CN113408090B - Node relation acquisition method based on symbol network and storage medium - Google Patents
Node relation acquisition method based on symbol network and storage medium Download PDFInfo
- Publication number
- CN113408090B CN113408090B CN202110598889.8A CN202110598889A CN113408090B CN 113408090 B CN113408090 B CN 113408090B CN 202110598889 A CN202110598889 A CN 202110598889A CN 113408090 B CN113408090 B CN 113408090B
- Authority
- CN
- China
- Prior art keywords
- node
- nodes
- negative
- similarity
- experiment
- 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
- 238000000034 method Methods 0.000 title claims abstract description 34
- 230000002776 aggregation Effects 0.000 claims abstract description 6
- 238000004220 aggregation Methods 0.000 claims abstract description 6
- 238000007477 logistic regression Methods 0.000 claims abstract description 4
- 238000004364 calculation method Methods 0.000 claims description 26
- 238000002474 experimental method Methods 0.000 claims description 24
- 238000012360 testing method Methods 0.000 claims description 11
- 238000005516 engineering process Methods 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 claims description 3
- 238000013468 resource allocation Methods 0.000 claims description 3
- 201000004216 Posterior amorphous corneal dystrophy Diseases 0.000 claims description 2
- 210000004556 brain Anatomy 0.000 claims description 2
- 238000004891 communication Methods 0.000 claims description 2
- 108700027610 cytoplasmic protein A Proteins 0.000 claims description 2
- 239000000284 extract Substances 0.000 claims description 2
- 230000006872 improvement Effects 0.000 claims description 2
- 230000008569 process Effects 0.000 claims description 2
- 238000005065 mining Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/18—Network design, e.g. design based on topological or interconnect aspects of utility systems, piping, heating ventilation air conditioning [HVAC] or cabling
-
- 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
- G06F2111/00—Details relating to CAD techniques
- G06F2111/02—CAD in a network environment, e.g. collaborative CAD or distributed simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/08—Probabilistic or stochastic CAD
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Geometry (AREA)
- Mathematical Analysis (AREA)
- Health & Medical Sciences (AREA)
- Pure & Applied Mathematics (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computational Mathematics (AREA)
- Computing Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Mathematical Optimization (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a node relation acquisition method and a storage medium based on a symbol network, wherein the node relation acquisition method comprises the following steps: step 1: establishing a social network model, and acquiring the degree and aggregation coefficient of the nodes; step 2: determining PA indexes and affinity between nodes; step 3: determining the probability of potential links between nodes; step 4: determining relevant characteristic attributes of the nodes; step 5: and fusing the attribute characteristics of the nodes, and judging the relationship polarity between the nodes by adopting a logistic regression model. Compared with the prior art, the method has the advantages of effectively realizing node relation acquisition in the symbol network, being high in accuracy and the like.
Description
Technical Field
The invention relates to the technical field of social networks, in particular to a node relation acquisition method based on a symbol network and a storage medium.
Background
The method has the advantages that the relation type prediction of the symbol network is simple, namely, the potential attitudes of a certain user node to other nodes are presumed, the research direction can be used for providing user personalized services for enterprises or individuals, and the method has very important theoretical significance and application value for further researching the topological structure, the functions, the dynamic behaviors and the like of the social network
The relationship between users in the research in the online social network not only comprises a display relationship formed by adding friends or attention to each other, but also comprises an implicit relationship for judging whether the users exist or not from the angles of behavior departure and preference of the users by judging whether the similarity exceeds a given threshold value, and in most existing researches, a negative relationship (namely an untrusted relationship) is directly ignored, and all existing relationship links are defaulting to be positive relationships, but in fact, the importance in the social network is not inferior to the positive relationship.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provide a node relation acquisition method based on a symbol network and a storage medium for effectively realizing node relation acquisition in the symbol network with high accuracy.
The aim of the invention can be achieved by the following technical scheme:
a node relation acquisition method based on a symbol network comprises the following steps:
step 1: establishing a social network model, and acquiring the degree and aggregation coefficient of the nodes;
step 2: determining PA indexes and affinity between nodes;
step 3: determining the probability of potential links between nodes;
step 4: determining relevant characteristic attributes of the nodes;
step 5: and fusing the attribute characteristics of the nodes, and judging the relationship polarity between the nodes by adopting a logistic regression model.
