CN105159922A - Label propagation algorithm-based posting data-oriented parallelized community discovery method - Google Patents
Label propagation algorithm-based posting data-oriented parallelized community discovery method Download PDFInfo
- Publication number
- CN105159922A CN105159922A CN201510469289.6A CN201510469289A CN105159922A CN 105159922 A CN105159922 A CN 105159922A CN 201510469289 A CN201510469289 A CN 201510469289A CN 105159922 A CN105159922 A CN 105159922A
- Authority
- CN
- China
- Prior art keywords
- sender
- consignment
- value
- label
- addressee
- 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.)
- Granted
Links
Classifications
-
- 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
-
- 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
- G06F16/951—Indexing; Web crawling techniques
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a label propagation algorithm-based posting data-oriented parallelized community discovery method. The method comprises: step S1: preprocessing posting data and structuring the posting data into text data according to a set format; step S2: integrating posting information among nodes in the text data, standardizing weight values of directed edges among the nodes, and finally constructing a posting directed weighted relational network model in the form of an adjacency table; step S3: by utilizing an improved label propagation algorithm, performing parallelized mining on a community structure in a posting network by applying a MapReduce frame; and step S4: analyzing the community structure obtained in the step S3 and discovering a community in the posting network. Compared to the prior art, the method has the characteristics that the expansibility and operational efficiency of a conventional label propagation algorithm are improved and the effect of mining the community in the posting network accurately and efficiently is finally achieved.
Description
Technical field
The present invention relates to a kind of method building consignment network based on consignment data, especially relate to a kind of based on the parallelization Combo discovering method of label propagation algorithm towards consignment data.
Background technology
The research origin of social network analysis, in early 1920s, lays particular emphasis on the relation between research social entity, such as: the interchange of group membership inside, and the trade between country, or the economic transaction between company.Along with the fast development of information, social networks complexity is increasing, no matter network manager or network research personnel, all wishes to have social networks structure to be familiar with clearly.Community mining is to understanding social networks structure important in inhibiting, the discovery of community structure has very important theory significance and practical value for analysis of networks topology, network functionality analysis and network behavior prediction, be widely used in the field such as social network and biological net, be now widely used in multiple field such as social networks, terroristic organization's identification.
First, community discovery algorithm based on cluster often only considers the attribute information of node, cause the useful information (weights as limit) ignoring other, and its needs an input parameter given in advance number of corporations (in the network), the accuracy causing corporations to divide is not high.Secondly, consider based on label pass-algorithm without any need for input parameter, and have linear time complexity, speed of convergence is very fast, and the degree of accuracy excavated is also higher, is suitable for corporations in large scale network and excavates.Finally, due to the fast development of computer technology and Internet technology, the ability that people obtain data constantly strengthens, the network size of Water demand also rises to the scale of 100 ten thousand to millions from original tens to a hundreds of node, cause non-distributed algorithm to be no longer applicable to community discovery in fairly large network.And the very applicable process large-scale data of MapReduce Computational frame in Hadoop platform, therefore in community mining algorithm, MapReduce Computational frame is introduced, community discovery in the extensive consignment network utilizing Distributed Calculation to solve is a realistic plan.
Summary of the invention
Object of the present invention be exactly in order to overcome above-mentioned prior art exist defect and provide a kind of based on the parallelization Combo discovering method of label propagation algorithm towards consignment data, constructing on consignment relational network model basis, utilize MapReduce distributed computing framework, improve extendability and the operational efficiency of conventional labels propagation algorithm, final realization excavates corporations in consignment network accurately and efficiently.
Object of the present invention can be achieved through the following technical solutions:
Based on the parallelization Combo discovering method of label propagation algorithm towards consignment data, comprising:
Step S1: pre-service consignment data, turns to text data according to setting format structure;
Step S2: consignment contact information between comprehensive text data interior joint, the weights of directed edge between standardization node, are finally built into the oriented relational network model of having the right of consignment with adjacency list form;
Step S3: utilize the label propagation algorithm improved, uses the community structure in MapReduce framework parallelization excavation consignment network;
Step S4: the analyzing step S3 community structure obtained, finds corporations in consignment network.
Described text data is uploaded in the HDFS (HadoopDistributedFileSystem) of Hadoop platform and stores and process.
Described step S1 is specially: for every bar consignment data, extract sender's name, sender telephone number, addressee's name, addressee's telephone number respectively, described sender's name, sender telephone number, addressee's name, addressee's telephone number correspond to four column informations of notebook data of often composing a piece of writing.
