CN110084395A - Prediction technique, device, server and the storage medium of network public-opinion evolution result - Google Patents
Prediction technique, device, server and the storage medium of network public-opinion evolution result Download PDFInfo
- Publication number
- CN110084395A CN110084395A CN201910120187.1A CN201910120187A CN110084395A CN 110084395 A CN110084395 A CN 110084395A CN 201910120187 A CN201910120187 A CN 201910120187A CN 110084395 A CN110084395 A CN 110084395A
- Authority
- CN
- China
- Prior art keywords
- opinion
- individual
- network
- result
- network public
- 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
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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Abstract
The embodiment of the invention discloses prediction technique, device, server and the storage mediums of a kind of network public-opinion evolution result, wherein the described method includes: obtaining network public-opinion propagates all individual informations, and constructs oriented weighted network according to the individual information；The initial opinion of individual is extracted from the individual information, and the prediction result of network public-opinion Temporal Evolution is calculated according to the initial opinion and the oriented weighted network.The evolution of real world network public-opinion can be predicted according to the obedience dependence between individual is propagated in live network, it can be improved the accuracy that the evolution of network public-opinion is stood up, and it can be rapidly performed by prediction, provide more efficient accurate decision support for network public-opinion control.
Description
Technical field
The present invention relates to network public-opinion technical field more particularly to a kind of prediction techniques of network public-opinion evolution result, dress
It sets, server and storage medium.
Background technique
With the development of China's mobile terminal, 4G and WIFI radio network technique, people obtain the mode of information also more
Efficient and convenient, netizen's scale constantly expands.By the end of in December, 2017, China's netizen's scale reaches 7.72 hundred million, China's cellular network
People's scale using the accounting of surfing Internet with cell phone crowd is 97.5% in netizen, mobile telephone instant communication userbase reaches up to 7.53 hundred million
7.2 hundred million people will increase by 55,620,000 people compared with the end of the year 2016, and the 93.3% of Zhan Shouji netizen, mobile phone searching and cell phone network news make
82.9% and 82.3% are respectively reached with rate, more and more people carry out the acquisition and friendship of information by the smart phone in hand
Stream.Wherein, wechat, microblogging, know etc. that social applications function is gradually improved, subscriber usage is also constantly being promoted, these networks
Platform has become the principal mode of information propagation, and gradually affects the trend of the public public opinion impetus.Therefore, its rule of developing is studied
Rule and mechanism can effectively inhibit the propagation of bad public sentiment, and social governor is helped to be best understood from the social will of the people, control public opinion
Guiding.
In the implementation of the present invention, inventor has found following technical problem: currently, generalling use complex network carrys out mould
Quasi- real world, regards each individual as a node, and proposing individual viewpoint could be into only in certain threshold value
The discrete type of row information exchange and the bounded trust model of continuous type.But above-mentioned model does not account for the complexity of Internet communication
Property, information diversity and individual difference so that the prediction result that network public-opinion develops has a certain difference with legitimate reading.
Summary of the invention
The embodiment of the invention provides a kind of prediction technique of network public-opinion evolution result, device, server and storages to be situated between
Matter, with the lower technical problem of the solution prediction result accuracy that network public-opinion develops in the prior art.
In a first aspect, the embodiment of the invention provides a kind of prediction techniques of network public-opinion evolution result, comprising:
It obtains network public-opinion and propagates all individual informations, and oriented weighted network is constructed according to the individual information；
The initial opinion of individual is extracted from the individual information, according to the initial opinion and the oriented weighted network meter
Calculate the prediction result of network public-opinion Temporal Evolution.
Further, described to include: according to the oriented weighted network of individual information building
The individual information includes: individual amount, individual information propagation interactive relation and individual cohesion；
The number of nodes of oriented weighted network is determined according to the individual amount；
The line of oriented weighted network is generated according to the information exchange relationship between individual；
The weight of the line is determined according to the cohesion between individual.
It is further, described that oriented weighted network is constructed according to the individual information further include:
Judge whether the individual is leader of opinion according to the individual information；
It is that the corresponding node of the leader of opinion distributes angle value by preset rules when the individual is leader of opinion.
Further, described according to the initial opinion and the oriented weighted network calculates network public-opinion Temporal Evolution
Prediction result include:
As Shu Oi-Oj Shu≤ε, prediction result is calculated according to such as under type:
Oj (t+1)=Oj (t)-wij* (Oj (t)-Oi (t)), wherein the Oj (t+1) is j node at the t+1 moment
Opinion as a result, the Oj (t) be j node t moment opinion as a result, wij is the weighted value that node i and node j form side, institute
State Oi (t) be i-node in the opinion of t moment as a result, the ε is initial opinion discrepancy threshold.
Further, the method also includes:
As Shu Oi-Oj Shu > ε, prediction result is calculated according to such as under type:
Oi (t+1)=Oi (t).
Second aspect, the embodiment of the invention also provides a kind of prediction meanss of network public-opinion evolution result, comprising:
Module is constructed, propagates all individual informations for obtaining network public-opinion, and oriented according to individual information building
Weighted network；
Computing module, for extracting the initial opinion of individual from the individual information, according to the initial opinion and described
Oriented weighted network calculates the prediction result of network public-opinion Temporal Evolution.
Further, the parsing module includes:
First determination unit, for determining the number of nodes of oriented weighted network according to the individual information；
Generation unit, for generating the line of oriented weighted network according to the information exchange relationship between individual；
Second determination unit, for determining the weight of the line according to the cohesion between individual.
Further, the building module further include:
Judging unit, for judging whether the individual is leader of opinion according to the individual information；
Allocation unit, for being the corresponding section of the leader of opinion by preset rules when the individual is leader of opinion
Point distributes angle value.
Further, the computing module is used for:
As Shu Oi-Oj Shu≤ε, prediction result is calculated according to such as under type:
Oj (t+1)=Oj (t)-wij* (Oj (t)-Oi (t)), wherein the Oj (t+1) is j node at the t+1 moment
Opinion as a result, the Oj (t) be j node t moment opinion as a result, wij is the weighted value that node i and node j form side, institute
State Oi (t) be i-node in the opinion of t moment as a result, the ε is initial opinion discrepancy threshold.
Further, described device further include:
Second prediction and calculation unit, for calculating prediction result according to such as under type as Shu Oi-Oj Shu > ε:
Oi (t+1)=Oi (t).
The third aspect, the embodiment of the invention also provides a kind of server, the server includes:
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes the prediction technique of any network public-opinion evolution result provided by the above embodiment.
Fourth aspect, it is described the embodiment of the invention also provides a kind of storage medium comprising computer executable instructions
Computer executable instructions when being executed by computer processor for execute it is provided by the above embodiment it is any as described in net
The prediction technique of network public sentiment evolution result.
Prediction technique, device, server and the storage medium of network public-opinion evolution result provided in an embodiment of the present invention lead to
It crosses collected network individual information, and oriented weighted network is constructed according to the individual information, and from the individual information
The initial opinion of middle extraction individual, and the network public-opinion evolution result that can be healed according to initial opinion and oriented weighted network.It can root
The evolution of real world network public-opinion is predicted according to the obedience dependence between individual is propagated in live network, Neng Gouti
The accuracy that the evolution of high network public-opinion is stood up, and it can be rapidly performed by prediction, more efficient standard is provided for network public-opinion control
True decision support.
Detailed description of the invention
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, of the invention other
Feature, objects and advantages will become more apparent upon:
Fig. 1 is the flow diagram of the prediction technique for the network public-opinion evolution result that the embodiment of the present invention one provides；
Fig. 2 is the flow diagram of the prediction technique of network public-opinion evolution result provided by Embodiment 2 of the present invention；
Fig. 3 is the knot of oriented weighted network in the prediction technique of network public-opinion evolution result provided by Embodiment 2 of the present invention
Structure schematic diagram；
Fig. 4 is the flow diagram of the prediction technique for the network public-opinion evolution result that the embodiment of the present invention three provides；
Fig. 5 is the structural schematic diagram of the prediction meanss for the network public-opinion evolution result that the embodiment of the present invention four provides；
Fig. 6 is the structural schematic diagram for the server that the embodiment of the present invention five provides.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limiting the invention.It also should be noted that in order to just
Only the parts related to the present invention are shown in description, attached drawing rather than entire infrastructure.
Embodiment one
Fig. 1 is the flow diagram for the prediction technique that the embodiment of the present invention one provides network public-opinion evolution result, this implementation
Example is applicable to the case where predicting network public-opinion evolution result, and this method can be by the prediction of network public-opinion evolution result
Device executes, and can be integrated in network transmitting service device, specifically comprises the following steps:
S110 obtains network public-opinion and propagates all individual informations, and constructs oriented weighted network according to the individual information.
Currently, for public sentiment develop aspect research establish to varying degrees it is undirected, have no right network topology structure, very
The aeoplotropism of network is had ignored in big degree, it is believed that individual interaction is two-way exchange, and in real life, due to internet
Fast development, the appearance of the forms such as wechat circle of friends, microblogging, more people begin to focus on public platform, microblogging etc., receive information
Publication, but exchanging and share with publisher, public sentiment is also one way propagation.In addition due to close and distant between individual
The difference of relationship, in the propagation that also will affect information to a certain degree.Therefore, in the present embodiment, according to spreading network information
Characteristic constructs oriented weighted network.
Illustratively, it is soft to can use existing various social tools for all individual informations of the acquisition network public-opinion propagation
Part extracts.Such as: for social tools such as microbloggings, the individual information can be extracted, comprising: its owner of interest
Member, and pay close attention to all personnel of the individual.The all personnel for paying close attention to the individual can receive the public sentiment viewpoint of individual sending.
For social tools such as wechats, the individual information may include: the good friend of all open surfaces pair of individual circle of friends.Based on upper
The propagation relationship for stating network public-opinion, can construct oriented weighted network.Optionally, which can be done to an oriented weighted network
The start node of network, and relationship is propagated according to it and determines other nodes.And so on, determine all sections of oriented weighted network
Point.And the directed edge of the oriented weighted network can be determined according to the propagation relationship between each node, and strong and weak really according to influence power
Determine the weighted value of directed edge.
Illustratively, it can use set G={ N, L, W } to indicate the oriented weighted network of building, wherein N (nodes)
All number of nodes in network are represented, L (links) represents the line between node, and G (weight) represents weight representated by line
Value.Weighted value can be indicated with matrix W=[wij], wherein i, j ∈ { 1,2 ..., N }, wij is indicated in node i to saving in matrix
The weight of the oriented line of point j, if the value is 0, then it represents that node i does not have oriented line to node j.
S120 extracts the initial opinion of individual, according to the initial opinion and the oriented weighting from the individual information
The prediction result of network query function network public-opinion Temporal Evolution.
Each individual can all generate the initial opinion of individual in the outburst of public sentiment event for the event.In real network not
With individual because the difference of its Knowledge Attainments, acquisition information channel etc., is also not quite similar to the view of public sentiment event.This is initially anticipated
See and designates individual to the attitude of the event.The usual attitude can maintain a period of time, and carry out its that viewpoint interacts with it
The viewpoint of its individual changes.Therefore, the initial opinion of individual is an important factor for network public-opinion event develops.
Illustratively, it can establish the initial opinion of individual and carry out the opinion of other individuals of information exchange therewith at any time
The function of variation, and calculated according to the function, to obtain the prediction result of network public-opinion Temporal Evolution.And it can be directed to
The result intervenes network public-opinion event.
The present embodiment constructs oriented weighted network by collected network individual information, and according to the individual information,
And the initial opinion of individual is extracted from the individual information, and the network public-opinion that can heal according to initial opinion and oriented weighted network
Evolution result.It can be according to evolution of the obedience dependence to real world network public-opinion propagated in live network between individual
It is predicted, can be improved the accuracy that the evolution of network public-opinion is stood up, and prediction can be rapidly performed by, be network public-opinion control
System provides more efficient accurate decision support.
Embodiment two
Fig. 2 is the flow diagram of the prediction technique of network public-opinion evolution result provided by Embodiment 2 of the present invention.This reality
It applies example to optimize based on above-described embodiment, in the present embodiment, add described according to individual information building is oriented
Network is weighed, is specifically optimized are as follows: the individual information includes: individual amount, individual information propagation interactive relation and the intimate pass of individual
System, the number of nodes of oriented weighted network is determined according to the individual information；It is generated according to the information exchange relationship between individual
The line of oriented weighted network；The weight of the line is determined according to the cohesion between individual.
Correspondingly, the prediction technique of network public-opinion evolution result provided by the present embodiment, specifically includes:
S210 obtains network public-opinion and propagates all individual informations, and the individual information includes: individual amount, individual information
Propagate interactive relation and individual cohesion.
During Internet communication, each can usually be participated in the user of network event propagation as an individual.
Therefore, it is necessary to obtain network public-opinion to propagate all individual informations, to realize the prediction to network public-opinion evolution result.It is exemplary
, the individual information may include: individual amount, individual information propagation interactive relation and individual cohesion.
Wherein, the individual amount can reflect in network event communication process, the individual amount of participation, according to individual
Quantity can determine the scale of network public-opinion event；
The individual information propagates interactive relation, can reflect the entire propagation path of network public-opinion event, is convenient for network
The process monitoring and prediction of result that public sentiment event develops；
The individual cohesion reflects relationship individual between in network public-opinion communication process.Usually in real network group
In body, individual carries out more or less different to other people the receiving degree of viewpoint when information interchange, and the sight between individual
Point acceptance can't generally be varied widely with interactive progress.Usual cohesion is higher, by other side persuade can
Energy property is stronger.A possibility that itself viewpoint changes is also bigger, and therefore, individual cohesion is that a progress network public-opinion developed
An important parameter in journey prediction.
Illustratively, the individual information can be obtained by social software, can be by all participation network public-opinion events
Number of users as individual amount.And it is propagated and is interacted as individual information according to individual publication content in social media
Relationship；The cohesion between individual can also be determined according to the interaction degree between user and history interactive information.
S220 determines the number of nodes of oriented weighted network according to the individual amount.
Illustratively, all individual amounts in network public-opinion event will can be participated in as the number of nodes to weighted network
Amount, and the node of oriented weighted network is established accordingly.
S230 generates the line of oriented weighted network according to the information exchange relationship between individual.
Wired weighted network is made of node and line, is indicated many objects and its is connected each other.In the present embodiment,
Can be using information exchange relationship as the line of weighted network, the line can be unidirectional, or two-way.Fig. 3
It is the structural schematic diagram of oriented weighted network in the prediction technique of network public-opinion evolution result provided by Embodiment 2 of the present invention.By
Fig. 3 can be seen that the user participated in one network public-opinion event of each node on behalf in figure.Line therein shows user
Between the propagation relationship for the network public-opinion event.
S240 determines the weight of the line according to the cohesion between individual.
Individual cohesion reflects relationship individual between in network public-opinion communication process.Usually in real network colony
In, individual carries out more or less different to other people the receiving degree of viewpoint when information interchange, and the viewpoint between individual
Acceptance can't generally be varied widely with interactive progress.In order to consider that intimate degree is not between individual in population
Together, weighted network topological structure is constructed, assigns weight to every directed edge in artificial network to indicate two associated individuals
Between close and distant relation, weight is bigger, indicates that two individuals are more intimate, easier to be affected, thus the present embodiment utilize with
Individual viewpoint acceptance when directed edge weight between two nodes is as information exchange.It at the beginning, can will be described intimate
Degree is used as individual acceptance, and as the weight of line.
In addition, also it is contemplated that the obedience degree of individual, the obedience degree are used to show that the individual to be easy to change itself viewpoint
Degree.Due to everyone personality and course of growth difference, whether itself viewpoint is easy to be persuaded there is also different,
Accordingly it is also possible to comprehensive cohesion and weight of the obedience degree as line.With concentrated expression, the individual arrives different crowds
Opinion acceptance.
S250 extracts the initial opinion of individual, according to the initial opinion and the oriented weighting from the individual information
The prediction result of network query function network public-opinion Temporal Evolution.
The present embodiment is specific to optimize are as follows: described by constructing oriented weighted network according to the individual information for described
Body information includes: individual amount, individual information propagation interactive relation and individual close relationship, is had according to individual information determination
To the number of nodes of weighted network；The line of oriented weighted network is generated according to the information exchange relationship between individual；According to a
Cohesion between body determines the weight of the line.Oriented weighted network can be constructed for network public-opinion event establishment, with
So that the model is more in line with the actual conditions of network information interaction, the prediction of network public-opinion evolution result can be further increased
Accuracy.
In a preferred embodiment of the present embodiment, oriented weighted network can will be constructed according to the individual information
It advanced optimizes are as follows: judge whether the individual is leader of opinion according to the individual information；It is leader of opinion in the individual
When, it is that the corresponding node of the leader of opinion distributes angle value by preset rules.In a network, leader of opinion usually can be
" public figure " very active on microblogging, that have jumpbogroup bean vermicelli again.Usually " bean vermicelli " is large number of for it.With stronger influence
Power.It typically is the scholars and famous person that have certain popularity, so microblog account always has large quantities of beans vermicelli to track, and therefore become quick-fried
The recourse of material person.Often their primary forwarding will make a microblogging prevail rapidly, someone says that these opinions are led
Sleeve has been half of media in fact --- they constantly guide speech and topic on internet.This microblogging epoch almost
It is equal to the epoch of leader of opinion, the influence power of leader of opinion should not be underestimated, even the active base of drive Sina weibo user
Plinth.And work as the kernel that leader of opinion changes the microblogging of oneself commercial interest, or winning eyeball merely attracts bean vermicelli, a large amount of
When unchecked information even rumour arbitrarily reprints reference, just become " setter " to spread rumour.Therefore, important
In network public-opinion evolutionary process, it often be unable to do without adding fuel to the flames for leader of opinion.Therefore, in the present embodiment, need to network
Leader carries out specially treated, to further increase the accuracy of prediction.Firstly, it is necessary to judge described according to the individual information
Whether body is leader of opinion.Illustratively, network leader can be determined whether it is according to its audience or " bean vermicelli " quantity, shown
Example property, its audience or " bean vermicelli " quantity are determined as leader of opinion in 1,000,000 or more individual.Determining that it is opinion neck
When sleeve, is scheduled to last according to default rule and distribute more angle value out.In network public-opinion evolutionary process, often many users are not
Leader of opinion is paid close attention to, but the opinion of leader of opinion can often be propagated otherwise, and influence the use that do not pay close attention to
In family.For the network public-opinion propagation condition that preferably reflects reality, need to be that leader of opinion's distribution is more according to default rule
Go out angle value.Illustratively, it can be allocated according to a certain percentage according to original angle value out of leader of opinion, for example, pressing
Go out angle value according to 200% pro rate.Why angle value is only distributed, this is allowed in real network public sentiment communication process,
The opinion of other users influences can be ignored for leader of opinion.It, can be with by distributing more out-degree for leader of opinion
So that the model is more in line with the actual conditions of network information interaction, the prediction of network public-opinion evolution result can be further increased
Accuracy.
Embodiment three
Fig. 4 is the flow diagram of the prediction technique for the network public-opinion evolution result that the embodiment of the present invention three provides.This reality
Example is applied to optimize based on above-described embodiment, it in the present embodiment, will be described according to the initial opinion and described oriented
The prediction result that weighted network calculates network public-opinion Temporal Evolution specifically optimizes are as follows:
As Shu Oi-Oj Shu≤ε, prediction result is calculated according to such as under type:
Oj (t+1)=Oj (t)-wij* (Oj (t)-Oi (t)), wherein the Oj (t+1) is j node at the t+1 moment
Opinion as a result, the Oj (t) be j node t moment opinion as a result, wij is the weighted value that node i and node j form side, institute
State Oi (t) be i-node in the opinion of t moment as a result, the ε is initial opinion discrepancy threshold.
Correspondingly, the prediction technique of network public-opinion evolution result provided by the present embodiment, specifically includes:
S310 obtains network public-opinion and propagates all individual informations, and constructs oriented weighted network according to the individual information.
S320 extracts the initial opinion of individual, as Shu Oi-Oj Shu≤ε, according to such as under type meter from the individual information
Calculate prediction result:
Oj (t+1)=Oj (t)-wij* (Oj (t)-Oi (t)), wherein the Oj (t+1) is j node at the t+1 moment
Opinion as a result, the Oj (t) be j node t moment opinion as a result, wij is the weighted value that node i and node j form side, institute
State Oi (t) be i-node in the opinion of t moment as a result, the ε is initial opinion discrepancy threshold.
Illustratively, when two individual opinions are initially present larger difference, often it can't be persuaded, and freely be existed
When the two opinion difference disagreement is little, be possible to generate viewpoint variation.Therefore, in the present embodiment, the two is first determined whether
Between initial opinion difference, difference be less than the ε be initial opinion discrepancy threshold when, utilize following formula calculate prediction knot
Fruit:
Oj (t+1)=Oj (t)-wij* (Oj (t)-Oi (t)), wherein the Oj (t+1) is j node at the t+1 moment
Opinion as a result, the Oj (t) be j node t moment opinion as a result, wij is the weighted value that node i and node j form side, institute
State Oi (t) be i-node in the opinion of t moment as a result, the ε is initial opinion discrepancy threshold.
Wherein, initial opinion can be indicated with number, be can be set and be uniformly distributed in [0,1] section.Wherein
Individual holds the viewpoint value in [0,0.3] section to oppose attitude, and (0.3,0.7) is neutral attitude, and [0.7,1] is to support attitude.
Optionally, the obedience degree a of individual can be added in the formula, a can be to be uniformly distributed in [0,1] section.
It is uncompromising stand that wherein individual, which holds the viewpoint value in [0,0.3] section, and (0.3,0.7) is neutral attitude, and [0.7,1] is malleable
Attitude.A is multiplied with wij and (Oj (t)-Oi (t)), to obtain more accurate budget result.
Optionally, above-mentioned parameter can be input to Netlogo and carry out operation, to realize the mesh for quickly calculating prediction result
's.
S330 calculates prediction result: Oi (t+1)=Oi (t) according to such as under type as Shu Oi-Oj Shu > ε.
Illustratively, when two individual opinions are initially present larger difference, often it can't be persuaded, viewpoint
It is not easy to change, therefore, using the original viewpoint of holding.
The present embodiment by by described according to the initial opinion and the oriented weighted network calculates network public-opinion at any time
Between the prediction result that develops specifically optimize are as follows: as Shu Oi-Oj Shu≤ε, prediction result is calculated according to such as under type: Oj (t+1)=
Oj (t)-wij* (Oj (t)-Oi (t)), wherein the Oj (t+1) be j node the t+1 moment opinion as a result, the Oj
(t) be j node t moment opinion as a result, wij is the weighted value that node i and node j form side, the Oi (t) is i-node
T moment opinion as a result, the ε be initial opinion discrepancy threshold.Operation can be carried out using existing collected data, it is comprehensive
It closes and considers various aspects factor, obtain the prediction result of network public-opinion Temporal Evolution.
Example IV
Fig. 5 is the structural schematic diagram of the prediction meanss for the network public-opinion evolution result that the embodiment of the present invention four provides, such as Fig. 5
Shown, described device includes:
Module 410 is constructed, propagates all individual informations for obtaining network public-opinion, and be built with according to the individual information
To weighted network；
Computing module 420, for extracting the initial opinion of individual from the individual information, according to the initial opinion and institute
State the prediction result that oriented weighted network calculates network public-opinion Temporal Evolution.
The prediction meanss of network public-opinion evolution result provided in this embodiment, by collected network individual information,
And oriented weighted network is constructed according to the individual information, and the initial opinion of individual is extracted from the individual information, and can root
According to initial opinion and oriented weighted network healing network public-opinion evolution result.It can be propagated between individual according in live network
Obey dependence the evolution of real world network public-opinion is predicted, can be improved network public-opinion evolution stand up it is accurate
Property, and it can be rapidly performed by prediction, more efficient accurate decision support is provided for network public-opinion control.
On the basis of the various embodiments described above, the parsing module includes:
First determination unit, for determining the number of nodes of oriented weighted network according to the individual information；
Generation unit, for generating the line of oriented weighted network according to the information exchange relationship between individual；
Second determination unit, for determining the weight of the line according to the cohesion between individual.
On the basis of the various embodiments described above, the building module further include:
Judging unit, for judging whether the individual is leader of opinion according to the individual information；
Allocation unit, for being the corresponding section of the leader of opinion by preset rules when the individual is leader of opinion
Point distributes angle value.
On the basis of the various embodiments described above, the computing module is used for:
As Shu Oi-Oj Shu≤ε, prediction result is calculated according to such as under type:
Oj (t+1)=Oj (t)-wij* (Oj (t)-Oi (t)), wherein the Oj (t+1) is j node at the t+1 moment
Opinion as a result, the Oj (t) be j node t moment opinion as a result, wij is the weighted value that node i and node j form side, institute
State Oi (t) be i-node in the opinion of t moment as a result, the ε is initial opinion discrepancy threshold.
On the basis of the various embodiments described above, described device further include:
Second prediction and calculation unit, for calculating prediction result according to such as under type as Shu Oi-Oj Shu > ε:
Oi (t+1)=Oi (t).
Any embodiment of that present invention can be performed in the prediction meanss of network public-opinion evolution result provided by the embodiment of the present invention
The prediction technique of provided network public-opinion evolution result has the corresponding functional module of execution method and beneficial effect.
Embodiment five
Fig. 6 is a kind of structural schematic diagram for server that the embodiment of the present invention five provides.Fig. 6, which is shown, to be suitable for being used to realizing
The block diagram of the exemplary servers 12 of embodiment of the present invention.The server 12 that Fig. 6 is shown is only an example, should not be to this
The function and use scope of inventive embodiments bring any restrictions.
As shown in fig. 6, server 12 is showed in the form of universal computing device.The component of server 12 may include but not
Be limited to: one or more processor or processing unit 16, system storage 28 connect different system components (including system
Memory 28 and processing unit 16) bus 18.
Bus 18 indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller,
Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.It lifts
For example, these architectures include but is not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC)
Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.
Server 12 typically comprises a variety of computer system readable media.These media can be and any can be serviced
The usable medium that device 12 accesses, including volatile and non-volatile media, moveable and immovable medium.
System storage 28 may include the computer system readable media of form of volatile memory, such as arbitrary access
Memory (RAM) 30 and/or cache memory 32.Server 12 may further include other removable/nonremovable
, volatile/non-volatile computer system storage medium.Only as an example, storage system 34 can be used for reading and writing not removable
Dynamic, non-volatile magnetic media (Fig. 6 do not show, commonly referred to as " hard disk drive ").Although being not shown in Fig. 6, can provide
Disc driver for being read and write to removable non-volatile magnetic disk (such as " floppy disk "), and to removable anonvolatile optical disk
The CD drive of (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these cases, each driver can
To be connected by one or more data media interfaces with bus 18.Memory 28 may include at least one program product,
The program product has one group of (for example, at least one) program module, these program modules are configured to perform each implementation of the invention
The function of example.
Program/utility 40 with one group of (at least one) program module 42 can store in such as memory 28
In, such program module 42 include but is not limited to operating system, one or more application program, other program modules and
It may include the realization of network environment in program data, each of these examples or certain combination.Program module 42 is usual
Execute the function and/or method in embodiment described in the invention.
Server 12 can also be logical with one or more external equipments 14 (such as keyboard, sensing equipment, display 24 etc.)
Letter can also enable a user to the equipment interacted with the device/server/server 12 with one or more and communicate, and/or with
Any equipment (such as network interface card, the modulation /demodulation that the server 12 is communicated with one or more of the other calculating equipment
Device etc.) communication.This communication can be carried out by input/output (I/O) interface 22.Also, server 12 can also pass through
Network adapter 20 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network, such as
Internet) communication.As shown, network adapter 20 is communicated by bus 18 with other modules of server 12.It should be understood that
Although not shown in the drawings, other hardware and/or software module can be used in conjunction with server 12, including but not limited to: microcode,
Device driver, redundant processing unit, external disk drive array, RAID system, tape drive and data backup storage
System etc..
Processing unit 16 by the program that is stored in system storage 28 of operation, thereby executing various function application and
Data processing, such as realize the prediction technique of network public-opinion evolution result provided by the embodiment of the present invention.
Embodiment six
The embodiment of the present invention six additionally provides a kind of storage medium comprising computer executable instructions, and the computer can
It executes instruction when being executed by computer processor for executing the pre- of such as network public-opinion evolution result provided by the above embodiment
Survey method.
The computer storage medium of the embodiment of the present invention, can be using any of one or more computer-readable media
Combination.Computer-readable medium can be computer-readable signal media or computer readable storage medium.It is computer-readable
Storage medium for example may be-but not limited to-the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, device or
Device, or any above combination.The more specific example (non exhaustive list) of computer readable storage medium includes: tool
There are electrical connection, the portable computer diskette, hard disk, random access memory (RAM), read-only memory of one or more conducting wires
(ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-
ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer-readable storage
Medium can be any tangible medium for including or store program, which can be commanded execution system, device or device
Using or it is in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited
In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can
Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for
By the use of instruction execution system, device or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited
In wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof
Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++,
Further include conventional procedural programming language-such as " C " language or similar programming language.Program code can be with
It fully executes, partly execute on the user computer on the user computer, being executed as an independent software package, portion
Divide and partially executes or executed on a remote computer or server completely on the remote computer on the user computer.?
Be related in the situation of remote computer, remote computer can pass through the network of any kind --- including local area network (LAN) or
Wide area network (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as mentioned using Internet service
It is connected for quotient by internet).
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (10)
1. a kind of prediction technique of network public-opinion evolution result characterized by comprising
It obtains network public-opinion and propagates all individual informations, and oriented weighted network is constructed according to the individual information；
The initial opinion of individual is extracted from the individual information, and net is calculated according to the initial opinion and the oriented weighted network
The prediction result of network public sentiment Temporal Evolution.
2. the method according to claim 1, wherein described construct oriented weighted network according to the individual information
Include:
The individual information includes: individual amount, individual information propagation interactive relation and individual cohesion；
The number of nodes of oriented weighted network is determined according to the individual amount；
The line of oriented weighted network is generated according to the information exchange relationship between individual；
The weight of the line is determined according to the cohesion between individual.
3. according to the method described in claim 2, it is characterized in that, described construct oriented weighted network according to the individual information
Further include:
Judge whether the individual is leader of opinion according to the individual information；
It is that the corresponding node of the leader of opinion distributes angle value by preset rules when the individual is leader of opinion.
4. according to the method described in claim 3, it is characterized in that, described according to the initial opinion and the oriented weighted network
Network calculate network public-opinion Temporal Evolution prediction result include:
As Shu Oi-Oj Shu≤ε, prediction result is calculated according to such as under type:
Oj (t+1)=Oj (t)-wij* (Oj (t)-Oi (t)), wherein the Oj (t+1) is opinion of the j node at the t+1 moment
As a result, the Oj (t) be j node t moment opinion as a result, wij is the weighted value that node i and node j form side, the Oi
(t) be i-node in the opinion of t moment as a result, the ε is initial opinion discrepancy threshold.
5. according to the method described in claim 4, it is characterized in that, the method also includes:
As Shu Oi-Oj Shu > ε, prediction result is calculated according to such as under type:
Oi(t+1)=Oi(t)。
6. a kind of prediction technique device of network public-opinion evolution result characterized by comprising
Module is constructed, propagates all individual informations for obtaining network public-opinion, and oriented weighting is constructed according to the individual information
Network；
Computing module, for extracting the initial opinion of individual from the individual information, according to the initial opinion and described oriented
The prediction result of weighted network calculating network public-opinion Temporal Evolution.
7. device according to claim 6, which is characterized in that the individual information includes: individual amount, individual information biography
Broadcast interactive relation and personal relationship；
The building module, comprising:
First determination unit, for determining the number of nodes of oriented weighted network according to the individual information；
Generation unit, for generating the line of oriented weighted network according to the information exchange relationship between individual；
Second determination unit, for determining the weight of the line according to the cohesion between individual.
8. device according to claim 7, which is characterized in that the building module further include:
Judging unit, for judging whether the individual is leader of opinion according to the individual information；
Allocation unit, for being the corresponding node point of the leader of opinion by preset rules when the individual is leader of opinion
Allot angle value.
9. a kind of server, which is characterized in that the server includes:
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
Now such as the prediction technique of network public-opinion evolution result as claimed in any one of claims 1 to 5.
10. a kind of storage medium comprising computer executable instructions, the computer executable instructions are by computer disposal
For executing the prediction technique of the network public-opinion evolution result as described in claim 1-5 mono- when device executes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910120187.1A CN110084395A (en) | 2019-02-18 | 2019-02-18 | Prediction technique, device, server and the storage medium of network public-opinion evolution result |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910120187.1A CN110084395A (en) | 2019-02-18 | 2019-02-18 | Prediction technique, device, server and the storage medium of network public-opinion evolution result |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110084395A true CN110084395A (en) | 2019-08-02 |
Family
ID=67413048
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910120187.1A Pending CN110084395A (en) | 2019-02-18 | 2019-02-18 | Prediction technique, device, server and the storage medium of network public-opinion evolution result |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110084395A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113761337A (en) * | 2020-12-31 | 2021-12-07 | 国家计算机网络与信息安全管理中心 | Event prediction method and device based on implicit elements and explicit relations of events |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102012929A (en) * | 2010-11-26 | 2011-04-13 | 北京交通大学 | Network consensus prediction method and system |
| CN105243593A (en) * | 2015-08-04 | 2016-01-13 | 电子科技大学 | Weighted network community clustering method based on hybrid measure |
-
2019
- 2019-02-18 CN CN201910120187.1A patent/CN110084395A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102012929A (en) * | 2010-11-26 | 2011-04-13 | 北京交通大学 | Network consensus prediction method and system |
| CN105243593A (en) * | 2015-08-04 | 2016-01-13 | 电子科技大学 | Weighted network community clustering method based on hybrid measure |
Non-Patent Citations (3)
| Title |
|---|
| 何玉梅: "基于微博的个体持续度舆论动力学研究", 《情报科学》 * |
| 宁连举、万志超: "基于团购商品评论的网络意见领袖识别", 《情报杂志》 * |
| 马永军，杜禹阳: "基于复杂网络Deffuant 模型的舆情演化规律研究", 《情报杂志》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113761337A (en) * | 2020-12-31 | 2021-12-07 | 国家计算机网络与信息安全管理中心 | Event prediction method and device based on implicit elements and explicit relations of events |
| CN113761337B (en) * | 2020-12-31 | 2023-10-27 | 国家计算机网络与信息安全管理中心 | Event prediction method and device based on implicit event element and explicit connection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Guo et al. | TaskMe: Toward a dynamic and quality-enhanced incentive mechanism for mobile crowd sensing | |
| WO2021031607A1 (en) | Risk control method, computer device, and readable storage medium | |
| US20180211335A1 (en) | Method and apparatus for estimating user influence on social platform | |
| Xiao et al. | A diversity-based selfish node detection algorithm for socially aware networking | |
| CN112104642B (en) | Abnormal account number determination method and related device | |
| CN110417879A (en) | A kind of message treatment method, device, equipment and storage medium | |
| CN105808649B (en) | A kind of search result ordering method and its equipment | |
| CN104008182A (en) | Measuring method of social network communication influence and measure system thereof | |
| US11245649B2 (en) | Personalized low latency communication | |
| EP4134900A2 (en) | Method and apparatus for recommending content, method and apparatus for training ranking model, device, and storage medium | |
| US20170351769A1 (en) | System and Method for a Platform to Identify and Connect Like-Minded Individuals Based on Interaction | |
| CN116032663B (en) | Privacy data processing system, method, equipment and medium based on edge equipment | |
| KR20170101416A (en) | Method for providing funding and consulting information related with entertainment by crowd funding system | |
| CN109348258A (en) | The anti-brush method, apparatus of user's interaction, server and medium based on live streaming platform | |
| CN110084395A (en) | Prediction technique, device, server and the storage medium of network public-opinion evolution result | |
| CN109559246A (en) | Enter group checking method, audit server, client and enters group auditing system | |
| CN108959450A (en) | It is a kind of popular to comment on the system of determination, method, apparatus and readable medium | |
| US11916853B2 (en) | Group type identification method and apparatus, computer device, and medium | |
| CN104301205B (en) | Interactive bootstrap technique and device | |
| Wang et al. | Spreading mechanism of Weibo public opinion phonetic representation based on the epidemic model | |
| CN103200073A (en) | Method and device for information processing | |
| CN113742581B (en) | Method and device for generating list, electronic equipment and readable storage medium | |
| CN115203564A (en) | Information flow recommendation method and device and computer program product | |
| CN114782077A (en) | Information screening method, model training method, device, electronic equipment and medium | |
| CN109858945A (en) | Memory, user's result data generation method and equipment based on wechat small routine |
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: 20190802 |
|
| RJ01 | Rejection of invention patent application after publication |