Preferably, the step 1 specifically includes:
abstracting the social network data set into an undirected graph g= (V, E), wherein V represents a set of nodes in the network and E represents a set of connected edges of the network; the non-existent contiguous edges in the network are denoted as (x, y) ∈U-E, where x, y ε V, U represents all possible edges in the network, and the degree and aggregate coefficient attributes of the nodes are obtained.
Preferably, the PA indicator between the nodes in the step 2 is specifically:
where k (x) and k (y) represent the degrees of nodes x and y, respectively.
Preferably, the intimacy between the nodes in the step 2 is specifically:
wherein Γ (x) and Γ (y) are the set of neighbor nodes of node x and node y, respectively; k (k) x and ky The degrees of nodes x and y, respectively; a 1 on the molecule indicates that there is a connected edge between node x and node y.
Preferably, the calculating method of the probability of potential link exists between the nodes in the step 3 is as follows:
preferably, the step 4 specifically includes:
node characteristics, node similarity characteristics and structure balance characteristics of the nodes are determined.
More preferably, the node characteristics include a positive input ratioNegative input ratio->Positive output ratio->Negative output ratio->And PA similarity; the PA similarity is the PA index;
positive input ratioThe calculation method of (1) is as follows:
negative input ratioThe calculation method of (1) is as follows:
positive output ratioThe calculation method of (1) is as follows:
negative output ratioThe calculation method of (1) is as follows:
wherein ,din (u) represents the total degree of ingress of node u; d, d out (u) represents the total degree of egress of node u; and />Respectively representing the positive input degree and the negative input degree of the node u; /> and />The positive and negative output of node u are represented, respectively.
More preferably, the node similarity feature includes positive similarity S + (u, v) and negative similarity S - (u, v) the calculation formulas are respectively:
wherein ,W+ Representing a set of nodes providing positive links to v; w (W) - Is a set of nodes representing passive links to v; sim (u, W) is the similarity between node u and node W;
the calculation formula of the similarity sim (u, w) between the nodes is as follows:
in the formula,e(u,i) and e(w,i) Is a relational tag of links pointing from node u and node w to node I, respectively, I being the set of common neighbor nodes of u and w.
More preferably, the structural balance feature is determined by negative triplet and negative quadruple features extracted from the triplet and quadruple attributes; the negative triplet ratio calculation formula of the nodes u and v is as follows:
wherein W represents the neighbors of node u and node v, w| is the number of common neighbors of node u and node v;
the negative four-tuple ratio calculation formula of the node u and the node v is as follows:
wherein ,represents the total number of all paths traversing path length 3 from node u to node v.
A storage medium having stored therein the symbol network-based node relation acquisition method of any one of the above.
Compared with the prior art, the invention has the following beneficial effects:
the method comprises the steps of obtaining node relations in a symbol network: the node relation acquisition method fully utilizes the topological characteristics and node similarity attributes in the symbol social network, and provides a passive relation mining technology based on the symbol network; because the existing link prediction technology pays less attention to the negative relations in the network, aiming at the problem, the node relation acquisition method in the invention fuses the attribute of the node and the similar characteristics among the nodes, and aims at the potential relation between the positive and negative relations, the characteristics suitable for relation type prediction are explored, the effective judgment of the relation type is realized, and the judgment accuracy is high.
