CN109327488A - Network information push method, device and server - Google Patents
Network information push method, device and server Download PDFInfo
- Publication number
- CN109327488A CN109327488A CN201710643388.0A CN201710643388A CN109327488A CN 109327488 A CN109327488 A CN 109327488A CN 201710643388 A CN201710643388 A CN 201710643388A CN 109327488 A CN109327488 A CN 109327488A
- Authority
- CN
- China
- Prior art keywords
- network
- rumour
- user
- network information
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Transfer Between Computers (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention provides a kind of network information push methods, device and server, this method in advance divides each network user, the easy forwarding more network user of network rumour is divided to the first group, when the network information of server push be network rumour a possibility that score be greater than or equal to the first preset fraction when, forbid promoting the network user's push network information for belonging to the first group in user to plan, so that the network user of easily forwarding network rumour can't see the network information, the network information is shielded to the network user for belonging to the first group in plan popularization user, in real life, the network user for being easy communication network rumour generally belongs to the first group, the network user due to belonging to the first group is checked at all less than being largely the network information of network rumour, therefore, Be effectively controlled to be the propagation of the network information of network rumour.
Description
Technical field
The present invention relates to fields of communication technology, more particularly relate to network information push method, device and server.
Background technique
Network rumour refers to not to be had by what network medium (such as network forum, social network sites, chat software etc.) propagated
It has factual evidence with aggressiveness, the language of purpose.It relates generally to emergency event, public sphere, famous person important official, overturn biography
The contents such as system, guilty of heterodoxy.Gossip propagation has sudden and spreads speed and be exceedingly fast, therefore easily causes to normal civil order
Adverse effect.It disguises replacement of concept, take a part for the whole, food rumour is impossible to guard against；It would rather believe it, not believe that its nothing, group psychology accelerate to pass
It broadcasts.
Therefore, the technological difficulties and main points that the propagation of network rumour is this field how to be controlled.
Summary of the invention
In view of this, the present invention provides a kind of network information push method, device and server, to overcome the prior art
The problem of propagation of middle control network rumour.
To achieve the above object, the invention provides the following technical scheme:
A kind of network information push method is applied to server, comprising:
It obtains the network information and user is promoted in network information plan to be pushed to；
Obtain a possibility that network information is network rumour score；
The first group divided in advance is obtained, the network user for belonging to first group easily forwards the degree of network rumour
Greater than the degree that the network user for being not belonging to first group easily forwards network rumour；
When the possibility score is greater than or equal to the first preset fraction, forbid belonging into plan popularization user
The network user of first group pushes the network information.
A kind of network information push device, comprising:
First obtains module, promotes user for obtaining the network information and network information plan to be pushed to；
Second obtains module, for obtaining a possibility that network information is network rumour score；
Third obtains module, and for obtaining the first group divided in advance, the network user for belonging to first group is easy
The degree of forwarding network rumour easily forwards the degree of network rumour greater than the network user for being not belonging to first group；
Disabled module, for forbidding to the plan when the possibility score is greater than or equal to the first preset fraction
Promote the network user's push network information for belonging to first group in user.
A kind of server, comprising:
Memory, for storing program；
For executing described program, described program is specifically used for the processor:
It obtains the network information and user is promoted in network information plan to be pushed to；
Obtain a possibility that network information is network rumour score；
The first group divided in advance is obtained, the network user for belonging to first group easily forwards the degree of network rumour
Greater than the degree that the network user for being not belonging to first group easily forwards network rumour；
When the possibility score is greater than or equal to the first preset fraction, forbid belonging into plan popularization user
The network user of first group pushes the network information.
It can be seen via above technical scheme that compared with prior art, the embodiment of the invention provides a kind of network informations
In method for pushing, each network user is divided in advance, the more network user of easy forwarding network rumour is drawn
Divide to the first group, score is default more than or equal to first a possibility that the network information of server push is network rumour divides
When number, forbid promoting the network user's push network information for belonging to the first group in user to plan, so that easily turning
The network user of hairnet network rumour can't see the network information, i.e., the network user for belonging to the first group in user is promoted to plan
The network information is shielded, in real life, the network user for being easy communication network rumour generally belongs to the first group, by
It is checked at all less than being largely the network information of network rumour, therefore, effectively in the network user for belonging to the first group
Control may for network rumour the network information propagation.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The embodiment of invention for those of ordinary skill in the art without creative efforts, can also basis
The attached drawing of offer obtains other attached drawings.
Fig. 1 is a kind of schematic diagram that server provided in an embodiment of the present invention realizes network information push process；
Fig. 2 is another schematic diagram that server provided in an embodiment of the present invention realizes network information push process；
Fig. 3 is the flow chart of network information push method provided in an embodiment of the present invention；
Fig. 4 is that the network information is obtained in network information push method provided in an embodiment of the present invention is network rumour
A kind of method flow schematic diagram of implementation of possibility score；
Fig. 5 is that the process provided in an embodiment of the present invention for obtaining possibility score with the network information according to lists of keywords is shown
It is intended to；
Fig. 6 is a kind of architecture diagram of network information push method provided in an embodiment of the present invention application；
Fig. 7 is a kind of architecture diagram of network information push method provided in an embodiment of the present invention application；
Fig. 8 is the structure chart of server provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Currently, the network user can touch network rumour in following several application scenarios.
The first application scenarios, server is unified to be pushed.
For example, NEWS SERVER and news client can be by network information push extremely after server receives the network information
Each client.The network user can view network rumour by client.
Second of application scenarios, good friend share.
For example, the good friend of the network user may group (such as circle of friends or public platform or group, for example, QQ groups, it is micro-
Believe group etc.) the inner network rumour shared, the network user can touch network rumour by circle of friends or group.Businessman can be
Share network rumour in public platform, the network user for paying close attention to the public platform can touch the network rumour.
The network user is after touching network rumour, if phase communication network rumour, is likely to occur reprinting network rumour again
The phenomenon that, increase a possibility that more networks user touches network rumour.
To sum up, in order to effectively control the propagation of network rumour, the network user's contact for being easy phase communication network rumour is prevented
It is crucial to network rumour.For this purpose, the embodiment of the invention provides a kind of network information push methods.Below with reference to above two
Application scenarios are illustrated this method.
For the first application scenarios, server can in advance be drawn the network user registered in the server
Point, specifically as shown in Figure 1, the easy more network user for forwarding network rumour is divided to the first group 1 by server 11,
The lesser network user of degree of easy forwarding network rumour is divided to third group 2, when server 11 wants push network letter
When breath, a possibility that available network information is network rumour score, if possibility score is greater than or equal to first default point
When number, illustrate that a possibility that network information is network rumour is very big, at this point, server 11 when promoting the network information, is prohibited
The network user for only belonging to the first group 1 into the network user registered in the server forbids wrapping to the first group 1
The all-network user that contains pushes the network information, and the can be not belonging into the network user registered in the server
The network user that the network user of one group, i.e. third group 2 include pushes the network information.
Preferably, the network user registered in server 11 is the network user and third that the first group 1 includes
The network user that group 2 includes, server 11 can be divided into the first group 1 and third group 2 to chartered network user.
For second of application scenarios, reference can be made to Fig. 2, it is assumed that the network user 21 needs to share the network information to second group
Body 3, if the second group 3 is wechat circle of friends, the network user 21 wants the institute that the network information is shared with to wechat circle of friends
There is good friend；If the second group 3 be QQ group, the network user 21 want by the network information be shared with the group it is all at
Member；If the second group 3 is public platform, the network user 21 wants for the network information to be shared with all nets for paying close attention to the public platform
Network user；Due to being divided to the network user registered in server 11, that is, the first group 1 and are divided
Three groups 2, it is possible to determine which network user 31 belongs to the first group 1 from the network user that the second group 3 includes,
If a possibility that network information is network rumour score is greater than or equal to the first preset fraction, can forbid to the second group 3
In belong to the first group 1 the network user 31 send the network information.The net of third group 2 can be belonged into the second group 3
Network user 32 sends the network information.
In conjunction with above two application scenarios, the process of network information push method provided in an embodiment of the present invention be may refer to
Shown in Fig. 3, this method comprises:
Step S301: obtaining the network information and user is promoted in network information plan to be pushed to.
For the first application scenarios, plan push user can be for chartered all-network is used in the server
Family, the network information refer to the server network information to be pushed.
For second of application scenarios, plan push user can be shared the institute for including to the second group by the network user
There is the network user, the network information is network user's network information to be shared.
Step S302: a possibility that network information is network rumour score is obtained.
Step S303: the first group divided in advance is obtained.
The network user for belonging to first group easily forwards the degree of network rumour to be greater than and is not belonging to first group
The network user easily forward the degree of network rumour.
Server can in advance divide chartered all-network user, all-network user can be divided
For Liang Ge group, i.e. the first group and third group.Preferably, network rumour number can be reprinted based on each network user to carry out
It divides, for example, the total degree that the network user for belonging to the first group reprints network rumour is greater than the network use for belonging to third group
The total degree of family reprinting network rumour；Belong to or, the average time that the network user for belonging to the first group reprints network rumour is greater than
The average time of network rumour is reprinted in the network user of third group；Or, belonging to receiving an education for the network user of the first group
Level is below the education level for belonging to the network user of third group；Or, belonging to the credulity of the network user of the first group
Rumour score is greater than the credulity rumour score for belonging to the network user of third group, wherein credulity rumour score, which can be, to be based on
The network user reprints what the user characteristics such as network rumour number, education level and age calculated.
Step S304: when the possibility score is greater than or equal to the first preset fraction, forbid promoting to the plan
The network user for belonging to first group in user pushes the network information.
For the first application scenarios, " forbid promoting the network use for belonging to first group in user to the plan
Family pushes the network information ", refer to and forbids pushing the network information to the all-network user belonged in the first group；Needle
To second of application scenarios, " forbids promoting to the plan and belong to described in network user's push of first group in user
The network information " refers to and the network user for belonging to the first group into the second group is forbidden to push the network information.
In network information push method provided in an embodiment of the present invention, each network user is divided in advance, it will be easy
The more network user of forwarding network rumour is divided to the first group, when the network information of server push is network ballad
When a possibility that speech score is greater than or equal to the first preset fraction, forbid promoting the network for belonging to the first group in user to plan
User pushes the network information, so that the network user of easily forwarding network rumour can't see the network information, i.e., to meter
It draws to promote and belongs to the network user of the first group in user and shield the network information, in real life, be easy communication network
The network user of rumour generally belongs to the first group, and the network user due to belonging to the first group is checked at all less than very great Cheng
It is the network information of network rumour on degree, therefore, being effectively controlled to be the propagation of the network information of network rumour.
In the first application scenarios, if server promote the network information initial stage, just to each new network information
Step S301 to step S304 is executed, then the network user for belonging to the first group just can not be from client (such as news client)
In view the network information, the embodiment of the present invention can control network from source (initial stage of the server push network information)
The propagation of rumour；In second of application scenarios, if server has pushed the network information, or to the net for belonging to third group
Network user has pushed the network information, and when the network user for belonging to third group shares the network information, server can also shield
It covers and belongs to the network user of the first group in the good friend of the network user and view the network information, to share in the network user
During network rumour, the propagation of network rumour is controlled.
In the first application scenarios, any increase newly can be added to server when promoting the network information by server
The network information executes step S301 to step S304.In this case, the propagation that network rumour can be controlled from most source, because thus
When the network information do not have any reprinting amount also, also see the network information without the network user, such network information is in Internet communication
During, the network user for belonging to the first group never views the network information.But due to can all generate daily
The a large amount of new network information, considerably increases the data processing amount of server.
In order to solve this problem, reprinting amount can be greater than or equal to the network information of reprinting amount threshold value as step
The network information in S301.After execute step S301 to step S304, server can shield all first groups that belong to
The network user, but before this, since there is the network information certain reprinting amount to belong to first in this process
The network user of group may view the network information.
In second of application scenarios, server, can be right when receiving the instruction of network user's sharing network information
Each network information that each network user shares executes step S301 to step S304, and advantage and disadvantage are the same as the first application scenarios；
Server can recorde the reprinting amount of each network information, server when receiving the network user and sharing the instruction of the network information,
It can first judge the reprinting amount of the network information, if reprinting amount is greater than or equal to reprinting amount threshold value, which is executed
Step S301 to step S304.
There are many ways to " obtaining a possibility that network information is network rumour score " in the embodiment of the present invention, this
Inventive embodiments are provided but are not limited to following several.
The first, obtain the network information be network rumour a possibility that score as shown in figure 4, this method comprises:
Step S401: the keyword for including by network information pass corresponding with pre-stored each rumour classification respectively
Keyword is matched, and a possibility that network information is each rumour classification score is obtained.
Step S401 may include: extracted from the network information it includes keyword；The pass for including by the network information
Keyword corresponding with pre-stored each rumour classification carries out keyword respectively.Or, step S401 may include: determining network
It include the number of the corresponding keyword of each rumour classification in the content that information includes.
The rumour classification of network rumour can be divided into: finance and economics, amusement, automobile, politics, science and technology, military affairs, is gone through at sport
The rumours classification such as history.Other classifications can also be divided into, the type of the divided rumour classification of network rumour can be according to reality
Depending on the situation of border, it is not limited here.
Assuming that pre-stored each rumour classification includes A class rumour, B class rumour and C class rumour；Assuming that A class rumour pair
The keyword answered includes A1, A2, A3 ... AM；The corresponding keyword of B class rumour includes: B1, B2, B3 ... BN；C class rumour is corresponding
Keyword include: C1, C2, C3 ... CQ；Pre-stored each rumour classification can be stored in a table, be formed crucial
Word list.Wherein, M, N and Q are the positive integer more than or equal to 1, the key that the size of M, N, Q include with corresponding rumour classification
Word total number is related.
The keyword that the network information includes can be compared with each corresponding keyword of rumour classification respectively, it is assumed that net
The keyword one that keyword that network information includes and A class rumour match shares M1, then what the network information belonged to A class rumour can
Energy property score can be SA=M1/M*100；Assuming that the keyword one that keyword and B class rumour that the network information includes match
A possibility that shared N1 be'ss a, then the network information belongs to B class rumour score can be SB=N1/N*100；Assuming that the network information includes
Keyword and the keyword one that matches of C class rumour share Q1, then a possibility that network information belongs to C class rumour score can
Think SC=Q1/Q*100.
The process that the corresponding keyword of each rumour classification is stored in advance includes:
Each network rumour, is divided into different rumour classifications by the matching degree based on the keyword that each network rumour includes；
The corresponding keyword of network rumour for being included by each rumour classification is determined as the corresponding keyword of each rumour classification.
Each network rumour can be divided by each network rumour being identified in history by way of text cluster
Different rumour classifications.Obtain each rumour classification.
Text cluster (Text clustering) clustering documents are mainly to assume according to famous cluster: similar document
Similarity is larger, and inhomogeneous Documents Similarity is smaller.As a kind of unsupervised machine learning method, cluster due to being not required to
Training process is wanted, and is not needed in advance to document mark classification by hand, therefore with certain flexibility and higher automatic
Change processing capacity, has become the important means that text information is effectively organized, makes a summary and navigated, be more and more
Researcher is of interest.
Keyword can also be extracted from the network rumour being identified in history.By the higher network of keyword registration
Information is determined as a rumour classification.
It, can be by counting the higher name of the frequency of occurrences in the network rumour that each rumour classification includes after determining rumour classification
Word, verb, to obtain each corresponding keyword of rumour classification.
Step S402: by maximum likelihood score of each rumour classification a possibility that corresponding in score, it is determined as the net
A possibility that network information score.
The process of possibility score is obtained according to lists of keywords and the network information as shown in figure 5, the network information 51 in Fig. 5
It is matched respectively with rumour classification each in lists of keywords 52, obtains a possibility that network information is each rumour classification score,
It such as is respectively SA, SB, SC, it is assumed that SC is greater than SB and SA, it is determined that score is SC a possibility that the network information.
Assuming that having in the network information, 70 keywords are identical as 70 keywords of C class rumour, and C class rumour includes altogether
A possibility that 100 keywords, the then network information is C class rumour score SC=70.
It is understood that if the network information is identified as network rumour, it can be by the corresponding key of the network information
The corresponding keyword of the corresponding rumour classification of word update, enables the server to constantly identify new network rumour.Specific method
Include:
By the corresponding rumour classification of the maximum likelihood score, it is determined as rumour classification belonging to the network information；
According to the corresponding keyword of the network information, the corresponding key of rumour classification belonging to the network information is updated
Word.
Second, obtaining a possibility that network information is network rumour score includes:
The network user of the network information is shared in analysis, for example, whether the network user reprinted network rumour, if reprinting
It crosses, then obtains the network user and reprint network rumour number T；Whether proactive dissemination crosses network rumour to the network user, if issuing,
Then obtain network user's delivery network rumour number S.
The audient of the network information is analyzed, which shares in the second group of the network information and belong to the first group
The accounting R of the number of the network user and the number for the network user for being not belonging to the first group.
The network information itself is analyzed, for the keyword keyword corresponding with each rumour classification that the network information includes is obtained
With degree U (score of a possibility that in matching degree U, that is, first way).
It is analyzed in conjunction with above three as a result, a possibility that determining network rumour score.Specific formula can be such that
Possibility score=P1*S+P2*T+P3*R+P4*U, wherein P1, P2, P3, P4 are weight, can be according to practical feelings
Condition setting.The method that machine learning can also be used, will determined network rumour has inputted classifier in history, to obtain
P1, P2, P3 and P4.
" dividing the process of the first group in advance " in the embodiment of the present invention includes:
According to the user characteristics of each network user, the credulity rumour score of each network user, credulity rumour point are determined respectively
A possibility that number is for characterizing network user's phase communication network rumour；Credulity rumour score is greater than or equal to the second preset fraction
The network user is divided to first group.
Optionally, credulity rumour score is less than to the network user of second preset fraction, is divided to the second group.
Wherein, user characteristics may include: two dimensions of the behavior of network rumour and essential information, wherein network rumour
Behavior includes: forwarding network rumour number and/or publication rumour number；Essential information includes: head portrait, gender, user belonging country
One or more of family province city, age of user, education level.
Optionally, the credulity rumour score of each network user=W1* network rumour behavior+W2* essential information, wherein W1
It is weight with W2, depending on occurrence can be according to actual conditions.
In a preferred embodiment, the credulity rumour score of each network user=W11* forwarding network rumour number+
W12* issues the rumour number+W21* education level+W22* age.
Wherein, W11+W12=W1；W21+W22=W2.
There are many network rumour behaviors of each network user and the acquisition methods of essential information, and the embodiment of the present invention provides
But it is not limited to following methods.
The first, the server 11 in the embodiment of the present invention is login account used in network user login server 11
Associated server belonging to associated client.
" associated server belonging to the associated client of login account " is exemplified below, if login account is wechat account
Number, then it is wechat client with the client of wechat account relating, the affiliated associated server of wechat client is wechat server,
Server 11 is wechat server at this time；Login account is QQ account, then is QQ client with the client of wechat account relating,
The affiliated associated server of QQ client is QQ server, and server 11 is QQ server at this time.
The network user can be registered by client, and the affiliated associated server of client can store chartered
The data of each network user, such as the behavior of network rumour and essential information of each network user.
Therefore, the data for each network user that server 11 can have been registered directly in server from itself storage
In database, the behavior of network rumour and essential information of each network user are obtained respectively.
Second, the server 11 in the embodiment of the present invention is not that account is logged in used in network user login server 11
Associated server belonging to number associated client.
It illustrates below and second situation is illustrated, if the login account that the client of user login services device 11 uses
For wechat account, then server 11 may be NEWS SERVER, and associated server belonging to the client of wechat account relating
For wechat server；If the login account that the client of user login services device 11 uses is QQ account, server 11 may
For NEWS SERVER, and associated server belonging to the client of QQ account relating is QQ server.
Since all data of the network user are stored in wechat server or QQ server, server 11 is not present
In, therefore server 11 is needed from the affiliated associated server of the associated client of communication identifier of each network user, is obtained respectively
Take the behavior of network rumour and essential information of each network user.
Wherein, communication identifier is the login account of the corresponding client of server described in network user login.
As shown in fig. 6, for a kind of architecture diagram of network information push method provided in an embodiment of the present invention application.
Assuming that the server 11 in the embodiment of the present invention is known as first server 61；It obtains and stores each network user's
The server of the behavior of network rumour and essential information is second server 62；Obtain the network information whether be network rumour possibility
Property score is third server 63, then the relationship between first server 61, second server 62 and third server 63 is such as
Shown in Fig. 6.
First server 61 can obtain the network rumour behavior of each network user from second server 62 and believe substantially
Breath, then, calculates the credulity rumour score of each network user；Or, directly obtaining each network user from second server 62
Credulity rumour score, at this time second server 62 can the behavior of network rumour and essential information according to each network user, meter
Calculate the credulity rumour score of each network user.
First server 61 can obtain a possibility that network information is network rumour score from third server 63.
When possibility score is greater than or equal to the first preset fraction, first server 61 forbids promoting in user to plan
Belong to network user's pushing network information of the first group.
In different application scenarios, first server 61, second server 62 and third server 63 can be same
Server, for example, application involved in the network rumour behavior of the first each network user and the acquisition methods of essential information
Scene.First server 61 and second server 62 may be independent server, for example, the network of second of each network user
Application scenarios involved in the acquisition methods of rumour behavior and essential information.
Server obtains and stores the network rumour behavior of each network user and the approach of essential information may include:
The approach for obtaining the age of each network user includes:
The first, identification card number；The network user may be bound bank card and client, due in binding bank
During card, therefore the age of the network user can be known according to identification card number by needing the network user to input identification card number.
Second, good friend's average age；Using the average value at the age of the good friend of the network user as the age of the network user.
The third, client uses the average age of crowd；The average age of each network user of the client will be used
Age as the network user.
4th kind, if head portrait is the network user itself, using image identification function, identify the age of the network user.
5th kind, when registration, the network user has input the age；When the network user registers, oneself may be had input
Age, at this point it is possible to which at the age that the network user is inputted, be determined as the age of the network user.
The approach for obtaining the education level of each network user includes:
The first, good friend's grouping；Good friend may be grouped by the network user, for example, " university classmate ", " senior middle school is same
Learn " etc., the title of identification good friend's grouping, using highest educational background as the education level of the network user.
Second, the educational background of the good friend of the network user；By the highest educational background of the good friend of the network user or minimum educational background, determine
For the education level of the network user.
The third, according to the network information that the network user shares with the communication records of other good friends and/or the network user, really
Determine the education level of the network user.
4th kind, the network user may have input the previous graduate college of oneself in registration, the graduation filled according to user
School determines the education level of the network user.
The approach of network rumour behavior for obtaining the network user includes:
The number of network rumour will be had determined as in the network information of network user's forwarding, be determined as forwarding network rumour
Number；
And/or
The number of network rumour will be had determined as in the network information of network user's publication, be determined as delivery network rumour
Number.
In a preferred embodiment, it can calculate each network by the behavior of network rumour, education level and age and use
The credulity rumour score at family.
It is understood that credulity rumour score is positively correlated with age, network rumour behavior, it is negatively correlated with educational background.
For example, education level is very low (primary school), the network ballad propagated in history if people's age is very big (50 years old)
Say that number is very much (10), then his credulity rumour score L will be very high.Formula can be such that
L=(J1* age)+(behavior of J2* network rumour)-(J3* education level)
Wherein J1, J2 and J3 are weights, can be adjusted according to practical application scene.If score L reaches a certain threshold
It is worth (such as 70 points), then it is assumed that the user belongs to the first group；Conversely, belonging to third group.
The embodiment of the invention also provides a kind of network information push device corresponding with network information push method, below
Network information push device is illustrated, each module that network information push device includes.Each unit, each subelement and network
Corresponding steps are corresponding in information-pushing method, therefore are no longer described in detail, and specific be described in detail can be found in network information push
The explanation of corresponding steps in method.
As shown in fig. 7, being a kind of structure chart of network information push device provided in an embodiment of the present invention, the network information
Driving means includes:
First obtains module 71, promotes and uses for obtaining the network information and network information plan to be pushed to
Family；
Second obtains module 72, for obtaining a possibility that network information is network rumour score；
Third obtains module 73 and belongs to the network user of first group for obtaining the first group divided in advance
The degree of easily forwarding network rumour easily forwards the degree of network rumour greater than the network user for being not belonging to first group；
Disabled module 74, for forbidding to the meter when the possibility score is greater than or equal to the first preset fraction
It draws and promotes the network user's push network information for belonging to first group in user.
Optionally, the first acquisition module includes:
First acquisition unit waits sharing to the network information of the second group for obtaining the network user；
First determination unit, the network user for including by second group are determined as the plan and promote user.
Optionally, the first acquisition module includes:
Second acquisition unit, for obtaining the server network information to be promoted；
Second determination unit, the network user for that will register in the server are determined as the plan and push away
Wide user.
Optionally, the second acquisition unit includes:
First obtains subelement, the network information for being greater than or equal to reprinting amount threshold value for obtaining reprinting amount；
Or,
Second obtains subelement, for obtaining the newly-increased network information for adding to the server.
Optionally, the second acquisition module includes:
Third acquiring unit, keyword for including by the network information respectively with pre-stored each rumour classification
Corresponding keyword is matched, and a possibility that network information is each rumour classification score is obtained；
Third determination unit is determined for the maximum likelihood score by each rumour classification a possibility that corresponding in score
A possibility that for the network information score.
Optionally, further includes:
First division module, the matching degree of the keyword for including based on each network rumour divide each network rumour
At different rumour classifications；
First determining module, the corresponding keyword of network rumour for being included by each rumour classification, is determined as each ballad
Say the corresponding keyword of classification.
Optionally, further includes:
Second determining module, for being determined as the network letter for the corresponding rumour classification of the maximum likelihood score
Rumour classification belonging to breath；
Update module, for updating rumour belonging to the network information according to the corresponding keyword of the network information
The corresponding keyword of classification.
Optionally, further includes:
Third determining module determines the credulity ballad of each network user for the user characteristics according to each network user respectively
Say score, credulity rumour score is for a possibility that characterizing network user's phase communication network rumour；
Second division module is divided for credulity rumour score to be greater than or equal to the network user of the second preset fraction
To first group.
Optionally, third determining module includes:
4th acquiring unit, for obtaining the behavior of network rumour and essential information of each network user respectively；
Computing unit, for according to pre-set network rumour behavior and the corresponding weight of essential information, with
And the behavior of network rumour and essential information of each network user, calculate separately out the credulity rumour score of each network user.
Optionally, the 4th acquiring unit includes:
Third obtains subelement, for the data from the data for being stored with each network user registered in server
In library, the behavior of network rumour and essential information of each network user are obtained respectively；
Or,
4th obtains subelement, for the affiliated associated server of the associated client of communication identifier from each network user
In, the behavior of network rumour and essential information of each network user are obtained respectively, and communication identifier is to take described in network user login
The login account for the corresponding client of device of being engaged in.
The embodiment of the invention also provides a kind of server, the structure chart of the server can be as shown in Figure 8, comprising:
Memory 81, for storing program；
Program may include program code, and said program code includes computer operation instruction.
Processor 82, for executing described program.
Memory 81 may include high speed RAM memory, it is also possible to further include nonvolatile memory (non-volatile
Memory), a for example, at least magnetic disk storage.
Processor 82 may be a central processor CPU or specific integrated circuit ASIC (Application
Specific Integrated Circuit), or be arranged to implement the integrated electricity of one or more of the embodiment of the present invention
Road.
Wherein, described program is specifically used for:
It obtains the network information and user is promoted in network information plan to be pushed to；
Obtain a possibility that network information is network rumour score；
The first group divided in advance is obtained, the network user for belonging to first group easily forwards the degree of network rumour
Greater than the degree that the network user for being not belonging to first group easily forwards network rumour；
When the possibility score is greater than or equal to the first preset fraction, forbid belonging into plan popularization user
The network user of first group pushes the network information.
Optionally, server can also include communication bus 83 and communication interface 84, wherein memory 81, processor
82, communication interface 84, mutual communication is completed by communication bus 83；
Optionally, communication interface 84 can be the interface of communication module, such as the interface of gsm module.
Finally, it is to be noted that, herein, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that the process, method, article or equipment for including a series of elements not only includes that
A little elements, but also including other elements that are not explicitly listed, or further include for this process, method, article or
The intrinsic element of equipment.In the absence of more restrictions, the element limited by sentence "including a ...", is not arranged
Except there is also other identical elements in the process, method, article or apparatus that includes the element.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with other
The difference of embodiment, the same or similar parts in each embodiment may refer to each other.
The foregoing description of the disclosed embodiments makes professional and technical personnel in the field can be realized or use the application.
Various modifications to these embodiments will be readily apparent to those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the application.Therefore, the application
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest scope of cause.
Claims (15)
1. a kind of network information push method, which is characterized in that be applied to server, comprising:
It obtains the network information and user is promoted in network information plan to be pushed to；
Obtain a possibility that network information is network rumour score；
The first group divided in advance is obtained, the network user for belonging to first group easily forwards the degree of network rumour to be greater than
The network user for being not belonging to first group easily forwards the degree of network rumour；
When the possibility score is greater than or equal to the first preset fraction, forbid belonging into plan popularization user described
The network user of first group pushes the network information.
2. network information push method according to claim 1, which is characterized in that the acquisition network information and the net
User is promoted in the plan to be pushed to of network information
The network user is obtained to wait sharing to the network information of the second group；
The network user that second group includes is determined as the plan and promotes user.
3. network information push method according to claim 1, which is characterized in that the acquisition network information and the net
User is promoted in the plan to be pushed to of network information
Obtain the server network information to be promoted；
The network user that will have been registered in the server is determined as the plan and promotes user.
4. network information push method according to claim 3, which is characterized in that described to obtain server network to be promoted
Information includes:
Obtain the network information that reprinting amount is greater than or equal to reprinting amount threshold value；
Or,
Obtain the newly-increased network information for adding to the server.
5. network information push method according to claim 1, which is characterized in that described to obtain the network information as network
A possibility that rumour, score included:
By keyword that the network information includes, keyword corresponding with pre-stored each rumour classification is matched respectively,
Obtain a possibility that network information is each rumour classification score；
By maximum likelihood score of each rumour classification a possibility that corresponding in score, a possibility that being determined as the network information
Score.
6. network information push method according to claim 5, which is characterized in that described that each rumour classification correspondence is stored in advance
The process of keyword include:
Each network rumour, is divided into different rumour classifications by the matching degree based on the keyword that each network rumour includes；
The corresponding keyword of network rumour for being included by each rumour classification is determined as the corresponding keyword of each rumour classification.
7. network information push method according to claim 6, which is characterized in that further include:
By the corresponding rumour classification of the maximum likelihood score, it is determined as rumour classification belonging to the network information；
According to the corresponding keyword of the network information, the corresponding keyword of rumour classification belonging to the network information is updated.
8. network information push method according to claim 1, which is characterized in that the preparatory process for dividing the first group
Include:
According to the user characteristics of each network user, determine that the credulity rumour score of each network user, credulity rumour score are used respectively
In characterize the network user's phase communication network rumour a possibility that；
Credulity rumour score is greater than or equal to the network user of the second preset fraction, is divided to first group.
9. network information push method according to claim 8, which is characterized in that the user according to each network user is special
Sign, determines that the credulity rumour score of each network user includes: respectively
The behavior of network rumour and essential information of each network user are obtained respectively；
According to pre-set network rumour behavior and the corresponding weight of essential information and the network of each network user
Rumour behavior and essential information calculate separately out the credulity rumour score of each network user.
10. network information push method according to claim 9, which is characterized in that described to obtain each network user's respectively
The behavior of network rumour and essential information include:
From being stored in the database of the data for each network user that the server is registered, each network is obtained respectively
The network rumour behavior of user and essential information；
Or,
From the affiliated associated server of the associated client of communication identifier of each network user, the net of each network user is obtained respectively
The behavior of network rumour and essential information, communication identifier are the login account of the corresponding client of server described in network user login
Number.
11. a kind of network information push device characterized by comprising
First obtains module, promotes user for obtaining the network information and network information plan to be pushed to；
Second obtains module, for obtaining a possibility that network information is network rumour score；
Third obtains module, and for obtaining the first group divided in advance, the network user for belonging to first group is easily forwarded
The degree of network rumour easily forwards the degree of network rumour greater than the network user for being not belonging to first group；
Disabled module, for forbidding promoting to the plan when the possibility score is greater than or equal to the first preset fraction
The network user for belonging to first group in user pushes the network information.
12. network information push device according to claim 11, which is characterized in that described first, which obtains module, includes:
First acquisition unit waits sharing to the network information of the second group for obtaining the network user；
First determination unit, the network user for including by second group are determined as the plan and promote user.
13. network information push device according to claim 11, which is characterized in that described first, which obtains module, includes:
Second acquisition unit, for obtaining the server network information to be promoted；
Second determination unit, the network user for that will register in the server are determined as the plan and promote use
Family.
14. network information push device according to claim 11, which is characterized in that described second, which obtains module, includes:
Third acquiring unit, the keyword for including by the network information are corresponding with pre-stored each rumour classification respectively
Keyword matched, obtain the network information be each rumour classification a possibility that score；
Third determination unit is determined as institute for the maximum likelihood score by each rumour classification a possibility that corresponding in score
A possibility that stating network information score.
15. a kind of server characterized by comprising
Memory, for storing program；
For executing described program, described program is specifically used for the processor:
It obtains the network information and user is promoted in network information plan to be pushed to；
Obtain a possibility that network information is network rumour score；
The first group divided in advance is obtained, the network user for belonging to first group easily forwards the degree of network rumour to be greater than
The network user for being not belonging to first group easily forwards the degree of network rumour；
When the possibility score is greater than or equal to the first preset fraction, forbid belonging into plan popularization user described
The network user of first group pushes the network information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710643388.0A CN109327488B (en) | 2017-07-31 | 2017-07-31 | Network information pushing method and device and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710643388.0A CN109327488B (en) | 2017-07-31 | 2017-07-31 | Network information pushing method and device and server |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109327488A true CN109327488A (en) | 2019-02-12 |
| CN109327488B CN109327488B (en) | 2021-08-13 |
Family
ID=65245111
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710643388.0A Expired - Fee Related CN109327488B (en) | 2017-07-31 | 2017-07-31 | Network information pushing method and device and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109327488B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111291394A (en) * | 2020-01-31 | 2020-06-16 | 腾讯科技（深圳）有限公司 | False information management method, false information management device and storage medium |
| CN112417258A (en) * | 2020-12-02 | 2021-02-26 | 深圳市罗湖医院集团 | Crushing method, platform and terminal for rumor information in health knowledge search engine |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103902621A (en) * | 2012-12-28 | 2014-07-02 | 深圳先进技术研究院 | Method and device for identifying network rumor |
| CN104361231A (en) * | 2014-11-11 | 2015-02-18 | 电子科技大学 | Method for controlling rumor propagation in complicated network |
| CN105871700A (en) * | 2016-05-31 | 2016-08-17 | 腾讯科技（深圳）有限公司 | Message propagation method and server |
| CN106022856A (en) * | 2016-05-05 | 2016-10-12 | 北京京东尚科信息技术有限公司 | Data display method and device |
-
2017
- 2017-07-31 CN CN201710643388.0A patent/CN109327488B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103902621A (en) * | 2012-12-28 | 2014-07-02 | 深圳先进技术研究院 | Method and device for identifying network rumor |
| CN104361231A (en) * | 2014-11-11 | 2015-02-18 | 电子科技大学 | Method for controlling rumor propagation in complicated network |
| CN106022856A (en) * | 2016-05-05 | 2016-10-12 | 北京京东尚科信息技术有限公司 | Data display method and device |
| CN105871700A (en) * | 2016-05-31 | 2016-08-17 | 腾讯科技（深圳）有限公司 | Message propagation method and server |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111291394A (en) * | 2020-01-31 | 2020-06-16 | 腾讯科技（深圳）有限公司 | False information management method, false information management device and storage medium |
| CN112417258A (en) * | 2020-12-02 | 2021-02-26 | 深圳市罗湖医院集团 | Crushing method, platform and terminal for rumor information in health knowledge search engine |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109327488B (en) | 2021-08-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200286463A1 (en) | Using communicative discourse trees to create a virtual persuasive dialogue | |
| Karami et al. | Twitter and research: A systematic literature review through text mining | |
| US11748572B2 (en) | Enabling chatbots by validating argumentation | |
| Meel et al. | Fake news, rumor, information pollution in social media and web: A contemporary survey of state-of-the-arts, challenges and opportunities | |
| US10679011B2 (en) | Enabling chatbots by detecting and supporting argumentation | |
| US20200410166A1 (en) | Enabling chatbots by detecting and supporting affective argumentation | |
| Aljofey et al. | An effective detection approach for phishing websites using URL and HTML features | |
| US11386274B2 (en) | Using communicative discourse trees to detect distributed incompetence | |
| CN111615706A (en) | Analysis of spatial sparse data based on sub-manifold sparse convolutional neural network | |
| US20180365593A1 (en) | Data loss prevention system for cloud security based on document discourse analysis | |
| Jones | The right to a human in the loop: Political constructions of computer automation and personhood | |
| CN112313740A (en) | Aggregating semantic information to improve understanding of users | |
| CN111709052B (en) | Private data identification and processing method, device, equipment and readable medium | |
| US10248645B2 (en) | Measuring phrase association on online social networks | |
| CN103250175A (en) | Systems and methods for navigating electronic texts | |
| US9483740B1 (en) | Automated data classification | |
| US9407589B2 (en) | System and method for following topics in an electronic textual conversation | |
| US8396935B1 (en) | Discovering spam merchants using product feed similarity | |
| US20170235836A1 (en) | Information identification and extraction | |
| CN110348907A (en) | A kind of orientation method and device of advertisement crowd | |
| CN110083759A (en) | Public opinion information crawler method, apparatus, computer equipment and storage medium | |
| Weiss | Big data shocks: an introduction to big data for librarians and information professionals | |
| CN109327488A (en) | Network information push method, device and server | |
| US9516089B1 (en) | Identifying and processing a number of features identified in a document to determine a type of the document | |
| Johnston et al. | Identifying extremism in text using deep learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210813 |