Described step S2 is specially:
201: for each sender, obtain logistics between this sender and other addressees and to come and go the adjacency list of frequency, and standardization is carried out to adjacency list;
202: next sender and addressee are flowed to any existence, add up them and be designated as shared transmission neighbours number respectively as corresponding during sender the quantity A that there is identical addressee, this quantity A;
203: next sender and addressee are flowed to any existence, add up them and be designated as shared reception neighbours number respectively as corresponding during addressee the quantity B that there is identical sender, this quantity B;
204: next sender and addressee are flowed to any existence, obtain shared transmission neighbours number between them with share receive neighbours' number and value, and should be worth as the shared neighbours' number between this sender and addressee, and standardization is carried out to shared neighbours' number;
205: the shared neighbours' number obtained in the weights of adjacency list step 201 obtained and step 204 obtains after being added in the ratio of α: 1-α to be considered post part frequency and jointly send neighbours' number and the common directed edge weights receiving neighbours' number simultaneously, and upgrade adjacency list, wherein, 0 < α < 1.
The label propagation algorithm of described improvement adopts the mode of successive ignition, and one time iterative process is specially:
301: the unique sign ID adding corresponding sender's node in the ending of the adjacency list of step S2 acquisition, as sender's node label Label, completes init Tag;
302: the adjacency list according to band node label exports multiple <key, value> form key-value pair, is divided into sender's key-value pair and addressee's key-value pair;
303: the key-value pair obtaining identical key value, travel through each value, first the value obtaining sender key-value pair is used for the value of the adjacency list representing this key value, and be stored in variable adjacent, secondly, for the value of addressee's key-value pair, weighted value sum under statistics Different L abel, and the node label NewLabel of this key value is upgraded according to the proportion of Different L abel;
304: NewLabel is added to adjacent ending place, export a new <key, value> form key-value pair, and upgrade the label of adjacency list, the community structure in consignment network is corresponding with the adjacency list containing label.
The stopping criterion for iteration of the label propagation algorithm of described improvement comprises: the node label that twice, front and back iterative process is greater than setting number percent does not change or reaches the iterations of setting.
Described setting number percent is 90%.
The iterations of described setting is 20 ~ 30 times.
Described step S4 is specially: the adjacency list obtained according to step S3, is considered as same corporations by the node of same label, thus finds corporations in consignment network.
Compared with prior art, the present invention has the following advantages:
1) prior art mainly excavates corporations based on uniprocessor algorithm, be not suitable for corporations in large scale network to excavate, the present invention is based on consignment data to build the method for consignment network, in consignment network, adopt parallel label propagation algorithm simultaneously, to excavate corporations in consignment network accurately and efficiently, be specially adapted to the excavation of large scale network, excavate corporations compared to conventional individual algorithm, the superiority of method provided by the present invention is fairly obvious.
2) in the weights calculating consignment network edge, the index in 3 is considered: 1, the logistics contact frequency of consignment both sides; 2, consignment both sides are added up respectively as the quantity that there is identical addressee corresponding during sender; 3, add up consignment both sides respectively as the quantity that there is identical sender corresponding during addressee, the weights on all limits in last the present invention these 3 index calculate networks comprehensive, thus excavation precision and accuracy are provided.
3) the inventive method is without any need for input parameter, and has linear time complexity, and speed of convergence is very fast, is suitable for corporations in large scale network and excavates.
4) in conjunction with MapReduce distributed computing framework, the text data of reaction consignment data is uploaded in the HDFS of Hadoop cluster and stores and process, improve extendability and the time efficiency of algorithm.
Accompanying drawing explanation
Fig. 1 is the overall flow figure of the inventive method;
Fig. 2 is the process flow diagram based on consignment data construct consignment relational network model;
Fig. 3 is the process flow diagram adopting the label propagation algorithm parallelization improved to excavate corporations.
Embodiment
Below in conjunction with the drawings and specific embodiments, the present invention is described in detail.The present embodiment is implemented premised on technical solution of the present invention, give detailed embodiment and concrete operating process, but protection scope of the present invention is not limited to following embodiment.
As shown in Figure 1, a kind of being divided into towards the parallelization Combo discovering method of consignment data based on label propagation algorithm builds consignment relational network model stage and excavation phase, specific as follows:
Step S1: pre-service consignment data, turns to text data according to setting format structure, and text data is uploaded in the HDFS of Hadoop cluster and stores and process.Be specially:
For every bar consignment data, extract sender's name, sender telephone number, addressee's name, addressee's telephone number respectively, sender's name, sender telephone number, addressee's name, addressee's telephone number correspond to four column informations of notebook data of often composing a piece of writing.
