CN109522489A - The determination method, apparatus and intelligent terminal of personage's cohesion - Google Patents
The determination method, apparatus and intelligent terminal of personage's cohesion Download PDFInfo
- Publication number
- CN109522489A CN109522489A CN201811430496.0A CN201811430496A CN109522489A CN 109522489 A CN109522489 A CN 109522489A CN 201811430496 A CN201811430496 A CN 201811430496A CN 109522489 A CN109522489 A CN 109522489A
- Authority
- CN
- China
- Prior art keywords
- node
- cohesion
- nodes
- social
- personage
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 230000000694 effects Effects 0.000 claims abstract description 35
- 238000000638 solvent extraction Methods 0.000 claims abstract description 13
- 239000011159 matrix material Substances 0.000 claims description 87
- 238000004364 calculation method Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 12
- 239000008280 blood Substances 0.000 claims description 10
- 210000004369 blood Anatomy 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 10
- 230000002452 interceptive effect Effects 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 240000000233 Melia azedarach Species 0.000 claims description 2
- 230000003993 interaction Effects 0.000 claims 1
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000003542 behavioural effect Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of determination method, apparatus of personage's cohesion and intelligent terminals, are related to field of computer technology, this method comprises: obtaining the people information in multiple social scenes；According to the corresponding people information of each social activity scene, multiple social scene partitionings are formed into multiple social classifications；According to the people information in each social classification, the corresponding personage's social networks of each social classification is constructed；According to multiple personage's social networks, different person-to-person cohesions are calculated.The present invention can effectively improve the accuracy of determining personage's cohesion.
Description
Technical field
The present invention relates to field of computer technology, more particularly, to the determination method, apparatus and intelligence of a kind of personage's cohesion
It can terminal.
Background technique
The determination of personage's cohesion convenient for finding the connection between different people, and it can be found that personage's connection it is intimate
Degree, and in the prior art, personage's cohesion is only calculated by single dimension, that is, single scene, for the relationship between individual
Calculating is excessively unilateral, while in single scene, community locating for individual is not considered yet, for the standard of obtained personage's cohesion
True property is to be improved.
Summary of the invention
In view of this, the purpose of the present invention is to provide a kind of determination method, apparatus of personage's cohesion and intelligent terminal,
The accuracy of determining personage's cohesion can be effectively improved.
To achieve the goals above, technical solution used in the embodiment of the present invention is as follows:
In a first aspect, the embodiment of the invention provides a kind of determination method of personage's cohesion, this method comprises: obtaining more
People information in a social activity scene；Wherein, people information includes blood relationship kinship, interpersonal interactive information, trading activity letter
One of breath and trip information are a variety of；According to the corresponding people information of each social activity scene, by multiple social scene partitionings
Form multiple social classifications；Wherein, at least one corresponding people information of social activity scene is included in each social classification；According to each
People information in social classification constructs the corresponding personage's social networks of each social classification；Wherein, include in personage's social networks
Multiple nodes and Lian Bian, the different individual of different node on behalf even have between two nodes at both ends in the company of expression and close
Connection；According to multiple personage's social networks, different person-to-person cohesions are calculated.
With reference to first aspect, the embodiment of the invention provides the first possible embodiments of first aspect, wherein root
According to multiple personage's social networks, the step of calculating different person-to-person cohesions, comprising: selected from each personage's social networks
The destination node for taking the personal difference of the difference of cohesion to be determined corresponding；According to modularity function and GN algorithm to each personage
Social networks carries out community's division, obtains the corresponding multiple communities of each personage's social networks；Determine each destination node at each one
Target community where in object social networks；Based on target community, the cohesion matrix of each destination node is calculated, and is generated and parent
The corresponding cohesion color image of density matrix；Wherein, cohesion matrix includes single order cohesion matrix, second order cohesion matrix
With one of three rank cohesion matrixes or a variety of；Cohesion color image is input to the network model that training obtains in advance；
Obtain the cohesion vector that network model is directed to the output of cohesion color image；Wherein, cohesion vector includes personage's social network
The cohesion of destination node and other nodes in network.
The possible embodiment of with reference to first aspect the first, the embodiment of the invention provides second of first aspect
Possible embodiment, wherein cohesion matrix includes single order cohesion matrix, and the calculation formula of single order cohesion matrixIt is as follows:
Wherein,Indicate that node i connects the number of nodes of first nodes with node j,Indicate that node i connects first nodes
Node total number,Indicate the node total number of node j connection first nodes, EiAnd EjRespectively indicate node i and the place node j
Community works as Ei=EjWhen, ν (Ei, Ej) it is 1, work as Ei≠EjWhen, ν (Ei, Ej) it is 0.5,Indicate the level-one section connecting with node i
Company's number of edges of point,Indicate that the first nodes connecting with node i connect the average weight on side,Indicate connect with node j one
Company's number of edges of grade node,It indicates to connect the average weight on side with the node j first nodes connecting, first nodes refer to and currently
The node that node is connected directly, the numerical value in single order cohesion matrix are obtained according to single order cohesion calculation formula, and single order is intimate
The numerical value in matrix is spent between 0 to 255.
