CN107895326A - A kind of community's construction method and device - Google Patents
A kind of community's construction method and device Download PDFInfo
- Publication number
- CN107895326A CN107895326A CN201711227646.3A CN201711227646A CN107895326A CN 107895326 A CN107895326 A CN 107895326A CN 201711227646 A CN201711227646 A CN 201711227646A CN 107895326 A CN107895326 A CN 107895326A
- Authority
- CN
- China
- Prior art keywords
- community
- node
- network
- initial
- preset value
- 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
- 238000010276 construction Methods 0.000 title claims abstract description 54
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 22
- 230000000977 initiatory effect Effects 0.000 claims abstract description 16
- 238000000034 method Methods 0.000 abstract description 11
- 238000010586 diagram Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 7
- 230000015654 memory Effects 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000004069 differentiation Effects 0.000 description 3
- 235000012364 Peperomia pellucida Nutrition 0.000 description 2
- 240000007711 Peperomia pellucida Species 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 230000018199 S phase Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Computing Systems (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Mathematical Physics (AREA)
- Fuzzy Systems (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (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)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of community's construction method and device, wherein, property value corresponding to each node that this method includes being directed in initial community network calculates its initial effects force value, wherein, the property value includes user's enquirement number, question answering number, obtains the number praised number and obtain thanks;Initial effects force value and PageRank algorithms based on each node calculate actual influence force value corresponding to each node;The maximum node of actual influence force value is chosen as core node to form first community with a node in each node from the initial community network, and the core node is marked;Judge that, if being not present, the first community structure is completed with the presence or absence of the adjacent node of first community in the initial community network.The present invention builds Web Community based on the attribute factor of network core node and each node itself, effectively overcomes core node and chooses the problem of fuzzy, improves the accuracy of community's structure.
Description
Technical field
The present invention relates to data mining technology field, in particular to a kind of community's construction method and device.
Background technology
Existing community's developing algorithm is generally included such as Kernighan-Lin algorithms and based on Laplace figure characteristic values
Community's developing algorithm based on figure division such as spectral bisection method, such as community discovery algorithm and base of the GN algorithms based on hierarchical clustering
Go to track the community's developing algorithm for the technology that virtual community develops in community content.
Wherein, in the community discovery algorithm based on figure division, Kernighan-Lin algorithms need to learn network society in advance
The size in area, otherwise calculation error is larger, and spectral bisection method then calculates characteristic vector and characteristic value, and amount of calculation is bigger, no
It is adapted to analysis catenet.In the community discovery algorithm based on hierarchical clustering technology, such as GN algorithms, though the algorithm degree of accuracy compared with
Height, but due to needing the side betweenness of constantly calculating community's each edge, cause amount of calculation very big.Drilled based on dynamic network community
In the community discovery algorithm of change, such as the skill that tracking virtual community differentiation is gone using community content of Hopcroft and Khan propositions
Art, it is necessary to which better parameter is set, it is difficult to adapt to changeable community evolution police, very big difficulty is brought to practical application.
The content of the invention
In view of this, the present invention provides a kind of community's construction method and device, can effectively solve the problem that above mentioned problem.
Present pre-ferred embodiments provide a kind of community's construction method, and community's construction method includes:
Its initial effects force value is calculated for property value corresponding to each node in initial community network, wherein, institute
Stating property value includes user's enquirement number, question answering number, obtains the number praised number and obtain thanks;
Initial effects force value and PageRank algorithms based on each node calculate actual influence power corresponding to each node
Value;
Chosen from the initial community network in each node the maximum node of actual influence force value as core node with
First community of the structure with a node, and the core node is marked.
In the selection of present pre-ferred embodiments, community's construction method also includes:
Judge with the presence or absence of the adjacent node of first community in the initial community network, if in the presence of for each
Individual adjacent node, calculate node fitness of each adjacent node relative to first community;
Judge whether each node fitness meets the first preset value, if satisfied, will then meet the neighbour of the first preset value
Connect node and add first community, and the adjacent node is marked and the first community after addition adjacent node is entered
Row renewal.
In the selection of present pre-ferred embodiments, if the initial community network includes the first community and multiple second
Community, community's construction method also include:
First community and each second intercommunal overlap coefficient are calculated respectively;
Judge whether each overlap coefficient is more than the second preset value, if being more than, overlap coefficient is preset more than second
Second community of value is incorporated into first community, and the community network of the first community after merging is updated;
The first community after renewal and remaining each second intercommunal overlap coefficient are calculated, and is performed described in judgement
Whether overlap coefficient is more than the second preset value, if being more than, overlap coefficient is more than into the second community of the second preset value to first
The step of community, the first community after renewal and any one remaining second intercommunal overlap coefficient are respectively less than the
Two preset values, then stop community's combining step, obtain optimal community network.