Step S2: consignment contact information between comprehensive text data interior joint, the weights of directed edge between standardization node, are finally built into the oriented relational network model of having the right of consignment with adjacency list form, and are uploaded in HDFS.As shown in Figure 2, be specially:
201: for each sender, obtain logistics between this sender and other addressees and to come and go the adjacency list of frequency, and standardization is carried out to adjacency list.Illustrate below:
1) first, based on MapReduce Computational frame, HDFS is stored in and text data after standardization in Map stage by row read step S1, the combination of its name and telephone number is used uniquely to indicate ID as it to sender and addressee respectively, export <key, value> form key-value pair, wherein key is sender ID, value is addressee ID.
2), under the Reduce stage obtains identical key value, namely in identical sender's situation, add up this sender and different addressee's logistics and to come and go frequency.Final only consider that logistics between this sender and other addressees is come and gone the adjacency list of frequency for each sender obtains one.
3) secondly, according to the adjacency list of each sender, setting frequency (rule of thumb getting 500 times in the present embodiment) is greater than when this sender sends express delivery frequency, then can judge that this sender is as logistics terminal or be the situation such as Taobao seller, therefore need the adjacency list of leaving out this sender, from the adjacency list of other senders, leave out this sender's node simultaneously.
4) last, according to the adjacency list of the new all senders produced, the statistics logistics maximum sender of contact frequency and addressee, if maximum contact number of times is Max, utilize Max to carry out the adjacency list of all senders of standardization: suppose certain sender adjacency list [S tR
1: C
1tR
2: C
2... tR
k: C
k], wherein t be separator, S is that Sender writes a Chinese character in simplified form, represent sender, R is that Receiver writes a Chinese character in simplified form, represent addressee, C is that Count writes a Chinese character in simplified form, and subscript k is the serial number of addressee and corresponding number of times, represent number of times, the addressee (R come and gone there being logistics with it
1, R
2and R
kdeng) contact number of times (C
1, C
2and C
kdeng) divided by Max, finally obtain the adjacency list after this sender's standardization, namely [S tR
1: W
1tR
2: W
2... tR
k: W
k], wherein, W
k=C
k/ Max.
202: try to achieve and share transmission neighbours number: flow to next sender and addressee to any existence, add up they exist identical addressee quantity A respectively as correspondence during sender, this quantity A is designated as to share and sends neighbours' number.Illustrate below:
1) first, under MapReduce Computational frame, read 1 in the Map stage) in each sender adjacency list [S tR
1: W
1tR
2: W
2... tR
k: W
k], export multiple <key, value> form key-value pair: <S ,+R
1tR
2... tR
k> (+in order to distinguish <key below, value> key-value pair) and <R
1, S tR
2... tR
k>, <R
2, S tR
1... tR
k> ..., <R
k, S tR
1... tR
k-1> etc.
2) <key of identical key value is obtained in the Reduce stage, value> key-value pair, travel through each value, first the value of band "+" is obtained, after being used " t " to be divided into array, these neighbor users are stored in a HashSet data structure set_key by the addressee that in array, element is current key user when being sender.Secondly, “ t is used to each value not with "+" remaining " be divided into array and resolve, result to be stored in the map of a HashMap data structure (key of map is first element of array after " t " divides, value be one for depositing the HashSet structure of other elements of array).Finally, travel through this map, seek common ground to value and the set_key of each element in map, to be the key value of this element and the key of current Reduce send neighbours' number respectively as shared during sender for the size of common factor.
203: try to achieve and share reception neighbours number: flow to next sender and addressee to any existence, add up they exist identical sender quantity B respectively as correspondence during addressee, this quantity B is designated as to share and receives neighbours' number.Illustrate below:
First, according to the adjacency list of sender each in step 201 [S tR
1: W
1tR
2: W
2... tR
k: W
k], for each addressee is established to the inverted index [R of sender
1tS
ltS
p... tS
n], subscript l, p, n represent down the sequence number of the sender after row; Secondly, be analogous to step 202 solution procedure, obtain any two senders and addressee having logistics to come and go, add up them respectively as shared reception neighbours number during addressee.
