CN105141499B - It is a kind of to recommend method based on the social network relationships of secret degree and known degree - Google Patents
It is a kind of to recommend method based on the social network relationships of secret degree and known degree Download PDFInfo
- Publication number
- CN105141499B CN105141499B CN201510388830.0A CN201510388830A CN105141499B CN 105141499 B CN105141499 B CN 105141499B CN 201510388830 A CN201510388830 A CN 201510388830A CN 105141499 B CN105141499 B CN 105141499B
- Authority
- CN
- China
- Prior art keywords
- msub
- degree
- mrow
- good friend
- secret
- 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.)
- Active
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Recommend method based on the social network relationships of secret degree and known degree the invention discloses a kind of, pass through the secret degree for defining social network relationships and known degree, analyze, calculate person to person's degree of a relation amount, the intimate degree of judgement relation, and new social networks are established for user's intelligent recommendation accordingly, effectively excavate potential human relationship in social field, enrich social networks network, the social networks degree of adhesion of user is improved, process is relatively easy, and effect is preferable.
Description
Technical field
The invention belongs to Artificial technical field of intelligence, and in particular to a kind of social activity based on secret degree and known degree
Cyberrelationship recommends the design of method.
Background technology
With the development of internet, daily routines are more and more combined together by people with internet, for the mankind
The service of social activities starts more and more to be paid close attention to by everybody, and social networks has become the important basis of the network user at present
One of using.The diversified network application that social networks (Social Network Service, SNS) is brought changes individual
To the use habit of internet, while positive impetus is played in the development to internet.Social networks is safeguarding individual pass
While being, new relation has also further been expanded.With the continuous expansion of SNS userbases, increasing user will
Real-life interpersonal relationships is extended in network, and society is simulated or rebuild based on society relation
Human relation network, individual work, emotion and actual life are closely coupled, the part in the life that becomes a reality.Social network
Standing in terms of the social life mode such as human communication and community activity is fundamentally changed has very big potentiality.
With the development of network technology, increasing social networking service is providing the platform of communication for users,
But customer relationship how is effectively expanded, intelligently excavates, safeguard and support interpersonal relation, intelligently understands user's
Relational network, it is the key problem that each SNS must be solved.Although some existing passes based on shortest path, graph theory at present
It is algorithm, but these algorithms or function are weaker, and relation excavation dynamics is small, or complexity is too high, when number of users is larger
When the speed of service it is extremely slow, it is impossible to well adapt to current social networking service present situation and requirement.
Relational links
In social networks, interpersonal relation is existing in a manner of link.Including " weak link " and " strong chain
Connect " two kinds of forms.What wherein weak link embodied is the process of information flow, is that inter-trade cross-cutting information is propagated；" strong chain
Connect " then reflect everyone the most intimate relation at one's side.SNS, can be by the money of interpersonal relationship by way of internet
Excavate completely in source.
Here those " strong links " for getting close to both had been contained, also contains those " weak links " for not meeting long.Pass through
SNS, user can easily recognize " friends of friends ", so as to find the people of oneself needs by the people of understanding, extend oneself
Human connection.At the same time, user can also scientifically manage the interpersonal relationships net resource of oneself by this platform of SNS, be certainly
Oneself wins more chances.SNS value root is that the authenticity of this platform information, and user provides the true money of oneself
Material, entire society's network is based entirely on realistic individual thing and relation, so as to provide a true, credible, effective social stage.
How on this virtual social stage valuable application is developed, effectively to promote emotion between friend and information to hand over
Stream, it is the key for playing SNS values.
Six Degrees are theoretical
" Six Degrees are theoretical, and " also referred to as six degrees of separation (Six Degrees of Separation) is theoretical.This is theoretical
Can generically it be illustrated as：" people that you are spaced between any one stranger is not over six, that is to say, that at most
By six people, you can just recognize any one stranger." theory resulted from the 1960s, by American Psychologist
Mil's Glenn proposes.
The theory thinks, people by six layers of interpersonal relationships can with find it is tellurian anyone.Although it is extremely
The present still only rests on controversial " hypothesis " stage, but causes the research and concern of every field scholar.