The possible embodiment of with reference to first aspect the first, the embodiment of the invention provides the third of first aspect
Possible embodiment, wherein cohesion matrix includes second order cohesion matrix and/or three rank cohesion matrixes, and second order is close
The calculation formula of density matrix and three rank cohesion matrixesIt is as follows:
Wherein,Indicate that node i connects the number of nodes of k grades of nodes with node j,Indicate that node i connects k grades of nodes
Node total number,Indicate the node total number of k grades of nodes of node j connection,Indicate that the path of node i k grades of nodes of connection is total
Number,Indicate that node i connects the average weight of k grades of node paths,Indicate the total number of paths of k grades of nodes of node j connection,Indicate k grades of node paths of node j connection average weight, k grades of nodes refer to after the node of k-1, present node interval
The node being connected with present node；The numerical value in numerical value and three rank cohesion matrixes in second order cohesion matrix is all in accordance with intimate
Spend calculation formulaObtain, the numerical value in numerical value and three rank cohesion matrixes in second order cohesion matrix 0 to 255 it
Between.
The third possible embodiment with reference to first aspect, the embodiment of the invention provides the 4th kind of first aspect
Possible embodiment, wherein the step of generating cohesion color image corresponding with cohesion matrix, comprising: according to intimate
The numerical value in matrix is spent, converts cohesion color image for cohesion matrix；Wherein, the range of the numerical value in cohesion matrix
It is identical with the pixel coverage of cohesion color image.
Second aspect, the embodiment of the present invention also provide a kind of determining device of personage's cohesion, comprising: obtain module, use
People information in the multiple social scenes of acquisition；Wherein, people information includes blood relationship kinship, interpersonal interactive information, friendship
Easy one of behavioural information and trip information or a variety of；Division module, for being believed according to the corresponding personage of each social activity scene
Multiple social scene partitionings are formed multiple social classifications by breath；Wherein, include at least one social scene in each social classification
Corresponding people information；Module is constructed, for constructing the corresponding people of each social classification according to the people information in each social classification
Object social networks；It wherein, include multiple nodes and Lian Bian in personage's social networks, the different individual of different node on behalf connects
There is association between two nodes at both ends in the company of expression；Computing module, for calculating not according to multiple personage's social networks
With person-to-person cohesion.
In conjunction with second aspect, the embodiment of the invention provides the first possible embodiments of second aspect, wherein parent
Density matrix includes single order cohesion matrix, and the calculation formula of single order cohesion matrixIt is as follows:
Wherein,Indicate that node i connects the number of nodes of first nodes with node j,Indicate that node i connects first nodes
Node total number,Indicate the node total number of node j connection first nodes, EiAnd EjSociety where respectively indicating node i and node j
Area works as Ei=EjWhen, ν (Ei, Ej) it is 1, work as Ei≠EjWhen, ν (Ei, Ej) it is 0.5,Indicate the first nodes connecting with node i
Company's number of edges,Indicate that the first nodes connecting with node i connect the average weight on side,Indicate the level-one connecting with node j
Company's number of edges of node,It indicates to connect the average weight on side with the node j first nodes connecting, first nodes refer to and currently
The node that node is connected directly, the numerical value in single order cohesion matrix are obtained according to single order cohesion calculation formula, and single order is intimate
The numerical value in matrix is spent between 0 to 255.
The third aspect, the embodiment of the invention provides a kind of intelligent terminals, including processor and memory；It is deposited on memory
Computer program is contained, computer program executes the 4th kind of possibility such as first aspect to first aspect when being run by processor
Any one of embodiment method.
Fourth aspect, the embodiment of the invention provides a kind of computer readable storage medium, computer readable storage mediums
On be stored with computer program, above-mentioned first aspect is executed when computer program is run by processor to the 4th kind of first aspect
The step of method of any one of possible embodiment.
The embodiment of the invention provides a kind of determination method, apparatus of personage's cohesion and intelligent terminals, more by obtaining
People information in a social activity scene, and according to the corresponding people information of each social activity scene, by multiple social scene partitioning shapes
At multiple social classifications, to construct the corresponding personage's social network of each social classification according to the people information in each social classification
Network, and then according to multiple personage's social networks, calculate different person-to-person cohesions.When due to determining personage's cohesion, examine
Consider the people information in multiple social scenes, and multiple social scenes are divided into multiple social classifications, leads to compared to the prior art
It crosses single scene and calculates personage's cohesion, the present invention can effectively improve the accuracy of determining personage's cohesion.