204: next sender and addressee are flowed to any existence, obtain shared transmission neighbours number between them with share receive neighbours' number and value, should and be worth as the shared neighbours' number between this sender and addressee, and try to achieve the maximal value sharing neighbours' number in whole network, with standardization each existing sender's node of logistics contact and shared neighbours' number of recipient node.
205: the shared neighbours' number obtained in the weights of adjacency list step 201 obtained and step 204 obtains after being added in the ratio of α: 1-α to be considered post part frequency and jointly send neighbours' number and the common directed edge weights receiving neighbours' number simultaneously, namely in adjacency list, the weights on limit account for anharmonic ratio example for α, and the anharmonic ratio example that accounts for jointly sending neighbours' number and the common neighbours of reception number is 1-α, wherein, 0 < α < 1, with new directed edge right value update adjacency list, the adjacency list newly produced is uploaded in HDFS.
More than complete the data processing building the consignment relational network model stage, as shown in Figure 2.Carry out the data processing of excavation phase below, as shown in Figure 3.
Step S3: utilize the label propagation algorithm improved, uses the community structure in MapReduce framework parallelization excavation consignment network.
The label propagation algorithm improved adopts the mode of successive ignition, and one time iterative process is specially:
301: the ending of adjacency list obtained in step S2 adds unique signs ID of corresponding sender's node, as sender's node label Label, completes init Tag, corresponding be with the adjacency list of node label be expressed as [S tR
1: W
1tR
2: W
2... tR
k: W
ktLabel].
In the 302:Map stage, the adjacency list according to band node label exports multiple <key, value> form key-value pair, is divided into sender's key-value pair <S ,+R
1: W
1tR
2: W
2... tR
k: W
k> (+in order to distinguish the <key produced below, value> key-value pair) and addressee's key-value pair <R
1, Label tW
1>, <R
2, Label tW
2> ..., <R
k,+Label tW
k>.
303: in the Reduce stage, obtain the <key of identical key value, value> key-value pair, travel through each value, first the value (being namely with the value of "+") obtaining sender key-value pair is used for the value of the adjacency list representing this key value, and be stored in variable adjacent, secondly, for the value (value not with "+") of addressee's key-value pair, weighted value sum under statistics Different L abel, and the node label NewLabel of this key value is upgraded according to the proportion of Different L abel, wherein, Label proportion is larger, the label of current key node more may upgrade Label for this reason.
304: the label NewLabel newly produced by key node adds adjacent ending place to, export a new <key, value> form key-value pair, i.e. <S, R
1: W
1tR
2: W
2... tR
k: W
ktNewLabel>, and upgrade the label of adjacency list, the community structure in consignment network is corresponding with the adjacency list containing label.
The stopping criterion for iteration of the label propagation algorithm improved comprises following two kinds: 1, each node label is basicly stable, namely the node label that before and after, twice iterative process is greater than setting number percent does not change, wherein, setting number percent in the present embodiment is 90%, 2, the iterations of setting is reached, generally get 20 ~ 30 times, in the present embodiment, get 25 times.
Step S4: the analyzing step S3 community structure obtained, finds corporations in consignment network, and result is stored in HDFS.Be specially:
According to the adjacency list that step S3 obtains, the node of same label is considered as same corporations, thus finds corporations in consignment network.
To sum up, building the consignment relational network model stage is process of data preprocessing, excavation phase iterative process, iterative process is based on the distributed form of unit label propagation algorithm implementation algorithm, simultaneously, due to the singularity of the consignment data of logistics, this patent considers the index in 3 in the weights calculating consignment network edge: 1, the logistics contact frequency of consignment both sides; 2, consignment both sides are added up respectively as the quantity that there is identical addressee corresponding during sender; 3, add up consignment both sides respectively as the quantity that there is identical sender corresponding during addressee, the weights on all limits in last the present invention these 3 index calculate networks comprehensive, thus realize excavating corporations in consignment network accurately and efficiently.
Claims (9)
1., based on the parallelization Combo discovering method of label propagation algorithm towards consignment data, it is characterized in that, comprising:
Step S1: pre-service consignment data, turns to text data according to setting format structure;
Step S2: consignment contact information between comprehensive text data interior joint, the weights of directed edge between standardization node, are finally built into the oriented relational network model of having the right of consignment with adjacency list form;
Step S3: utilize the label propagation algorithm improved, uses the community structure in MapReduce framework parallelization excavation consignment network;
Step S4: the analyzing step S3 community structure obtained, finds corporations in consignment network.