Restlet frameworks
The issue of the relation of social networks is to be presented in the form of " service " on network, it is therefore desirable to using service frame
SNS is issued out by frame in a manner of Web Service.Restlet is the lightweight REST frameworks under a Java, and it is fuzzy
Boundary between Web site and Web service, so as to help developer to build Web applications.
REST is a kind of client terminal/server structure, and its connection protocol has Stateless, it is desirable to which client passes through every time
Status information all in application must be included by crossing the information of stateless connection protocol transmission, i.e., every from client to server
It is individual request all must include understands all information necessary to the request, it is impossible to using it is any storage on the server up and down
Therefore text, session status will all be stored in client.REST Stateless improves the observability of system, reliability and can
Retractility, it is not necessary to preserve the state between multiple requests, server component can discharges rapidly resource and further simplifies it
Realize, while monitoring system also it is unnecessary to determine whole properties of request and check the data of multiple requests, in addition, Communication book
The Stateless of body can allow a series of difference handled in requests of different servers to be asked, and improve the extensions of server
Property.But the performance of network is so but reduced, because client has to send some data repeated, then for raising
The efficiency of system and the noticeable performance of user, and make system that there is stratification, REST has used caching mechanism.
Caching component plays the part of an arbitrator between clients and servers, and the response asked previously can be reused,
To respond same request later, if forwarding this request to server, obtained response may be with existing sound in caching
Should be identical.But this equally exists a problem, exactly if data outmoded in caching obtain with request is dealt into server
Data differences very greatly, will reduce reliability, and key is the cache policy selected.This problem of performance does not have inherently
There is a perfect solution, an optimal equalization point can only be found as far as possible according to the needs of system.
Servlet frameworks
The customer relationship issue result of social networks exists in the form of Web page.Servlet is client's request and service
The intermediate layer of device response, it is the java application of the server end inside Web server, has independently of platform and association
The characteristic of view, dynamic Web page can be generated.Different from the java application of traditional start up with command-line options, Servlet by
Web server is loaded, and the Web server must include the Java Virtual Machine for supporting Servlet.From realization,
Servlet can respond any kind of request, but Servlet is only used for extending based on http protocol in most cases
Web server.
Secret degree
Secret degree is the far and near close and distant degree of relation between description user and good friend, and secret degree is higher, illustrates user to good
Friendly relation is nearer, then at the good friend obtain information reliability it is bigger, meanwhile, the webpage of friend recommendation, the article delivered,
It is also bigger that answer to problem is concerned the chance adopted.Therefore the high people of those secret degree, it should be in relation recommendation
More forward position.
Known degree
Known degree is to represent the degree that a people is known by the public, understood, and is the breadth and depth of social influence, is evaluation
The objective yardstick of reputation size.The known degree of one people has close relationship with his personal story, such as one is calculating
Machine network field had more than ten years experience and was responsible for the known degree of the expert of multinomial catenet architecture design and can be significantly greater than
The people that this field there is not experience is related at the beginning of one.The known degree of one people is higher, the webpage of his recommendation, the blog delivered, returns
The authority of question and answer topic is higher, it should is in higher priority in relation recommendation.
The content of the invention
The invention aims to solve in the prior art based on shortest path, the ralation method of graph theory or function compared with
Weak, relation excavation dynamics is small, or complexity is too high, and when number of users is larger, the speed of service is extremely slow, it is impossible to suitable well
Social networking service present situation that should be preceding and the problem of requiring, it is proposed that a kind of to be closed based on the social networks of secret degree and known degree
It is recommendation method.
