CN105354749A - Social network based mobile terminal user grouping method - Google Patents
Social network based mobile terminal user grouping method Download PDFInfo
- Publication number
- CN105354749A CN105354749A CN201510678903.XA CN201510678903A CN105354749A CN 105354749 A CN105354749 A CN 105354749A CN 201510678903 A CN201510678903 A CN 201510678903A CN 105354749 A CN105354749 A CN 105354749A
- Authority
- CN
- China
- Prior art keywords
- user
- attribute
- terminal user
- users
- terminal
- 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
Links
- 238000000034 method Methods 0.000 title abstract description 12
- 238000005295 random walk Methods 0.000 claims abstract description 23
- 239000011159 matrix material Substances 0.000 claims abstract description 22
- 238000004891 communication Methods 0.000 claims abstract description 16
- RZVAJINKPMORJF-UHFFFAOYSA-N Acetaminophen Chemical compound CC(=O)NC1=CC=C(O)C=C1 RZVAJINKPMORJF-UHFFFAOYSA-N 0.000 claims abstract 3
- 230000007704 transition Effects 0.000 claims description 19
- 238000005516 engineering process Methods 0.000 claims description 15
- 230000003416 augmentation Effects 0.000 claims description 2
- 101000685990 Homo sapiens Specifically androgen-regulated gene protein Proteins 0.000 claims 1
- 102100023355 Specifically androgen-regulated gene protein Human genes 0.000 claims 1
- 238000012546 transfer Methods 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000013508 migration Methods 0.000 description 5
- 230000005012 migration Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 3
- 238000010295 mobile communication Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000013468 resource allocation Methods 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Telephonic Communication Services (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention discloses a social network based mobile terminal user grouping method. The method comprises: according to history of communication between terminal users, quantizing communication contact to generate a social relational graph (STG); in combination with preference attributes of the terminal users, generating an attribute relational graph (ARG) taking preference degrees between the terminal users and attributes as weights; generating a social relation-attribute graph in combination with the STG and the ARG, designing an SAPLA algorithm to predict unknown attributes of the terminal users, and adjusting preference degrees of known attributes; and proposing an SARA algorithm by utilizing a random walk model, combining transfer probabilities between the terminal users and between the terminal users and the attributes, giving out a transfer probability matrix between the terminal users, with relatively low complexity, giving out a random walk distance matrix Rl by utilizing the transfer probability matrix, setting a target function in combination with the matrix Rl, and grouping the terminal users until the target function is converged. According to the method, the complexity of operation is lowered and the accuracy of grouping is improved.
Description
Technical field
The present invention relates to mobile communication technology and Data Mining, in particular, the present invention relates to a kind of mobile phone users group technology based on community network, can relation effectively between digging user attribute and user, reasonably divide into groups.
Background technology
Because the accumulation of data large in real world generates, achievement in research for network is more and more excavated by people and utilizes, for people are more deeply familiar with the network system of all kinds of complexity in real world, and effective help is provided to these Systematical control or application.Community network can reflect members of society and mutual relationship thereof, and how by the analysis to community network, excavate the stealthy relation be hidden under surface relationships, and according to these relations, user is divided into groups, optimization existing communication Resource Allocation in Networks, raising telex network are experienced, brought to society the aspects such as great economic benefit to have very great meaning simultaneously.This just needs to obtain a kind of rationally effective user grouping scheme the complicated social relationships formed between user.
And the formation of community network is mainly derived from connecting each other of interpersonal outwardness, meanwhile, the subjective preference for things of people also affects the formation of community network, so need the feature in conjunction with the objective connection existed between user and user self, could potential relation more effectively between digging user, carry out the grouping of rational community.
Realizing in process of the present invention, inventor finds:
In existing technical scheme, the weight between user is not set according to the user's historical behavior shown in mobile communications network scene between terminal user, influence power between user can not well embody, simultaneously comprehensive not for the attribute forecast of user, the unpredictable user of going out does not like a certain things, and higher according to transition probability matrix computational complexity between the user of random walk model generation in traditional community's group technology, greatly reduce feasibility and the practicality of terminal user's group technology.
