CN105335892A - Realization method for discovering important users of social network - Google Patents
Realization method for discovering important users of social network Download PDFInfo
- Publication number
- CN105335892A CN105335892A CN201510732810.0A CN201510732810A CN105335892A CN 105335892 A CN105335892 A CN 105335892A CN 201510732810 A CN201510732810 A CN 201510732810A CN 105335892 A CN105335892 A CN 105335892A
- Authority
- CN
- China
- Prior art keywords
- node
- algorithm
- social networks
- network
- implementation method
- 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 claims abstract description 30
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 65
- 230000003993 interaction Effects 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 230000010354 integration Effects 0.000 claims description 2
- 230000001105 regulatory effect Effects 0.000 claims description 2
- 238000011524 similarity measure Methods 0.000 claims description 2
- 238000012795 verification Methods 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 6
- 238000004088 simulation Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 2
- 208000015181 infectious disease Diseases 0.000 description 2
- 230000016507 interphase Effects 0.000 description 2
- 230000001902 propagating effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 108010022579 ATP dependent 26S protease Proteins 0.000 description 1
- 208000035473 Communicable disease Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000036039 immunity Effects 0.000 description 1
- 230000001524 infective effect Effects 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 238000005295 random walk Methods 0.000 description 1
- 238000003786 synthesis reaction 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
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)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a realization method for discovering important users of a social network. According to the method, when the ability of different users in a network to influence each other is solved, node similarity is put forward to measure the degree to which a node is influenced by a neighbor node thereof, and the importance of a node is obtained by comprehensively considering the local influence and global influence of the node. The method of the invention has the following advantages: (1) by using the LeaderRank algorithm as an improved algorithm, the possibility that the PageRank algorithm is trapped in a dangling node is avoided, and the convergence speed of the algorithm is increased; (2) node similarity calculation takes into consideration the incoming edge and the outgoing edge of nodes; and (3) the local and global functions of nodes are considered comprehensively, and the accuracy of the algorithm is improved.
Description
Technical field
The present invention relates to the implementation method that a kind of social networks responsible consumer finds, belong to network communication technology field.
Background technology
Important node compares other nodes in network, enough can produce a small amount of node of great function to the 26S Proteasome Structure and Function of whole network.In recent years, scholar proposes a lot of index and algorithm in important node sequence, mainly contain the following aspects: 1. based on the sort method of nodes neighbors node, as at document BonacichP " Factoringandweightingapproachestostatusscoresandcliqueid entification " (JournalofMathematicalSociology.1972, 2 (1): 113-120) degree of proposition centrality (degreecentrality), namely the neighbor node of node its influence powers more are larger, its shortcoming is the local message only considering node, 2. based on the sort method in path, as document FreemanLC " Centralityinsocialnetworksconceptualclarification " (SocialNetworks, 1978,1 (3): 215 – 239) propose close to centrality (closenesscentrality), weigh the importance of node by other all nodal distance mean values in computing node and network, shortcoming is that time complexity is higher, 3. the sort method of feature based vector, as document BrinS " TheAnatomyofaLarge-ScaleHypertextualWebSearchEngine " (ComputerNetworks & IsdnSystems, 1998,30 (98): 107 – 117) PageRank algorithm is proposed, the importance of each node of thinking this algorithm depends on the quality and quantity of other nodes pointing to it, and shortcoming is easily absorbed in hanging node.Document L ü L " LeadersinSocialNetworks, theDeliciousCase " (PlosOne, 2011, 6 (6): e21202) and document LiQ " IdentifyinginfluentialspreadersbyweightedLeaderRank " (PhysicaAStatisticalMechanics & ItsApplications, 2014, 404 (24): 47-55) LeaderRank algorithm is proposed on the basis of PageRank algorithm, by adding a background node, all nodes of this node and network are bi-directionally connected, carry out redirect probability s in alternative PageRank algorithm, thus improve convergence of algorithm speed and robustness.4., based on the sort method removing and shrink of node, weigh the importance of node by removing the destructiveness of node to network, but its computation complexity is high.Existing algorithm considers the importance of node in the overall situation or local importance mostly, have ignored the impact of node interphase interaction on whole network.
SIR model is model the most classical in Epidemic Model, and wherein S represents susceptible person (Susceptible), refers to not obtain patient, but lacks immunity, easily receives infection after contacting with the infected; I represents the infected (Infective), refers to the people catching infectious disease, and it can propagate to S class members; R represent the person of removing (Removal), refer to, refer to be isolated, or because recovering the immune people of tool.Usual use SIR propagation model, verifies the validity of important node sort algorithm.Generally, the velocity of propagation of selected node is faster, and namely in certain hour, I state node number growth rate is faster, and node is more important.And the present invention can solve problem above well.
Summary of the invention
The object of the invention is to overcome above-mentioned existing methodical deficiency, the implementation method that a kind of social networks responsible consumer finds is provided, the method finds algorithm based on the important node of LeaderRank algorithm and node similarity, improve the robustness of network, reduce iterations, and can solve as PageRank algorithm is absorbed in the problem of hanging node when node random walk.
The present invention solves the technical scheme that its technical matters takes: the present invention is applied under social networks pays close attention to the network of relation, and carry out importance sorting to nodes, its direct object is not the important node captured dynamically in network.The existing social networks of methods combining of the present invention, is not the dynamic concern relation captured in existing social networks, provides important node.
Method of the present invention is based on intrinsic social networks, and adopts MATLAB platform as visual software, is provided by the important node ranking results of network.
The present invention, when computing node importance degree, takes into full account the overall situation and the local feature of node, considers that the dynamics of node Thermodynamic parameters is different, namely there is the relation of close and distant distance, thus provide importance calculation method.
Method flow:
Step 1: by concern relation, information is built to the social networks requiring to analyze and listens to network A ij, adopt LeaderRank algorithm, calculate the overall importance degree of each node;
Step 2: the similarity adopting the Similarity Measure node between two of definition, as node local interaction;
Step 3: adopt SimRank algorithm, calculate the importance degree of node, it is sorted;
Step 4: adopt SIR propagation model, contrast other classic algorithm, checking validity.
Further, in step 1 of the present invention, adopt the overall importance degree of LeaderRank Algorithm for Solving node, comprise a background node, LeaderRank algorithm comprises the steps:
A. at original A
ijbasis on, add a background node, be namely interconnected with other nodes in network, obtain new network A
ij';
B. by A
ij' calculate
C. basis
after continuous iteration is extremely stable, calculate
Finally obtain the LR value of each node.
Wherein
for node v
iout-degree,
for the element in basic Google matrix, n is network node sum, does not namely comprise background node, LR
gk () is kth step background node v
gimportance degree.
Further, in step 2 of the present invention, node similarity takes into full account that node enters limit and goes out limit, and calculating formula of similarity is:
Wherein α
ifor node v
ithe set of neighbor node, γ is regulating parameter (0 < γ < 1).
represent node v
iwith node v
jthe node number of common sensing,
represent common and point to node v
iwith node v
jnode number.
Further, in step 3 of the present invention, integration node local and global characteristics, described SimRank algorithm equation is:
Further, in step 4 of the present invention, adopt SIR propagation model meet node between the power that influences each other difference, the influence power of a side to the opposing party that neighbor node number is many is larger; Meet in real network, when common good friend's number of two people is consistent, the few side of good friend's number to think a side that the opposing party and its relation can be more than good friend's number think the other side and its relation more intimate.When to adopt SIR propagation model to meet the right similarity of node be 0, between node, still there is interaction.
Beneficial effect:
1, the present invention is the overall importance degree adopting LeaderRank algorithm computing node, reduces iterations, improves network robustness, and avoids node and be absorbed in hanging node.
2, the present invention introduces the concept of node similarity, takes into full account entering limit and going out the impact of limit on node interphase interaction of node.
3, the SimRank algorithm of the present invention's proposition, be the feature considering the node overall situation and local, meet real network, its ranking results is more accurate.
4, the verification model SIR propagation model of the present invention's employing, simply, directly can show the validity of proposed SimRank algorithm.
5, the present invention is the equation of the local network characteristics based on LeaderRank algorithm synthesis node, and it is visual to adopt MATLAB platform to carry out, and improves the accuracy of pitch point importance ranking results.
Accompanying drawing explanation
Fig. 1 is configuration diagram of the present invention.