In the selection of present pre-ferred embodiments, if the initial community network includes the first community and multiple second
Community, community's construction method also include:
First community and each second intercommunal overlap coefficient are calculated respectively;
Judge whether each overlap coefficient is more than the second preset value, and when the overlap coefficient is multiple, choose weight
Maximum in folded coefficient, first community is incorporated into by the second community corresponding to the maximum, and to first after merging
The community network of community is updated;
The first community after renewal and remaining each second intercommunal overlap coefficient are calculated, and is performed described in judgement
Whether overlap coefficient is more than the second preset value, if being more than, overlap coefficient is more than into the second community of the second preset value to first
The step of community, the first community after renewal and any one remaining second intercommunal overlap coefficient are respectively less than the
Two preset values, then stop community's combining step, obtain optimal community network.
In the selection of present pre-ferred embodiments, community's construction method also includes:
Search in the initial community network that institute is no to have the adjacent node not being labeled, if being not present, optimal community
Network struction is completed.
In the selection of present pre-ferred embodiments, the initial community network can be generated by following steps:
User's visit capacity in forum is chosen to be marked more than the topic of the 3rd preset value;
User data corresponding to the topic is extracted, and the user included in the user data mutually pays close attention to information structure
Build to form community network;
The node that unallocated to any community is chosen from the community network forms initial community network.
In the selection of present pre-ferred embodiments, the initial community network haves no right network to be oriented.
Present pre-ferred embodiments also provide a kind of community's construction device, and community's construction device includes:
First computing module, it is every in initial community network for being directed to for each node in initial community network
Property value corresponding to one node calculates its initial effects force value, wherein, the property value includes user and puts question to number, problem to return
Answer number, obtain the number praised number and obtain thanks;
Second computing module, each node is calculated for the initial effects force value based on each node and PageRank algorithms
Corresponding actual influence force value;
Community's generation module, for choosing actual influence force value maximum from each node in the initial community network
Node, to build the first community, and the core node is marked as core node.
In the selection of present pre-ferred embodiments, community's construction device also includes:
3rd computing module, for judging in the initial community network with the presence or absence of the adjacent section of first community
Point, if in the presence of for each adjacent node, calculating node fitness of each adjacent node relative to first community;
Community renewal module, for judging whether the node fitness meets the first preset value, if satisfied, then by the neighbour
Connect node and add first community, and the adjacent node is marked and the first community after addition adjacent node is entered
Row renewal.
In the selection of present pre-ferred embodiments, the initial community network includes the first community and multiple second societies
Area, community's construction device also include:
4th computing module, for calculating the first community and each second intercommunal overlap coefficient respectively;
Judge module, for judging whether each overlap coefficient is more than the second preset value, if being more than, by overlap coefficient
The second community more than the second preset value is incorporated into first community, and the community network of the first community after merging is carried out
Renewal;
5th computing module, for calculating the first community after updating and remaining each second intercommunal overlapping system
Number, and perform and judge whether the overlap coefficient is more than the second preset value, if being more than, overlap coefficient is more than the second preset value
The second community to the first community the step of, the first community after renewal with remaining any one is second intercommunal
Overlap coefficient is respectively less than the second preset value, then stops community's combining step.
Compared with prior art, a kind of community's construction method and device provided by the invention, wherein, by accessing forum
The extraction and analysis of data, realize the structure that the attribute factor based on network core node and each node itself realizes Web Community
Build, effectively overcome core node and choose the problem of fuzzy, improve the accuracy of community's structure.
In addition, compared with traditional community division method, the community's construction method based on core node of the invention provided
The overlapping community network of directed networkses can be effectively marked off, division accuracy rate is high, and can realize the standard of community's dynamic evolution
Really tracking.
Brief description of the drawings
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by embodiment it is required use it is attached
Figure is briefly described, it will be appreciated that the following drawings illustrate only certain embodiments of the present invention, therefore be not construed as pair
The restriction of scope, for those of ordinary skill in the art, on the premise of not paying creative work, can also be according to this
A little accompanying drawings obtain other related accompanying drawings.
Fig. 1 is the application scenarios schematic diagram of community's construction device provided in an embodiment of the present invention.
Fig. 2 is the schematic flow sheet of community's construction method provided in an embodiment of the present invention.
Fig. 3 is the sub-step schematic flow sheet of the step S110 shown in Fig. 2.
Fig. 4 is the structural representation of the initial community network provided in the present embodiment.