Other features and advantages of the present invention will illustrate in the following description, also, partly become from specification
It obtains it is clear that understand through the implementation of the invention.The objectives and other advantages of the invention are in specification, claims
And specifically noted structure is achieved and obtained in attached drawing.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
It, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical solution in the prior art
Embodiment or attached drawing needed to be used in the description of the prior art be briefly described, it should be apparent that, it is described below
Attached drawing is some embodiments of the present invention, for those of ordinary skill in the art, before not making the creative labor
It puts, is also possible to obtain other drawings based on these drawings.
Fig. 1 shows a kind of flow chart of the determination method of personage's cohesion provided by the embodiment of the present invention；
Fig. 2 shows the flow charts of the determination method of another kind personage cohesion provided by the embodiment of the present invention；
Fig. 3 shows a kind of structural block diagram of the determining device of personage's cohesion provided by the embodiment of the present invention；
Fig. 4 shows a kind of structural schematic diagram of intelligent terminal provided by the embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with attached drawing to the present invention
Technical solution be clearly and completely described, it is clear that described embodiments are some of the embodiments of the present invention, rather than
Whole embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not making creative work premise
Under every other embodiment obtained, shall fall within the protection scope of the present invention.
In view of in the prior art, only personage's cohesion being calculated by single dimension, that is, single scene, for individual
Between relationship calculate excessively unilateral, while in single scene, community locating for individual is not considered yet, for obtained personage parent
The accuracy of density is to be improved, is based on this, a kind of determination method, apparatus of personage's cohesion provided in an embodiment of the present invention and
Intelligent terminal can effectively improve the accuracy of determining personage's cohesion.
For convenient for understanding the present embodiment, first really to a kind of personage cohesion disclosed in the embodiment of the present invention
The method of determining describes in detail.
A kind of flow chart of the determination method of personage's cohesion shown in Figure 1, this method is by intelligence such as computers
Energy terminal executes, method includes the following steps:
Step S102 obtains the people information in multiple social scenes；Wherein, people information include blood relationship kinship,
One of interpersonal interactive information, trading activity information and trip information are a variety of.
Interpersonal interactive information includes communication information, such as chat message, and trading activity information includes the letter such as transfer accounts, remit money
Breath, trip information includes vehicle traveling information.
Multiple social scene partitionings are formed multiple societies according to the corresponding people information of each social activity scene by step S104
Hand over classification；Wherein, at least one corresponding people information of social activity scene is included in each social classification.
It in one embodiment, can be three social classifications, the first social classification packet by multiple social scene partitionings
The people informations such as blood relationship kinship are included, the second social classification includes interpersonal interactive information etc., and third social activity classification includes transaction
Behavioural information and trip information etc..
Step S106 constructs the corresponding personage's social networks of each social classification according to the people information in each social classification；
It wherein, include multiple nodes and Lian Bian, the different individual of different node on behalf, even in the company of expression two in personage's social networks
There is association between two nodes at end.
It is such as three above-mentioned social classifications by multiple social scene partitionings, then each social classification corresponds to a personage society
Hand over network, that is, construct three personage's social networks, each personage's social networks includes multiple nodes and Lian Bian, two nodes it
Between associated size can be indicated with weight, node i.e. represent individual, the lineal blood such as in blood relationship kinship, within 3 generations
The weight of parent is 3, and the weight of other relationships is 1.
Step S108 calculates different person-to-person cohesions according to multiple personage's social networks.
Specifically, personage's social networks can be carried out to the division of community, community divide can using modularity function and
GN algorithm can also use other methods, obtain the corresponding multiple communities of each personage's social networks, determine each destination node institute
Community personage's cohesion, Ren Wuqin can be obtained by personage's cohesion matrix according to the community where each destination node
Each position corresponds to a node in density matrix, and each position indicates the cohesion of destination node and other each nodes.
The determination method of above-mentioned personage's cohesion provided in an embodiment of the present invention, by obtaining the people in multiple social scenes
Object information, and according to the corresponding people information of each social activity scene, multiple social scene partitionings are formed into multiple social classifications, from
And according to the people information in each social classification, the corresponding personage's social networks of each social classification is constructed, and then according to multiple people
Object social networks calculates different person-to-person cohesions.When due to determining personage's cohesion, consider in multiple social scenes
People information, and multiple social scenes are divided into multiple social classifications, personage is calculated by single scene compared to the prior art
Cohesion, the present invention can effectively improve the accuracy of determining personage's cohesion.
For ease of understanding, the determination method based on another personage's cohesion provided in this embodiment is given below, referring to
A kind of flow chart of the determination method of personage's cohesion shown in Fig. 2, method includes the following steps:
Step S202 obtains the people information in multiple social scenes；Wherein, people information include blood relationship kinship,
One of interpersonal interactive information, trading activity information and trip information are a variety of.
Multiple social scene partitionings are formed multiple societies according to the corresponding people information of each social activity scene by step S204
Hand over classification；Wherein, at least one corresponding people information of social activity scene is included in each social classification.
