KR101396013B1 - Method and Server for Establishing Cognitive Social Network - Google Patents

Abstract

A method and server for establishing a cognitive social network are provided. The method of constructing a cognitive-based social network according to an embodiment of the present invention extracts customary activity information of a user and generates a personal social trust map in which the trusts of the persons directly related to the user and the persons concerned are displayed together , And synthesizes personal social trust maps to generate a total social trust map, and constructs a cognitive social network for each user from the entire social trust map. Thus, it is possible to construct a cognitive social network that can autonomously recognize the relationship between users by analyzing the interaction with information of various sources.

Description

TECHNICAL FIELD The present invention relates to a method and a server for establishing a cognitive type social network,

The present invention relates to a method for constructing a social network and a server, and more particularly, to a method and a server for constructing a social network in a mobile environment.

An online social network refers to a human network formed by users through information sharing, exchange, and transactions using the Internet. While in the real world, people live limited social relationships with friends, family, and colleagues, online forms social relationships in an open manner with relatively diverse people.

Users often express their views and opinions on their various experiences through social network services (SNS) such as blogs, Twitter ^TM , and Facebook ^TM . As such, social activities through social networks (or social network services) are a new form of collaboration and communication.

On the other hand, in the relationship between the traditional users, it was possible to qualitatively recognize the degree of psychological and social trust based on the past experience. However, in the online social network, due to the diversity of relationships formed from different sources, It became difficult to recognize.

For a reliable relationship model in online social networks, it is important to abstract psychological and social information into electronic quantitative information.

However, existing social networks recognize the relationship between fragmented users and can not control the uncertainty and ambiguity of the relationship between users. In addition, information leaks and privacy issues are being revealed due to indiscreet sharing of information.

Accordingly, it is required to search for a method for establishing a relationship between trusted users in an online social network.

SUMMARY OF THE INVENTION The present invention has been made in order to solve the above-mentioned problems, and it is an object of the present invention to provide a cognitive social network construction method and a server which can autonomously recognize a relationship among users by analyzing an interaction with information of various sources.

According to an aspect of the present invention, there is provided a method of constructing a cognitive-based social network, comprising: extracting customary activity information of a user; Generating a personal social trust map in which the trustees directly related to the user and the trustees are displayed together using the extracted conventional activity information; Synthesizing the personal social trust maps to generate a total social trust map; And building a cognitive social network for each user from the total social trust map.

And, the conventional activity information may be a call record.

In addition, the reliability may be determined using at least one of a call frequency, a call duration and a call update analyzed from the call history.

And, in the building step, the awareness-based social network can be constructed by reflecting personal information on the entire social trust map.

Further, the method of constructing a cognitive-based social network according to an exemplary embodiment of the present invention may further include receiving a user profile, wherein the personal information includes at least one of a total of all persons included in the personal social trust map, The constructing step may construct the cognitive social network from the total social trust map by adjusting the reliability based on the empathy level for each user from the total social trust map .

The attribute may include at least one of age, sex, address, and occupation.

Also, in the constructing step, the awareness-based social network may be constructed by reflecting environmental activity information together with the personal information on the entire social trust map.

According to another aspect of the present invention, there is provided a method of constructing a cognitive-based social network, comprising: measuring similarity for each user; And clustering users based on the measured similarity, wherein the constructing step comprises constructing the perceptual social network by adjusting the reliability on the entire social trust map based on the personal information and the clustering result .

Further, the method of constructing a cognitive-based social network according to an embodiment of the present invention may further include extracting SNS (Social Network Services) activity information of users, The degree of similarity can be measured for each user.

In the constructing step, the awareness-based social network may be constructed by reflecting environmental activity information on the entire social trust map.

In addition, the method of constructing a cognitive-based social network according to an embodiment of the present invention may further include recommending a user who is highly reliable from the cognitive-based social network and customarily recommending the user.

Meanwhile, the cognitive-based social network construction server according to another exemplary embodiment of the present invention may include a user who uses the user's customary activity information, A communication module receiving the social trust map; And a processor for synthesizing the personal social trust maps received through the communication module to generate a total social trust map and constructing a perceived social network for each user from the total social trust map.