Fig. 5 is another sub-process schematic diagram of community's construction method provided in an embodiment of the present invention.
Fig. 6 is another sub-process schematic diagram of community's construction method provided in an embodiment of the present invention.
Fig. 7 is the frame structure schematic diagram of community's construction device provided in an embodiment of the present invention.
Icon:10- electric terminals;100- communities construction device;The computing modules of 110- first;The computing modules of 120- second;
130- communities generation module;The computing modules of 140- the 3rd;150- Community renewal modules;The computing modules of 160- the 4th;170- judges
Module;The computing modules of 180- the 5th;200- memories;300- storage controls;400- processors.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
Part of the embodiment of the present invention, rather than whole embodiments.The present invention implementation being generally described and illustrated herein in the accompanying drawings
The component of example can be configured to arrange and design with a variety of.
Therefore, below the detailed description of the embodiments of the invention to providing in the accompanying drawings be not intended to limit it is claimed
The scope of the present invention, but be merely representative of the present invention selected embodiment.It is common based on the embodiment in the present invention, this area
The every other embodiment that technical staff is obtained under the premise of creative work is not made, belong to the model that the present invention protects
Enclose.
It should be noted that:Similar label and letter represents similar terms in following accompanying drawing, therefore, once a certain Xiang Yi
It is defined, then it further need not be defined and explained in subsequent accompanying drawing in individual accompanying drawing.
As shown in figure 1, it is the side provided in an embodiment of the present invention using community's construction method and the electric terminal 10 of device
Mount structure schematic diagram.The electric terminal 10 includes community's construction device 100, memory 200, storage control 300 and place
Manage device 400.
Wherein, the memory 200, storage control 300,400 each element of processor are mutual directly or indirectly
It is electrically connected with, to realize the transmission of data or interaction.For example, pass through one or more communication bus or signal between these elements
Line, which is realized, to be electrically connected with.Community's construction device 100 include it is at least one can be stored in the form of software or firmware it is described
In memory 200 or the software function module that is solidificated in the operating system of the electric terminal 10.The processor 400 is in institute
State and the memory 200 is accessed under the control of storage control 300, held for what is stored in the execution memory 200
Row module, such as software function module included by community's construction device 100 and computer program etc..
Alternatively, the electric terminal 10 may be, but not limited to, smart mobile phone, IPAD, computer, server etc..
It should be appreciated that the structure shown in Fig. 1 is only to illustrate.The electric terminal 10 can have it is more more than shown in Fig. 1 or
The less component of person, or there is the configuration different from shown in Fig. 1.Wherein, each component shown in Fig. 1 can be by software, hardware
Or its combination is realized.
As shown in Fig. 2 it is a kind of schematic flow sheet for community's construction method that present pre-ferred embodiments provide.The society
Area's construction method is applied to the electric terminal 10 shown in Fig. 1.Below will be exemplified by knowing question and answer forum, with reference to Fig. 2 to the society
The idiographic flow and step of area's construction method are described in detail.
Step S110, its initial effects power is calculated for property value corresponding to each node in initial community network
Value.Alternatively, as shown in figure 3, the initial community network can be realized by following sub-step.
Sub-step S111, choose user's visit capacity in forum and be marked more than the topic of the 3rd preset value.
Sub-step S112, extract user data corresponding to the topic, and the user's phase included in the user data
Mutually concern information architecture forms community network.
Sub-step S113, the node that unallocated to any community is chosen from the community network form initial community network.
In the present embodiment, exemplified by knowing question and answer forum, multiple topics according to present in the forum and access are different
The user situation of topic, the 3rd is more than to user's visit capacity in the forum according to prefixed time interval using crawler algorithm etc. and is preset
The topic of value is chosen, marked.Wherein, the 3rd preset value can be 1200 etc., and the prefixed time interval can select
It is selected as one week, two weeks etc., the present embodiment is not limited herein.
Further, after the user data mark of the 3rd preset value is more than to visit capacity, it can extract marked use
User data, and it is initial according to the user included in user data mutually to pay close attention to the foundation such as the access relation between information or each user
Community network, wherein, the initial community network can have no right network, and the different use of different node on behalf in the network to be oriented
Family, alternatively, the network structure of the initial community network may be, but not limited to, as shown in Figure 4.
Alternatively, the property value can include, but are not limited to user's enquirement number, question answering number, obtain and praise number
And obtain number thanked etc..Wherein, the initial effects power of each node can pass through formula Wi=(0.15 × Nask+0.20
×Nans+0.30×Nagr+0.35×Ntha) be calculated.In formula, WiRepresent the value of the initial effects power of node i, Nask、Nans、
Nagr、NthaUser puts question to number, question answering number, obtains the number praised number and obtain thanks respectively corresponding to node i.