Fig. 2 is method flow diagram of the present invention.
Fig. 3 is the method flow diagram of example of the present invention.
Fig. 4 is the schematic diagram of simulation result 1 of the present invention.
Fig. 5 is the schematic diagram of simulation result 2 of the present invention.
Embodiment
Below in conjunction with Figure of description, the invention is described in further detail.
The terminological interpretation that the present invention relates to, comprising:
The propagation importance degree matrix S of node
iRbe defined as the mean value that the node repeatedly propagating I state and R state in artificial network accounts for the ratio of whole network.Carry out propagation emulation to each node in network respectively, namely emulation only has a node to be in I state each time, and other nodes are be all S state, and choosing travel-time step is 10, carries out 100 times propagate emulation, therefore node v to each node
ipropagation importance degree be:
Wherein n
j_i_srepresent that Initial travel node is node v
ijth time to propagate in emulation the node number of S state in network after 10 steps are propagated.
By calculating the pitch point importance of each algorithm and propagating importance degree relation, carry out the validity of evaluation algorithm.
As shown in Figure 1, the present invention is the pitch point importance value being calculated tested network by SimRank algorithm, then shown in Fig. 4, Fig. 5 of being provided display algorithm validity by SIR, all emulation is completed by MATLAB.
If Fig. 2 is process flow diagram of the present invention, first build A
ij, and then calculate each node LR value, then computing node between similarity, thus calculate the SR value of each node, propagate simulating, verifying finally by SIR.
Shown in example flow chart as of the present invention in Fig. 3, it is a kind of important node discover method based on LeaderRank algorithm and node similarity, comprising:
1, by concern relation, information is built to the social networks requiring to analyze and listen to network A
ij, adopt LeaderRank algorithm, calculate the overall importance degree of each node.Specific practice is as follows:
A. initialization: giving LR initial value to each node is
B. by the LR value of each node of formulae discovery;
C. b is repeated until the LR value of each node is not in change
2, node similarity matrix SIM is calculated.Specific practice is as follows:
A. select node, calculate the similarity with its neighbor node, obtain node similarity matrix;
B. travel through all nodes and obtain node similarity matrix SIM.
3, adopt SimRank algorithm, calculate the importance degree of node, it is sorted.
4, SIR is carried out to node and propagate emulation, obtain the linear relationship of node importance and node propagation importance.Concrete grammar comprises as follows:
A. initialization: select a node as the node of R state;
B. the SIR carrying out 10 time steps propagates, and obtains the ratio that I state and R state node account for all nodes in network;
C. step b100 time is repeated to the node selected, thus obtain the propagation importance degree S of Multi simulation running posterior nodal point
iR;
D. a is gone to step, other nodes in traverses network.
E. draw linear relationship Fig. 5 of node importance and node propagation importance, wherein horizontal ordinate is node importance, and ordinate is that node propagates importance.
Shown in simulation result as of the present invention in Fig. 4.The linear degree performance of PageRank, LeaderRank and SimRank pitch point importance and propagation importance degree is better.In other words, this algorithm degree of being better than centrality and close to centrality in important node sequence.In the part that in Fig. 4 (c), (d), (e) figure, circle marks, LeaderRank, PageRank, its sir value that algorithm rank value is high are low, and this algorithm linear degree is good, known algorithm is finding in the algorithm that importance is low, more outstanding than other two kinds of algorithms; In addition, in figure in oval mark, this algorithm is in high its dispersion degree of part of node importance lower than other two kinds of algorithms, and known algorithm is more effective at discovery network-critical node.
Shown in simulation result as of the present invention in Fig. 5.The important node ranking results of this algorithm is better than PageRank and LeaderRank performance.Fig. 5 (a), (b), (c) they are this algorithm and the comparing result of PageRank, in figure (a), (b), and the I state ratio S of this algorithm
imaximal value is more than 0.5, and higher than PageRank algorithm, and when the former increases, the latter have dropped, and shows that the propagation degree of depth of this algorithm is higher than the latter, also demonstrates the performance of this network core node of this algorithm picks more superior than PageRank.In figure (c), both difference ratios are more obvious, and the slope of this algorithm, higher than the latter, shows that this algorithm velocity of propagation is higher than the latter, describes this algorithm and is better than PageRank at whole network node importance sorting.In like manner, from the comparing result of Fig. 5 (d), (e), (f) this algorithm and LeaderRank, the maximal value of this algorithm I state and slope are all higher than the latter, illustrate no matter this algorithm is on this server node of discovery or on whole network node importance sorting, is all better than LeaderRank.
