CN109658279A - Social network relationships recommended method based on cohesion and credit worthiness - Google Patents

Social network relationships recommended method based on cohesion and credit worthiness Download PDF

Info

Publication number
CN109658279A
CN109658279A CN201811566313.8A CN201811566313A CN109658279A CN 109658279 A CN109658279 A CN 109658279A CN 201811566313 A CN201811566313 A CN 201811566313A CN 109658279 A CN109658279 A CN 109658279A
Authority
CN
China
Prior art keywords
friend
user
dimension
direct
target
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201811566313.8A
Other languages
Chinese (zh)
Inventor
唐雪飞
李金海
马晨曦
胡茂秋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
CHENGDU COMSYS INFORMATION TECHNOLOGY Co Ltd
Original Assignee
CHENGDU COMSYS INFORMATION TECHNOLOGY Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by CHENGDU COMSYS INFORMATION TECHNOLOGY Co Ltd filed Critical CHENGDU COMSYS INFORMATION TECHNOLOGY Co Ltd
Priority to CN201811566313.8A priority Critical patent/CN109658279A/en
Publication of CN109658279A publication Critical patent/CN109658279A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/01—Social networking

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Computing Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Tourism & Hospitality (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The social network relationships recommended method based on cohesion and credit worthiness that the present invention provides a kind of, belongs to field of artificial intelligence.The present invention is by defining cohesion and credit worthiness in social network relationships, and it analyzes accordingly, calculate person to person's degree of a relation amount, the intimate degree of judgement relationship, and new social networks are established for user's intelligent recommendation accordingly, calculating process is relatively easy, and intelligent recommendation result is more accurate, the user experience is improved.