Each social activity scene is corresponding with different people informations, and multiple social activity scenes can be divided into multiple social classifications,
Such as three social classifications of above-mentioned division, social classification is obtained according to multiple social scene partitionings, and the other number of social category can
With determines according to actual conditions.
Step S206 constructs the corresponding personage's social networks of each social classification according to the people information in each social classification；
It wherein, include multiple nodes and Lian Bian, the different individual of different node on behalf, even in the company of expression two in personage's social networks
There is association between two nodes at end.
Each social activity classification has corresponding personage's social networks, and the node on behalf in social networks is personal, two nodes
Between associated size can be indicated with weight, the incidence relation that the specific size of such as above-mentioned cited weight indicates.
Step S208 chooses the corresponding mesh of the personal difference of difference of cohesion to be determined from each personage's social networks
Mark node.
The personal corresponding destination node of difference for choosing cohesion to be determined according to the actual situation, can be to be determined
The people destination node corresponding with another people of cohesion is also possible to a people of cohesion to be determined and more
Personal corresponding destination node.
Step S210 carries out community's division to each personage's social networks according to modularity function and GN algorithm, obtains every
The corresponding multiple communities of a personage's social networks.
The side betweenness of each edge in personage's social networks is calculated according to GN algorithm, and is deleted when betweenness is maximum, then count
Calculate personage's social networks in it is remaining while while betweenness, when the value maximum of modularity function Q complete community division, modularity
Function Q is as follows:
Wherein, eijIt indicates the ratio of community i and community j internal edges number and total number of edges, indicates inside community i and community j
Point associated by the number on all sides and the ratio of total number of edges.
Step S212, the target community where determining each destination node in each personage's social networks.
There are multiple communities in personage's social networks, the position at place determines mesh in personage's social networks according to destination node
Mark the target community where node.
Step S214 is based on target community, calculates the cohesion matrix of each destination node；Wherein, cohesion matrix includes
One of single order cohesion matrix, second order cohesion matrix and three rank cohesion matrixes are a variety of.
Cohesion matrix includes single order cohesion matrix, and the calculation formula of single order cohesion matrixIt is as follows:
Wherein,Indicate that node i connects the number of nodes of first nodes with node j,Indicate that node i connects first nodes
Node total number,Indicate the node total number of node j connection first nodes, EiAnd EjSociety where respectively indicating node i and node j
Area works as Ei=EjWhen, ν (Ei, Ej) it is 1, work as Ei≠EjWhen, ν (Ei, Ej) it is 0.5,Indicate the first nodes connecting with node i
Company's number of edges,Indicate that the first nodes connecting with node i connect the average weight on side,Indicate the level-one connecting with node j
Company's number of edges of node,Indicate that the average weight for connecting side with the node j first nodes connecting, first nodes refer to and work as prosthomere
The node being connected directly is put, the numerical value in single order cohesion matrix is obtained according to single order cohesion calculation formula, single order cohesion
Numerical value in matrix is between 0 to 255.
Cohesion matrix includes second order cohesion matrix and/or three rank cohesion matrixes, and second order cohesion matrix and three
The calculation formula of rank cohesion matrixIt is as follows:
Wherein,Indicate that node i connects the number of nodes of k grades of nodes with node j,Indicate that node i connects k grades of nodes
Node total number,Indicate the node total number of k grades of nodes of node j connection,Indicate that node i connects the total number of paths of k grades of nodes,Indicate that node i connects the average weight of k grades of node paths,Indicate the total number of paths of k grades of nodes of node j connection,Indicate k grades of node paths of node j connection average weight, k grades of nodes refer to after the node of k-1, present node interval
The node being connected with present node；
The numerical value in numerical value and three rank cohesion matrixes in second order cohesion matrix is all in accordance with cohesion calculation formula
It obtains, the numerical value in numerical value and three rank cohesion matrixes in second order cohesion matrix is between 0 to 255.
The numerical value of each position is obtained according to above-mentioned cohesion calculation formula in cohesion matrix, such as in the parent of n × n
In density matrix, the corresponding node in each position, if the number of nodes currently selected less than n × n, without the corresponding position of node
Setting is indicated with 0, and the size of n is obtained by the following formula:
Wherein, floor (x) indicates to take the integer part of x, and N is the node total number in each personage's social networks, duplicate node
It only counts primary.
Step S216 converts cohesion color image for cohesion matrix according to the numerical value in cohesion matrix；Its
In, the range of the numerical value in cohesion matrix is identical with the pixel coverage of cohesion color image.
The color image that length and width are n × n is established, picture has the channel R, the channel G and channel B, such as three personage's social activities
Cohesion matrix in three personage's social networks is separately input to obtain after the channel R, the channel G and channel B corresponding by network
Cohesion color image, as the single order cohesion matrix in three personage's social networks is separately input to the RGB figure of color image
As obtaining single order cohesion color image behind channel.Since the pixel coverage of cohesion color image is 0 to 255 and cohesion
The numberical range of matrix is identical, therefore, obtains corresponding pixel size according to the numerical values recited of position each in cohesion matrix
Corresponding cohesion color image, each cohesion matrix can be converted into a cohesion color image.