The technical scheme is that：It is a kind of to recommend method based on the social network relationships of secret degree and known degree, including
Following steps：
S1, the direct good friend's set F for obtaining good friend requestor AA={ U1,U2,...,Um}；
S2, initialization establish final good friend requestor A commending friends set FRA；
S3, friend recommendation threshold value M is set；
S4, calculate FAIn each directly good friend and A relation weights；
The good friend U of S5, lookup and A relation maximum weightk, obtain UkDirect good friend set
S6, define UkDirect good friend setTwo degree of good friends set that secret degree dimension values for A are 2, is calculated
In each two degree of good friends and A relation weights；
S7, by all two degree good friends addition FR with A relation weights more than or equal to MA；
S8, to each new addition FRACommending friends Vj, obtain its direct good friend's set
S9, the secret degree dimension values of good friend add to 1, it is every in the N-dimensional degree good friend set for each A that calculation procedure S8 is obtained
One good friend and A relation weights；
S10, all N-dimensional degree good friends with A relation weights more than or equal to M are added into FRA；
S11, judge whether good friend's secret degree dimension values are equal to 6；
If then enter step S12；
If otherwise return to step S8；
S12, by commending friends set FRARecommend good friend requestor A.
Further, commending friends set FRAIt is initialized as empty set.
Further, commending friends set
Further, step S4 is specially：
To each A direct good friend Ui∈FA, U is calculated according to formula (1)iWith A relation weights
In formulaRepresent A and UiSecret degree, span is [0,1]；RARepresent the most grand duke in A direct good friend
Degree of knowing, span are [0,1]；ρ is represented In shared importance ratio, span is [0, l].
Further, step S6 is specially：
Define UkDirect good friend setTwo degree of good friends set that secret degree dimension values for A are 2, to each Uk's
Two degree of good friends of direct good friend, i.e. AV is calculated according to formula (2)iWith A relation weights
In formulaRepresent A and ViSecret degree, span is [0,1]；Represent UkDirect good friend in maximum
Known degree, span are [0,1]；ρ is represented In shared importance ratio, span is [0, l]；Table
Show A and ViGood friend's secret degree dimension, in this stepσ represents that user to the degree of concern of internuncial number, takes
It is (0, l) to be worth scope.
Further, step S9 is specially：
The secret degree dimension values of good friend are added 1, collected according to formula (3) calculation procedure S8 each A obtained N-dimensional degree good friend
Each good friend in conjunctionWith A relation weights
In formulaRepresent A and XiSecret degree, span is [0,1]；Represent VjDirect good friend in maximum
Known degree, span are [0,1]；ρ is represented In shared importance ratio, span is [0, l]；
Represent A and XiGood friend's secret degree dimension, often perform a deuterzooid step,Value add 1；σ represents user to internuncial number
Purpose degree of concern, span are (0, l).
The beneficial effects of the invention are as follows：The present invention passes through the secret degree for defining social network relationships and known degree, analysis, meter
Person to person's degree of a relation amount is calculated, judges the intimate degree of relation, and establishes new social networks accordingly for user's intelligent recommendation,
Potential human relationship in social field has effectively been excavated, has enriched social networks network, has improved the society of user
Network degree of adhesion is handed over, process is relatively easy, and effect is preferable.
Brief description of the drawings
Fig. 1 is provided by the invention a kind of based on the social network relationships of secret degree and known degree recommendation method flow diagram.
Embodiment
Embodiments of the invention are further described below in conjunction with the accompanying drawings.
In the present invention, if good friend requestor is A, it would be desirable to find a suitable user B for requestor A and be used as it
Commending friends so that A and B meets three following conditions：
(1) A and B relation is as far as possible intimate, then A obtained at B useful information possibility it is bigger, we use private here
Density weighs the intimate degree between A and B.
Secret degree is the far and near close and distant degree of relation between description user and good friend, and secret degree is higher, illustrates user to good
Friendly relation is nearer, then at the good friend obtain information reliability it is bigger, meanwhile, the webpage of friend recommendation, the article delivered,
It is also bigger that answer to problem is concerned the chance adopted.Therefore the high people of those secret degree, it should be in relation recommendation
More forward position.
(2) targeted customer B known degree should be as high as possible, then the credibility for the information that A is obtained at B is higher.
Known degree is to represent the degree that a people is known by the public, understood, and is the breadth and depth of social influence, is evaluation
The objective yardstick of reputation size.The known degree of one people has close relationship with his personal story, such as one is calculating
Machine network field had more than ten years experience and was responsible for the known degree of the expert of multinomial catenet architecture design and can be significantly greater than
The people that this field there is not experience is related at the beginning of one.The known degree of one people is higher, the webpage of his recommendation, the blog delivered, returns
The authority of question and answer topic is higher, it should is in higher priority in relation recommendation.