Description

Social network relationship recommendation method based on intimacy degree and credibility degree
Technical Field
The invention belongs to the technical field of artificial intelligence, and particularly relates to a social network relationship recommendation method based on intimacy and credibility.
Background
With the rapid development of internet technology, the intersection of work and life of people and the internet is becoming more and more compact, and social networks have become an indispensable part of life of people. The social network can further expand new relationships while maintaining the individual relationships of the users. The virtual network is used for grafting the emotional relationship between people in the real society, so that more new relationships can be expanded on the social network, and the life style of people is changed. How to effectively expand user relationships and maintain relationships among individuals is a core problem that each Social Network Service (SNS) platform must solve.
The social network provides convenience for users to make friends on the network, but with the development of the internet, the number of users is more and more, and how to find a suitable friend-making object for the users is an important problem to be solved by the social network service. The intelligent recommendation of friends and the establishment of new social relations for users are problems that must be solved for the development of each social network platform. In the prior art, the method for recommending friends and establishing a new social relationship for a user is complex in operation process, less accurate in intelligent recommendation result and poor in user experience.
Disclosure of Invention
The invention aims to solve the problems of intelligent friend recommendation in the prior art, and provides a method for automatically recommending social relations for users and expanding friend spaces of the users through a series of calculation and operation steps based on intimacy and credibility indexes.
A social network relationship recommendation method based on intimacy degree and credibility degree comprises the following steps:
s1, acquiring a direct friend set of the user A, wherein the direct friend is a user with a dimension of 1, and the dimension is equal to the number of the middlings among the users plus one;
s2, calculating the relation weight of each friend in the direct friend set of the user A and the user A to obtain the friend U with the maximum relation weight with the user AkLet friends UkIs a target friend;
s3, acquiring a direct friend set of the target friend, adding one to the dimension of the friend in the friend set of the target friend relative to the dimension of the target friend and the user A, calculating a relation weight value of each friend in the friend set of the target friend and the user A, and adding the friend of which the relation weight value is not less than a preset weight value threshold into a recommended friend set of the user A;
s4, judging whether the dimension between the friend who joins the recommended friend set and the user A is smaller than a preset dimension threshold value, and if so, enabling the friend who joins the recommended friend set to be a target friend, and returning the process to the step S3;
and S5, when the dimension between the friend who joins the recommended friend set and the user A is not less than the preset dimension threshold value, obtaining the recommended friend set of the user A.
Further, the step S1 includes the following steps:
acquiring a direct friend set F with dimension 1 of a user AA＝{U1,U2,...,UmWherein, the dimension of 1 represents that there is no middle person between friends.
Further, the step S2 includes the following steps:
initializing user A's set of recommended friends as null, FRA{ }, and
for each friend U of user Ai∈FACalculate UiRelationship weight with user A
Where ρ representsIn thatThe ratio of the total weight of the ingredients is [0, l](ii) a I represents the intimacy between users, and the value range is [0,1 ]]，Representing users A and Ui(iii) the degree of intimacy therebetween; r represents the maximum credibility in the direct friends of the user, and is definedC represents the credit degree of the user, and the value range of C is [0, l]I.e. byRepresents UiMaximum reputation in direct friends of (1);
to obtainMaximum value ofI.e. direct friend U of user akHas the largestLet UkAre target friends.
Further, the step S3 includes the following steps:
acquiring a direct friend set F ═ { V ] of the target friend1,V2,...,VnAnd calculating direct friend V of each target friendiRelationship weight with user A
Wherein,representing users A and ViDimension between, whose value is equal to users A and ViThe middle between the two is added with one; sigma represents the attention of the user to the number of the middlemans, and the value range of sigma is [0, l]；
For each oneV ofiTo be added to the recommended friend set FR of user AAAnd M is a preset weight threshold.
Further, the step S4 includes the following steps:
for each addition of FRAV ofiJudgment ofWhether or not less than a preset dimension threshold, if so, addingInto FRAV ofiDimension (d) ofWhen the value is less than the preset dimension threshold value, V is setiSet as the target friend, the flow returns to the step S3.
The invention has the beneficial effects that: the invention provides a social network relationship recommendation method based on intimacy and credibility, which is characterized in that intimacy and credibility in a social network relationship are defined, the degree of interpersonal relationship is analyzed and calculated according to the intimacy and credibility, the intimacy degree of the relationship is judged, a new social relationship is established for intelligent recommendation of a user according to the degree of intimacy and credibility, the operation process is relatively simple, the intelligent recommendation result is more accurate, and the user experience is improved.
Drawings
FIG. 1 is a flow chart of an embodiment of the present invention.
Detailed Description
The following are some technical principles involved in the present invention:
1. relationship linking
In a social network, person-to-person relationships exist in a linked fashion. Including both "weak links" and "strong links". The weak link reflects the process of information circulation, and is information transmission across industries and fields, and the strong link reflects the most intimate relationship around each person. The SNS can completely mine the resources of the interpersonal relationship network in an internet way,
both "strong links" that are close and "weak links" that are not in place for a long time are included herein. Through the SNS, the user can easily know 'friends of friends', so that the user can find the needed person through the known person and expand the personal pulse. Meanwhile, the user can scientifically manage own interpersonal network resources through the SNS platform, and more opportunities are won for the user. The value of the SNS lies in the authenticity of the platform information, users provide real materials of the SNS, and the whole social network is completely based on real characters and relations, so that a real, credible and effective social stage is provided. How to develop a valuable application on this virtual social stage to actually promote the emotion and information exchange among friends is a key to developing the value of SNS.
2. Six degree space theory
The "Six-degree space" theory is also referred to as Six degree segregation (Six segregation) theory. This theory can be colloquially explained as: "you will not have more than six people separated from any stranger, that is, you can know any stranger by six people at most. "this theory was generated in the 60's of the 20 th century and was proposed by the american psychologist milger.
The theory holds that people can find any person on the earth through the six layers of interpersonal relations. Although it has remained in the controversial "hypothesis" phase to date, it has been the subject of research and attention of scholars in various fields.
3. Intimacy degree
The new density describes the degree of closeness and closeness of the relationship between the user and the friend, the higher the new density is, the closer the relationship between the user and the friend is, the higher the reliability of obtaining information from the friend is, and meanwhile, the greater the chances that the webpage recommended by the friend, the published article and the answer to the question are concerned and adopted are. Those with a high new density should therefore be at a more advanced position in the relationship recommendation.