Drawings
FIG. 1 is a flow chart of a node relationship acquisition method of the present invention;
FIG. 2 is a graph showing the comparison of the link prediction experimental AUC values of the symbol network-based passive relation mining method and the reference algorithm of the present invention on 3 data sets in the embodiment of the present invention;
FIG. 3 is a schematic diagram showing the comparison of the F1 value and the AUC value of the symbol network-based passive relation mining method and the reference algorithm relation type prediction experiment according to the present invention on 3 data sets;
FIG. 3 (a) is a diagram showing the comparison of the predicted F1 values; fig. 3 (b) is a graph showing comparison of AUC values of the predicted results.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
A method for acquiring node relation based on a symbol network, the flow of which is shown in figure 1, comprises the following steps:
step 1: establishing a social network model, and acquiring the degree and aggregation coefficient of the nodes;
abstracting the social network data set into an undirected graph g= (V, E), wherein V represents a set of nodes in the network and E represents a set of connected edges of the network; the non-existing connected edges in the network are expressed as (x, y) E U-E, wherein x, y E V and U represent all possible edges in the network, and the degree and the aggregation coefficient attribute of the nodes are obtained;
step 2: determining PA indexes and affinity between nodes;
the PA index between nodes is specifically:
wherein k (x) and k (y) represent the degrees of nodes x and y, respectively;
the intimacy between nodes is specifically:
wherein Γ (x) and Γ (y) are the set of neighbor nodes of node x and node y, respectively; k (k) x and ky The degrees of nodes x and y, respectively; 1 on the molecule represents that a communication edge exists between a node x and a node y;
step 3: determining the probability of potential links between nodes;
the calculation method of the potential link probability between the nodes comprises the following steps:
step 4: determining relevant characteristic attributes of the nodes;
determining node characteristics, node similarity characteristics and structure balance characteristics of the nodes;
the node characteristics include a positive input ratioNegative input ratio->Positive output ratio->Negative output ratio->And PA similarity; the PA similarity is the PA index;
positive input ratioThe calculation method of (1) is as follows:
negative input ratioThe calculation method of (1) is as follows:
positive output ratioThe calculation method of (1) is as follows:
negative output ratioThe calculation method of (1) is as follows:
wherein ,din (u) represents the total degree of ingress of node u; d, d out (u) represents the total degree of egress of node u; and />Respectively representing the positive input degree and the negative input degree of the node u; /> and />Respectively representing the positive output degree and the negative output degree of the node u;
the node similarity features include positive similarity S + (u, v) and negative similarity S - (u, v) the calculation formulas are respectively:
wherein ,W+ Representing a set of nodes providing positive links to v; w (W) - Is a set of nodes representing passive links to v; sim (u, W) is the similarity between node u and node W;
the calculation formula of the similarity sim (u, w) between the nodes is as follows:
in the formula,e(u,i) and e(w,i) Is a relationship label of links pointing from node u and node w to node I, respectively, I is a set of common neighbor nodes of u and w;
the structure balance characteristics are determined by the negative triplet and the negative quadruple characteristics extracted from the triplet attribute and the quadruple attribute; the negative triplet ratio calculation formula of the nodes u and v is as follows:
wherein W represents the neighbors of node u and node v, w| is the number of common neighbors of node u and node v;
the negative four-tuple ratio calculation formula of the node u and the node v is as follows:
wherein ,representing the total number of all paths traversing path length 3 from node u to node v;
step 5: fusing the attribute characteristics of the nodes, judging the relationship polarity between the nodes by adopting a logistic regression model, and deducing the symbol e of a given edge e (u, v) uv Whether it is negative.
The effect of the node relation acquiring method in this embodiment can be further described through the following experiment.
Experimental conditions: the experiment was performed on a Jet Brains PyCharm Community software platform under the hardware Intel (R) Core (TM) i7-8550U [email protected],Windows 10 system.
The experimental contents are as follows: the experiment of the invention is that the method of the invention is adopted to carry out link prediction and relation type prediction on three symbol network data sets of Bitcoin-Alpha, bitcoin-Otc and Slashdot respectively with 5 prior technologies of Common Neighbors (CN) algorithm, adamic-Adar (AA) algorithm, preferential Attachment (PA) algorithm, jaccard algorithm and Resource Allocation (RA) algorithm.
Experiment one: and (5) link prediction experiments.