(3) go-between undergone from A to B should lack as far as possible, because often passing through a sponsor, secret degree will decay one
Secondary, B helps A wish to be also gradually reduced.
Recommend method based on the social network relationships of secret degree and known degree the invention provides a kind of, as shown in figure 1, bag
Include following steps：
S1, the direct good friend's set F for obtaining good friend requestor AA={ U1,U2,...,Um}；
Here A direct good friend is that A secret degree dimension values are 1 once good friend.
S2, initialization establish final good friend requestor A commending friends set FRA；
Commending friends set FRAEmpty set is initialized as, final good friend requestor A commending friends can all deposit in FRAIn.
Due to A direct good friend's set FAIn user be A good friend, it is not necessary that A is recommended again, therefore
FRAIn will not deposit FAIn user, i.e.,
S3, friend recommendation threshold value M is set；
S4, calculate FAIn each directly good friend and A relation weights；
To each A direct good friend Ui∈FA, U is calculated according to formula (1)iWith A relation weights
In formulaRepresent A and UiSecret degree, span is [0,1].
Here the secret degree between user, I are described with variable IABI.e. expression user A and B secret degree, its value are closer
0 represents that A and B secret degree is lower, on the contrary then secret degree is higher.If A and B do not recognize completely, IAB=0, and if only if A with
I when B is identicalAB=1.Further, since the situation that A recognizes B and B does not recognize A is there may be, so IAB≠IBA.Initial
When, IABSet by A, be updated later by system automatically according to the activity between A, B and operation.
RARepresent that the maximum in A direct good friend is known to spend, span is [0,1].
If variable CAWith representing known degree of the user A in setting field, such as art of mathematics, physics field etc., value
Scope is [0,1].The value represents that the known degree of user is lower closer to 0, and the known degree of on the contrary then user is higher.CAInitial value by
System is set according to the natural quality of the user A by management staff or audit crew, later by system according to user's
Activity and operation are updated.Due to FA={ U1,U2,...,Um, definitionThen RARepresent
It is maximum in A direct good friend known to spend.
ρ is represented In shared importance ratio, span is [0, l].The smaller explanation pair of ρ values's
Concern is fewer, and to RAConcern is more.As ρ=0, represent that maximum known degree is uniquely paid close attention in user A direct good friend
Factor, the algorithm are degenerated to maximum known degree in the direct good friend for calculating user A；As ρ=1, A and U is representediSecret degree be
The factor uniquely paid close attention to, the algorithm, which is degenerated to, calculates A and UiSecret degree.
The good friend U of S5, lookup and A relation maximum weightk, obtain UkDirect good friend set
S6, define UkDirect good friend setTwo degree of good friends set that secret degree dimension values for A are 2, is calculated
In each two degree of good friends and A relation weights；
To each UkDirect good friend, i.e. the two of A degree of good friendsV is calculated according to formula (2)iWeighed with A relation
Value
In formulaRepresent A and ViSecret degree, span is [0,1]；Represent UkDirect good friend in maximum
Known degree, span are [0,1]；ρ is represented In shared importance ratio, span is [0, l].
Represent A and ViGood friend's secret degree dimension, due to U in this stepkIt is A direct good friend, ViIt is UkIt is straight
Connect friend, A and ViRelation be to pass through UkCome what is transmitted, therefore claim ViFor A two degree of good friends, i.e.,
σ represents user to the degree of concern of internuncial number, and span is (0, l), and σ values are bigger, weightsDecline
Subtract faster.
S7, by all two degree good friends addition FR with A relation weights more than or equal to MA；
S8, to each new addition FRACommending friends Vj, obtain its direct good friend's set
S9, the secret degree dimension values of good friend add to 1, it is every in the N-dimensional degree good friend set for each A that calculation procedure S8 is obtained
One good friend and A relation weights；
Here according to each good friend in formula (3) calculation procedure S8 each A obtained N-dimensional degree good friend setWith A relation weights
In formulaRepresent A and XiSecret degree, span is [0,1]；Represent VjDirect good friend in maximum
Known degree, span are [0,1]；ρ is represented In shared importance ratio, span is [0, l]；
Represent A and XiGood friend's secret degree dimension, often perform a deuterzooid step,Value add 1；σ represents user to internuncial number
Purpose degree of concern, span are (0, l).