Cohesion color image is input to the network model that training obtains in advance by step S218.
In one embodiment, the training process of network model is specific as follows:
(1) training picture is obtained.
Training picture can be according to the cohesion color image obtained in the above method by cohesion matrix, such as single order
Cohesion matrix is corresponding with single order cohesion color image, in one embodiment, can input simultaneously according to the above method
Obtained single order cohesion color image, second order cohesion color image and three rank cohesion color images.
(2) network model is trained by training picture, obtains the loss function value of network model.
By taking single order cohesion matrix to the corresponding cohesion color image of three rank cohesion matrixes as an example, network model
Loss function L are as follows:
L=f (qt,q1)+f(qt,q2)+f(qt,q3)
Wherein, qtIndicate the numerical value of corresponding practical personage's cohesion, q1、q2And q3Respectively indicate point of network model prediction
Not Dui Yingyu single order cohesion color image, second order cohesion color image and three rank cohesion color images numerical value, f (qt,
qk) indicating the penalty values in k rank cohesion color image, k takes the numerical value in 1,2 and 3, f (qt,qk) may be expressed as:
Wherein, n indicates the corresponding node total number of training picture.
Such as single order cohesion color image, second order cohesion color image and the three rank cohesion color images of above-mentioned input
Deng three color images, every color image is all a feature extraction network, such as above-mentioned q1、q2And q3, i.e. respectively single order
The number extracted in the feature extraction network of cohesion color image, second order cohesion color image and three rank cohesion color images
Value, the numerical value q with practical personage's cohesiontThe calculation formula for substituting into penalty values, so that penalty values be calculated.
(3) by back-propagation algorithm, the network parameter of the loss function value adjustment network model based on network model, directly
To network model loss function value convergence when, deconditioning.
When the loss function of network model converges to preset threshold, indicate network model can to personage's cohesion into
Row accurately calculates and exports preferable as a result, stopping the training to network model at this time, and training is completed.
Step S220 obtains the cohesion vector that network model is directed to the output of cohesion color image；Wherein, cohesion to
Cohesion of the amount comprising destination node and other nodes in personage's social networks.
Obtained each position in cohesion vector corresponds to a node in personage's social networks, each position
On numerical value indicate destination node and other nodes cohesion.
In conclusion the determination method of above-mentioned personage's cohesion provided in an embodiment of the present invention, cohesion matrix is converted
For cohesion picture, and cohesion picture is inputted into network model, so that it is defeated for cohesion color image to obtain network model
Cohesion vector out.When due to determining personage's cohesion, the people information in multiple social scenes is considered, and by multiple social activities
Scene is divided into multiple social classifications, calculates personage's cohesion by single scene compared to the prior art, the present invention can be effective
Improve the accuracy for determining personage's cohesion.
Corresponding to the determination method of aforementioned personage's cohesion, the embodiment of the invention provides a kind of determinations of personage's cohesion
Device, referring to a kind of structural block diagram of the determining device of personage's cohesion shown in Fig. 3, which is comprised the following modules:
Module 302 is obtained, for obtaining the people information in multiple social scenes；Wherein, people information includes blood relationship parent
One of category relationship, interpersonal interactive information, trading activity information and trip information are a variety of；
Division module 304, for according to the corresponding people information of each social activity scene, multiple social scene partitionings to be formed
Multiple social activity classifications；Wherein, at least one corresponding people information of social activity scene is included in each social classification；
Module 306 is constructed, for constructing the corresponding personage society of each social classification according to the people information in each social classification
Hand over network；It wherein, include multiple nodes and Lian Bian, the different individual of different node on behalf, Lian Bianbiao in personage's social networks
Show between even two nodes at side both ends that there is association；
Computing module 308, for calculating different person-to-person cohesions according to multiple personage's social networks.
The determining device of above-mentioned personage's cohesion provided in an embodiment of the present invention when due to determining personage's cohesion, considers
People information in multiple social activity scenes, and multiple social scenes are divided into multiple social classifications, pass through compared to the prior art
Single scene calculates personage's cohesion, and the present invention can effectively improve the accuracy of determining personage's cohesion.
