the social network service method comprises the steps of: 16. A computer-readable medium having recorded thereon a program for performing the method according to any one of claims 10 to 15.

Images