As described above, according to the present invention, it is possible to construct a cognitive social network that can autonomously recognize the relationship between users by analyzing the interaction with information of various sources. Since the cognitive social network constructed in this way is constructed based on customary activity information, personal information, and environmental activity information, it is possible to establish a more reliable relationship among users in the online social network, and it becomes possible to recommend a personalized person.

BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a diagram illustrating a BD-based cognitive-based social network construction method according to an exemplary embodiment of the present invention;
FIG. 2 is a diagram illustrating the results of calculation of the credibility of the persons to be included in the call record and the user's personal social trust map,
Figure 3 illustrates a personal social trust map and an autonomic cognitive social network generated through the method shown in Figure 1;
FIG. 4 is a diagram illustrating a method of constructing a BD-based and PD-based awareness-based social network according to another embodiment of the present invention;
5 is a diagram illustrating a UI screen used for inputting a user profile,
6 is a diagram illustrating a personal social trust map and an autonomic cognitive social network generated through the method shown in FIG.
FIG. 7 is a diagram illustrating a method of constructing a cognitive-based social network based on BD and ED according to another embodiment of the present invention;
8 is a diagram illustrating a personal social trust map and an autonomic cognitive social network generated through the method shown in FIG. 7,
FIG. 9 is a view for explaining a method of constructing a cognitive-type social network based on BD, PD, and ED according to another embodiment of the present invention;
10 illustrates an example of a personal social trust map and an autonomic cognitive social network generated through the method shown in FIG. 9;
11 is a block diagram of a client providing information necessary for establishing a cognitive-based social network,
12 is a block diagram of a server for performing cognitive type social network construction.

Hereinafter, the present invention will be described in detail with reference to the drawings.

In the preferred embodiments of the present invention, a method for analyzing the interaction of information from various sources and establishing a social network capable of autonomously recognizing the relationship between users is presented.

In the preferred embodiments of the present invention, various kinds of information will be used, such as Behavioral Interaction Information, Personal Information, and Environmental Activity Information.

One. BD ( Behavioral Determinant ) Based Cognitive type Social  network

BD-based cognitive social network is a social network that autonomously recognizes and builds relationships among users based on behavioral activity information.

Conventional activity information means that a user interacts directly or indirectly with other users on an online social network. The call log information of the user can be used as the conventional activity information, which will be described in detail with reference to FIG.

1 is a diagram for explaining a BD-based cognitive-based social network construction method according to an embodiment of the present invention.

In order to construct a BD-based cognitive-based social network, as shown in FIG. 1, a client corresponding to a user's mobile device first extracts its own call record (S110) A trust map is generated (S120). The personal trust map generated in step S120 is transmitted to the server.

A personal social trust map is a map showing the credibility of the people (family, co-worker, friend, etc.) who have a direct relationship with the user of the mobile device and their associates. Here, reliability is a measure of how closely the relationship between the user and the stakeholder is expressed, expressed as a minimum of 0 (no relation) and a maximum of 1 (having a close relationship).

In order to quantitatively deduce the reliability to be included in the personal social trust map generated in step S120, the client analyzes the call frequency, the duration and the call recency in the call history extracted in step S110 do.

Specifically, the reliability of the party A having a high communication frequency with the user can be set to be higher than the reliability of the party B having a low communication frequency with the user.

Also, the reliability of the person C having a long conversation duration with the user can be set higher than that of the person D having a short conversation duration with the user.

Here, the duration of the call can be divided into the duration of the transmitted call and the duration of the received call. The transmission call duration time is a time when the user has continued to make a telephone call to the person concerned, and the incoming call duration time is a time when the user has received a telephone call from the person concerned and continued the call.

If the user shows a preference for transmission, it is preferable to give a higher weight to the transmission call duration time than the reception call duration time. On the other hand, when the user shows a tendency toward reception, it is preferable to give a higher weight to the duration of the incoming call than the duration of the transmission call.

On the other hand, the reliability of the party E who has the latest call date and time with the user can be set higher than the reliability of the party F who is behind the latest call date and time with the user.

FIG. 2 illustrates the results of steps S110 and S120 shown in FIG. Specifically, the call record extracted through step S110 is illustrated on the left side of FIG. 2, and the persons (represented by a telephone number) to be included in the user's personal social trust map and the reliability calculation result thereof are illustrated on the right side of FIG. Respectively.

Referring back to FIG. 1, step S120 and subsequent steps will be described in detail.

The server combines the personal social trust maps generated by the plurality of clients in step S120 to generate a total social trust map (S130). By the total social trust map generated in step S130, an indirect relationship other than a direct relationship with the user is also generated. If the direct relationship is 'Friend', the indirect relationship becomes 'Friend of A Friend'.

Thereafter, the server constructs the entire social trust map generated in step S130 as a DB (S140), and constructs an autonomous cognitive social network for each user using the DB constructed in step S140 (S150). In step S150, the autonomous cognitive social network constructed for each user is transmitted to each user's client.

The autonomic cognitive social network generated in step S150 is the same as the personal social trust map generated in step S120 in that it is constructed for each user. However, autonomic cognitive social networks differ from personal social trust schemes, which include those who have direct relationships, as well as individuals who have indirect relationships, as well as individuals with direct relationships.

Furthermore, autonomic cognitive social networks have more credibility for those who have an indirect relationship, as well as for those who have a direct relationship.

The reliability of an indirect person is determined through the calculation using the credibility of the person who has a direct relationship.

For example, 'A and B', 'B and C' and 'C and D' have a direct relationship, 'A and B' have a reliability of 0.7, 'B and C' And the reliability between D 'and D' is 0.8.

In this case, 'A and C' have an indirect relation according to 'A → B → C', and the reliability of 'A and C' is set to 0.7 * 0.5 / 10 ² . Here, 0.7 is the reliability between A and B, 0.5 is the reliability between B and C, and the exponent of 10 is the number of direct connections between A and C '.

In addition, 'A and D' have an indirect relationship according to 'A → B → C → D', and the reliability of 'A and D' is set to 0.7 * 0.5 * 0.8 / 10 ³ . Here, 0.7 is the reliability between A and B, 0.5 is the reliability between B and C, 0.8 is the reliability between C and D, and the index 3 of 10 is the direct connection between A and D to be.

In addition, 'B and D' have an indirect relation according to 'B → C → D', and the reliability of 'B and D' is set to 0.5 * 0.8 / 10 ² . Here, 0.5 is the reliability between B and C, 0.8 is the reliability between C and D, and 2 is the number of direct connections between B and D '.

FIG. 3 illustrates results of performing steps S120 and S150 shown in FIG. Specifically, a personal social trust map generated through step S120 is illustrated on the left side of FIG. 3, and an autonomic cognitive social network generated through step S150 is illustrated on the right side of FIG.

In the autonomic cognitive social network, since there are further added persons having an indirect relationship, as shown in FIG. 3, the trust rank may be different from the personal social trust map, and further includes the persons not included in the personal social trust map .

Referring back to FIG. 1, step S150 and subsequent steps will be described in detail.

In step S160, the client selects and personalizes highly reliable users from the autonomic cognitive social network generated in step S150 received from the server, and outputs the result in a customized manner.

The persons selected in step S160 may include persons having an indirect relationship as well as persons having a direct relationship with the user in the autonomic cognitive social network.

2. BD  And PD ( Personal Determinant ) Based Cognitive type Social  network

BD and PD-based cognitive social networks are social networks that autonomously recognize and build relationships among users based on personal information in addition to customary activity information.

Personal information is attributes that define the extent of the user's own self, such as age, gender, address, occupation, and so on. Personal information is used to build relationships in the premise that those who share the same attributes can have similar tendencies.

FIG. 4 is a diagram illustrating a method of constructing a cognitive-type social network based on BD and PD according to another embodiment of the present invention.

In order to construct a cognitive-type social network based on BD and PD, as shown in FIG. 4, a client corresponding to a user's mobile device extracts its own call record (S210) and receives a user profile from a user S220). The user profile input through step S220 is transmitted to the server.

A UI (User Interface) screen used for inputting a user profile in step S220 is illustrated in FIG. As shown in FIG. 5, in step S220, the user name, age, gender, address, job, and Twitter ^TM ID are input to the user profile.

Thereafter, the client generates a personal social trust map of the user using the call log extracted in step S210 (S230). The personal trust map generated in step S230 is transmitted to the server. The detailed description of the personal social trust map has been described above, so that a detailed description thereof will be omitted.

The server combines the personal social trust maps generated by the plurality of clients in step S230 to generate a total social trust map (S240). By the total social trust map generated in step S240, an indirect relationship other than a direct relationship with the user is also generated.

Meanwhile, the server deduces the group empathy based on the user profile received from the client (S250). Group empathy refers to the degree of homogeneity or homogeneity of groups according to certain attributes in a social network.

A high level of group empathy means that the group has a high degree of cohesion or association. It can deduce the group empathy level for each attribute by using the link relation or the degree of sharing between the attributes possessed by the users.

Specifically, in step S250, the server calculates the proportion of the persons having the same attribute as the user among the total persons included in the personal social trust map generated in step S230, and weights the group, thereby deducing the group consensus for each user do.

For example, it is assumed that there are 100 persons involved in the personal social trust map, 23 persons having the same age as the user, 62 persons having the same sex as the user, 10 persons having the same address as the user, It is assumed that there are 15 persons with the same occupation, and weights of 0.5, 0.2, 0.8, and 0.6 for age, sex, address, and occupation.

In this case, the group empathy for the age was 0.115 (= 23/100 * 0.5), the group empathy for the sex was 0.124 (= 62/100 * 0.2), and the group empathy for the address was 0.08 = 10/100 * 0.8), and the group consensus for job is 0.09 (= 15/100 * 0.6).

Thereafter, the server constructs the entire social trust map generated in step S240 and the group empathy derived in step S250 as a DB (S260). Using the DB constructed in step S260, the server creates an autonomous cognitive social network (S270). In step S270, the autonomous cognitive social network constructed for each user is transmitted to each user's client.

In step S280, the client selects and personalizes the user and the highly reliable persons from the autonomic cognitive-based social network established in step S270 received from the server, and outputs the result in a customized manner.

The autonomic cognitive social network constructed in the step S270 is based on the entire social trust map generated in the step S240, but since the reliability is adjusted according to the attribute based on the group sympathy derived in the step S250, The social network of the autonomic cognitive type is constructed.

In other words, the trust among the persons included in the total social trust map for the persons having the same age, sex, address, or occupation is increased, and the more the same attributes, the greater the degree of weighting.

FIG. 6 illustrates the results of performing steps S230 and S270 shown in FIG. Specifically, the personal social trust map generated through step S230 is illustrated on the left side of FIG. 6, and the autonomic cognitive social network generated through step S270 is illustrated on the right side of FIG.

In the autonomic cognitive social network, the number of persons having an indirect relationship is further added and the group consensus based on the user profile is reflected. Therefore, as shown in FIG. 6, the reliability ranking may be different from the personal social trust map, It is possible to include more people who were not included in the trust map.

3. BD  And ED ( Environmental Determinant ) Based Cognitive type Social  network

BD and ED-based cognitive social networks are social networks that autonomously recognize and build relationships among users based on environmental activity information in addition to customary activity information.

Environmental activity information refers to information about the user's social activities due to the influence of the user's environment. If the above-mentioned personal information is static information, the environmental activity information may be dynamic information.

Environmental activity information is used to form a relationship on the premise that users' SNS activity information can be used and those who have similar activities can have similar tendencies.

FIG. 7 is a view for explaining a method of constructing a cognitive-type social network based on BD and ED according to another embodiment of the present invention.

In order to construct a cognitive-type social network based on BD and ED, as shown in FIG. 7, a client corresponding to a user's mobile device extracts its own call record (S305) and receives a user profile from a user S310). The user profile input through step S310 is transmitted to the server.

Thereafter, the client generates a personal social trust map of the user using the call log extracted in step S305 (S315). The personal trust map generated in step S315 is transmitted to the server.

The server combines the personal social trust maps generated by the plurality of clients in step S315 to generate a total social trust map (S320). The indirect trust relationship is also generated by the entire social trust map generated in step S320, in addition to the direct relationship with the user.

Meanwhile, also according to the user profile input UI screen shown in Figure 5, a user profile, you can see that receiving some kind of ID on Twitter ^TM of SNS in addition to the user's name, age, sex, address and occupation.

Accordingly, the server extracts the SNS activity information of the users using the SNS IDs of the users input in step S310 (S325). The SNS activity information extracted in step S325 includes not only interests, political views, religious views, and posts written by the user through the SNS.

Thereafter, the server measures similarity based on the SNS activity information extracted in operation S325 (S330). In step S330, the degree of similarity between the users is measured as a vector after extracting meaningful words from the SNS activity information for each user.

Next, the server clusters users based on the degree of similarity measured in step S330 (S335). In step S335, the user belongs to a cluster represented by the user having the highest degree of similarity with the user. Thus, users with high similarity belong to the same cluster.

The similarity measurement in step S330 and the clustering in step S335 are performed for each attribute of the SNS activity. In other words, similarity measurement and clustering are performed on the basis of interests, similarity measurement and clustering are performed on the basis of politics, similarity measurement and clustering are performed on the basis of religion, and similarity measurement and clustering Is performed.

Thereafter, the server constructs the entire social trust map generated in step S320 and the clustering result in step S335 as a DB (S340), and constructs an autonomic cognitive social network for each user using the DB constructed in step S340 (S345). In step S345, the autonomous cognitive social network constructed for each user is transmitted to each user's client.

In step S350, the client selects and personalizes highly reliable users from the autonomic cognitive social network constructed in step S345, which is received from the server, in a customized manner.

The autonomic cognitive social network constructed in step S345 is based on the entire social trust map generated in step S320, but in step S150 of FIG. 1 in that reliability is adjusted according to the attribute based on the clustering result in step S335. And is different from the autonomous cognitive social network constructed in step S270 of FIG.

That is, the reliability of the persons belonging to the same cluster among the persons included in the entire social trust map is increased, and the more the same clusters belonging to each other, the greater the degree of weighting.

FIG. 8 illustrates the results of the operations of steps S315 and S345 shown in FIG. Specifically, the personal social trust map generated in step S315 is illustrated on the left side of FIG. 8, and the autonomic cognitive social network generated in step S345 is illustrated on the right side of FIG.

In the autonomic cognitive social network, since the persons having the indirect relationship are added and the clustering result based on the SNS activity information is reflected, as shown in FIG. 8, the reliability ranking can be different from the personal social trust map, It is possible to include more people who were not included in the trust map.

4. BD , PD  And ED  Based Cognitive type Social  network

A cognitive social network based on BD, PD, and ED is a social network that autonomously recognizes and builds relationships among users based on both conventional activity information, personal information, and environmental activity information.

FIG. 9 is a view for explaining a method of constructing a cognitive-type social network based on BD, PD, and ED according to another embodiment of the present invention.

In order to construct a cognitive-based social network based on BD, PD, and ED, a client corresponding to a user's mobile device first extracts its own call record (S405) and inputs a user profile from the user (S410). The user profile input through step S410 is transmitted to the server.

Thereafter, the client generates a personal social trust map of the user using the call log extracted in step S405 (S415).

The server combines the personal social trust maps generated by the plurality of clients in step S415 to generate the entire social trust map (S420).

On the other hand, the server inferences the group consensus based on the user profile received from the client (S425).

In operation S430, the server extracts SNS activity information of the users using the SNS IDs of the user profiles inputted in operation S410. Thereafter, the server measures similarity based on the SNS activity information extracted in operation S430 (S435). Next, the server clusters users based on the similarity measured in step S435 (S440).

Thereafter, the server constructs a DB as a DB from the entire social trust map generated in step S420, the group empathy inferred in step S425, and the clustering result obtained in step S440 (S445). Using the DB constructed in step S445, An autonomous cognitive social network is constructed (S450). In step S450, the autonomous cognitive social network constructed for each user is transmitted to each user's client.

In step S455, the client selects and personalizes the user and the highly trusted persons from the autonomous cognitive-based social network established in step S450 received from the server, and outputs the result in a customized manner.

FIG. 10 illustrates results of performing steps S415 and S450 shown in FIG. Specifically, the personal social trust map generated through step S415 is illustrated on the left side of FIG. 10, and the autonomic cognitive social network generated through step S450 is illustrated on the right side of FIG.

In the autonomic cognitive social network, more indirect persons are added, and the clustering results based on the group empathy based on the user profile and the SNS activity information are reflected. Therefore, as shown in FIG. 10, It may be different, and may include more people who are not included in the personal social trust map.

5. Client

11 is a block diagram of a client 500 providing information necessary for constructing a cognitive-based social network. 11, the client 500 includes a touch screen 510, a processor 520, a communication module 530, and a DB 540.

The touch screen 510 functions as input means for receiving a user profile and display means for displaying a personalized character recommendation result.

The communication module 530 establishes and maintains a communication connection with a server to be described later, delivers the personal social trust map and the user profile to the server, and receives the autonomous cognitive social network information from the server.

DB 540 stores a personal social trust map, a user profile, an autonomic cognitive social network, a personalized person recommendation result, and the like.

The processor 520 executes the touch screen manager 521, the profile manager 523, the behavior form manager 525, the DB manager 527 and the communication manager 529.

The touch screen manager 521 manages user input and display through the touch screen 510 and the DB manager 527 manages information storage / reading and the like of the DB 540. The communication manager 529 manages information storage / (530).

The profile manager 523 transfers the user profile inputted by the touch screen manager 521 to the communication manager 529 and transmits the user profile to the server.

The behavioral form manager 525 extracts the call log, generates a personal social trust map of the user using the extracted call logs, and transmits the personal trust trust map to the server through the communication manager 529.

6. Server

12 is a block diagram of a server 600 that performs cognitive type social network construction. As shown in FIG. 12, the server 600 includes a communication module 610, a processor 620, and a DB 630.

The communication module 610 establishes and maintains a communication connection with the client 500 to receive the personal social trust map and the user profile from the client 500 and transmits the autonomous cognitive social network information to the client 500 do.

The DB 630 stores the entire social trust map, group consensus, clustering result, and the like.

The processor 620 includes a communication manager 621, a total social trust map manager 622, a group empathy inference manager 623, an SNS activity based similarity measure / clustering manager 624, a DB manager 625, And launches the social network construction manager 626.

The communication manager 621 manages communication by the communication module 610.

The total social trust map manager 622 combines the personal social trust maps received by the communication manager 621 from the plurality of clients 500 to generate a total social trust map.

The group empathy degree inference manager 623 deduces the group empathy based on the user profile received from the client 500 and the SNS activity based similarity measurement / clustering manager 624 extracts the SNS activity information of the users, Based similarity measure and similarity based user clustering.

DB manager 625 stores and manages the entire social trust map, group empathy, and clustering results in DB 630.

The autonomic cognitive type social network construction manager 626 constructs an autonomous cognitive social network by obtaining at least one of the entire social trust map stored in the DB 630, the group empathy level and the clustering result through the DB manager 625, And transmits the constructed autonomic cognitive social network to the clients through the communication manager 621.

7. Variation example

Thus far, preferred embodiments have been described in detail for constructing a cognitive social network capable of autonomously recognizing relationships among users by analyzing interactions with various sources of information.

In the above embodiment, the call record presented by the customary activity information of the user corresponds to an example for convenience of explanation, and therefore can be replaced with other information (for example, an SMS message record). In addition, the method of establishing the reliability from the user's conventional activity information is also exemplary and can be modified in various ways.

In addition, in the above embodiment, the attributes included in the user profile presented as personal information, such as age, gender, address, and occupation, are also examples for convenience of explanation, and thus may be replaced with other information. In addition, the method of inferring group consensus from personal information is also exemplary and can be modified in various ways.

Similarly, in the above embodiment, since the SNS activity information provided by the environmental activity information is also an example for convenience of explanation, it can be replaced with other information. In addition, the method of measuring and clustering the similarity from the environmental activity information is also an exemplary one, and it can be modified in various ways.

It goes without saying that the technical idea of the present invention can also be applied to a computer-readable recording medium having a computer program for performing the functions of the apparatus and method according to the present embodiment. In addition, the technical idea according to various embodiments of the present invention may be embodied in computer-readable code form recorded on a computer-readable recording medium. The computer-readable recording medium is any data storage device that can be read by a computer and can store data. For example, the computer-readable recording medium may be a ROM, a RAM, a CD-ROM, a magnetic tape, a floppy disk, an optical disk, a hard disk drive, or the like. In addition, the computer readable code or program stored in the computer readable recording medium may be transmitted through a network connected between the computers.

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 exemplary embodiments, but, on the contrary, It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the present invention.

500: client 510: touch screen
520: Processor 521: Touch Screen Manager
523: Profile Manager 525: Behavior Forms Manager
527: DB Manager 529: Communication Manager
530: Communication module 540: DB
600: server 610: communication module
620: Processor 621: Communications Manager
622: Full Social Trust Map Manager
623: Collective empathy inference manager
624: SNS activity-based similarity measure / clustering manager
625: DB Manager
626: Self-aware cognitive social network builder
630: DB

Claims (12)

The client extracting customary activity information of the user;
Using the extracted conventional activity information, generating a personal social trust map in which the client directly associates with the user and the trustworthiness of the persons concerned together;
The server synthesizing the personal social trust maps to generate a total social trust map;
Receiving, by the client, a user profile; And
Constructing a cognitive social network for each user based on the total social trust map;
Wherein, in the constructing step,
The cognitive social network is constructed by reflecting personal information on the whole social trust map,
The personal information may include:
Wherein the emoticon is inferred from the persons having the same attributes as the attributes included in the user profile among all the persons involved in the personal social trust map.
The method according to claim 1,
The conventional activity information may include,
Wherein the call history is a call record.
3. The method of claim 2,
The reliability,
Wherein the call history is determined using at least one of a call frequency, a call duration time, and a call update time analyzed from the call history.
delete The method according to claim 1,
The personal information may include:
Is the empathy deduced from the ratio of the persons having the same attribute,
Wherein, in the constructing step,
Wherein the cognitive type social network is constructed from the total social trust map by adjusting reliability based on empathy level for each user.
6. The method of claim 5,
The above-
Age, gender, address, and occupation of the cognitive social network.
The method according to claim 1,
Wherein, in the constructing step,
Wherein the cognitive-based social network is constructed by reflecting environmental activity information together with the personal information on the entire social trust map.
8. The method of claim 7,
Wherein the server measures a degree of similarity for each user; And
Further comprising the step of the server clustering users based on the measured similarity,
Wherein, in the constructing step,
Wherein the cognitive type social network is constructed by adjusting reliability on the entire social trust map based on the personal information and the clustering result.
9. The method of claim 8,
Further comprising: the server extracting SNS (Social Network Services) activity information of users,
Wherein the similarity measuring step comprises:
Wherein the degree of similarity is measured for each user based on the extracted SNS activity information.
The method according to claim 1,
Wherein, in the constructing step,
Wherein the perceptual social network is constructed by reflecting environmental activity information on the entire social trust map.
The method according to claim 1,
Further comprising the step of the client selecting and customizing highly trusted individuals from the cognitive type social network.
A communication module receiving the personal social trust map and the user profile in which the persons who have a direct relationship with the user using the user's customary activity information and the trustworthiness of the persons concerned together; And
And a processor configured to synthesize the personal social trust maps received through the communication module to generate a total social trust map and construct a perceived social network for each user from the total social trust map,
The processor comprising:
The cognitive social network is constructed by reflecting personal information on the whole social trust map,
The personal information may include:
Wherein the empathy is inferred from the persons having the same attributes as the attributes included in the user profile among all the persons involved in the personal social trust map.

Images