Above-mentioned computing module 308 is further used for, and cohesion matrix includes single order cohesion matrix, and single order cohesion square
The calculation formula of battle arrayIt is as follows:
Wherein,Indicate that node i connects the number of nodes of first nodes with node j,Indicate that node i connects first nodes
Node total number,Indicate the node total number of node j connection first nodes, EiAnd EjSociety where respectively indicating node i and node j
Area works as Ei=EjWhen, ν (Ei, Ej) it is 1, work as Ei≠EjWhen, ν (Ei, Ej) it is 0.5,Indicate the first nodes connecting with node i
Company's number of edges,Indicate that the first nodes connecting with node i connect the average weight on side,Indicate the level-one connecting with node j
Company's number of edges of node,It indicates to connect the average weight on side with the node j first nodes connecting, first nodes refer to and currently
The node that node is connected directly, the numerical value in single order cohesion matrix are obtained according to single order cohesion calculation formula, and single order is intimate
The numerical value in matrix is spent between 0 to 255.
The technical effect of device provided by the present embodiment, realization principle and generation is identical with previous embodiment, for letter
It describes, Installation practice part does not refer to place, can refer to corresponding contents in preceding method embodiment.
The embodiment of the invention provides a kind of intelligent terminal, a kind of structural schematic diagram of intelligent terminal shown in Figure 4,
The intelligent terminal includes: processor 40, memory 41, bus 42 and communication interface 43, the processor 40,43 and of communication interface
Memory 41 is connected by bus 42；Processor 40 is for executing the executable module stored in memory 41, such as computer
Program.
Wherein, memory 41 may include high-speed random access memory (RAM, Random Access Memory),
It may further include non-labile memory (non-volatile memory), for example, at least a magnetic disk storage.By extremely
A few communication interface 43 (can be wired or wireless) is realized logical between the system network element and at least one other network element
Letter connection, can be used internet, wide area network, local network, Metropolitan Area Network (MAN) etc..
Bus 42 can be isa bus, pci bus or eisa bus etc..The bus can be divided into address bus, data
Bus, control bus etc..Only to be indicated with a four-headed arrow convenient for indicating, in Fig. 4, it is not intended that an only bus or
A type of bus.
Wherein, memory 41 is for storing program, and the processor 40 executes the journey after receiving and executing instruction
Sequence, method performed by the device that the stream process that aforementioned any embodiment of the embodiment of the present invention discloses defines can be applied to handle
In device 40, or realized by processor 40.
Processor 40 may be a kind of IC chip, the processing capacity with signal.During realization, above-mentioned side
Each step of method can be completed by the integrated logic circuit of the hardware in processor 40 or the instruction of software form.Above-mentioned
Processor 40 can be general processor, including central processing unit (Central Processing Unit, abbreviation CPU), network
Processor (Network Processor, abbreviation NP) etc.；It can also be digital signal processor (Digital Signal
Processing, abbreviation DSP), specific integrated circuit (Application Specific Integrated Circuit, referred to as
ASIC), ready-made programmable gate array (Field-Programmable Gate Array, abbreviation FPGA) or other are programmable
Logical device, discrete gate or transistor logic, discrete hardware components.It may be implemented or execute in the embodiment of the present invention
Disclosed each method, step and logic diagram.General processor can be microprocessor or the processor is also possible to appoint
What conventional processor etc..The step of method in conjunction with disclosed in the embodiment of the present invention, can be embodied directly in hardware decoding processing
Device executes completion, or in decoding processor hardware and software module combination execute completion.Software module can be located at
Machine memory, flash memory, read-only memory, programmable read only memory or electrically erasable programmable memory, register etc. are originally
In the storage medium of field maturation.The storage medium is located at memory 41, and processor 40 reads the information in memory 41, in conjunction with
Its hardware completes the step of above method.
The embodiment of the invention also provides a kind of computer readable storage medium, it is stored on computer readable storage medium
Computer program, when computer program is run by processor the step of the method for any one of execution previous embodiment.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description
Specific work process, can be with reference to the corresponding process in previous embodiment, and details are not described herein.
The determination method, apparatus of personage's cohesion provided by the embodiment of the present invention and the computer program of intelligent terminal produce
Product, the computer readable storage medium including storing program code, before the instruction that said program code includes can be used for execution
Method described in the embodiment of the method for face, specific implementation can be found in embodiment of the method, and details are not described herein.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic or disk.
Finally, it should be noted that embodiment described above, only a specific embodiment of the invention, to illustrate the present invention
Technical solution, rather than its limitations, scope of protection of the present invention is not limited thereto, although with reference to the foregoing embodiments to this hair
It is bright to be described in detail, those skilled in the art should understand that: anyone skilled in the art
In the technical scope disclosed by the present invention, it can still modify to technical solution documented by previous embodiment or can be light
It is readily conceivable that variation or equivalent replacement of some of the technical features；And these modifications, variation or replacement, do not make
The essence of corresponding technical solution is detached from the spirit and scope of technical solution of the embodiment of the present invention, should all cover in protection of the invention
Within the scope of.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (9)
1. a kind of determination method of personage's cohesion characterized by comprising
Obtain the people information in multiple social scenes；Wherein, the people information includes blood relationship kinship, interpersonal interaction letter
One of breath, trading activity information and trip information are a variety of；
According to the corresponding people information of each social scene, multiple social scene partitionings are formed into multiple social categories
Not；Wherein, include at least one corresponding people information of social activity scene in each social classification；
According to the people information in each social classification, the corresponding personage's social networks of each social activity classification is constructed；Wherein,
It include multiple nodes and Lian Bian, the different individual of the different node on behalf, the Lian Bianbiao in personage's social networks
Show between even two nodes at side both ends that there is association；
According to multiple personage's social networks, different person-to-person cohesions are calculated.