S10, all N-dimensional degree good friends with A relation weights more than or equal to M are added into FRA；
S11, judge whether good friend's secret degree dimension values are equal to 6, if then entering step S12, if otherwise return to step S8；
Here the secret degree dimension values upper limit is taken 6 to be the result drawn according to Six Degrees theory.
S12, by commending friends set FRARecommend good friend requestor A.
Meet that the suitable user B of three conditions of the foregoing description is contained in commending friends set FRAIn.
One of ordinary skill in the art will be appreciated that embodiment described here is to aid in reader and understands this hair
Bright principle, it should be understood that protection scope of the present invention is not limited to such especially statement and embodiment.This area
Those of ordinary skill can make according to these technical inspirations disclosed by the invention various does not depart from the other each of essence of the invention
The specific deformation of kind and combination, these deform and combined still within the scope of the present invention.
Claims (5)
1. a kind of recommend method based on the social network relationships of secret degree and known degree, it is characterised in that comprises the following steps：
S1, the direct good friend's set F for obtaining good friend requestor AA={ U1,U2,...,Um}；
S2, initialization establish final good friend requestor A commending friends set FRA；
S3, friend recommendation threshold value M is set；
S4, calculate FAIn each directly good friend and A relation weights；The step S4 is specially：
To each A direct good friend Ui∈FA, U is calculated according to formula (1)iWith A relation weights
<mrow>
<msub>
<mi>W</mi>
<mrow>
<msub>
<mi>AU</mi>
<mi>i</mi>
</msub>
</mrow>
</msub>
<mo>=</mo>
<msub>
<mi>&rho;I</mi>
<mrow>
<msub>
<mi>AU</mi>
<mi>i</mi>
</msub>
</mrow>
</msub>
<mo>+</mo>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>-</mo>
<mi>&rho;</mi>
<mo>)</mo>
</mrow>
<msub>
<mi>R</mi>
<mi>A</mi>
</msub>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
In formulaRepresent A and UiSecret degree, span is [0,1]；RARepresent that the maximum in A direct good friend is known to spend,
Span is [0,1]；ρ is represented In shared importance ratio, span is [0, l]；
The good friend U of S5, lookup and A relation maximum weightk, obtain UkDirect good friend set
S6, define UkDirect good friend setTwo degree of good friends set that secret degree dimension values for A are 2, is calculatedIn it is each
Two degree of good friends and A relation weights；
S7, by all two degree good friends addition FR with A relation weights more than or equal to MA；
S8, to each new addition FRACommending friends Vj, obtain its direct good friend's set
S9, the secret degree dimension values of good friend are added to 1, each in the N-dimensional degree good friend set for each A that calculation procedure S8 is obtained
Good friend and A relation weights；
S10, all N-dimensional degree good friends with A relation weights more than or equal to M are added into FRA；
S11, judge whether good friend's secret degree dimension values are equal to 6；
If then enter step S12；
If otherwise return to step S8；
S12, by commending friends set FRARecommend good friend requestor A.
2. according to claim 1 recommend method based on the social network relationships of secret degree and known degree, it is characterised in that
The commending friends set FRAIt is initialized as empty set.