The proportion of the test set divided by the experiment is 10%, one side is randomly selected from the test set in the experiment every time, then one side is randomly selected from the non-existing data set, then the similarity scores of the two sides are calculated, if the score of the side in the test set is larger than the score of the non-existing side, 1 is added, and if the score of the side in the test set is equal, 0.5 is added, n independent repeated experiments are completed, and an AUC index is used as an evaluation index. The experimental results are shown in FIG. 2. As can be seen from FIG. 2, the method PACD of the present invention is quite obvious in terms of improvement of prediction accuracy compared with other 5 reference algorithms.
Experiment II: and (5) a relation type prediction experiment.
The experiment randomly extracts 10% of data from the original data set as a test set, the rest of the data are used for training the model, and then the effect of the model is evaluated by using the test data by completing training of the model. The whole process is repeated for 10 times, so that the validity of the evaluation result is ensured. Finally, the method provided by the invention is compared and analyzed with 3 existing symbol prediction methods. The experimental results are shown in FIG. 3. As can be seen from fig. 3, the proposed relational type prediction model Ne-LP achieves almost optimal performance on these three data sets, which indicates that the present invention effectively selects suitable network topology attributes and successfully applies relevant social theory to our model, so that the predicted performance is improved to some extent.
The present embodiment also relates to a storage medium in which any one of the above node relation acquisition methods is stored.
While the invention has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions of equivalents may be made and equivalents will be apparent to those skilled in the art without departing from the scope of the invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (2)
1. The node relation acquisition method based on the symbol network is characterized by comprising the following steps of:
step 1: establishing a social network model, and acquiring the degree and aggregation coefficient of the nodes;
step 2: determining PA indexes and affinity between nodes;
step 3: determining the probability of potential links between nodes;
step 4: determining relevant characteristic attributes of the nodes;
step 5: fusing attribute characteristics of the nodes, and judging relationship polarities among the nodes by adopting a logistic regression model;
the step 1 specifically comprises the following steps:
abstracting the social network data set into an undirected graph g= (V, E), wherein V represents a set of nodes in the network and E represents a set of connected edges of the network; the non-existing connected edges in the network are expressed as (x, y) E U-E, wherein x, y E V and U represent all possible edges in the network, and the degree and the aggregation coefficient attribute of the nodes are obtained;
the PA index between the nodes in the step 2 specifically includes:
wherein k (x) and k (y) represent the degrees of nodes x and y, respectively;
the intimacy between the nodes in the step 2 is specifically:
wherein Γ (x) and Γ (y) are the set of neighbor nodes of node x and node y, respectively; k (k) x and ky The degrees of nodes x and y, respectively; 1 on the molecule represents that a communication edge exists between a node x and a node y;
the calculation method of the potential link probability between the nodes in the step 3 comprises the following steps:
the step 4 specifically comprises the following steps:
determining node characteristics, node similarity characteristics and structure balance characteristics of the nodes;
the node characteristics comprise positive input ratioNegative input ratio->Positive output ratio->Negative output ratio->And PA similarity; the PA similarity is the PA index;
positive input ratioThe calculation method of (1) is as follows:
negative input ratioThe calculation method of (1) is as follows:
positive output ratioThe calculation method of (1) is as follows:
negative output ratioThe calculation method of (1) is as follows:
wherein ,din (u) represents the total degree of ingress of node u; d, d out (u) represents the total degree of egress of node u; and />Respectively representing the positive input degree and the negative input degree of the node u; /> and />Respectively representing the positive output degree and the negative output degree of the node u;
the node similarity features comprise positive similarity S + (u, v) and negative similarity S - (u, v) the calculation formulas are respectively:
wherein ,W+ Representing a set of nodes providing positive links to v; w (W) - Is a set of nodes representing passive links to v; sim (u, W) is the similarity between node u and node W;
the calculation formula of the similarity sim (u, w) between the nodes is as follows:
in the formula,e(u,i) and e(w,i) Is a relationship label of links pointing from node u and node w to node I, respectively, I is a set of common neighbor nodes of u and w;
the structure balance characteristics are determined by negative triples and negative quadruple characteristics extracted from the triples and the quadruples; the negative triplet ratio calculation formula of the nodes u and v is as follows:
wherein W represents the neighbors of node u and node v, w| is the number of common neighbors of node u and node v;
the negative four-tuple ratio calculation formula of the node u and the node v is as follows:
wherein ,representing the total number of all paths traversing path length 3 from node u to node v;
the node relation acquisition method is further described through the following experiments:
experimental conditions: the experiment is completed on a Jet Brains PyCharm Community software platform under a hardware Intel (R) Core (TM) i7-8550U [email protected],Windows 10 system;
the experimental contents are as follows: the experiment is an experiment of carrying out link prediction and relation type prediction on three symbol network data sets of Bitcoin-Alpha, bitcoin-Otc and Slassdot respectively by adopting the method and 5 prior technologies of a Common neighbor algorithm, an Adamic-Adar algorithm, a Preferential Attachment algorithm, a Jaccard algorithm and a Resource Allocation algorithm;
experiment one: a link prediction experiment;
the proportion of the test set divided by the experiment is 10%, one side is randomly selected from the test set in the experiment every time, then one side is randomly selected from the non-existing data set, then the similarity scores of the two sides are calculated, if the score of the side in the test set is larger than the score of the non-existing side, 1 is added, and if the scores are equal, 0.5 is added, n independent repeated experiments are completed, and an AUC index is used as an evaluation index; compared with other 5 reference algorithms, the PACD method has obvious improvement on the prediction accuracy;
experiment II: a relation type prediction experiment;
the experiment randomly extracts 10% of data from an original data set to serve as a test set, the rest data are used for training the model, and then the effect of the model is evaluated by using the test data through training the model; the whole process is repeated for 10 times, so that the validity of the evaluation result is ensured; finally, the method provided by the invention is compared and analyzed with 3 existing symbol prediction methods.
2. A storage medium, wherein the storage medium stores the symbol network-based node relation acquisition method as claimed in claim 1.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110598889.8A CN113408090B (en) | 2021-05-31 | 2021-05-31 | Node relation acquisition method based on symbol network and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110598889.8A CN113408090B (en) | 2021-05-31 | 2021-05-31 | Node relation acquisition method based on symbol network and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113408090A CN113408090A (en) | 2021-09-17 |
CN113408090B true CN113408090B (en) | 2023-10-27 |
Family
ID=77675277
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110598889.8A Active CN113408090B (en) | 2021-05-31 | 2021-05-31 | Node relation acquisition method based on symbol network and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113408090B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117669739B (en) * | 2024-01-26 | 2024-05-24 | 中国矿业大学(北京) | Agent-based intelligent negotiation strategy optimization method and system |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105515859A (en) * | 2015-12-01 | 2016-04-20 | 内蒙古工业大学 | Method and system for carrying out community detection to symbol network based on path similarity |
CN106780067A (en) * | 2016-12-14 | 2017-05-31 | 南京工业职业技术学院 | It is a kind of to consider the sign prediction method that node locally marks characteristic |
CN108537569A (en) * | 2018-03-07 | 2018-09-14 | 西北大学 | The advertisement sending method that interpersonal relationships perceives in online social networks |
CN110019653A (en) * | 2019-04-08 | 2019-07-16 | 北京航空航天大学 | A kind of the social content characterizing method and system of fusing text and label network |
CN110334285A (en) * | 2019-07-04 | 2019-10-15 | 仲恺农业工程学院 | Symbolic network community discovery method based on structural balance constraint |
CN111178414A (en) * | 2019-12-20 | 2020-05-19 | 大连民族大学 | Prediction method of edge-connected symbol in symbol network |
CN112214661A (en) * | 2020-10-12 | 2021-01-12 | 西华大学 | Emotional unstable user detection method for conventional video comments |