2. the method according to claim 1, wherein calculating different according to multiple personage's social networks
The step of cohesion between people, comprising:
The corresponding destination node of the personal difference of difference of cohesion to be determined is chosen from each personage's social networks；
Community's division is carried out to each personage's social networks according to modularity function and GN algorithm, obtains each personage
The corresponding multiple communities of social networks；
Target community where determining each destination node in each personage's social networks；
Based on the target community, the cohesion matrix of each destination node is calculated, and is generated and the cohesion matrix pair
The cohesion color image answered；Wherein, the cohesion matrix includes single order cohesion matrix, second order cohesion matrix and three ranks
One of cohesion matrix is a variety of；
The cohesion color image is input to the network model that training obtains in advance；
Obtain the cohesion vector that the network model is directed to cohesion color image output；Wherein, the cohesion to
Cohesion of the amount comprising destination node and other nodes in personage's social networks.
3. according to the method described in claim 2, it is characterized in that, the cohesion matrix includes single order cohesion matrix, and
The calculation formula of the single order cohesion matrixIt is as follows:
Wherein,Indicate that node i connects the number of nodes of first nodes with node j,Indicate the section of node i connection first nodes
Point sum,Indicate the node total number of node j connection first nodes, EiAnd EjCommunity where respectively indicating node i and node j,
Work as Ei=EjWhen, ν (Ei, Ej) it is 1, work as Ei≠EjWhen, ν (Ei, Ej) it is 0.5,Indicate the company for the first nodes connecting with node i
Number of edges,Indicate that the first nodes connecting with node i connect the average weight on side,Indicate the first nodes connecting with node j
Company's number of edges,Indicate that the average weight for connecting side with the node j first nodes connecting, the first nodes refer to and work as prosthomere
The node being connected directly is put, the numerical value in the single order cohesion matrix is obtained according to the single order cohesion calculation formula, institute
The numerical value in single order cohesion matrix is stated between 0 to 255.
4. according to the method described in claim 2, it is characterized in that, the cohesion matrix include second order cohesion matrix and/
Or three rank cohesion matrixes, and the calculation formula of the second order cohesion matrix and the three ranks cohesion matrixIt is as follows:
Wherein,Indicate that node i connects the number of nodes of k grades of nodes with node j,Indicate that node i connects the node of k grades of nodes
Sum,Indicate the node total number of k grades of nodes of node j connection,Indicate that node i connects the total number of paths of k grades of nodes,Indicate that node i connects the average weight of k grades of node paths,Indicate the total number of paths of k grades of nodes of node j connection,Indicate that the average weight of k grades of node paths of node j connection, the k grades of node refer to and k-1, present node interval section
The node being connected after point with present node；
The numerical value in numerical value and the three ranks cohesion matrix in the second order cohesion matrix is all in accordance with the cohesion meter
Calculate formulaIt obtains, the numerical value in numerical value and the three ranks cohesion matrix in the second order cohesion matrix is arrived 0
Between 255.
5. according to the method described in claim 4, it is characterized in that, described generate cohesion corresponding with the cohesion matrix
The step of color image, comprising:
According to the numerical value in the cohesion matrix, the cohesion color image is converted by the cohesion matrix；Wherein,
The range of numerical value in the cohesion matrix is identical with the pixel coverage of the cohesion color image.
6. a kind of determining device of personage's cohesion characterized by comprising
Module is obtained, for obtaining the people information in multiple social scenes；Wherein, the people information includes that blood relationship relatives are closed
One of system, interpersonal interactive information, trading activity information and trip information are a variety of；
Division module will multiple social activity scene partitioning shapes for according to the corresponding people information of each social scene
At multiple social classifications；Wherein, include at least one corresponding people information of social activity scene in each social classification；
Module is constructed, for constructing the corresponding personage of each social activity classification according to the people information in each social classification
Social networks；It wherein, include multiple nodes and Lian Bian, different of the different node on behalf in personage's social networks
People, the company have association when indicating the company between two nodes at both ends；
Computing module, for calculating different person-to-person cohesions according to multiple personage's social networks.