4. Degree of credit
The credibility represents the degree of knowing and understanding of a person by the public, the breadth and depth of social influence, and is an objective scale for evaluating the popularity. The reputation of a person is closely related to the experiences of the person, for example, the reputation of an expert who has experienced for more than a decade in the field of computer networking and is responsible for the design of a large network architecture is significantly greater than that of a person who has not experienced the field. The higher the reputation of a person, the higher the authority of the web page he recommends, the blog published, and the answer question, and the higher priority should be in the relationship recommendation.
In the invention, in order to realize the purpose of finding a suitable user B for a friend requester A, the A and the B are required to meet the following three conditions:
making a relationship between a and B as close as possible, the more likely it is that a will get useful information from B, where we use intimacy to measure the intimacy between a and B.
The reputation of the target person B should be as high as possible, the higher the confidence level of the information a obtains from B.
The number of people in the middle of the experience from A to B is as small as possible, because the intimacy degree is attenuated once without an introduction, and the willingness of B to help A is gradually reduced.
In achieving this, the present invention defines the following variables:
the intimacy degree I is used for describing intimacy degree among users, and the numeric area of the intimacy degree I is [0, l]。IABRepresenting the intimacy degree of the users A and B, the higher the value of the intimacy degree of the users A and B is, and the lower the intimacy degree is in contrast. If A and B are not known at all, then IAB＝0，IAB1 is true if and only if a-B. In addition, IABIndicating that a is sent from user a, i.e. a does not recognize B, and I may be a case where a recognizes B but not B, IAB≠IBA. At the initial state, IABMay be set by user a and later automatically updated based on activities and operations between A, B.
And D, measuring the index of intimacy transfer. If A and B are direct friends, i.e. the two know directly without an intermediary, DAB1 is ═ 1; if the relationship between A and B is transmitted through the middle person C, namely A is the friend of C, C is the friend of B, and the middle person C exists between the users A and B, DAB2. In summary, the dimension between two users is equal to the number of intermediaries between two users plus one. A buddy with dimension 1 is a direct buddy.
The credit degree C is used for describing the credit degree of a certain user in a specific area, and the value range is [0, l]. A closer value to O indicates a lower reputation for the user, whereas a higher reputation for the user is indicated. CAThe initial value of (a) is set by the system according to the natural attribute of the user A by a background administrator or a censor, and then the system updates according to the activity and operation of the user.
R represents the maximum reputation among a user's direct friends. If the direct friend set of the user A is FA＝{U1,U2,...,Um}, the maximum reputation among the direct friends of user A
The embodiments of the present invention will be further described with reference to the accompanying drawings.
Referring to fig. 1, the social network relationship recommendation method based on intimacy degree and reputation provided by the present invention is implemented by the following steps:
s1, acquiring a direct friend set of the user A, wherein the direct friend set is a user with the dimension of 1, and the dimension is equal to the number of the middlings among the users plus one.
In this embodiment, a direct friend set F with dimension 1 of the user a is obtainedA＝{U1,U2,...,Um}。
S2, calculating the relation weight of each friend in the direct friend set of the user A and the user A to obtain the friend U with the maximum relation weight with the user AkLet friends UkAre target friends.
In this embodiment, the recommended friend set of the initialization user a is null, i.e., FRA{ }, andand finally, storing the friend recommended by the user A in the set.
Direct friend U to each user Ai∈FACalculate UiRelationship weight with user A
Wherein,represents UiThe degree of recommendation to the user A, the larger the value, the more worthwhile to be recommended; p representsIn thatThe ratio of the total weight of the ingredients is [0, l]The value of rho can be adjustedInAndthe ratio of (A) to (B); i represents the intimacy between users, and the value range is [0,1 ]]，Representing users A and Ui(iii) the degree of intimacy therebetween; r representsThe maximum reputation among the user's immediate friends,c represents the credit degree of the user, and the value range of C is [0, l]I.e. byRepresents UiMaximum reputation in direct friends of (1);
the order is obtained by calculating the relation weight of each user A's direct friend and user ATaking a maximum valueI.e. direct friend U of user akHas the largestLet UkAre target friends.
S3, acquiring a direct friend set of the target friend, adding one to the dimension of the friend in the friend set of the target friend and the dimension of the user A relative to the dimension of the target friend and the user A, calculating a relation weight value of each friend in the friend set of the target friend and the user A, and adding the friend of which the relation weight value is not less than a preset weight value threshold value to the recommended friend set of the user A.
In this embodiment, the direct friend set F ═ V of the target friend is obtained1,V2,...,VnAnd calculating direct friend V of each target friendiRelationship weight with user A
Wherein,representing users A and ViThe dimension between; sigma represents the attention of the user to the number of the middlemans, and the value range of sigma is [0, l]The larger the value is, the weight value isThe larger the influence of the dimension is, the faster the weight attenuation speed is caused by the increase of the number of middlers and the increase of the dimension.
For each oneV ofiTo be added to the recommended friend set FR of user AAAnd M is a preset weight threshold.
S4, judging whether the dimension between the friend who joins the recommended friend set and the user A is smaller than a preset dimension threshold value, and if so, making the friend who joins the recommended friend set a target friend, and returning the process to the step S3.
In this embodiment, step S4 is implemented by the following steps:
s41, judging the newly added recommended friend set FRAV ofiIs less than a preset dimension threshold.
S42, if newly added ViDimension D ofAViIf the value is less than the preset dimension threshold value, the newly added V is addediThe target buddy is set and the flow returns to S3.
In this embodiment, the preset dimension threshold value is 6 according to the six-dimensional space theory, and may be other values.
In this embodiment, V which joins the recommended friend set in the first batchiDimension is 2, in case of dimension threshold equal to 6, 2 < 6, then newly added ViReturning to the step S3 as the target friend to continue friend recommendation, and repeating until adding a new friendV iniIs equal to 6, the repetition ends.
S43, if newly added ViDimension (d) ofNot less than the preset dimension threshold, the flow advances to step S5.
S5, when the dimension between the friend who joins the recommended friend set and the user A is not less than the preset dimension threshold value, the recommended friend set of the user A is obtained.
In this embodiment, after the repetition in step S4 is finished, the complete recommended friend set FR of the user a is obtainedA。
It will be appreciated by those of ordinary skill in the art that the examples provided herein are intended to assist the reader in understanding the principles of the invention and are to be construed as being without limitation to such specifically recited examples and embodiments. Those skilled in the art can make various other specific changes and combinations based on the teachings of the present invention without departing from the spirit of the invention, and these changes and combinations are within the scope of the invention.

Claims (5)

1. A social network relationship recommendation method based on intimacy degree and credibility is characterized by comprising the following steps:
s1, acquiring a direct friend set of the user A, wherein the direct friend is a user with a dimension of 1, and the dimension is equal to the number of the middlings among the users plus one;
s2, calculating the relation weight of each friend in the direct friend set of the user A and the user A to obtain the friend U with the maximum relation weight with the user AkLet friends UkIs a target friend;
s3, acquiring a direct friend set of the target friend, adding one to the dimension of the friend in the friend set of the target friend relative to the dimension of the target friend and the user A, calculating a relation weight value of each friend in the friend set of the target friend and the user A, and adding the friend of which the relation weight value is not less than a preset weight value threshold into a recommended friend set of the user A;
s4, judging whether the dimension between the friend who joins the recommended friend set and the user A is smaller than a preset dimension threshold value, and if so, enabling the friend who joins the recommended friend set to be a target friend, and returning the process to the step S3;
and S5, when the dimension between the friend who joins the recommended friend set and the user A is not less than the preset dimension threshold value, obtaining the recommended friend set of the user A.
2. The method for recommending social network relationships based on intimacy and reputation according to claim 1, wherein the step S1 comprises the following steps:
acquiring a direct friend set F with dimension 1 of a user AA＝{U1,U2,...,UmWherein, the dimension of 1 represents that there is no middle person between friends.
3. The method for recommending social network relationships based on intimacy and reputation according to claim 2, wherein the step S2 comprises the following steps:
initializing user A's set of recommended friends as null, FRA{ }, and
for each friend U of user Ai∈FACalculate UiRelationship weight with user A
Where ρ representsIn thatThe ratio of the total weight of the ingredients is [0, l](ii) a I represents the intimacy between users, and the value range is [0,1 ]]，Representing users A and Ui(iii) the degree of intimacy therebetween; r represents the maximum credibility in the direct friends of the user, and is definedC represents the credit degree of the user, and the value range of C is [0, l]I.e. byRepresents UiMaximum reputation in direct friends of (1);
to obtainMaximum value ofI.e. direct friend U of user akHas the largestLet UkAre target friends.
4. The method for recommending social network relationships based on intimacy and reputation according to claim 3, wherein the step S3 comprises the following steps:
acquiring a direct friend set F ═ { V ] of the target friend1,V2,...,VnAnd calculating direct friend V of each target friendiRelationship weight with user A
Wherein,representing users A and ViDimension between, whose value is equal to users A and ViThe middle between the two is added with one; sigma represents the attention of the user to the number of the middlemans, and the value range of sigma is [0, l]；
For each oneV ofiTo be added to the recommended friend set FR of user AAAnd M is a preset weight threshold.
5. The method for recommending social network relationships based on intimacy and reputation according to claim 4, wherein the step S4 comprises the following steps:
for each addition of FRAV ofiJudgment ofWhether it is less than the preset dimension threshold, when FR is addedAV ofiDimension (d) ofWhen the value is less than the preset dimension threshold value, V is setiSet as the target friend, the flow returns to the step S3.
CN201811566313.8A 2018-12-19 2018-12-19 Social network relationships recommended method based on cohesion and credit worthiness Pending CN109658279A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811566313.8A CN109658279A (en) 2018-12-19 2018-12-19 Social network relationships recommended method based on cohesion and credit worthiness