CN112269923A (en) * | 2020-10-14 | 2021-01-26 | 西华大学 | Network public opinion control method based on structural hole |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101969395B (en) * | 2009-07-28 | 2013-02-27 | 华为技术有限公司 | Method for configuring code, method and system for detecting path and network equipment |
US20140046976A1 (en) * | 2012-08-11 | 2014-02-13 | Guangsheng Zhang | Systems, methods, and user interface for effectively presenting information |
US20140195931A1 (en) * | 2013-01-07 | 2014-07-10 | dotbox, inc. | Validated Product Recommendation System And Methods |
-
2021
- 2021-05-31 CN CN202110598889.8A patent/CN113408090B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105515859A (en) * | 2015-12-01 | 2016-04-20 | 内蒙古工业大学 | Method and system for carrying out community detection to symbol network based on path similarity |
CN106780067A (en) * | 2016-12-14 | 2017-05-31 | 南京工业职业技术学院 | It is a kind of to consider the sign prediction method that node locally marks characteristic |
CN108537569A (en) * | 2018-03-07 | 2018-09-14 | 西北大学 | The advertisement sending method that interpersonal relationships perceives in online social networks |
CN110019653A (en) * | 2019-04-08 | 2019-07-16 | 北京航空航天大学 | A kind of the social content characterizing method and system of fusing text and label network |
CN110334285A (en) * | 2019-07-04 | 2019-10-15 | 仲恺农业工程学院 | Symbolic network community discovery method based on structural balance constraint |
CN111178414A (en) * | 2019-12-20 | 2020-05-19 | 大连民族大学 | Prediction method of edge-connected symbol in symbol network |
CN112214661A (en) * | 2020-10-12 | 2021-01-12 | 西华大学 | Emotional unstable user detection method for conventional video comments |
CN112269923A (en) * | 2020-10-14 | 2021-01-26 | 西华大学 | Network public opinion control method based on structural hole |
Non-Patent Citations (3)
Title |
---|
implicit negative link prediction with a network topology perspective;Bo Zhang, et al;IEEE transactions on computational social systems(early access);1-11 * |
王伟 ; 薛苗苗 ; 刘沫萌.一种面向符号社交网络的负链路预测方法.西安工程大学学报.2021,100-106. * |
社交网络中基于节点关系评估的信息传播影响分析;张亚;中国优秀硕士学位论文全文数据库 基础科学辑;A002-73 * |
Also Published As
Publication number | Publication date |
---|---|
CN113408090A (en) | 2021-09-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP2498440B1 (en) | Configuration method and system of complex network and configuration and management module of server resources | |
CN113821793B (en) | Multi-stage attack scene construction method and system based on graph convolution neural network | |
CN110033097B (en) | Method and device for determining association relation between user and article based on multiple data fields | |
CN110719106B (en) | Social network graph compression method and system based on node classification and sorting | |
CN108881250A (en) | Powerline network security postures prediction technique, device, equipment and storage medium | |
Meng et al. | A method to solve cold-start problem in recommendation system based on social network sub-community and ontology decision model | |
CN112464107B (en) | Social network overlapping community discovery method and device based on multi-label propagation | |
CN112364257B (en) | Knowledge graph-based user group recommendation system and method | |
CN113408090B (en) | Node relation acquisition method based on symbol network and storage medium | |
CN108449311B (en) | Social relationship hiding method based on attack node similarity | |
CN106817390B (en) | User data sharing method and device | |
Patidar et al. | Predicting friends and foes in signed networks using inductive inference and social balance theory | |
Zheng et al. | Jora: Weakly supervised user identity linkage via jointly learning to represent and align | |
CN115686868A (en) | Cross-node-oriented multi-mode retrieval method based on federated hash learning | |
Jiang et al. | SA framework based de-anonymization of social networks | |
Lei et al. | Federated learning over coupled graphs | |
CN111274457B (en) | Network graph segmentation method and storage medium | |
CN116132167B (en) | Multi-protocol botnet detection method oriented to Internet of things | |
CN116992307A (en) | Social network user matching method and device based on graph network characteristic rapid aggregation | |
Sharma et al. | Comparative analysis of different algorithms in link prediction on social networks | |
CN112685614B (en) | Social media robot group rapid detection method | |
CN111444454B (en) | Dynamic community division method based on spectrum method | |
Li et al. | DTCMF: Dynamic trust-based context-aware matrix factorization for collaborative filtering | |
Yarava et al. | An efficient trust inference model in online social networks using fuzzy petri nets | |
Hoang et al. | Cluster-based anonymization of directed graphs |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |