Method and device for extracting relationship circle of members in social network service (SNS) network

1. A method for extracting a relationship circle of members in a social network service (SNS) network, comprising:

(a) selecting target people in the SNS network; and

(b) analyzing relationship chains of the target people, and extracting the relationship circle of the target people from the relationship chains of the target people according to feature filtering conditions;

wherein the relationship chains comprise contact person's information of the target people comprising feature information of a contact person; and

the operation of extracting the relationship circle of the target people from the relationship chains of the target people according to feature filtering conditions comprises:

extracting relationship circle members of the target people from the relationship chains of the target people according to the feature filtering conditions and the feature information of the contact person;

wherein the step (a) comprises:

(a1) establishing a concerned group database, and selecting the target people from the concerned group database according to query conditions; and

(a2) setting a scale predetermined value of the relationship circle of the target people, a level predetermined value of the relationship circle of the target people and feature filtering conditions of relationship circle members;

wherein the step (b) comprises:

(b1) extracting the contact person's information of the target people from the relationship chains of the target people; and

(b2) selecting the relationship circle members of the target people according to the feature filtering conditions and the contact person's information, and determining levels of the relationship circle members within the relationship circle;

wherein the step (b2) comprises:

(b21) setting a current level of the relationship circle to O, and adding the target people as relationship circle members to an unprocessed queue, meanwhile flushing a processed queue;

(b22) determining whether the scale of a current relationship circle reaches the scale predetermined value, if it is, extracting the current relationship circle, otherwise proceeding to step (b23);

(b23) determining whether the unprocessed queue is empty, if it is, extracting the current relationship circle, otherwise removing a first relationship circle member from the unprocessed queue as a current relationship circle member added to the processed queue, and setting a current level to be a level of the current relationship circle member;

(b24) extracting feature information of the current relationship circle member, and determining whether the current level is O, if it is, proceeding to step (b26), otherwise proceeding to step (b25);

(b25) determining whether the feature information of the current relationship circle member meets the feature filtering conditions, if it is, proceeding to step (b26), otherwise proceeding to step (b22);

(b26) determining whether the current level plus 1 is smaller than the level predetermined value, if it is, proceeding to step (b27), otherwise proceeding to step (b22)

(b27) traversing every contact person of the current relationship circle member, if the contact person is neither in the unprocessed queue nor in the processed queue, the contact person as a relationship circle member is added to a tail of the unprocessed queue, setting a level of the contact person to the current level plus 1; otherwise proceeding to step (b28); and

(b28) storing the feature information, contact person's information and levels of the current relationship circle member in a relationship circle database, and then proceeding to step (b22).

2. The method of claim 1 , wherein the concerned group database stores feature information of concerned group and unique identifies of the concerned group corresponding to the SNS network.

3. The method of claim 1 , further comprising:

(c) displaying the relationship circle members according to levels based on information of the relationship circle database.

4. The method of claim 1 , further comprising:

(d) extracting relationship information and/or feature information of each relationship circle member of the relationship circle, and calculating influence of each relationship circle member in the relationship circle according to the relationship information and/or feature information.

5. The method of claim 4 , wherein the step (d) comprises:

(d1) extracting feature information of the relationship circle members, and calculating characteristics ratings of the relationship circle members according to the matching degree between the feature information of the relationship circle members and the feature filtering conditions of the relationship circle;

(d2) extracting relationship information of the relationship circle members, and calculating relationship ratings of the relationship circle members according to relationship information of the relationship circle members; and

(d3) calculating influence of the relationship circle members according to weighted results of the characteristics ratings and the relationship ratings.