3. according to claim 1 recommend method based on the social network relationships of secret degree and known degree, it is characterised in that
The commending friends set
4. according to claim 1 recommend method based on the social network relationships of secret degree and known degree, it is characterised in that
The step S6 is specially：
Define UkDirect good friend setTwo degree of good friends set that secret degree dimension values for A are 2, to each UkIt is direct
Two degree of good friends of good friend, i.e. AV is calculated according to formula (2)iWith A relation weights
<mrow>
<msub>
<mi>W</mi>
<mrow>
<msub>
<mi>AV</mi>
<mi>i</mi>
</msub>
</mrow>
</msub>
<mo>=</mo>
<msub>
<mi>&rho;I</mi>
<mrow>
<msub>
<mi>AV</mi>
<mi>i</mi>
</msub>
</mrow>
</msub>
<mo>+</mo>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>-</mo>
<mi>&rho;</mi>
<mo>)</mo>
</mrow>
<msub>
<mi>R</mi>
<msub>
<mi>U</mi>
<mi>k</mi>
</msub>
</msub>
<mo>-</mo>
<msub>
<mi>&sigma;D</mi>
<mrow>
<msub>
<mi>AV</mi>
<mi>i</mi>
</msub>
</mrow>
</msub>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>2</mn>
<mo>)</mo>
</mrow>
</mrow>
In formulaRepresent A and ViSecret degree, span is [0,1]；Represent UkDirect good friend in maximum known in
Degree, span is [0,1]；ρ is represented In shared importance ratio, span is [0, l]；Represent A
With ViGood friend's secret degree dimension, in this stepσ represents user to the degree of concern of internuncial number, value
Scope is (0, l).
5. according to claim 1 recommend method based on the social network relationships of secret degree and known degree, it is characterised in that
The step S9 is specially：
The secret degree dimension values of good friend are added 1, according in formula (3) calculation procedure S8 each A obtained N-dimensional degree good friend set
Each good friendWith A relation weights
<mrow>
<msub>
<mi>W</mi>
<mrow>
<msub>
<mi>AX</mi>
<mi>i</mi>
</msub>
</mrow>
</msub>
<mo>=</mo>
<msub>
<mi>&rho;I</mi>
<mrow>
<msub>
<mi>AX</mi>
<mi>i</mi>
</msub>
</mrow>
</msub>
<mo>+</mo>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>-</mo>
<mi>&rho;</mi>
<mo>)</mo>
</mrow>
<msub>
<mi>R</mi>
<msub>
<mi>V</mi>
<mi>j</mi>
</msub>
</msub>
<mo>-</mo>
<msub>
<mi>&sigma;D</mi>
<mrow>
<msub>
<mi>AX</mi>
<mi>i</mi>
</msub>
</mrow>
</msub>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>3</mn>
<mo>)</mo>
</mrow>
</mrow>
In formulaRepresent A and XiSecret degree, span is [0,1]；Represent VjDirect good friend in maximum known in
Degree, span is [0,1]；ρ is represented In shared importance ratio, span is [0, l]；Represent A
With XiGood friend's secret degree dimension, often perform a deuterzooid step,Value add 1；σ represents user to internuncial number
Degree of concern, span are (0, l).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510388830.0A CN105141499B (en) | 2015-07-03 | 2015-07-03 | It is a kind of to recommend method based on the social network relationships of secret degree and known degree |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510388830.0A CN105141499B (en) | 2015-07-03 | 2015-07-03 | It is a kind of to recommend method based on the social network relationships of secret degree and known degree |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105141499A CN105141499A (en) | 2015-12-09 |
| CN105141499B true CN105141499B (en) | 2018-03-09 |
Family
ID=54726715
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510388830.0A Active CN105141499B (en) | 2015-07-03 | 2015-07-03 | It is a kind of to recommend method based on the social network relationships of secret degree and known degree |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105141499B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105740342A (en) * | 2016-01-22 | 2016-07-06 | 天津中科智能识别产业技术研究院有限公司 | Social relation topic model based social network friend recommendation method |
| CN107376357A (en) * | 2016-05-17 | 2017-11-24 | 蔡小华 | A kind of good friend's interaction class internet game method |
| CN108600076A (en) * | 2017-03-07 | 2018-09-28 | 中移（杭州）信息技术有限公司 | A kind of social networks method for building up and system |
| CN108616447B (en) * | 2018-04-17 | 2019-09-17 | 北京达佳互联信息技术有限公司 | Customer relationship bootstrap technique, device and the electronic equipment of social networks |
| CN109658279A (en) * | 2018-12-19 | 2019-04-19 | 成都康赛信息技术有限公司 | Social network relationships recommended method based on cohesion and credit worthiness |