Claims (9)
1. an implementation method for social networks responsible consumer discovery, it is characterized in that, described method comprises the steps:
Step 1: by concern relation, information is built to the social networks requiring to analyze and listens to network A
ij, adopt LeaderRank algorithm, calculate the overall importance degree of each node;
Step 2: the similarity adopting the Similarity Measure node between two of definition, as node local interaction;
Step 3: adopt SimRank algorithm, calculate the importance degree of node, it is sorted;
Step 4: adopt SIR propagation model, contrast other classic algorithm, checking validity.
2. the implementation method of a kind of social networks responsible consumer discovery according to claim 1, it is characterized in that, in described step 1, adopt the overall importance degree of LeaderRank Algorithm for Solving node, comprise a background node, LeaderRank algorithm comprises the steps:
A. at original A
ijbasis on, add a background node, be namely interconnected with other nodes in network, obtain new network A
ij';
B. by A
ij' calculate
C. basis
After continuous iteration is extremely stable, calculate
Finally obtain the LR value of each node;
Wherein
for node v
iout-degree,
for the element in basic Google matrix, n is network node sum, does not namely comprise background node, LR
gk () is kth step background node v
gimportance degree.
3. the implementation method of a kind of social networks responsible consumer discovery according to claim 1, is characterized in that, in described step 2, node similarity takes into full account that node enters limit and goes out limit, and calculating formula of similarity is:
Wherein α
ifor node v
ithe set of neighbor node, γ is regulating parameter (0 < γ < 1),
represent node v
iwith node v
jthe node number of common sensing,
represent common and point to node v
iwith node v
jnode number.
4. the implementation method of a kind of social networks responsible consumer discovery according to claim 1, is characterized in that, in described step 3, and integration node local and global characteristics, described SimRank algorithm equation is:
5. the implementation method of a kind of social networks responsible consumer discovery according to claim 1, it is characterized in that in step 4, is the validity adopting SIR propagation model verification algorithm.
6. the implementation method of a kind of social networks responsible consumer discovery according to claim 4, is characterized in that: it is more that the algorithm of employing meets the neighbor node number be connected with node, and the importance degree of node is higher.
7. the implementation method that finds of a kind of social networks responsible consumer according to claim 4, is characterized in that: the algorithm of employing meet node between the power that influences each other difference, the influence power of a side to the opposing party that neighbor node number is many is larger; Meet in real network, when common good friend's number of two people is consistent, the few side of good friend's number to think a side that the opposing party and its relation can be more than good friend's number think the other side and its relation more intimate.
8. the implementation method that finds of a kind of social networks responsible consumer according to claim 4, is characterized in that: the algorithm of employing meets node right similarity when being 0, still has interaction between node.
9. the implementation method of a kind of social networks responsible consumer discovery according to claim 4, is characterized in that: described method is applied to social networks and pays close attention in the network of relation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510732810.0A CN105335892A (en) | 2015-10-30 | 2015-10-30 | Realization method for discovering important users of social network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510732810.0A CN105335892A (en) | 2015-10-30 | 2015-10-30 | Realization method for discovering important users of social network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105335892A true CN105335892A (en) | 2016-02-17 |
Family
ID=55286403
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510732810.0A Pending CN105335892A (en) | 2015-10-30 | 2015-10-30 | Realization method for discovering important users of social network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105335892A (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105956925A (en) * | 2016-04-23 | 2016-09-21 | 时趣互动(北京)科技有限公司 | Method and device for discovering important users on the basis of spreading networks |
CN106096075A (en) * | 2016-05-25 | 2016-11-09 | 中山大学 | A kind of message propagation model based on social networks |
CN106127590A (en) * | 2016-06-21 | 2016-11-16 | 重庆邮电大学 | A kind of information Situation Awareness based on node power of influence and propagation management and control model |
CN106330534A (en) * | 2016-08-19 | 2017-01-11 | 上海电机学院 | Link prediction method on weighted network based on Benefit Ranks |
CN106529562A (en) * | 2016-09-09 | 2017-03-22 | 浙江工业大学 | OSS (Open Source software) project developer prediction method based on Email networks |
CN106789338A (en) * | 2017-01-18 | 2017-05-31 | 北京航空航天大学 | A kind of method that key person is found in the extensive social networks of dynamic |
CN106844697A (en) * | 2017-01-25 | 2017-06-13 | 中国矿业大学 | It is a kind of that tracking is propagated based on the potential social network information for propagating collection |
CN107423743A (en) * | 2017-03-20 | 2017-12-01 | 重庆邮电大学 | The dynamic network state evolution method for visualizing of introduced feature component similarity |
CN109034562A (en) * | 2018-07-09 | 2018-12-18 | 中国矿业大学 | A kind of social networks node importance appraisal procedure and system |
CN109065179A (en) * | 2018-08-22 | 2018-12-21 | 昆明理工大学 | Dynamic Simulation Method when a kind of sky of disease infectious process |
CN109617871A (en) * | 2018-12-06 | 2019-04-12 | 西安电子科技大学 | Network node immunization method based on community structure information and threshold value |
CN111934915A (en) * | 2020-07-17 | 2020-11-13 | 合肥本源量子计算科技有限责任公司 | Network node sequencing display method and device |
CN112148991A (en) * | 2020-10-16 | 2020-12-29 | 重庆理工大学 | Social network node influence recommendation method for fusion degree discount and local node |
CN112612968A (en) * | 2020-12-17 | 2021-04-06 | 北京理工大学 | Link recommendation method in dynamic social network based on long-term income |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103116611A (en) * | 2013-01-25 | 2013-05-22 | 西安市烟草专卖局 | Social network opinion leader identification method |
CN104008165A (en) * | 2014-05-29 | 2014-08-27 | 华东师范大学 | Club detecting method based on network topology and node attribute |
CN104598605A (en) * | 2015-01-30 | 2015-05-06 | 福州大学 | Method for user influence evaluation in social network |
-
2015
- 2015-10-30 CN CN201510732810.0A patent/CN105335892A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103116611A (en) * | 2013-01-25 | 2013-05-22 | 西安市烟草专卖局 | Social network opinion leader identification method |
CN104008165A (en) * | 2014-05-29 | 2014-08-27 | 华东师范大学 | Club detecting method based on network topology and node attribute |
CN104598605A (en) * | 2015-01-30 | 2015-05-06 | 福州大学 | Method for user influence evaluation in social network |
Cited By (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105956925B (en) * | 2016-04-23 | 2021-07-02 | 时趣互动(北京)科技有限公司 | Important user discovery method and device based on propagation network |
CN105956925A (en) * | 2016-04-23 | 2016-09-21 | 时趣互动(北京)科技有限公司 | Method and device for discovering important users on the basis of spreading networks |
CN106096075B (en) * | 2016-05-25 | 2019-05-31 | 中山大学 | A kind of construction method of the message propagation model based on social networks |
CN106096075A (en) * | 2016-05-25 | 2016-11-09 | 中山大学 | A kind of message propagation model based on social networks |
CN106127590A (en) * | 2016-06-21 | 2016-11-16 | 重庆邮电大学 | A kind of information Situation Awareness based on node power of influence and propagation management and control model |
CN106330534A (en) * | 2016-08-19 | 2017-01-11 | 上海电机学院 | Link prediction method on weighted network based on Benefit Ranks |
CN106529562A (en) * | 2016-09-09 | 2017-03-22 | 浙江工业大学 | OSS (Open Source software) project developer prediction method based on Email networks |
CN106789338A (en) * | 2017-01-18 | 2017-05-31 | 北京航空航天大学 | A kind of method that key person is found in the extensive social networks of dynamic |
CN106789338B (en) * | 2017-01-18 | 2020-10-30 | 北京航空航天大学 | Method for discovering key people in dynamic large-scale social network |
CN106844697A (en) * | 2017-01-25 | 2017-06-13 | 中国矿业大学 | It is a kind of that tracking is propagated based on the potential social network information for propagating collection |
CN106844697B (en) * | 2017-01-25 | 2019-07-23 | 中国矿业大学 | It is a kind of that tracking is propagated based on the potential social network information for propagating collection |
CN107423743B (en) * | 2017-03-20 | 2020-11-17 | 重庆邮电大学 | Dynamic network state evolution visualization method introducing feature component similarity |
CN107423743A (en) * | 2017-03-20 | 2017-12-01 | 重庆邮电大学 | The dynamic network state evolution method for visualizing of introduced feature component similarity |
CN109034562A (en) * | 2018-07-09 | 2018-12-18 | 中国矿业大学 | A kind of social networks node importance appraisal procedure and system |
CN109034562B (en) * | 2018-07-09 | 2021-07-23 | 中国矿业大学 | Social network node importance evaluation method and system |
CN109065179A (en) * | 2018-08-22 | 2018-12-21 | 昆明理工大学 | Dynamic Simulation Method when a kind of sky of disease infectious process |
CN109065179B (en) * | 2018-08-22 | 2021-10-22 | 昆明理工大学 | Space-time dynamic simulation method for disease infection process |
CN109617871A (en) * | 2018-12-06 | 2019-04-12 | 西安电子科技大学 | Network node immunization method based on community structure information and threshold value |
CN111934915A (en) * | 2020-07-17 | 2020-11-13 | 合肥本源量子计算科技有限责任公司 | Network node sequencing display method and device |
CN112148991A (en) * | 2020-10-16 | 2020-12-29 | 重庆理工大学 | Social network node influence recommendation method for fusion degree discount and local node |
CN112612968A (en) * | 2020-12-17 | 2021-04-06 | 北京理工大学 | Link recommendation method in dynamic social network based on long-term income |
CN112612968B (en) * | 2020-12-17 | 2024-04-09 | 北京理工大学 | Link recommendation method in dynamic social network based on long-term benefits |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105335892A (en) | Realization method for discovering important users of social network | |
CN106875281B (en) | Social network node mining activation method based on greedy subgraph | |
Herrero | Self-avoiding walks on scale-free networks | |
CN107276793B (en) | Node importance measurement method based on probability jump random walk | |
CN102411687B (en) | Deep learning detection method of unknown malicious codes | |
CN105761153A (en) | Implementation method for discovering important users of weighting network | |
CN104134159A (en) | Method for predicting maximum information spreading range on basis of random model | |
CN104462190A (en) | On-line position prediction method based on mass of space trajectory excavation | |
CN103116611A (en) | Social network opinion leader identification method | |
CN104123279A (en) | Clustering method for keywords and device | |
CN112446634B (en) | Method and system for detecting influence maximization node in social network | |
CN103530402A (en) | Method for identifying microblog key users based on improved Page Rank | |
CN104537096A (en) | Microblog message influence measuring method based on microblog message propagation tree | |
WO2016090877A1 (en) | Generalized maximum-degree random walk graph sampling algorithm | |
CN105447565A (en) | On-chip network mapping method based on discrete bat algorithm | |
CN105162654A (en) | Link prediction method based on local community information | |
CN110705045A (en) | Link prediction method for constructing weighting network by using network topological characteristics | |
CN109949174A (en) | A kind of isomery social network user entity anchor chain connects recognition methods | |
CN102819611B (en) | Local community digging method of complicated network | |
CN105869054A (en) | Three-degree influence principle-based social network influence maximizing method | |
CN102915369A (en) | Method for ranking web pages on basis of hyperlink source analysis | |
CN102708277B (en) | Snow depth Based Inverse Design Method based on ant group algorithm | |
CN105302823A (en) | Overlapped community parallel discovery method and system | |
CN110162716A (en) | A kind of influence power community search method and system based on community's retrieval | |
CN113409576A (en) | Bayesian network-based traffic network dynamic prediction method and 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 | ||
CB03 | Change of inventor or designer information | ||
CB03 | Change of inventor or designer information |
Inventor after: Gu Yiran Inventor after: Zhu Ziyan Inventor after: Meng Fanrong Inventor before: Zhu Ziyan Inventor before: Gu Yiran Inventor before: Meng Fanrong |
|
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160217 |