Step S120, initial effects force value and PageRank algorithms based on each node calculate real corresponding to each node
Border influences force value.
It should be noted here that calculating the actual influence force value of each node using PageRank algorithms, the present embodiment is simultaneously unlimited
In the algorithm.
Step S130, the maximum section of actual influence force value is chosen in unlabelled each node from the initial community network
Put as core node to form first community with a node, and the core node is marked.
Specifically, due to there may be node that is marked and being under the jurisdiction of other communities in the initial community network, because
This, when building the first community, unlabelled each node should be chosen from the initial community network and calculates its actual influence power,
First community is built using the maximum node of actual influence power as core node again, now first community is to possess one
The small community of core node, and the community fitness f of first communityC=0, the member node number n in communityc=1, community
Maximum adaptation degreeIt should be noted that in order to make a distinction, the core is tackled when core node is added into first community
Heart node is marked.
Property value in the present embodiment at first based on each node in network determines core node, then is built based on the core node
The problem of mode of vertical first community can avoid node selection from obscuring.In addition, during actual implementation, same initial community can be based on
Network establishes multiple multiple first communities for including a core node simultaneously, and the core node in each community is different.
Step S140, judge to whether there is the adjacent node of first community in the initial community network, if in the presence of,
For each adjacent node, node fitness of each adjacent node relative to first community is calculated;
Specifically, because the core node in first community is that actual influence power is maximum in the initial community network
Node, therefore, after the Primary Construction of the first community is completed, should also judge in the initial community network with the presence or absence of described the
The adjacent node of one community.Where it is assumed that the collection of the first community C adjacent node is combined into V (C), and if V (C) empty set, described
Adjacent node is not present in one community C, then performs step S140.Conversely, if V (C) is not empty set, the first community C
Adjacent node be present, then need to perform step S150 as shown in Figure 5, it is specific as follows.Alternatively, in the present embodiment, the adjoining
Calculation the present embodiment of node is not limited herein.
In addition, if V (C) is not empty set, need to calculate each adjacent node in the V (C) relative to first community
Node fitness.Specifically, in the present embodiment, first according to formulaAsk for the society of first community
Area fitness fC, further according to formulaAsk for adjacent node i node fitnessIn formula, fCFor first
Community C community's fitness,All company's side numbers between first community's C internal nodes,To be saved inside the first community C
All company's side numbers between point and community's external node, α is fitness parameter,Represent node of the node i on the first community C
Fitness, fC+{i}The community's fitness added for the first community C after node i, fC-{i}For the first community C do not add node i it
Preceding community's fitness.
Step S150, judges whether each node fitness meets the first preset value, if satisfied, will then meet that first is pre-
If the adjacent node of value adds first community, and the adjacent node is marked and to adding the after adjacent node
One community is updated.
Specifically, first preset value can be 0, for example, when choosing the adjacent node i of node fitness maximum,
IfThen node i is added in the first community C and plus mark.Now, the first community C community's maximum adaptation degreeCommunity nodes nc=nc+1.If conversely,Then illustrate that the first community C adjacent node is all not belonging to
One community, in other words, now the first community C community's fitness reaches peak value, that is, has obtained a first larger community, the
One community structure is completed.
In addition, actual when implementing, also need to search in the initial community network that institute is no to have the adjacent node not being labeled,
If being not present, optimal community network structure is completed.
Further, for the community network with overlapping community structure, the overlapping nodes between Liang Ge communities are Liang Ge societies
The main carriers of information transmission between area, therefore, if the overlapping nodes ignored in community ignore that it is each intercommunal overlapping
Effect of the node in community's evolution.So, for two stable communities, overlapping nodes other nodes that compare are dissolved into it
In a community possibility it is bigger, its EVOLUTION ANALYSIS to community has great importance, so the overlapping nodes by community
Also the core node collection of each community is addedCan more it be stablized and community network that structure is optimal.This implementation
In example, overlapping nodes are added by core node collection (the first community) by step as shown in Figure 6, it is specific as follows.
Step S160, the first community and each second intercommunal overlap coefficient are calculated respectively.
In the present embodiment, due to being removed in the initial community network outside the first newly-built community, it is also possible to it be present
His multiple second communities, therefore, in order that each community network is optimal, also need to merge the similar community of community network.