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811566313.8A CN109658279A (en) 2018-12-19 2018-12-19 Social network relationships recommended method based on cohesion and credit worthiness

Publications (1)

Publication Number Publication Date
CN109658279A true CN109658279A (en) 2019-04-19

Family

ID=66115437

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811566313.8A Pending CN109658279A (en) 2018-12-19 2018-12-19 Social network relationships recommended method based on cohesion and credit worthiness

Country Status (1)

Country Link
CN (1) CN109658279A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111858692A (en) * 2020-07-30 2020-10-30 重庆新申言科技有限公司 System and method for calculating interpersonal relationship based on classmate records
CN115865485A (en) * 2022-11-30 2023-03-28 上海纽盾科技股份有限公司 Stranger safety precaution method and system based on meta universe

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130166574A1 (en) * 2011-12-27 2013-06-27 Nhn Corporation Social network service system and method for recommending friend of friend based on intimacy between users
CN104202319A (en) * 2014-08-28 2014-12-10 北京淘友天下科技发展有限公司 Method and device for social relation recommendation
CN105141499A (en) * 2015-07-03 2015-12-09 电子科技大学 Social network relationship recommendation method based on privacy degree and publicity degree

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130166574A1 (en) * 2011-12-27 2013-06-27 Nhn Corporation Social network service system and method for recommending friend of friend based on intimacy between users
CN104202319A (en) * 2014-08-28 2014-12-10 北京淘友天下科技发展有限公司 Method and device for social relation recommendation
CN105141499A (en) * 2015-07-03 2015-12-09 电子科技大学 Social network relationship recommendation method based on privacy degree and publicity degree

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111858692A (en) * 2020-07-30 2020-10-30 重庆新申言科技有限公司 System and method for calculating interpersonal relationship based on classmate records
CN115865485A (en) * 2022-11-30 2023-03-28 上海纽盾科技股份有限公司 Stranger safety precaution method and system based on meta universe
CN115865485B (en) * 2022-11-30 2024-06-07 上海纽盾科技股份有限公司 Stranger safety precaution method and system based on meta universe

Similar Documents

Publication Publication Date Title
Jain et al. Discover opinion leader in online social network using firefly algorithm
CN103077247B (en) The method for building up of friends transmission tree in a kind of social networks
CN109241440A (en) It is a kind of based on deep learning towards implicit feedback recommended method
CN108647800B (en) Online social network user missing attribute prediction method based on node embedding
CN110162717A (en) A kind of method and apparatus of commending friends
CN109783614B (en) Differential privacy disclosure detection method and system for to-be-published text of social network
Ren et al. Where are you settling down: Geo-locating twitter users based on tweets and social networks
CN111428127B (en) Personalized event recommendation method and system integrating theme matching and bidirectional preference
CN107391542A (en) A kind of open source software community expert recommendation method based on document knowledge collection of illustrative plates
CN112507245B (en) Social network friend recommendation method based on graph neural network
KR101356948B1 (en) User interest inference method and system in sns using topics on social activities with neighbors
Wang et al. A multidimensional network link prediction algorithm and its application for predicting social relationships
Ma et al. Balancing user profile and social network structure for anchor link inferring across multiple online social networks
CN110147498A (en) A kind of knowledge method for pushing, device and storage equipment, program product
WO2017027667A1 (en) Method and system for characterizing a user&#39;s reputation
CN114201516B (en) User portrait construction method, information recommendation method and related devices
Hassan et al. Friendship Dynamics: Modelling Social Relationships through a Fuzzy Agent‐Based Simulation
CN116244513A (en) Random group POI recommendation method, system, equipment and storage medium
CN109658279A (en) Social network relationships recommended method based on cohesion and credit worthiness
Patra et al. Risk analysis in diabetes prediction based on a new approach of ranking of generalized trapezoidal fuzzy numbers
CN110795640B (en) Self-adaptive group recommendation method for compensating group member difference
CN116842277A (en) Social recommendation method based on cross-topic comparison learning
CN107590742B (en) Behavior-based social network user attribute value inversion method
CN113987366A (en) Personalized search method and system fusing search behavior and friend network
Guidi et al. SentiTrust: A New Trust Model for Decentralized Online Social Media

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20190419