2. according to claim 1ly it is characterized in that based on the parallelization Combo discovering method of label propagation algorithm towards consignment data, described text data is uploaded in the HDFS of Hadoop cluster and stores and process.
3. according to claim 1 based on the parallelization Combo discovering method of label propagation algorithm towards consignment data, it is characterized in that, described step S1 is specially: for every bar consignment data, extract sender's name, sender telephone number, addressee's name, addressee's telephone number respectively, described sender's name, sender telephone number, addressee's name, addressee's telephone number correspond to four column informations of notebook data of often composing a piece of writing.
4. according to claim 1 based on the parallelization Combo discovering method of label propagation algorithm towards consignment data, it is characterized in that, described step S2 is specially:
201: for each sender, obtain logistics between this sender and other addressees and to come and go the adjacency list of frequency, and standardization is carried out to adjacency list;
202: next sender and addressee are flowed to any existence, add up them and be designated as shared transmission neighbours number respectively as corresponding during sender the quantity A that there is identical addressee, this quantity A;
203: next sender and addressee are flowed to any existence, add up them and be designated as shared reception neighbours number respectively as corresponding during addressee the quantity B that there is identical sender, this quantity B;
204: next sender and addressee are flowed to any existence, obtain shared transmission neighbours number between them with share receive neighbours' number and value, and should be worth as the shared neighbours' number between this sender and addressee, and standardization is carried out to shared neighbours' number;
205: the shared neighbours' number obtained in the weights of adjacency list step 201 obtained and step 204 obtains after being added in the ratio of α: 1-α to be considered post part frequency and jointly send neighbours' number and the common directed edge weights receiving neighbours' number simultaneously, and upgrade adjacency list, wherein, 0 < α < 1.
5. according to claim 1ly it is characterized in that based on the parallelization Combo discovering method of label propagation algorithm towards consignment data, the label propagation algorithm of described improvement adopts the mode of successive ignition, and one time iterative process is specially:
301: the unique sign ID adding corresponding sender's node in the ending of the adjacency list of step S2 acquisition, as sender's node label Label, completes init Tag;
302: the adjacency list according to band node label exports multiple <key, value> form key-value pair, is divided into sender's key-value pair and addressee's key-value pair;
303: the key-value pair obtaining identical key value, travel through each value, first the value obtaining sender key-value pair is used for the value of the adjacency list representing this key value, and be stored in variable adjacent, secondly, for the value of addressee's key-value pair, weighted value sum under statistics Different L abel, and the node label NewLabel of this key value is upgraded according to the proportion of Different L abel;
304: NewLabel is added to adjacent ending place, export a new <key, value> form key-value pair, and upgrade the label of adjacency list, the community structure in consignment network is corresponding with the adjacency list containing label.
6. according to claim 5 based on the parallelization Combo discovering method of label propagation algorithm towards consignment data, it is characterized in that, the stopping criterion for iteration of the label propagation algorithm of described improvement comprises: the node label that twice, front and back iterative process is greater than setting number percent does not change or reaches the iterations of setting.
7. according to claim 6ly it is characterized in that based on the parallelization Combo discovering method of label propagation algorithm towards consignment data, described setting number percent is 90%.
8. according to claim 6ly it is characterized in that based on the parallelization Combo discovering method of label propagation algorithm towards consignment data, the iterations of described setting is 20 ~ 30 times.
9. according to claim 5 based on the parallelization Combo discovering method of label propagation algorithm towards consignment data, it is characterized in that, described step S4 is specially: the adjacency list obtained according to step S3, is considered as same corporations by the node of same label.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510469289.6A CN105159922B (en) | 2015-08-03 | 2015-08-03 | The parallelization Combo discovering method towards consignment data based on label propagation algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510469289.6A CN105159922B (en) | 2015-08-03 | 2015-08-03 | The parallelization Combo discovering method towards consignment data based on label propagation algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105159922A true CN105159922A (en) | 2015-12-16 |
| CN105159922B CN105159922B (en) | 2018-08-24 |
Family
ID=54800779
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510469289.6A Expired - Fee Related CN105159922B (en) | 2015-08-03 | 2015-08-03 | The parallelization Combo discovering method towards consignment data based on label propagation algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105159922B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109993477A (en) * | 2018-01-03 | 2019-07-09 | 阿里巴巴集团控股有限公司 | Label, querying method, barcode scanning gun, equipment, the medium of logistics task |
| CN112990633A (en) * | 2019-12-18 | 2021-06-18 | 菜鸟智能物流控股有限公司 | Index data generation method, logistics cost simulation method, equipment and storage medium |
| CN113449112A (en) * | 2020-03-24 | 2021-09-28 | 顺丰科技有限公司 | Abnormal consignment behavior identification method and device, computer equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102663108A (en) * | 2012-04-16 | 2012-09-12 | 南京大学 | Medicine corporation finding method based on parallelization label propagation algorithm for complex network model |
| US20120290293A1 (en) * | 2011-05-13 | 2012-11-15 | Microsoft Corporation | Exploiting Query Click Logs for Domain Detection in Spoken Language Understanding |
-
2015
- 2015-08-03 CN CN201510469289.6A patent/CN105159922B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120290293A1 (en) * | 2011-05-13 | 2012-11-15 | Microsoft Corporation | Exploiting Query Click Logs for Domain Detection in Spoken Language Understanding |
| CN102663108A (en) * | 2012-04-16 | 2012-09-12 | 南京大学 | Medicine corporation finding method based on parallelization label propagation algorithm for complex network model |
Non-Patent Citations (2)
| Title |
|---|
| MICHELE COVELL 等: "Efficient and Accurate Label Propagation on Dynamic Graphs and Label Sets", 《INTERNATIONAL JOURNAL ON ADVANCES IN NETWORKS AND SERVICES》 * |
| 董哲 等: "基于链路标签传播的重叠社团发现算法", 《计算机工程与设计》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109993477A (en) * | 2018-01-03 | 2019-07-09 | 阿里巴巴集团控股有限公司 | Label, querying method, barcode scanning gun, equipment, the medium of logistics task |
| CN109993477B (en) * | 2018-01-03 | 2023-04-07 | 阿里巴巴集团控股有限公司 | Logistics task marking and inquiring method, code scanning gun, equipment and medium |
| CN112990633A (en) * | 2019-12-18 | 2021-06-18 | 菜鸟智能物流控股有限公司 | Index data generation method, logistics cost simulation method, equipment and storage medium |
| CN112990633B (en) * | 2019-12-18 | 2024-04-05 | 菜鸟智能物流控股有限公司 | Index data generation method, logistics cost simulation method, equipment and storage medium |
| CN113449112A (en) * | 2020-03-24 | 2021-09-28 | 顺丰科技有限公司 | Abnormal consignment behavior identification method and device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105159922B (en) | 2018-08-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10846052B2 (en) | Community discovery method, device, server and computer storage medium | |
| CN103678671B (en) | A kind of dynamic community detection method in social networks | |
| Gregori et al. | Parallel k-clique community detection on large-scale networks | |
| CN105512242B (en) | A kind of parallel recommendation method based on social network structure | |
| CN102810113B (en) | A kind of mixed type clustering method for complex network | |
| CN105279187A (en) | Edge clustering coefficient-based social network group division method | |
| CN104995870A (en) | Multi-objective server placement determination | |
| Liu et al. | Efficient mining of large maximal bicliques | |
| CN104268271A (en) | Interest and network structure double-cohesion social network community discovering method | |
| WO2014107988A1 (en) | Method and system for discovering and analyzing micro-blog user group structure | |
| CN105893381A (en) | Semi-supervised label propagation based microblog user group division method | |
| CN105335438A (en) | Local shortest loop based social network group division method | |
| CN105069290A (en) | Parallelization critical node discovery method for postal delivery data | |
| CN104700311B (en) | A kind of neighborhood in community network follows community discovery method | |
| CN105159922A (en) | Label propagation algorithm-based posting data-oriented parallelized community discovery method | |
| CN106294805A (en) | Data processing method and device | |
| CN114372133A (en) | Query information question answering method, related device and computer program product | |
| CN111178678B (en) | Network node importance evaluation method based on community influence | |
| CN114153996B (en) | Multi-map attention cooperative geoscience knowledge map updating method and device | |
| CN115965795A (en) | Deep darknet group discovery method based on network representation learning | |
| Zhu et al. | Social sensing of the imbalance of urban and regional development in China through the population migration network around spring festival | |
| CN104462095A (en) | Extraction method and device of common pars of query statements | |
| Kumam et al. | Fixed point theorems on ordered metric spaces through a rational contraction | |
| CN108011735B (en) | Community discovery method and device | |
| Liu et al. | The existence of periodic solutions of higher order nonlinear periodic difference equations |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180824 Termination date: 20210803 |