Specifically, formula can be passed throughThe first community and each second intercommunal overlap coefficient are calculated, and
Realize that community merges using overlap coefficient as judge index.In formula:OijFor the first community i and the second community j overlap coefficient, |
Si∩Sj| it is the first community i and the second jointly owned nodes of community j, | min (Si,Sj) | it is the first community i and the second society
The nodes of the community of scale is smaller in area j.
Step S170, judges whether each overlap coefficient is more than the second preset value, if being more than, overlap coefficient is more than
Second community of the second preset value is incorporated into first community, and the community network of the first community after merging is carried out more
Newly.
Specifically, second preset value can carry out flexible design according to the actual requirements, and the present embodiment is not limited herein.
Further, since there may be multiple second communities, and more than the second preset value overlap coefficient also likely to be present it is multiple, therefore,
When actually implementing, if more than the second preset value overlap coefficient to be multiple, also can be by being chosen most from multiple overlap coefficients
Big value, then the second community corresponding to the maximum is incorporated into first community, and the first community network after merging is entered
Row renewal.
Step S180, the first community after renewal and remaining each second intercommunal overlap coefficient are calculated, and held
Row judges whether the overlap coefficient is more than the second preset value, if being more than, overlap coefficient is more than into the second of the second preset value
The step of community to the first community, the first community and any one remaining second intercommunal overlapping system after renewal
Number is respectively less than the second preset value, then stops community's combining step, obtain optimal community network.In the present embodiment, community is being carried out
During merging, it is understood that there may be multiple community's combining steps, i.e., only when overlap coefficient is unsatisfactory for merging condition, stop merging step
Suddenly, so as to obtaining optimal community network.
, can walking always by core node collection at this it should be noted that the community's construction method provided in the present embodiment
Determine the forerunner of community under adjacent moment, follow-up thought, community's set G of adjacent time pointtAnd Gt+1In communityCore point collection meet relationAnd at this
It is not community to exist in setOverlapping nodes node, i.e. the node is pertaining only to communitySo communityAnd communityIt there is the Evolvement of forerunner-follow-up.If for example, communityFor communityForerunner, then
It is communityFor communityIt is follow-up thenAnd then it can be provided based on this method and every kind of community is developed
The detailed description of pattern, it is specific as follows.
Community produces:If for all communities under moment tWith some community under moment t+1Not
It can meetThen illustrateIt is in community caused by moment t+1.
Wither away community:If for all communities under moment t+1With some community under moment t
It can not meetThen illustrateWithered away when under moment t+1.
Community increases:If for the community under moment tWith the community under moment t+1Can man-to-man satisfactionOrAnd communityScale compare communityGreatly, then community is illustratedInscribed in t+1
There occurs community's growth.
Shrink community:If for the community under moment tWith the community under moment t+1Can man-to-man satisfactionOrAnd communityScale compare communityIt is small, then illustrate communityInscribed in t+1
There occurs community's contraction.
Community divides:If for the community under moment tWith two or more the community under moment t+1 all
Differentiation relation can be formed, is such as metThen communityThere occurs society under moment t+1
Differentiation is split.
Community merges:If for the community under moment t+1With two or more the community under moment t
Evolvement can be formed, is such as metThen communityUnder moment t+1 there occurs
Community merges.
Further, as shown in fig. 7, community's construction device 100 that the present embodiment provides is applied to the electric terminal 10,
And community's construction device 100 includes the first computing module 110, the second computing module 120, community's generation module the 130, the 3rd and counted
Calculate module 140, Community renewal module 150, the 4th computing module 160, the computing module 180 of judge module 170 and the 5th.
First computing module 110, based on property value corresponding to each node used in for initial community network
Calculate its initial effects force value.In the present embodiment, institute during the description as described in first computing module 110 is specifically referred to Fig. 2
The step S110 shown detailed description, that is, the step S110 can be performed by first computing module 110.
Second computing module 120, based on the initial effects force value based on each node and PageRank algorithms
Calculate actual influence force value corresponding to each node.In the present embodiment, the description as described in second computing module 120 specifically refers to
To the detailed description of the step S120 shown in Fig. 2, that is, the step S120 can be held by second computing module 120
OK.
Community's generation module 130, it is real for not chosen from the initial community network in labeled each node
Border influences the maximum node of force value as core node to form the first community, and the core node is marked.This implementation
In example, the description as described in community's generation module 130 specifically refers to the detailed description to the step S130 as shown in Fig. 2,
That is, the step S130 can be performed by community's generation module 130.
3rd computing module 140, for judging in the initial community network with the presence or absence of first community
Adjacent node, if in the presence of for each adjacent node, calculating each adjacent node and adapted to relative to the node of first community
Degree.In the present embodiment, the description as described in the 3rd computing module 140 is specifically referred to the step S140 as shown in Fig. 5
It is described in detail, that is, the step S140 can be performed by the 3rd computing module 140.
The Community renewal module 150, for judging whether the node fitness meets the first preset value, if satisfied,
The adjacent node is then added into first community, and the adjacent node is marked and to adding the after adjacent node
One community is updated.In the present embodiment, the description as described in the Community renewal module 150 is specifically referred to as shown in Fig. 5
Step S150 detailed description, that is, the step S150 can be performed by the Community renewal module 150.
4th computing module 160, for calculating the first community and each second intercommunal overlap coefficient.This
In embodiment, the description as described in the 4th computing module 160 specifically refers to retouching in detail to the step S160 as shown in Fig. 6
State, that is, the step S160 can be performed by the 4th computing module 160.
The judge module 170,, will if being more than for judging whether each overlap coefficient is more than the second preset value
The second community that overlap coefficient is more than the second preset value is incorporated into first community, and to the community of the first community after merging
Network is updated.In the present embodiment, the step of description as described in the judge module 170 is specifically referred to as shown in Fig. 6
S170 detailed description, that is, the step S170 can be performed by the judge module 170.
5th computing module 180, for calculating between the first community after updating and remaining each second community
Overlap coefficient, and perform and judge whether the overlap coefficient is more than the second preset value, if being more than, overlap coefficient is more than the
The step of the second community to the first community of two preset values, the first community and any one remaining second society after renewal
Overlap coefficient between area is respectively less than the second preset value, then stops community's combining step.In the present embodiment, on the described 5th meter
The description of calculation module 180 specifically refers to the detailed description to the step S180 shown in Fig. 6, that is, the step S180 can
To be performed by the 5th computing module 180.
In summary, the present invention provides a kind of community's construction method and device, wherein, carried by accessing data to forum
Analysis is taken, realizes the structure that the attribute factor based on network core node and each node itself realizes Web Community, effectively
Overcome core node and choose the problem of fuzzy, improve the accuracy of community's structure.
In addition, compared with traditional community division method, the community's construction method based on core node of the invention provided
The overlapping community network of directed networkses can be effectively marked off, division accuracy rate is high, and can realize the standard of community's dynamic evolution
Really tracking.
In the description of the invention, term " setting ", " connected ", " connection " should be interpreted broadly, for example, it may be fixed
Connect or be detachably connected, or be integrally connected;Can be mechanical connection or electrical connection;Can be direct
It is connected, can also be indirectly connected by intermediary, can be the connection of two element internals.For the ordinary skill of this area
For personnel, the concrete meaning of above-mentioned term in the present invention can be understood with concrete condition.
In several embodiments that the embodiment of the present invention is provided, it should be understood that disclosed apparatus and method, also may be used
To realize by other means.Apparatus and method embodiment described above is only schematical, for example, the stream in accompanying drawing
Journey figure and block diagram show that the device of the predetermined number embodiment according to the present invention, method and computer program product may be real
Existing architectural framework, function and operation.At this point, each square frame in flow chart or block diagram can represent module, a journey
A part for sequence section or code.A part for the module, program segment or code includes one or predetermined number is used to realize
Defined logic function.
It should also be noted that at some as in the implementation replaced, the function of being marked in square frame can also be with difference
The order marked in accompanying drawing occurs.For example, two continuous square frames can essentially perform substantially in parallel, they are sometimes
It can also perform in the opposite order, this is depending on involved function.It is also noted that in block diagram and/or flow chart
The combination of each square frame and the square frame in block diagram and/or flow chart, the special of function as defined in performing or action can be used
Hardware based system is realized, or can be realized with the combination of specialized hardware and computer instruction.
The preferred embodiments of the present invention are the foregoing is only, are not intended to limit the invention, for the skill of this area
For art personnel, the present invention can have various modifications and variations.Within the spirit and principles of the invention, that is made any repaiies
Change, equivalent substitution, improvement etc., should be included in the scope of the protection.
Claims (10)
1. a kind of community's construction method, it is characterised in that community's construction method includes:
Its initial effects force value is calculated for property value corresponding to each node in initial community network, wherein, the category
Property value include user put question to number, question answering number, obtain praise number and obtain thank number;
Initial effects force value and PageRank algorithms based on each node calculate actual influence force value corresponding to each node;
The maximum node of actual influence force value is chosen in each node as core node from the initial community network to build
The first community with a node, and the core node is marked.
2. community's construction method according to claim 1, it is characterised in that community's construction method also includes:
Judge with the presence or absence of the adjacent node of first community in the initial community network, if in the presence of adjacent for each
Node is connect, calculates node fitness of each adjacent node relative to first community;
Judge whether each node fitness meets the first preset value, if satisfied, will then meet that the adjacent of the first preset value is saved
Point adds first community, and the adjacent node is marked and the first community after addition adjacent node is carried out more
Newly.
3. community's construction method according to claim 1, it is characterised in that if the initial community network includes first
Community and multiple second communities, community's construction method also include:
First community and each second intercommunal overlap coefficient are calculated respectively;
Judge whether each overlap coefficient is more than the second preset value, if being more than, overlap coefficient is more than the second preset value
Second community is incorporated into first community, and the community network of the first community after merging is updated;
Calculate the first community after renewal and remaining each second intercommunal overlap coefficient, and perform judge it is described overlapping
Whether coefficient is more than the second preset value, if being more than, overlap coefficient is more than to the second community to the first community of the second preset value
The step of, it is pre- that the first community after renewal with any one remaining second intercommunal overlap coefficient is respectively less than second
If value, then stop community's combining step, obtain optimal community network.
4. community's construction method according to claim 1, it is characterised in that if the initial community network includes first
Community and multiple second communities, community's construction method also include:
First community and each second intercommunal overlap coefficient are calculated respectively;
Judge whether each overlap coefficient is more than the second preset value, and when the overlap coefficient is multiple, choose overlapping system
Maximum in number, the second community corresponding to the maximum is incorporated into first community, and to the first community after merging
Community network be updated;
Calculate the first community after renewal and remaining each second intercommunal overlap coefficient, and perform judge it is described overlapping
Whether coefficient is more than the second preset value, if being more than, overlap coefficient is more than to the second community to the first community of the second preset value
The step of, it is pre- that the first community after renewal with any one remaining second intercommunal overlap coefficient is respectively less than second
If value, then stop community's combining step, obtain optimal community network.
5. community's construction method according to any one of claim 1-4, it is characterised in that community's construction method is also
Including:
Search in the initial community network that institute is no to have the adjacent node not being labeled, if being not present, optimal community network
Structure is completed.
6. community's construction method according to claim 1, it is characterised in that the initial community network can pass through following step
Rapid generation:
User's visit capacity in forum is chosen to be marked more than the topic of the 3rd preset value;
User data corresponding to the topic is extracted, and the user included in the user data mutually pays close attention to information architecture shape
Into community network;
The node that unallocated to any community is chosen from the community network forms initial community network.
7. community's construction method according to claim 1 or 6, it is characterised in that the initial community network is oriented nothing
Weigh network.
8. a kind of community's construction device, it is characterised in that community's construction device includes:
First computing module, for being directed to each in initial community network for each node in initial community network
Property value corresponding to node calculates its initial effects force value, wherein, the property value includes user and puts question to number, question answering time
Number, obtain the number praised number and obtain thanks;
Second computing module, it is corresponding to calculate each node for the initial effects force value based on each node and PageRank algorithms
Actual influence force value;
Community's generation module, for choosing the maximum node of actual influence force value from each node in the initial community network
As core node to build the first community, and the core node is marked.
9. community's construction device according to claim 8, it is characterised in that community's construction device also includes:
3rd computing module, for judging with the presence or absence of the adjacent node of first community in the initial community network, if
In the presence of for each adjacent node, calculating node fitness of each adjacent node relative to first community;
Community renewal module, for judging whether the node fitness meets the first preset value, if satisfied, then saving the adjoining
Point adds first community, and the adjacent node is marked and the first community after addition adjacent node is carried out more
Newly.
10. community's construction device according to claim 8, it is characterised in that the initial community network includes first
Community and multiple second communities, community's construction device also include:
4th computing module, for calculating the first community and each second intercommunal overlap coefficient respectively;
Judge module, for judging whether each overlap coefficient is more than the second preset value, if being more than, overlap coefficient is more than
Second community of the second preset value is incorporated into first community, and the community network of the first community after merging is carried out more
Newly;
5th computing module, for calculating the first community after updating and remaining each second intercommunal overlap coefficient,
And perform and judge whether the overlap coefficient is more than the second preset value, if being more than, overlap coefficient is more than the second preset value
The step of second community to the first community, the first community after renewal with remaining any one is second intercommunal heavy
Folded coefficient is respectively less than the second preset value, then stops community's combining step.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711227646.3A CN107895326A (en) | 2017-11-29 | 2017-11-29 | A kind of community's construction method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711227646.3A CN107895326A (en) | 2017-11-29 | 2017-11-29 | A kind of community's construction method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107895326A true CN107895326A (en) | 2018-04-10 |
Family
ID=61806689
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711227646.3A Pending CN107895326A (en) | 2017-11-29 | 2017-11-29 | A kind of community's construction method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107895326A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109241248A (en) * | 2018-07-13 | 2019-01-18 | 广州神马移动信息科技有限公司 | Determination method, apparatus, the system of reply content in online Knowledge Community |
CN110263264A (en) * | 2019-06-28 | 2019-09-20 | 南昌航空大学 | A method of obtaining community network key node |
CN111125481A (en) * | 2018-10-31 | 2020-05-08 | 百度在线网络技术(北京)有限公司 | Community discovery method, device and equipment |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2012216943A (en) * | 2011-03-31 | 2012-11-08 | Kddi Corp | Network community structure detection device and method |
CN106951524A (en) * | 2017-03-21 | 2017-07-14 | 哈尔滨工程大学 | Overlapping community discovery method based on node influence power |
CN107153713A (en) * | 2017-05-27 | 2017-09-12 | 合肥工业大学 | Overlapping community detection method and system based on similitude between node in social networks |
-
2017
- 2017-11-29 CN CN201711227646.3A patent/CN107895326A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2012216943A (en) * | 2011-03-31 | 2012-11-08 | Kddi Corp | Network community structure detection device and method |
CN106951524A (en) * | 2017-03-21 | 2017-07-14 | 哈尔滨工程大学 | Overlapping community discovery method based on node influence power |
CN107153713A (en) * | 2017-05-27 | 2017-09-12 | 合肥工业大学 | Overlapping community detection method and system based on similitude between node in social networks |
Non-Patent Citations (2)
Title |
---|
吴琪 等: "基于种子节点扩展的启发式重叠社区发现算法", 《通信与信息技术》 * |
张燃: "基于图挖掘的社交网络可视化研究", 《万方数据 中国学位论文全文数据库》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109241248A (en) * | 2018-07-13 | 2019-01-18 | 广州神马移动信息科技有限公司 | Determination method, apparatus, the system of reply content in online Knowledge Community |
CN111125481A (en) * | 2018-10-31 | 2020-05-08 | 百度在线网络技术(北京)有限公司 | Community discovery method, device and equipment |
CN110263264A (en) * | 2019-06-28 | 2019-09-20 | 南昌航空大学 | A method of obtaining community network key node |
CN110263264B (en) * | 2019-06-28 | 2021-04-27 | 南昌航空大学 | Method for acquiring social network key node |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104995870B (en) | Multiple target server arrangement determines method and apparatus | |
CN105045818B (en) | A kind of recommendation methods, devices and systems of picture | |
CN110297911A (en) | Internet of Things (IOT) calculates the method and system that cognition data are managed and protected in environment | |
CN107895326A (en) | A kind of community's construction method and device | |
CN106650725A (en) | Full convolutional neural network-based candidate text box generation and text detection method | |
CN110489655A (en) | Hot content determination, recommended method, device, equipment and readable storage medium storing program for executing | |
CN107025509A (en) | Decision system and method based on business model | |
CN107507073A (en) | Based on the service recommendation method for trusting extension and the sequence study of list level | |
CN107992585A (en) | Universal tag method for digging, device, server and medium | |
CN107291337A (en) | A kind of method and device that Operational Visit is provided | |
CN111125519B (en) | User behavior prediction method, device, electronic equipment and storage medium | |
CN105912448A (en) | Intelligent method for calibrating battery capacity | |
CN110458572A (en) | The determination method of consumer's risk and the method for building up of target risk identification model | |
CN107453928A (en) | A kind of power telecom network pitch point importance evaluation method and device | |
CN109274987A (en) | A kind of video collection sort method, server and readable storage medium storing program for executing | |
CN107481054A (en) | The push of hotel's favor information and device, electronic equipment, storage medium | |
CN108121716A (en) | The approaches and problems uniprocesser system of process problem list | |
CN110263181A (en) | The method for digging of the structure of knowledge and the planing method of learning path | |
CN104462443B (en) | Data processing method and device | |
CN107562966A (en) | The optimization system and method based on intelligence learning for web page interlinkage retrieval ordering | |
CN107247798A (en) | The method and apparatus for building search dictionary | |
CN110059172A (en) | The method and apparatus of recommendation answer based on natural language understanding | |
CN109493077A (en) | Activity recognition method and device, electronic equipment, storage medium | |
CN109710832A (en) | It is a kind of for search for boarding program method and apparatus | |
CN109523436A (en) | User's learning management method, apparatus, computer installation, storage medium |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180410 |
|
RJ01 | Rejection of invention patent application after publication |