7. device according to claim 6, which is characterized in that the cohesion matrix includes single order cohesion matrix, and
The calculation formula of the single order cohesion matrixIt is as follows:
Wherein,Indicate that node i connects the number of nodes of first nodes with node j,Indicate the section of node i connection first nodes
Point sum,Indicate the node total number of node j connection first nodes, EiAnd EjCommunity where respectively indicating node i and node j,
Work as Ei=EjWhen, ν (Ei, Ej) it is 1, work as Ei≠EjWhen, ν (Ei, Ej) it is 0.5,Indicate the company for the first nodes connecting with node i
Number of edges,Indicate that the first nodes connecting with node i connect the average weight on side,Indicate the first nodes connecting with node j
Company's number of edges,Indicate that the average weight for connecting side with the node j first nodes connecting, the first nodes refer to and work as prosthomere
The node being connected directly is put, the numerical value in the single order cohesion matrix is obtained according to the single order cohesion calculation formula, institute
The numerical value in single order cohesion matrix is stated between 0 to 255.
8. a kind of intelligent terminal, which is characterized in that including processor and memory；
Computer program is stored on the memory, the computer program executes such as right when being run by the processor
It is required that 1 to 5 described in any item methods.
9. a kind of computer readable storage medium, computer program, feature are stored on the computer readable storage medium
The step of being, the described in any item methods of the claims 1 to 5 executed when the computer program is run by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811430496.0A CN109522489A (en) | 2018-11-27 | 2018-11-27 | The determination method, apparatus and intelligent terminal of personage's cohesion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811430496.0A CN109522489A (en) | 2018-11-27 | 2018-11-27 | The determination method, apparatus and intelligent terminal of personage's cohesion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109522489A true CN109522489A (en) | 2019-03-26 |
Family
ID=65793494
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811430496.0A Pending CN109522489A (en) | 2018-11-27 | 2018-11-27 | The determination method, apparatus and intelligent terminal of personage's cohesion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109522489A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111611531A (en) * | 2020-05-20 | 2020-09-01 | 杭州中奥科技有限公司 | Personnel relationship analysis method and device and electronic equipment |
| CN111708821A (en) * | 2020-06-19 | 2020-09-25 | 浙江大华技术股份有限公司 | Method and device for determining personnel intimacy and storage medium |
-
2018
- 2018-11-27 CN CN201811430496.0A patent/CN109522489A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111611531A (en) * | 2020-05-20 | 2020-09-01 | 杭州中奥科技有限公司 | Personnel relationship analysis method and device and electronic equipment |
| CN111611531B (en) * | 2020-05-20 | 2023-11-21 | 杭州中奥科技有限公司 | Personnel relationship analysis method and device and electronic equipment |
| CN111708821A (en) * | 2020-06-19 | 2020-09-25 | 浙江大华技术股份有限公司 | Method and device for determining personnel intimacy and storage medium |
| CN111708821B (en) * | 2020-06-19 | 2023-07-14 | 浙江大华技术股份有限公司 | Method, device and storage medium for determining personnel intimacy |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109544396A (en) | Account recommended method, device, server, terminal and storage medium | |
| CN107169463A (en) | Method for detecting human face, device, computer equipment and storage medium | |
| CN112396189A (en) | Method and device for multi-party construction of federal learning model | |
| US20130124448A1 (en) | Method and system for selecting a target with respect to a behavior in a population of communicating entities | |
| CN108022171B (en) | Data processing method and equipment | |
| CN107895038A (en) | A kind of link prediction relation recommends method and device | |
| CN110009365B (en) | User group detection method, device and equipment for abnormally transferring electronic assets | |
| CN112221159B (en) | Virtual item recommendation method and device and computer readable storage medium | |
| CN107818514B (en) | Method, device and terminal for controlling information propagation of online social network | |
| CN103310353B (en) | The data filtering of a kind of attack resistance optimizes system and method | |
| CN115270001B (en) | Privacy protection recommendation method and system based on cloud collaborative learning | |
| CN109522489A (en) | The determination method, apparatus and intelligent terminal of personage's cohesion | |
| CN111639230B (en) | Similar video screening method, device, equipment and storage medium | |
| Alvarez Fernandez et al. | A simheuristic algorithm for video streaming flows optimisation with QoS threshold modelled as a stochastic single-allocation p-hub median problem | |
| CN105844577A (en) | Relation network recognition method and device | |
| Jiang et al. | Temporal action-graph games: A new representation for dynamic games | |
| CN110765350A (en) | Data fusion method and device for member points | |
| CN111611532A (en) | Character relation completion method and device and electronic equipment | |
| He et al. | Blockchain Operations in the Presence of Security Concerns | |
| Bozzo et al. | Vulnerability and power on networks | |
| CN110490598A (en) | Method for detecting abnormality, device, equipment and storage medium | |
| CN111353001A (en) | Method and device for classifying users | |
| CN109255099B (en) | Computer readable storage medium, data processing method, data processing device and server | |
| CN112085530A (en) | Dynamic price adjusting method and system and electronic equipment | |
| CN109712012B (en) | Social network partitioning method, device, equipment and 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: 20190326 |
|
| RJ01 | Rejection of invention patent application after publication |