Summary of the invention
For the deficiencies in the prior art, propose a kind of mobile phone users group technology based on community network reducing computational complexity, improve grouping accuracy.Technical scheme of the present invention is as follows: a kind of mobile phone users group technology based on community network, and it comprises the following steps:
A, entry terminal user data, set up sociogram STG according to the correspondence between terminal user, i.e. G
1=V1, E1}, wherein, | V1|=n GC group connector number of users, wherein n represents GC group connector number of users, the degree of association communicated between two terminal users in E1 representative graph, generating different social relationships classification, distributing corresponding class weights for being in inhomogeneous user
and according to the cohesion w between class weight computing terminal user
s(u
i, a
j);
B, set up attributed relational graph ARG, i.e. G
2={ V2, E2, A}, wherein, | V|=n, n GC group connector number of users, | A|=m, m is attribute number, and in E2 representative graph, user exists the degree of association to attribute, sets up social property-relation augmentation figure (SARG), social relationships-attribute link prediction (SAPLA) algorithm is adopted to predict the user and attribute that there is not the degree of association, simultaneously according to the cohesion between the middle terminal user that there is contact of sociogram (STG), the preference existed between the user of the degree of association and attribute is adjusted, terminal user u
ifor attribute a
jbetween preference be expressed as weight w
a(u
i, a
j);
C. utilize social relationships-attribute to merge (SARA) algorithm, obtain the transition probability matrix P between terminal user, provide random walk distance matrix R
l;
D. according to random walk distance matrix R
land clustering algorithm, target setting function, determines community's group center point, divides into groups to terminal user, until objective function converges, completes mobile phone users grouping
Further, described end-user listening data comprises: terminal user collects U={u
1, u
2... u
n, terminal user's property set A={a
1, a
2..., a
m, wherein a
ithere is n
iindividual value, namely
a
jkthe value of an expression jth attribute is a kth value in codomain.
Further, in described steps A, by statistics terminal user based on the communication history of communication time period CS, communication frequency CF, commitment defini interval CI, channel seizure ratio CO, user is classified and distributes to each class user class weights
in class, quantize telex network contact by communication frequency CF and channel seizure ratio CO, thus obtain cohesion w between terminal user
s(u
i, u
j).
Further, in described step B, according to social relationships-attribute link prediction (SAPLA) algorithm to the w between terminal user and attribute
a(u
i, a
j) predict, if w
a(u
i, a
j) < 0, represent this user taking a passive attitude to this attribute, namely unreachable between user and attribute, by p (u
i, a
j) be set to 0.
Further, in described step C, merge (SARA) algorithm according to social relationships-attribute, namely utilize transition probability P between the terminal user obtained in sociogram STG respectively
u, the user arrived-attribute transition probability P in ARG
uawith attribute-user's transition probability P
au, call formula
with
wherein c ∈ (0, the 1) initial probability that is random walk, the l obtained between terminal user walks random walk distance matrix R
l.
Further, in described step D, walk random walk distance matrix R according to acquired l
l, determine to contact with other users k user node comparatively closely, calculate cluster coefficients
will
value carry out arranging and choose a maximum k value, be k central point
and by all node u
i∈ | V| distributes to the central point from it with maximum travel distance, until objective function converges.
Further, according to the user arrived-attribute transition probability P in ARG
uawith attribute-user's transition probability P
au, P
uap
aurepresent in any two users and whether there is common attribute, formula
show if two users have predicable and existed to write to each other, then the probability shifted between these two users is larger, and namely two users have higher cohesion.
Advantage of the present invention and beneficial effect as follows:
The present invention is applied to the grouping problem of mobile terminal in mobile communication network user.Compared with prior art, the SAPLA algorithm of proposition can be predicted the attributes preferred of terminal user; SARA algorithm can make full use of the attributive character between terminal user, reduces computational complexity simultaneously and realizes difficulty.Along with constantly popularizing of mobile terminal device, be widely used in people's daily life along with mobile network service, therefore personalized and real-time accurately for user provides the problem of the mobile network service interested to them for how solving requirements of mobile subscribers, make terminal user divide into groups to have application prospect more and more widely, this patent may bring huge economic benefit.
Accompanying drawing explanation
Fig. 1 the invention provides preferred embodiment to utilize community network under mobile network's scene to the method schematic diagram that terminal user divides into groups;
Fig. 2 for be divided into four class schematic diagram in sociogram STG by customer relationship;
Fig. 3 is SAPLA algorithm schematic diagram of the present invention.
Embodiment
Below in conjunction with accompanying drawing, the invention will be further described:
By the writing to each other of outwardness between terminal user, the sociogram STG based on this can be set up, meanwhile, transfer process characteristic between terminal user meets Markov property, so walk transition probability according to n, can seem between digging user and there is not the implication relation under contacting directly.And constantly popularizing along with mobile terminal device, be widely used in people's daily life along with mobile network service, how to solve requirements of mobile subscribers personalized and real-time accurately for user provides the mobile network service interested to them, the importance that community is divided into groups highlights day by day.Be different from conventional internet network, mobile network has oneself characteristic, and namely its community network is comparatively sparse simultaneously, therefore the attribute of terminal user is introduced into community's grouping, and reasonably community's grouping can be made more accurately to become possibility.
Specifically comprise as follows in the present invention:
A. first according to the communication history of terminal user, set up sociogram STG, Figure 2 shows that and customer relationship is divided into four class schematic diagram in sociogram STG.Wherein, four indexs are defined as follows:
1) communication frequency CF: i.e. user u
itimes N is contacted with this user in time Δ t
i,jaccount for the ratio contacting number of times with all users, therefore CF can be expressed as
2) communication time period CS: talk period is divided into two period segment={working, leisure}, wherein { 9:00-12:00,13:00-18:00} are defined as working hour, and other times are defined as the spare time.This index describes user u
iperiod h is contacted with this user in time Δ t
i,jaccount for the ratio of working hour, therefore CS can be expressed as
3) channel seizure ratio CO: i.e. user u
iwith this user's communication duration X in time Δ t
i,jaccount for the ratio with all user's communication durations, therefore CO can be expressed as
4) commitment defini interval CI: i.e. u
iin time Δ t, contact ratio distance once accounting for the time interval contacted with all users with the time interval contacted with this user, therefore CI can be expressed as
B. consider above index, different social relationships classification can be generated, for the user being in different classes distributes corresponding class weights
call formula
and the cohesion w calculated between user
s(u
i, u
j), can be expressed as
wherein
Figure 3 shows that SAPLA algorithm schematic diagram of the present invention.SAPLA algorithm detailed process is:
A. first N is defined
p(u
i) represent and terminal user u
ithe user be connected, N
a(u
i) represent and terminal user u
ithe attribute be connected, | N (a
j)
+| represent and attribute a
jconnect and w
a(u
i, a
jterminal user's number of)>=0, in like manner | N (a
j)
-| be representative and attribute a
jthere is attribute limit but w
a(u
i, a
j) terminal user's number of < 0.Defined attribute a
jto terminal user u
ithe probability of migration is
B. the weight of attribute is considered to be divided into overall weight w
g(u
i, a
j) and partial weight w
l(u
i, a
j).Overall situation weight represents the significance level of this attribute to all terminal users, and partial weight represents the impact that user on the preference of attribute produced of this attribute owing to having the neighbor user of writing to each other to bring with user.Then overall weight and partial weight calculate respectively as follows:
C. make following adjustment to the weight between user and attribute, wherein γ represents Dynamic gene, and 0≤γ≤1, the probability after can ensureing to adjust still is less than 1:
So upgrade user u
ito attribute a
jprobability p (the u of migration
i, a
j) be:
And Update attribute a
jto terminal user u
iprobability p (a of migration
j, u
i).
SARA algorithm realization process:
A. according to random walk model, suppose that l is the maximum step-length of a summit random walk from i-th summit to jth, and suppose that c ∈ (0,1) is the initial probability of random walk, then from i-th summit to the random walk distance d (v on a jth summit
i, v
j) be defined as follows:
Wherein τ representative to be walked from i-th summit a paths on a jth summit, and step-length is length (τ), and the transition probability of correspondence is p (τ).Random walk distance matrix be by each summit between the matrix that forms of random walk distance, can by formula
represent.P
athe transition probability matrix of model, and R
lit is then the random walk distance matrix that l walks Nei Keda.So we can according to R
lweigh the intimate degree between two summits.Terminal user u
ito u
jthe probability of migration is
The transition probability matrix of definition terminal user migration is P
u, wherein (P
u)
i,j=p (i, j), the user be made up of to attribute transition probability matrix user-attribute P
uaand attribute-user's transition probability P
au, then user's cohesion is by calling formula
obtain, namely between terminal user except writing to each other of having existed, the same alike result existed between different user is more, and the cohesion between user also increases thereupon.Simultaneously when terminal user's number is constant, only during adding users attribute, only need to upgrade P
uap
auvalue, thus when meeting certain condition, traditional random walk model can be improved and causes along with the increase of terminal user's attribute number the defect that the computation complexity of probability transfer matrix also increases.
B. according to k-means method, community's grouping is carried out to terminal user.Consider according to SARA algorithm, can obtain the random walk distance between end-user node, the larger expression of the distance between user reachable path is more, and cohesion is higher, draws the social relationships-attributed graph (SARG) with weight simultaneously.So, k-means method classical in figure clustering algorithm can be adopted to divide into groups to user, because user is more prone to be connected with the node comparing active (popular), so adopt following steps:
(1) according to R
ldetermine to contact with other users k end-user node the most closely, and be set to central point c
i, 1≤i≤k.User u
icluster coefficients be defined as follows:
Represent and terminal user u
ithe reality leg-of-mutton length of side weights sum of the neighbor node and its formation that are connected and the ratio of all leg-of-mutton length of side weights sum that should obtain in theory.When
time, represent u
iall neighbours between be all interconnected, define Global-Coupling network.Will
value carry out arranging and choose a maximum k value, be k central point
wherein
represent the central point of during the t time iteration the i-th bunch.
(2) by all end-user node u
i∈ | V| distributes to the central point from it with maximum travel distance, namely
(3) all end-user node are all carried out after cluster, to central point c
iupgrade, make the value of following formula objective function maximum:
This formula represents that to make the user in group and the random walk distance between central point user maximum with the ratio of mean distance in group.When the value of objective function is maximum, represent that objective function is restrained, cluster process terminates.
These embodiments are interpreted as only being not used in for illustration of the present invention limiting the scope of the invention above.After the content of reading record of the present invention, technician can make various changes or modifications the present invention, and these equivalence changes and modification fall into the scope of the claims in the present invention equally.
Claims (7)
1., based on a mobile phone users group technology for community network, it is characterized in that, comprise the following steps:
A, entry terminal user data, set up sociogram STG according to the correspondence between terminal user, i.e. G
1=V1, E1}, wherein, | V1|=n, wherein n represents GC group connector number of users, the degree of association communicated between two terminal users in E1 representative graph, generating different social relationships classification, distributing corresponding class weights for being in inhomogeneous user
and according to the cohesion w between class weight computing terminal user
s(u
i, a
j);
B, set up attributed relational graph ARG, i.e. G
2={ V2, E2, A}, wherein, | V|=n, n GC group connector number of users, | A|=m, m is attribute number, and in E2 representative graph, user exists the degree of association to attribute, sets up social property-relation augmentation figure SARG, social relationships-attribute link prediction SAPLA algorithm is adopted to predict the user and attribute that there is not the degree of association, simultaneously according to the cohesion between the terminal user that there is contact in sociogram STG, the preference existed between the user of the degree of association and attribute is adjusted, terminal user u
ifor attribute a
jbetween preference be expressed as weight w
a(u
i, a
j);
C. utilize social relationships-attribute to merge SARA algorithm, obtain the transition probability matrix P between terminal user, provide random walk distance matrix R
l;
D. according to random walk distance matrix R
land clustering algorithm, target setting function, determines community's group center point, divides into groups to terminal user, until objective function converges, completes mobile phone users grouping.
2. a kind of mobile phone users group technology based on community network according to claim 1, it is characterized in that, described end-user listening data comprises: terminal user collects U={u
1, u
2... u
n, terminal user's property set A={a
1, a
2..., a
m, wherein a
ithere is n
iindividual value, namely
a
jkthe value of an expression jth attribute is a kth value in codomain.
3. a kind of mobile phone users group technology based on community network according to claim 1, it is characterized in that, in described steps A, by statistics terminal user based on the communication history of communication time period CS, communication frequency CF, commitment defini interval CI, channel seizure ratio CO, user is classified and distributes to each class user class weights
in class, quantize telex network contact by communication frequency CF and channel seizure ratio CO, thus obtain cohesion w between terminal user
s(u
i, u
j).
4. a kind of mobile phone users group technology based on community network according to claim 1, is characterized in that, in described step B, according to social relationships-attribute link prediction SAPLA algorithm to the w between terminal user and attribute
a(u
i, a
j) predict, if w
a(u
i, a
j) < 0, represent this user taking a passive attitude to this attribute, namely unreachable between user and attribute, by p (u
i, a
j) be set to 0.
5. a kind of mobile phone users group technology based on community network according to claim 1, it is characterized in that, in described step C, merge SARA algorithm according to social relationships-attribute, namely utilize transition probability P between the terminal user obtained in sociogram STG respectively
u, the user arrived-attribute transition probability P in ARG
uawith attribute-user's transition probability P
au, call formula
with
wherein c ∈ (0, the 1) initial probability that is random walk, the l obtained between terminal user walks random walk distance matrix R
l.
6. a kind of mobile phone users group technology based on community network according to claim 1, is characterized in that, in described step D, walks random walk distance matrix R according to acquired l
l, determine to contact with other users k user node comparatively closely, calculate cluster coefficients
will
value carry out arranging and choose a maximum k value, be k central point
and by all node u
i∈ | V| distributes to the central point from it with maximum travel distance, until objective function converges.
7. a kind of mobile phone users group technology based on community network according to claim 5, is characterized in that, according to the user arrived-attribute transition probability P in ARG
uawith attribute-user's transition probability P
au, P
uap
aurepresent in any two users and whether there is common attribute, formula
show if two users have predicable and existed to write to each other, then the probability shifted between these two users is larger, and namely two users have higher cohesion.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510678903.XA CN105354749A (en) | 2015-10-16 | 2015-10-16 | Social network based mobile terminal user grouping method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510678903.XA CN105354749A (en) | 2015-10-16 | 2015-10-16 | Social network based mobile terminal user grouping method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105354749A true CN105354749A (en) | 2016-02-24 |
Family
ID=55330716
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510678903.XA Pending CN105354749A (en) | 2015-10-16 | 2015-10-16 | Social network based mobile terminal user grouping method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105354749A (en) |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105812593A (en) * | 2016-03-30 | 2016-07-27 | 中国联合网络通信集团有限公司 | Method and device for grading users |
CN105824921A (en) * | 2016-03-16 | 2016-08-03 | 广州彩瞳网络技术有限公司 | User social relation recognition device and method |
CN106100870A (en) * | 2016-05-31 | 2016-11-09 | 武汉大学 | A kind of community network event detecting method based on link prediction |
CN106202869A (en) * | 2016-06-27 | 2016-12-07 | 深圳市嘉兰图设计股份有限公司 | Familiarity number system and emotional affection communication method |
CN107341571A (en) * | 2017-06-27 | 2017-11-10 | 华中科技大学 | A kind of social network user behavior prediction method based on quantization social effectiveness |
CN108391257A (en) * | 2018-02-26 | 2018-08-10 | 重庆邮电大学 | Resource allocation methods based on Game Theory under a kind of community network D2D scenes |
CN108615198A (en) * | 2018-04-26 | 2018-10-02 | 北京小米移动软件有限公司 | Methods of exhibiting, device and the storage medium that social networking application releases news |
CN109256215A (en) * | 2018-09-04 | 2019-01-22 | 华东交通大学 | A kind of disease association miRNA prediction technique and system based on from avoidance random walk |
CN110083777A (en) * | 2018-01-26 | 2019-08-02 | 腾讯科技(深圳)有限公司 | A kind of social network user group technology, device and server |
CN110851655A (en) * | 2019-11-07 | 2020-02-28 | 中国银联股份有限公司 | Method and system for simplifying complex network |
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 |
CN111461118A (en) * | 2020-03-31 | 2020-07-28 | 中国移动通信集团黑龙江有限公司 | Interest feature determination method, device, equipment and storage medium |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101149756A (en) * | 2007-11-09 | 2008-03-26 | 清华大学 | Individual relation finding method based on path grade at large scale community network |
CN104636382A (en) * | 2013-11-13 | 2015-05-20 | 华为技术有限公司 | Social relation reasoning method and device |
CN104636439A (en) * | 2015-01-04 | 2015-05-20 | 中国联合网络通信集团有限公司 | Method and device for analyzing user social relation |
-
2015
- 2015-10-16 CN CN201510678903.XA patent/CN105354749A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101149756A (en) * | 2007-11-09 | 2008-03-26 | 清华大学 | Individual relation finding method based on path grade at large scale community network |
CN104636382A (en) * | 2013-11-13 | 2015-05-20 | 华为技术有限公司 | Social relation reasoning method and device |
CN104636439A (en) * | 2015-01-04 | 2015-05-20 | 中国联合网络通信集团有限公司 | Method and device for analyzing user social relation |
Non-Patent Citations (1)
Title |
---|
杨静 等: "基于用户空间相关性的一种SDMA分组策略研究", 《重庆邮电大学学报(自然科学版)》 * |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105824921A (en) * | 2016-03-16 | 2016-08-03 | 广州彩瞳网络技术有限公司 | User social relation recognition device and method |
US10860595B2 (en) | 2016-03-16 | 2020-12-08 | Guangzhou Uc Network Technology Co., Ltd. | User social-relationship identification apparatus, method, and terminal device |
CN105812593A (en) * | 2016-03-30 | 2016-07-27 | 中国联合网络通信集团有限公司 | Method and device for grading users |
CN106100870A (en) * | 2016-05-31 | 2016-11-09 | 武汉大学 | A kind of community network event detecting method based on link prediction |
CN106202869B (en) * | 2016-06-27 | 2019-05-03 | 深圳市嘉兰图设计股份有限公司 | Emotional affection way system and emotional affection communication method |
CN106202869A (en) * | 2016-06-27 | 2016-12-07 | 深圳市嘉兰图设计股份有限公司 | Familiarity number system and emotional affection communication method |
CN107341571A (en) * | 2017-06-27 | 2017-11-10 | 华中科技大学 | A kind of social network user behavior prediction method based on quantization social effectiveness |
CN107341571B (en) * | 2017-06-27 | 2020-05-19 | 华中科技大学 | Social network user behavior prediction method based on quantitative social influence |
CN110083777A (en) * | 2018-01-26 | 2019-08-02 | 腾讯科技(深圳)有限公司 | A kind of social network user group technology, device and server |
CN110083777B (en) * | 2018-01-26 | 2022-11-25 | 腾讯科技(深圳)有限公司 | Social network user grouping method and device and server |
CN108391257B (en) * | 2018-02-26 | 2023-09-26 | 重庆邮电大学 | Resource allocation method based on auction theory in social network D2D scene |
CN108391257A (en) * | 2018-02-26 | 2018-08-10 | 重庆邮电大学 | Resource allocation methods based on Game Theory under a kind of community network D2D scenes |
CN108615198A (en) * | 2018-04-26 | 2018-10-02 | 北京小米移动软件有限公司 | Methods of exhibiting, device and the storage medium that social networking application releases news |
CN109256215B (en) * | 2018-09-04 | 2021-04-06 | 华东交通大学 | Disease-associated miRNA prediction method and system based on self-avoiding random walk |
CN109256215A (en) * | 2018-09-04 | 2019-01-22 | 华东交通大学 | A kind of disease association miRNA prediction technique and system based on from avoidance random walk |
CN110851655A (en) * | 2019-11-07 | 2020-02-28 | 中国银联股份有限公司 | Method and system for simplifying complex network |
CN110851655B (en) * | 2019-11-07 | 2024-05-17 | 中国银联股份有限公司 | Method and system for simplifying complex network |
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 |
CN111461118A (en) * | 2020-03-31 | 2020-07-28 | 中国移动通信集团黑龙江有限公司 | Interest feature determination method, device, equipment and storage medium |
CN111461118B (en) * | 2020-03-31 | 2023-11-24 | 中国移动通信集团黑龙江有限公司 | Interest feature determining method, device, equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105354749A (en) | Social network based mobile terminal user grouping method | |
CN103064917B (en) | The high-impact customer group of a kind of specific tendency towards microblogging finds method | |
CN103325061B (en) | A kind of community discovery method and system | |
CN103559407B (en) | A kind of commending system for measuring direct graph with weight interior joint cohesion and method | |
CN107277889A (en) | A kind of network clustering method of wireless sensor based on k means | |
CN103577876B (en) | Based on feedforward neural network credible with insincere user identification method | |
CN101826114A (en) | Multi Markov chain-based content recommendation method | |
CN104035987B (en) | A kind of micro blog network user force arrangement method | |
CN106875281B (en) | Social network node mining activation method based on greedy subgraph | |
CN101505311A (en) | Information transmission method and system based on socialized network | |
CN110267292A (en) | Cellular network method for predicting based on Three dimensional convolution neural network | |
CN105404943A (en) | User behavior prediction method facing mobile social environment | |
CN103596191A (en) | Intelligent configuration system and intelligent configuration method for wireless sensor network | |
CN111158912A (en) | Task unloading decision method based on deep learning in cloud and mist collaborative computing environment | |
CN108182640A (en) | A kind of method that maximizing influence problem is solved based on user behavior propagation model | |
CN103118102B (en) | A kind of under cloud computing environment statistics and control system and the method for spatial data accessing rule | |
Yan et al. | Distributed edge caching with content recommendation in fog-rans via deep reinforcement learning | |
CN115879542A (en) | Federal learning method oriented to non-independent same-distribution heterogeneous data | |
CN103345513A (en) | Friend recommendation method based on friend relationship spread in social network | |
CN103942298A (en) | Recommendation method and system based on linear regression | |
WO2024056051A1 (en) | Non-intrusive flexible load aggregation characteristic identification and optimization method, apparatus, and device | |
Li et al. | An effective reliability evaluation method for power communication network based on community structure | |
CN107465571A (en) | Tactical network simulated training background service flow generation method based on statistical property | |
CN105243121A (en) | Data mining based text data network construction system | |
CN103838964A (en) | Social relationship network generation method and device based on artificial transportation system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into 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: 20160224 |