| CN109815414A (en) * | 2019-01-23 | 2019-05-28 | 四川易诚智讯科技有限公司 | Social networks character relation analysis method based on multitiered network community division |
| CN109859064A (en) * | 2019-01-31 | 2019-06-07 | 北京俩俩科技有限公司 | Friend recommendation method and system based on hail fellow relationship |
| CN111343690A (en) * | 2020-03-01 | 2020-06-26 | 内蒙古科技大学 | Opportunistic network routing method based on fine-grained social relationship and community cooperation |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102255890A (en) * | 2011-05-30 | 2011-11-23 | 苏宁军 | User recommendation and information interaction system and method |
| CN102724139A (en) * | 2012-06-28 | 2012-10-10 | 奇智软件（北京）有限公司 | Method and device for friend recommending through instant messaging |
| CN103514215A (en) * | 2012-06-28 | 2014-01-15 | 北京奇虎科技有限公司 | Method and device for generating social contact influence information for user |
| CN103823888A (en) * | 2014-03-07 | 2014-05-28 | 安徽融数信息科技有限责任公司 | Node-closeness-based social network site friend recommendation method |
-
2015
- 2015-07-03 CN CN201510388830.0A patent/CN105141499B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102255890A (en) * | 2011-05-30 | 2011-11-23 | 苏宁军 | User recommendation and information interaction system and method |
| CN102724139A (en) * | 2012-06-28 | 2012-10-10 | 奇智软件（北京）有限公司 | Method and device for friend recommending through instant messaging |
| CN103514215A (en) * | 2012-06-28 | 2014-01-15 | 北京奇虎科技有限公司 | Method and device for generating social contact influence information for user |
| CN103823888A (en) * | 2014-03-07 | 2014-05-28 | 安徽融数信息科技有限责任公司 | Node-closeness-based social network site friend recommendation method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105141499A (en) | 2015-12-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105141499B (en) | It is a kind of to recommend method based on the social network relationships of secret degree and known degree | |
| Almogren et al. | Ftm-iomt: Fuzzy-based trust management for preventing sybil attacks in internet of medical things | |
| CN105654388B (en) | A kind of modeling method of dynamic social network Information Propagation Model | |
| Wang et al. | An information spreading model based on online social networks | |
| Gonczarowski et al. | A stable marriage requires communication | |
| CN103279887A (en) | Information-theory-based visual analysis method and system for micro-blog spreading | |
| CN106373015A (en) | Intimacy determination method and system in social network | |
| CN103530428A (en) | Same-occupation type recommendation method based on developer practical skill similarity | |
| Kornienko et al. | Friendship networks and ethnic-racial identity development: Contributions of social network analysis. | |
| Sun et al. | Asymmetrical dynamics of epidemic propagation and awareness diffusion in multiplex networks | |
| CN104009993A (en) | Trust evaluation method based on fuzzy filtration | |
| Antoniadis et al. | Communities of followers in tourism twitter accounts of European countries | |
| Yang et al. | Global dynamical analysis of a heroin epidemic model on complex networks | |
| Zhang et al. | A Customer‐Centric Trust Evaluation Model for Personalized Service Selection | |
| CN104009992A (en) | Trust evaluation system construction method based on fuzzy control | |
| Mukkamala et al. | Presence of social presence during disasters | |
| Rastogi | A power law approach to estimating fake social network accounts | |
| Šuvakov et al. | Collective emotion dynamics in chats with agents, moderators and Bots | |
| Palchykov et al. | Transmission of cultural traits in layered ego-centric networks | |
| CN109658279A (en) | Social network relationships recommended method based on cohesion and credit worthiness | |
| Simo et al. | Privinfervis: Towards enhancing transparency over attribute inference in online social networks | |
| Jang et al. | Partner Selection for Agents: A Utility Theory Approach | |
| Cho et al. | A Dynamic Foundation of the Rawlsian Maxmin Criterion | |
| Lu | A Study of Mobile User Satisfaction Based on Feature Extraction | |
| Kavianpouret | Al,“Calculating trust value in information propagation for online social network sites.” |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |