CN110196955A - Information processing method, device and storage medium - Google Patents
Information processing method, device and storage medium Download PDFInfo
- Publication number
- CN110196955A CN110196955A CN201810522210.5A CN201810522210A CN110196955A CN 110196955 A CN110196955 A CN 110196955A CN 201810522210 A CN201810522210 A CN 201810522210A CN 110196955 A CN110196955 A CN 110196955A
- Authority
- CN
- China
- Prior art keywords
- parameter
- user node
- attention rate
- degree
- rate parameter
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
This application discloses a kind of information processing method, device and storage mediums, comprising: receives the description information of social network structure；Receive the first attention rate parameter for the event of each user node in the social network structure；According to the first attention rate parameter of each user node, the first attention rate parameter of the second user node being connected with each user node, weight parameter and received media releasing parameter, determine the second attention rate parameter of each user node, the third attention rate parameter of event is determined according to the second attention rate parameter of each user node, the variation tendency of third attention rate parameter is determined when the convergence of third attention rate parameter, when third attention rate parameter does not restrain, above-mentioned steps are repeated until third attention rate parameter restrains.
Description
Technical field
This application involves technical field of data processing more particularly to information processing methods, device and storage medium.
Background technique
The research of information disclosure model can be divided into three aspects: content research, Internet communication dynamics research and user's row
For research.Information content research is mainly the propagation characteristic from text angle research information itself；Internet communication dynamics research
Consider influence of the topological structure of network to communication mode；User property (such as interest-degree, year are then mainly studied in user behavior research
Age etc.) and influence of the behavioural characteristic to communication mode.In the prior art, for the emulation of information disclosure model (for example, for
The emulation of user's attention rate of media event), method for qualitative analysis is mostly used greatly, it can not be accurate, quantitative by the method for modeling
The mode that ground description information is propagated.
Summary of the invention
The embodiment of the present application provides a kind of information processing method, comprising:
The description information of social network structure is received, the description information includes include more in the social network structure
Between the user node that connection relationship and every two between a user node information, the multiple user node are connected
Weight parameter, the weight parameter is to characterize the correlation degree between be connected two user nodes；
Receive the first attention rate parameter for the event of each user node in the social network structure；
Following steps S1-S2 is executed for each first user node in the social network structure:
S1: receiving media releasing parameter, according to the description information, determines one to be connected with first user node
A or multiple second user nodes determine the weight of each second user node in one or more of second user nodes
Parameter and the first attention rate parameter；
S2: according to the first attention rate parameter of first user node, each second user node described first
Attention rate parameter and the weight parameter and the media releasing parameter currently determined, determine the of first user node
Two attention rate parameters；
S3: each first is determined according to the second attention rate parameter of the first user node each in the social network structure
The mean value of second attention rate parameter of user node is closed the mean value of the second attention rate parameter as the third of the event
Note degree parameter, and record the third attention rate parameter currently determined；
S4: when third participation parameter convergence, determine that third is joined according to each third participation parameter recorded
With the variation tendency of degree parameter；
S5: when the third participation parameter does not restrain, by the first user node each in the social network structure
The first participation parameter is assigned a value of the second participation parameter of each first user node respectively, returns to step
S1。
Present application example additionally provides a kind of information processing unit, comprising:
First receiving unit, to receive the description information of social network structure, the description information includes the social activity
Connection relationship and every two phase between multiple user node information for including in network structure, the multiple user node
Weight parameter between the user node of connection, the weight parameter is to characterize the pass between be connected two user nodes
Connection degree；
Second receiving unit, to receive each user node in the social network structure for the of the event
One attention rate parameter；
Variation tendency determination unit, to execute following processing:
Following steps S1-S2 is executed for each first user node in the social network structure:
S1: receiving media releasing parameter, according to the description information, determines one to be connected with first user node
A or multiple second user nodes determine the weight of each second user node in one or more of second user nodes
Parameter and the first attention rate parameter；
S2: according to the first attention rate parameter of first user node, each second user node described first
Attention rate parameter and the weight parameter and the media releasing parameter currently determined, determine the of first user node
Two attention rate parameters；
S3: each first is determined according to the second attention rate parameter of the first user node each in the social network structure
The mean value of second attention rate parameter of user node is closed the mean value of the second attention rate parameter as the third of the event
Note degree parameter, and record the third attention rate parameter currently determined；
S4: when third participation parameter convergence, determine that third is joined according to each third participation parameter recorded
With the variation tendency of degree parameter；
S5: when the third participation parameter does not restrain, by the first user node each in the social network structure
The first participation parameter is assigned a value of the second participation parameter of each first user node respectively, returns to step
S1。
Present application example additionally provides a kind of computer readable storage medium, is stored with computer-readable instruction, can make
At least one processor executes method as described above.
Using above scheme provided by the present application, determine that the variation tendency of the attention rate parameter of event is more accurate.
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
Some embodiments of invention without any creative labor, may be used also for those of ordinary skill in the art
To obtain other drawings based on these drawings.
Fig. 1 is the flow diagram of one example information processing method of the application；
Fig. 2 is the flow diagram for the second attention rate parameter that one example of the application determines each user node；
Fig. 3 is influence factor schematic diagram of one instance user of the application to the reaction of event；
Fig. 4 is interactional structural schematic diagram between itself each factor of one instance user of the application；
Fig. 5 is interactional structural schematic diagram between itself each factor of one instance user of the application and external factor；
Fig. 6 is the detailed process schematic diagram of one example information processing method of the application；
Fig. 7 (a) illustrate the simulation value of Japanese Kanto earthquake event-consumers information exchange behavior (ib) in 2011 with
Actual comparison figure on GoogleTrend and Twitter；
Fig. 7 (b) illustrate Fukushima, Japan nuclear radiation media event user information interbehavior simulation values in 2011 with
Actual comparison figure on GoogleTrend and Twitter；
Fig. 8 (a) illustrates the simulation value for the tsunami media event user emotion reaction that Japanese Kanto earthquake in 2011 causes
With the comparison diagram of the actual value in Twitter；
Fig. 8 (b) is illustrated in Fukushima, Japan nuclear radiation media event user emotion reaction simulation values in 2011 and Twitter
Actual comparison figure；
Fig. 9 is the structural schematic diagram of one example information processing unit of the application；And
Figure 10 is the calculating equipment composition structural schematic diagram in the embodiment of the present application.
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 the described embodiment is only a part of the embodiment of the present invention, instead of all the embodiments.Based on this
Embodiment in invention, every other reality obtained by those of ordinary skill in the art without making creative efforts
Example is applied, shall fall within the protection scope of the present invention.
Applicant has found under study for action, on the one hand, people are to the interbehavior of information and its own cognitive ability and emerging
Interest has much relations.For example, anxiety and pressure will if people feel very big uncertainty to external information
Increase, people and then the anxiety and pressure that itself is discharged by interbehaviors such as search information.In addition, applicant also sends out
Existing, the emotional intensity of people equally has an impact information exchange behavior, and emotional intensity can promote the interbehaviors such as information search,
Specifically, the people for having high emotion to react event often searches for and shares more information relevant to event.It is another
Aspect, applicant further found that, people are by mass media (such as TV or newspaper) and social media obtains and event topic
Relevant essential information.The covering of mass media pair and information concerning events will increase people's information exchange behavior, human behavior
It is also influenced by their spatial neighbors and social media circle of friends with mood.This interaction and public medium between crowd
External action plays an increasingly important role during individual decision making.To sum up, individual is based on the inside between factor at heart
The process of the influence meeting joint effect personal policy-making of interaction and social media and the network media to people.
Based on above-mentioned discovery, for mode accurate, that quantitatively description information is propagated, for example, accurately portraying media event
Attention rate variation tendency, this application provides information processing method, device and storage mediums.At information provided by the present application
Reason method can be executed by terminal device, can also be executed by server.The terminal device can be mobile phone, plate etc.
Portable computing device, PC machine etc..
Information processing method provided by the present application, as shown in Figure 1, mainly comprising the steps that
S101: receiving the description information of social network structure, and the description information includes wrapping in the social network structure
User's section that connection relationship and every two between multiple user node information for including, the multiple user node are connected
Weight parameter between point, the weight parameter is to characterize the correlation degree between be connected two user nodes.
In this example, the application provides a kind of model (also referred to as simulation model), and the model is by executing step S101-
The development trend of S108 simulated events, the trend for example, the attention rate parameter of event changes with time.Wherein step S101-
S102 is the process of initialization, as the model process of assigning initial value, in this example, to each step of step S101-S102
Sequence is without limitation.During initialization, media releasing prediction model r (t) can also be initialized, media hair
The media releasing information of cloth model characterization event changes with time trend.Issue the step of prediction model r (t) to determine lower section
Rapid S103-S108 recycle every time in the media releasing parameter used, which is that the related of media releasing information is joined
Number.The social network structure be it is virtual, simulate the topological structure of true social networks, react in actual life people with
Relationship of the people in social networks.The description information include the information of each of social network structure individual (herein,
Individual is also referred to as user node) and its locating environmental information.Social network structure can use G=<A, L, R>expression.Wherein A
={ aiIt is one group of network individual, each individual possesses the circle of friends of oneself, this circle of friends constitutes the local environment of individual.
Individual aiIt is connected with the individual in local environment.Set L={ < ai,aj,wij> | i ≠ j } it include user node aiIt is (also referred to as a
Body) circle of friends in user node aj, while further including user node aiWith each user node ajBetween weight parameter, should
The correlation degree between two user nodes that weight parameter characterization is connected, for example, the intimate degree between good friend.Individual ai
Local environment indicate that it contains individual a with symbol EliOne group of immediate neighbor or friend, El (ai)={ aj|<ai,aj>∈
L}.Behavior imitation and mood diffusion of the local environment between individual provide platform, and then influence the behaviour decision making mistake of individual
Journey.
S102: the first attention rate for the event for receiving each user node in the social network structure is joined
Number.
The first attention rate parameter is to characterize user to the degree of concern of the event.The first attention rate parameter
It may include the first participation, the first mood degree and the first cognition degree, first participation, the first mood degree and the first cognition
During degree is initialization, the good parameter of received user setting.Wherein, the first participation ib represents the letter of individual observable
It ceases interbehavior and delivers the quantity of media relevant to the event for example, forwarding the quantity of the media of the event.First
Mood degree ei represents anxiety degree of individual during some semiotics, and the first cognition degree rp represents individual to theme
Perceptual interest and risk recognize.First participation, the first mood degree are being initialized to the user node in social network structure
And when the first cognition degree, the user property value pc of each user node in social network structure can also be initialized, which belongs to
Property value represent individual personality attribute, wherein 1 represents optimistic type, 0 represents pessimism personality.It is each with normal distribution in initialization
The user property value of user node carries out tax initial value.For the benefit of simulation calculation, first participation, the first mood degree, first
Operation is all normalized in cognition degree and the user property value.
Heterogeneousization propagation characteristic is presented in event in social networks, it may be assumed that only a small amount of event can attract the attention of people
And excite a large number of users information exchange behavior；Meanwhile for some event, have the user of interbehavior same the event
It presents heterogeneous, it may be assumed that the event can only activate the information exchange behavior of specific user.It is social when being initialized to ib
The ib of user node in network structure is in normal distribution, according to the overall distribution to the user node in social network structure
Ib assigns initial value.Correspondingly, ei, rp of each user node and user property value pc are also in normal distribution, according to the normal state
Ei, rp to each user node and user property value pc assign initial value respectively for distribution.When assigning initial value, first with a normal state point
Cloth generates one group of random number, these random numbers is distributed to each user node in network.To ib, ei of each user node,
The initial value that rp and pc is assigned is unrelated with the development trend of the event finally emulated, and the normal distribution can be mean value with 0.5,
0.3 or 0.2 is variance.The mean and variance of the normal distribution can also be using other parameter values.
When carrying out tax initial value to the first attention rate parameter, the first attention rate parameter is carried out according to above-mentioned normal distribution
After assigning initial value, the first attention rate parameter of certain customers' node in social network structure can also be carried out according to the event
Adjustment.It is right when certain customers' node in social network structure is different from other users node to the susceptibility of the event
First attention rate parameter of this certain customers' node is adjusted.For example, when the event to be emulated is earthquake, then relative in
State, Japan is higher to the susceptibility of the event, carries out to ib, ei and rp of the user node for representing Japan in social network structure
It is corresponding to be turned up.
S103: following steps S104-S105 is executed for each first user node in the social network structure.
S104: receiving media releasing parameter, is connected according to the description information, determination with first user node
One or more second user nodes determine the power of each second user node in one or more of second user nodes
Weight parameter and the first attention rate parameter.
During initialization, prediction model r (t) can be issued with initial media.Can above-mentioned steps S101 it
Preceding initial media issues prediction model, initial media publication can also predict mould between above-mentioned steps S101 and S102
Type can also issue prediction model by initial media after above-mentioned steps S102.The media releasing prediction model is to table
Sign media releasing information changes with time trend.It is every executed a S103-S108 after, according to media releasing prediction model r
(t) media releasing parameter is determined.In step S104, determining media releasing parameter is directly received.Wherein, in each S103-
Media releasing parameter in the circulate operation of S108 is different, and the t value in each circulate operation is different, determining media releasing ginseng
Number is different, and after every circulate operation for executing a S103-S108, t value adds 1.Wherein, the media releasing parameter is the matchmaker of event
The parameter of body release information may include the quantity of the media side of the media releasing amount of the event, the publication event, described
Event is from initial release to issuing time etc. so far.When determining r (t), corresponding matchmaker is determined according to the type of the event
Body issues prediction model, and media releasing prediction model may include normal distribution model and damped expoential distributed model, work as event
When being emergency event, for example, tsunami event, then correspondingly adopt damped expoential distributed model, when event, which is, to predict event,
For example, hurricane event, then correspondingly adopt normal distribution model.Normal distribution model is indicated with following formula (1):
Damped expoential distributed model is indicated with following formula (2):
R (t)=exp (- t)α (2)
User is determined by the type of event still uses damped expoential distributed model using normal distribution model, with event
Corresponding media releasing prediction model is related with the type of event.When user inputs r (t) by interface, user can determine r
(t) parameter in is later inputted media releasing prediction model by interface.User is determining media releasing prediction model
When parameter, the media releasing information of event can be fitted according to the media releasing data of event (for example, media releasing amount, sends
The quantity etc. of the media of event) change with time trend, media releasing prediction model is determined according to the trend that fitting obtains
In parameter.In this implementation, user determines the parameter of media releasing prediction model, the media releasing prediction mould received
Type is the media releasing prediction model for determining parameter.In another middle implementation, received media releasing prediction model is
The media releasing prediction model for not determining parameter, the media releasing data of event is obtained by simulation model, and then according to media
Publication data determine the parameter of media releasing prediction model.The media releasing data may include on website with the event phase
The quantity of the media of pass.For example, can use the report that the softwares such as crawler crawl the news on news website for news
Road quantity obtains the report quantity of the news of a period of time, is fitted Xin Wen Bao according to the news report quantity of described a period of time
The trend of road quantity determines the parameter of news briefing prediction model according to the trend.
Media releasing model is that the media releasing of the event is believed to determine media releasing parameter, the media releasing parameter
The relevant parameter of breath.For each user node in social network structure, it can recycle and execute step S104-S105, until event
Third attention rate parameter convergence.When determining media releasing parameter, media releasing model is determined according to current cycle-index
In time t, i.e. t in formula (1) and formula (2).For example, being currently to recycle for the first time, then t=1, is currently to follow for the second time
When ring, t=2, and so on determine every time circulation when t value, and then determine media releasing parameter.The description of social network structure
Information includes the information of each body (also referred to as user node) and friend circle or the neighbours of each individual.It is saved for a user
Point determines that the one or more second user nodes being connected with the user node (determine one by one according to the description information
The good friend or neighbours of body), while determining the corresponding weight parameter of each second user node for being connected with the first user node.It should
Weight parameter characterizes the correlation degree between the first user node being connected and second user node, for example, between good friend
Intimate degree or interactional degree.
S105: according to the first attention rate parameter of first user node, each second user node described
One attention rate parameter and the weight parameter and the media releasing parameter currently determined, determine first user node
Second attention rate parameter.
People play different role in information communication process, explain people's behaviour decision making process and characteristics in spreading information
Rule is an eternal topic.People are based on self psychology and external action (friend to the reaction of uncertainty event
And institute, mass media) between interaction.It wherein, include interactive row relevant to the event to the reaction of uncertainty event
For and mood etc..The interbehavior includes, for example, the quantity of the model relevant to the event of forwarding, deliver with
The quantity etc. of the relevant model of the event, the interbehavior can be characterized with participation (ib).The mood includes
Body can characterize the anxiety degree of event, the mood with mood degree (ei).The self psychology includes individual
Ib and ei, while further including cognition degree (rp) of the individual to the event.The first attention rate parameter may include the ib,
Ei and rp.The external action includes the influence of mass media, for example, will affect for the quantity of the news report of an event
Reaction of the individual for the event, i.e., the described media releasing parameter will affect the attention rate parameter of individual.The external action
It further include social networks, for example, influence of the good friend of individual to the concern of event to the individual, influence of the good friend to individual is by each
The attention rate parameter of good friend and the corresponding weight parameter of each good friend determine.First attention rate parameter of i.e. each second user node and
Weight parameter will affect the attention rate parameter of the first user node.Thus, in this step, according to the first of the first user node
Attention rate parameter, the first attention rate parameter of each second user node and weight parameter and the media currently determined hair
Cloth parameter determines the second attention rate parameter of first user node.Wherein, the second attention rate parameter is once to follow
The attention rate parameter of the first user node updated in ring calculating, carries out by the attention rate parameter of each first user node
After update to get to each first user node the second attention rate parameter after, when executing cycle calculations next time, by each first
Second attention rate parameter assignment of user node gives the first attention rate parameter of each first user node.Influence personal policy-making process
All factors all can time to time change, thus need recycle execute, until according to the attention rate parameter of each user node it is true
The attention rate parameter of fixed event restrains.
S106: each is determined according to the second attention rate parameter of the first user node each in the social network structure
The mean value of second attention rate parameter of one user node, using the mean value of the second attention rate parameter as the third of the event
Attention rate parameter, and record the third attention rate parameter currently determined.
After performing step S104-S105, according to the second attention rate parameter of determining each first user node, determine
The third attention rate parameter of the event.Using the mean value of the second attention rate parameter of each first user node as the event
Third attention rate parameter.When in the second attention rate parameter and third attention rate parameter including multiple parameters, for example, participation ib
And when mood degree ei, using the mean value of the ib of each first user node as the ib of event, accordingly, by each first user node
Ei of the mean value of ei as event.
S107: when third participation parameter convergence, third is determined according to each third participation parameter recorded
The variation tendency of participation parameter.
S108: when the third participation parameter does not restrain, by the first user node each in the social network structure
The first participation parameter be assigned a value of the second participation parameter of each first user node respectively, return to step
S103。
In this example, the attention rate parameter for iteratively solving the user node in social network structure, until according to each use
The attention rate parameter (third attention rate parameter) of the attention rate parameter definite event of family node restrains.According to true in each circulation
Fixed third attention rate parameter, determines the variation tendency of third attention rate parameter, the variation tendency body of the third attention rate parameter
Variation tendency of the current family to the concern of the event.
Using above scheme provided by the present application, according to individual in social networks itself to the attention rate parameter of event, a
The good friend or neighbours of body are to the media releasing parameter more new individual of the attention rate parameter of event and the event to the pass of event
Note degree parameter.The attention rate parameter that event is determined according to attention rate parameter individual in social networks, with the attention rate of individual
The update of parameter determines the variation tendency of the attention rate parameter of event.In the attention rate parameter variation tendency for the event that determines, examine
Concern of the good friend in attention rate parameter, mass media's (media releasing parameter) and the social networks of individual itself to individual is considered
The influence of parameter is spent, the variation tendency of the attention rate parameter of definite event is more accurate.
In some instances, when executing above-mentioned steps S106, as shown in Figure 2, comprising the following steps:
S201: according to the first attention rate parameter of each second user node and the weight parameter, described
One attention rate parameter determines the first attention rate parameter change that each second user node generates first user node
Amount.
S202: it according to the first attention rate parameter and the media releasing parameter of first user node, determines
Second attention rate parameter change amount of first user node.
S203: according to the first attention rate parameter, the first attention rate parameter change amount and second concern
Parameter change amount is spent, determines the second attention rate parameter.
In above-mentioned steps S201, (used with first according to the good friend of (the first user node) individual in social network structure
Each second user node that family node is connected) attention rate parameter determine influence of its good friend to the first attention rate parameter.?
In above-mentioned steps S202, the influence of the attention rate parameter and social media of individual itself to the attention rate parameter of individual is determined, i.e.,
It determines the influence of the first attention rate parameter and media releasing parameter of individual to the attention rate of the first user node, that is, determines second
Attention rate parameter change amount.In step S203, according to the first attention rate parameter change amount and the second attention rate parameter change amount
It determines attention rate parameter change amount, and then determines that described second closes according to the attention rate parameter change amount, the first attention rate parameter
Note degree parameter.
Reaction of the user to event, as shown in figure 3, mainly being influenced by internal factor and external factor.Wherein it is internal because
Element refers to the internal factor of individual, and external factor then refers to other individuals associated with individual and environment.Wherein, internal factor
Including cognition degree (pr), interbehavior (ib) and intensity (ei) is influenced, external factor includes mass media and society
Communications media.Wherein, mass media includes public news, TV and broadcast etc., and social dissemination media include personal social
Network.
User is influenced to there is interaction, for example, in the communication process of event, people between the factor of the reaction of event
Can go to search with the information concerning events, for example, people spontaneously seek and share to have with event by modern communications channel
The message of pass mitigates the anxiety because of caused by the uncertainty of event with this.Influence user to each factor of the reaction of event it
Between the relationship that influences each other it is as shown in table 1, wherein interbehavior is also referred to as participation:
Table 1
Fig. 4 illustrates the correlation between internal factor individual in the communication process of event.In Fig. 4, arrow
Influence of the factor to another factor is represented, these influences constitute two kinds of feedback loops.Come from the behavior angle of observable
It sees, both feedback loops can be divided into clockwise enhancing feedback loop and weakening feedback loop counterclockwise.Enhancing feedback loop will excite
Individual makes more information exchange behaviors, and weakens feedback loop and then pass through the cognition and anxiety reduced to the external world, into one
Step reduces the information exchange behavior of individual.
Fig. 5 then further illustrates the influencing each other between each factor during event propagation.User is influenced to thing
The external factor of the reaction of part equally plays huge effect, the external factor include mass media and individual it is good
Friend or neighbours.In general, people are the basic letters that event is obtained by mass media (such as TV or newspaper etc.)
Breath, mass media will increase the mankind to the covering of information concerning events and seek behavior for the information of the event.People
The influence of their good friend or neighbours are similarly subjected to the reaction of event, as shown in figure 5, being mainly reflected in the individual for belonging to good friend
Between behavior imitation and mood diffusion.In Fig. 5, for external factor to individual event response influence, firstly, greatly
Many media will directly affect the cognition of individual to the report of event, and this cognition will further influence individual as the factor of adjusting
Mood and participative behavior.Secondly, social media provides a platform with exchanging for participative behavior for the mood of individual, between individual
Mood and participative behavior imitate meeting Spreading and diffusion in social media, and then form a kind of external feedback ring between individuals.
In some instances, the first attention rate parameter includes the first participation, the first mood degree and the first cognition degree,
The first attention rate parameter change amount includes the first mood degree knots modification, and the second attention rate parameter change amount includes second
Mood degree knots modification；
When determining the first attention rate parameter change amount, comprising steps of
S11: according to the first mood degree and weight parameter of each second user node, first user node
First cognition degree, determine that the first mood degree that each second user node generates first user node changes
Amount；
In step s 11, determine each second user node being connected with the first user node to the first user node
The influence of mood degree, i.e., the first mood degree knots modification of caused first user node.As shown in figure 5, individual interconnected
There are the diffusions of mood between (also referred to as user node), according to the mood degree and weight parameter of each good friend of an individual, really
The mood degree knots modification that fixed each good friend generates individual.
When determining the second attention rate parameter change amount, comprising steps of
S12: according to first participation of first user node, the first mood degree, first cognition
Degree and the media releasing parameter, the first participation and the first cognition degree for determining first user node are to described the
Second mood degree knots modification of the generation of one user node.
In step s 12, determine the first cognition degree, the first participation and media releasing parameter of the first user node to
The second mood degree knots modification that one user node generates.In Fig. 5, the first mood degree corresponds to mood, the corresponding ginseng of the first participation
With behavior, the corresponding cognition of the first cognition degree.Mass media's (corresponding media releasing parameter) will affect the cognition of individual, cognition
And then the mood and participative behavior of individual are influenced, meanwhile, participative behavior also will affect the mood of individual.In this step, it determines
Influence of the internal factor of individual to mood.
In some instances, the first mood degree knots modification is determined according to following formula (3):
Wherein,
Wherein, the wijFor the weight parameter for the second user node j being connected with the first user node i, the eiiFor
The first mood degree of first user node i, eijFor the first mood degree of second user node j, the rpiFor the first user node
The first cognition degree of i.
In some instances, the second mood degree knots modification is determined according to following formula (6):
FPM(eii)=eii·[1-r(t)·ibi·(1-rpi)] (6)
Wherein, the eiiFor the first mood degree of the first user node i, the ibiFor the first ginseng of the first user node i
With degree, the rpiFor the first cognition degree of the first user node i, the r (t) is the media releasing parameter.
In some instances, the first attention rate parameter includes the first participation, the first mood degree and the first cognition degree,
The first attention rate parameter change amount includes the first participation knots modification, and the second attention rate parameter change amount includes second
Participation knots modification；
When determining the first attention rate parameter change amount, comprising steps of
S21: according to the first participation, weight parameter and first user node of each second user node
The first cognition degree, determine the first participation knots modification that each second user node generates first user node.
In the step s 21, determine each second user node being connected with the first user node to the first user node
The influence of participation, i.e., the first participation knots modification of caused first user node.As shown in figure 5, individual interconnected
There are the imitations of behavior between (also referred to as user node), are joined according to the first participation of each good friend of an individual and weight
Number determines the participation knots modification that each good friend generates individual.
When determining the second attention rate parameter change amount, comprising steps of
S22: according to the first participation of first user node, the first mood degree, the first cognition degree and the matchmaker
Body issues parameter, determines that the first mood degree of first user node and the first cognition degree generate first user node
The second participation knots modification.
In step S22, determine the first cognition degree, the first mood degree and the media releasing parameter of the first user node to
The second participation knots modification that one user node generates.In Fig. 5, the first mood degree corresponds to mood, the corresponding ginseng of the first participation
With behavior, the corresponding cognition of the first cognition degree.Mass media's (corresponding media releasing parameter) will affect the cognition of individual, cognition
And then the mood and participative behavior of individual are influenced, meanwhile, mood also will affect the participative behavior of individual.In this step, it determines
Influence of the internal factor of individual to participative behavior.
In some instances, the first participation knots modification is determined according to following formula (7):
Wherein,
Wherein,
Wherein, the wijFor the weight parameter for the second user node j being connected with the first user node i, the ibiFor
The first participation of first user node i, ibjFor the first participation of second user node j, the rpiFor the first user node
The first cognition degree of i.
In some instances, the second participation knots modification is determined according to following formula (10):
FPM(ibi)=ibi·[1-(1-r(t))·(1-eii)(1-rpi)] (10)
Wherein, the ibiFor the first participation of the first user node i, the eiiFor the first feelings of the first user node
Thread degree, the rpiFor the first cognition degree of the first user node i, the r (t) is the media releasing parameter.
In some instances, the method further includes following steps:
S31: receiving the property parameters of the event, receives the user property value of each user node in the social networks.
Wherein, the first attention rate parameter includes the first participation, the first mood degree and the first cognition degree；
When executing above-mentioned steps S2, the method further includes following steps:
S32: according to the first mood degree of first user node, the first participation, the first cognition degree, user property value
And the media releasing parameter determines the second cognition degree of first user node.
In step S31, in initialization, the property parameters (p) of event are received, the value of p is determined according to the grade of event,
The p value of negative event is 0, and the p value of positive event is 1.Wherein p is a value between [0,1].As shown in figure 5, individual
Cognition will receive the influence of external factor (for example, mass media), while also being influenced (example by internal factor
Such as, mood and participative behavior).Thus, in this step, determine the first mood degree, the first participation and the outside of individual itself
Influence of the media releasing parameter to personal view.
In some instances, when determining second cognition degree,
Cognition degree knots modification is determined by following formula (11):
Wherein, Frp=rpi·[1-ibi·r(t)·(pci·p+(1-pci)·(1-p))] (12)
Second cognition degree is determined according to first cognition degree and the cognition degree knots modification；
Wherein, the eiiFor the first mood degree of the first user node, the rpiFor the first cognition of the first user node
Degree, the ibiFor the first participation of the first user node, the r (t) is the media releasing parameter, the pciIt is described
The user property value of first user node, the p are the property parameters of the event.
In some instances, information processing method provided by the present application further includes steps of
Receive the weight of the first attention rate parameter change amount and the coupling ginseng of the second attention rate parameter change amount
Number；According to the first attention rate parameter change amount, the second attention rate parameter change amount, the coupling parameter, determines and close
Note degree parameter change amount；Second attention rate is determined according to the first attention rate parameter and the attention rate parameter change amount
Parameter.
In this example,
Δsi=μ FSN(si)+(1-μ)FPM(si) (13)
Wherein, u be the coupling parameter, characterization the first attention rate parameter change amount and the second attention rate parameter change amount it
Between weight.Attention rate parameter change amount is determined according to formula (13), by the first attention rate parameter and attention rate parameter change amount
Adduction as the second attention rate parameter.In formula (13), the siRefer to ei or ib parameter.
In some instances, when executing above-mentioned steps S109, information processing method provided by the present application further comprises
Following steps:
In response to the update request to media releasing parameter, the media releasing parameter is updated.
Before recycle next time, media releasing parameter is updated according to media releasing model r (t).Specifically
Ground, determines the t value in circulation every time, updates media releasing parameter according to determining t value.In addition, when having emergency event
When, it needs to correct media releasing prediction model r (t), for example, after seismic events occur, occur later when event is earthquake again
Aftershock, media releasing prediction model before corresponds to the case where there is no aftershocks, thus needs to media releasing prediction model
It is modified.Revised media releasing prediction model is inputted by relevant interface, when simulation model executes next circulation
When, media releasing parameter is updated according to new media releasing prediction model.
The detailed process of information processing method provided by the present application, as shown in fig. 6, mainly comprising the steps that
S601: each major parameter is initialized.In initialization, the description information of the social network structure of setting is received, is connect
Ib, ei, rp and pc of each user in the social network structure of setting are received, while receiving the media releasing prediction mould of the event of setting
Type receives the grade p of the event of setting.
S602: current cycle-index is determined by media releasing parameter according to media releasing prediction model.
S603: the mood degree of i-th of user in social network structure is updated.
S604: the cognition degree of i-th of user in social network structure is updated.
S605: the participation of i-th of user in social network structure is updated.
S606: judge whether user is that the last one user in social network structure holds when for the last one user
Otherwise row step S607 executes step S603-S605 to user next in social network structure.
S607: the mood degree average value and participation average value of each user in social network structure are determined, mood degree is put down
The mood degree and participation of mean value and participation average value as event, and record the mood degree and participation of definite event.
S608: judging whether the mood degree of event and participation restrain, and when not restraining, executes step S609, works as convergence
When, execute step S610.
S609: when media releasing prediction model is updated, new media releasing prediction model is obtained.Step is executed later
S611: by cycle-index plus 1, return step S602 later.
S610: the mood degree variation tendency and event of event are determined according to each mood degree and participation of the event of record
The variation tendency of participation.
S611: by cycle-index plus 1.
It is verified by the simulation model that truthful data proposes the application.For example, with Japanese Kanto earthquake in 2011
The tsunami of initiation and Fukushima, Japan nuclear leakage are example, by crawler crawl the data that the data on news website crawl include from
The data obtained on GoogleTrend and Twitter obtain multiple users from the data of website and deliver, forward model quantity
Summation, and the section 0-1 is normalized to, using the third participation (ib) as the event.User is analyzed simultaneously to deliver, forward
The content of text of model determines the mood degree of each model, the ei by the average mood degree (ei) of each model as event.Wherein,
Fig. 7 (a) is illustrated in the tsunami media event that Japanese Kanto earthquake in 2011 causes, the emulation of user information interbehavior (ib)
Value and the actual comparison figure on GoogleTrend and Twitter；Fig. 7 (b) illustrates Fukushima, Japan nuclear radiation news in 2011
Actual comparison figure in event, on user information interbehavior simulation value and GoogleTrend and Twitter.Fig. 8 (a) Fig. 8
(b) comparison of the simulation result and truthful data of emotional reactions (ei) is illustrated, wherein Fig. 8 (a) illustrates 2011 years Japan and closes
In the tsunami media event that eastern earthquake causes, the comparison diagram of the actual value in the simulation value and Twitter of user emotion reaction；Figure
8 (b) illustrate in Fukushima, Japan nuclear radiation media event in 2011, and user emotion reacts actual value in simulation value and Twitter
Comparison diagram.Verification result experiment shows that simulation model provided by the present application has preferable precision of prediction.
Present invention also provides a kind of information processing units 900, as shown in Figure 9, comprising:
First receiving unit 901, to receive the description information of social network structure, the description information includes the society
Hand over the connection relationship and every two between the multiple user node information for including in network structure, the multiple user node
The weight parameter between user node being connected, the weight parameter is to characterize between be connected two user nodes
Correlation degree；
Second receiving unit 902, to receive each user node in the social network structure for the event
The first attention rate parameter；
Variation tendency determination unit 903, to execute following processing:
Following steps S1-S2 is executed for each first user node in the social network structure:
S1: receiving media releasing parameter, according to the description information, determines one to be connected with first user node
A or multiple second user nodes determine the weight of each second user node in one or more of second user nodes
Parameter and the first attention rate parameter；
S2: according to the first attention rate parameter of first user node, each second user node described first
Attention rate parameter and the weight parameter and the media releasing parameter currently determined, determine the of first user node
Two attention rate parameters；
S3: each first is determined according to the second attention rate parameter of the first user node each in the social network structure
The mean value of second attention rate parameter of user node is closed the mean value of the second attention rate parameter as the third of the event
Note degree parameter, and record the third attention rate parameter currently determined；
S4: when third participation parameter convergence, determine that third is joined according to each third participation parameter recorded
With the variation tendency of degree parameter；
S5: when the third participation parameter does not restrain, by the first user node each in the social network structure
The first participation parameter is assigned a value of the second participation parameter of each first user node respectively, returns to step
S1。
Using information processing unit provided by the present application, the attention rate of event is joined according to individual in social networks itself
Number, the good friend of individual or neighbours are to the attention rate parameter of event and the media releasing parameter more new individual of the event to event
Attention rate parameter.The attention rate parameter that event is determined according to attention rate parameter individual in social networks, with the pass of individual
The update of note degree parameter determines the variation tendency of the attention rate parameter of event.In the attention rate parameter variation tendency for the event that determines
When, it is contemplated that the good friend in the attention rate parameter of individual itself, mass media's (media releasing parameter) and social networks is to individual
Attention rate parameter influence, the variation tendency of the attention rate parameter of definite event is more accurate
In some instances, the variation tendency determination unit 903, to:
According to the first attention rate parameter of each second user node and the weight parameter, first concern
Parameter is spent, determines the first attention rate parameter change amount that each second user node generates first user node；
According to the first attention rate parameter and the media releasing parameter of first user node, described is determined
Second attention rate parameter change amount of one user node；
According to the first attention rate parameter, the first attention rate parameter change amount and the second attention rate parameter
Knots modification determines the second attention rate parameter.
The embodiment of the present application also provides a kind of computer readable storage mediums, are stored with computer-readable instruction, can be with
At least one processor is set to execute method as described above.
Figure 10 shows the composite structural diagram of the calculating equipment where information processing unit 900.As shown in Figure 10, the calculating
Equipment includes one or more processor (CPU) 1002, communication module 1004, memory 1006, user interface 1010, and
For interconnecting the communication bus 1008 of these components.
Processor 1002 can send and receive data by communication module 1004 to realize network communication and/or locally lead to
Letter.
User interface 1010 includes one or more output equipments 1012 comprising one or more speakers and/or one
A or multiple visual displays.User interface 1010 also includes one or more input equipments 1014 comprising such as, key
Disk, mouse, voice command input unit or loudspeaker, touch screen displays, touch sensitive tablet, posture capture camera or other are defeated
Enter button or control etc..
Memory 1006 can be high-speed random access memory, such as DRAM, SRAM, DDR RAM or other deposit at random
Take solid storage device；Or nonvolatile memory, such as one or more disk storage equipments, optical disc memory apparatus, sudden strain of a muscle
Deposit equipment or other non-volatile solid-state memory devices.
The executable instruction set of 1006 storage processor 1002 of memory, comprising:
Operating system 1016, including the journey for handling various basic system services and for executing hardware dependent tasks
Sequence；
Using 1018, including some or all of information processing unit 900 unit or module.Information processing unit 900
In at least one unit can store machine-executable instruction.Processor 1002 is by executing each unit in memory 1006
In machine-executable instruction at least one unit, and then can be realized at least one module in above-mentioned each unit or module
Function.
It should be noted that step and module not all in above-mentioned each process and each structure chart be all it is necessary, can
To ignore certain steps or module according to the actual needs.Each step execution sequence be not it is fixed, can according to need into
Row adjustment.The division of each module is intended merely to facilitate the division functionally that description uses, and in actual implementation, a module can
It is realized with point by multiple modules, the function of multiple modules can also be realized by the same module, these modules can be located at same
In a equipment, it can also be located in different equipment.
Hardware module in each embodiment can in hardware or hardware platform adds the mode of software to realize.Above-mentioned software
Including machine readable instructions, it is stored in non-volatile memory medium.Therefore, each embodiment can also be presented as software product.
In each example, hardware can be by special hardware or the hardware realization of execution machine readable instructions.For example, hardware can be with
Permanent circuit or logical device (such as application specific processor, such as FPGA or ASIC) specially to design are used to complete specifically to grasp
Make.Hardware also may include programmable logic device or circuit by software provisional configuration (as included general processor or other
Programmable processor) for executing specific operation.
In addition, each example of the application can pass through the data processor by data processing equipment such as computer execution
To realize.Obviously, data processor constitutes the application.In addition, being commonly stored data processing in one storage medium
Program is by directly reading out storage medium or the storage by program being installed or being copied to data processing equipment for program
It is executed in equipment (such as hard disk and/or memory).Therefore, such storage medium also constitutes the application, and present invention also provides one
Kind non-volatile memory medium, wherein being stored with data processor, this data processor can be used for executing in the application
State any one of method example example.
The corresponding machine readable instructions of Figure 10 module can make operating system operated on computer etc. to complete to retouch here
The some or all of operation stated.Non-volatile computer readable storage medium storing program for executing can be institute in the expansion board in insertion computer
In the memory of setting or write the memory being arranged in the expanding element being connected to a computer.Be mounted on expansion board or
CPU on expanding element etc. can be according to instruction execution part and whole practical operations.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Within mind and principle, any modification, equivalent substitution, improvement and etc. done be should be included within the scope of the present invention.
Claims (15)
1. a kind of information processing method characterized by comprising
The description information of social network structure is received, the description information includes the multiple use for including in the social network structure
The power between user node that connection relationship and every two between family nodal information, the multiple user node are connected
Weight parameter, the weight parameter is to characterize the correlation degree between be connected two user nodes；
Receive the first attention rate parameter for the event of each user node in the social network structure；
Following steps S1-S2 is executed for each first user node in the social network structure:
S1: receiving media releasing parameter, according to the description information, determine one to be connected with first user node or
Multiple second user nodes determine the weight parameter of each second user node in one or more of second user nodes
With the first attention rate parameter；
S2: according to the first attention rate parameter of first user node, first concern of each second user node
The media releasing parameter spending parameter and the weight parameter and currently determining determines that the second of first user node is closed
Note degree parameter；
S3: each first user is determined according to the second attention rate parameter of the first user node each in the social network structure
The mean value of second attention rate parameter of node, using the mean value of the second attention rate parameter as the third attention rate of the event
Parameter, and record the third attention rate parameter currently determined；
S4: when third participation parameter convergence, third participation is determined according to each third participation parameter recorded
The variation tendency of parameter；
S5:, will be described in the first user node each in the social network structure when the third participation parameter does not restrain
First participation parameter is assigned a value of the second participation parameter of each first user node respectively, returns to step S1.
2. the method according to claim 1, wherein when executing above-mentioned steps S2, comprising:
According to the first attention rate parameter of each second user node and the weight parameter, first attention rate ginseng
Number, determines the first attention rate parameter change amount that each second user node generates first user node；
According to the first attention rate parameter and the media releasing parameter of first user node, determine that described first uses
Second attention rate parameter change amount of family node；
According to the first attention rate parameter, the first attention rate parameter change amount and the second attention rate parameter change
Amount, determines the second attention rate parameter.
3. according to the method described in claim 2, it is characterized in that, the first attention rate parameter includes the first participation, the
One mood degree and the first cognition degree, the first attention rate parameter change amount include the first mood degree knots modification, and described second closes
Note degree parameter change amount includes the second mood degree knots modification；
When determining the first attention rate parameter change amount, comprising:
According to the first mood degree and weight parameter of each second user node, described the of first user node
One cognition degree determines the first mood degree knots modification that each second user node generates first user node；
When determining the second attention rate parameter change amount, comprising:
According to first participation of first user node, the first mood degree, first cognition degree, Yi Jisuo
Media releasing parameter is stated, the first participation and the first cognition degree for determining first user node are to first user node
Generation the second mood degree knots modification.
4. according to the method described in claim 3, it is characterized in that, the first mood degree knots modification is according to following formula (1)
To determine:
Wherein,
Wherein, the wijFor the weight parameter for the second user node j being connected with the first user node i, the eiiIt is first
The first mood degree of user node i, eijFor the first mood degree of second user node j, the rpiFor the first user node i's
First cognition degree.
5. according to the method described in claim 3, it is characterized in that, the second mood degree knots modification is according to following formula (4)
To determine:
FPM(eii)=eii·[1-r(t)·ibi·(1-rpi)] (4)
Wherein, the eiiFor the first mood degree of the first user node i, the ibiFirst for the first user node i participates in
Degree, the rpiFor the first cognition degree of the first user node i, the r (t) is the media releasing parameter.
6. according to the method described in claim 2, it is characterized in that, the first attention rate parameter includes the first participation, the
One mood degree and the first cognition degree, the first attention rate parameter change amount include the first participation knots modification, and described second closes
Note degree parameter change amount includes the second participation knots modification；
When determining the first attention rate parameter change amount, comprising:
Recognize according to the first of the first participation of each second user node, weight parameter and first user node
Degree of knowing determines the first participation knots modification that each second user node generates first user node；
When determining the second attention rate parameter change amount, comprising:
Joined according to the first participation of first user node, the first mood degree, the first cognition degree and the media releasing
Number determines the second ginseng that the first mood degree of first user node and the first cognition degree generate first user node
With degree knots modification.
7. according to the method described in claim 6, it is characterized in that, the first participation knots modification is according to following formula (5)
To determine:
Wherein,
Wherein, the wijFor the weight parameter for the second user node j being connected with the first user node i, the ibiIt is first
The first participation of user node i, ibjFor the first participation of second user node j, the rpiFor the first user node i's
First cognition degree.
8. according to the method described in claim 6, it is characterized in that, the second participation knots modification is according to following formula (8)
To determine:
FPM(ibi)=ibi·[1-(1-r(t))·(1-eii)(1-rpi)] (8)
Wherein, the ibiFor the first participation of the first user node i, the eiiFor the first mood degree of the first user node,
The rpiFor the first cognition degree of the first user node i, the r (t) is the media releasing parameter.
9. the method according to claim 1, wherein the method further includes: receive the category of the event
Property parameter, receives the user property value of each user node in the social networks；
Wherein, the first attention rate parameter includes the first participation, the first mood degree and the first cognition degree；
When executing above-mentioned steps S2, the method further includes:
According to the first mood degree, the first participation, the first cognition degree, user property value and the matchmaker of first user node
Body publication parameter determines the second cognition degree of first user node.
10. according to the method described in claim 9, it is characterized in that, determining that second cognition degree includes:
Cognition degree knots modification is determined by following formula (9):
Wherein Frp=rpi·[1-ibi·r(t)·(pci·p+(1-pci)·(1-p))] (10)
Second cognition degree is determined according to first cognition degree and the cognition degree knots modification；
Wherein, the eiiFor the first mood degree of the first user node, the rpiFor the first cognition degree of the first user node,
The ibiFor the first participation of the first user node, the r (t) is the media releasing parameter, the pciIt is described first
The user property value of user node, the p are the property parameters of the event.
11. according to the method described in claim 2, it is characterized in that, the method further includes:
Receive the weight of the first attention rate parameter change amount and the coupling parameter of the second attention rate parameter change amount；
Wherein, described according to the first attention rate parameter, the first attention rate parameter change amount and second concern
Parameter change amount is spent, determines that the second attention rate parameter includes:
According to the first attention rate parameter change amount, the second attention rate parameter change amount, the coupling parameter, determines and close
Note degree parameter change amount；
The second attention rate parameter is determined according to the first attention rate parameter and the attention rate parameter change amount.
12. the method according to claim 1, wherein the method is further wrapped when executing above-mentioned steps S5
It includes:
In response to the update request to media releasing parameter, the media releasing parameter is updated.
13. a kind of information processing unit characterized by comprising
First receiving unit, to receive the description information of social network structure, the description information includes the social networks
Connection relationship and every two between multiple user node information for including in structure, the multiple user node are connected
User node between weight parameter, the weight parameter is to characterize the association journey between be connected two user nodes
Degree；
Second receiving unit, to receive the first pass for the event of each user node in the social network structure
Note degree parameter；
Variation tendency determination unit, to execute following processing:
Following steps S1-S2 is executed for each first user node in the social network structure:
S1: receiving media releasing parameter, according to the description information, determine one to be connected with first user node or
Multiple second user nodes determine the weight parameter of each second user node in one or more of second user nodes
With the first attention rate parameter；
S2: according to the first attention rate parameter of first user node, first concern of each second user node
The media releasing parameter spending parameter and the weight parameter and currently determining determines that the second of first user node is closed
Note degree parameter；
S3: each first user is determined according to the second attention rate parameter of the first user node each in the social network structure
The mean value of second attention rate parameter of node, using the mean value of the second attention rate parameter as the third attention rate of the event
Parameter, and record the third attention rate parameter currently determined；
S4: when third participation parameter convergence, third participation is determined according to each third participation parameter recorded
The variation tendency of parameter；
S5:, will be described in the first user node each in the social network structure when the third participation parameter does not restrain
First participation parameter is assigned a value of the second participation parameter of each first user node respectively, returns to step S1.
14. device according to claim 13, which is characterized in that the variation tendency determination unit, to:
According to the first attention rate parameter of each second user node and the weight parameter, first attention rate ginseng
Number, determines the first attention rate parameter change amount that each second user node generates first user node；
According to the first attention rate parameter and the media releasing parameter of first user node, determine that described first uses
Second attention rate parameter change amount of family node；
According to the first attention rate parameter, the first attention rate parameter change amount and the second attention rate parameter change
Amount, determines the second attention rate parameter.
15. a kind of computer readable storage medium, is stored with computer-readable instruction, at least one processor can be made to execute such as
The described in any item methods of claim 1-12.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810522210.5A CN110196955B (en) | 2018-05-28 | 2018-05-28 | Information processing method, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810522210.5A CN110196955B (en) | 2018-05-28 | 2018-05-28 | Information processing method, device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110196955A true CN110196955A (en) | 2019-09-03 |
| CN110196955B CN110196955B (en) | 2023-07-07 |
Family
ID=67751377
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810522210.5A Active CN110196955B (en) | 2018-05-28 | 2018-05-28 | Information processing method, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110196955B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112487201A (en) * | 2020-11-26 | 2021-03-12 | 西北工业大学 | Knowledge graph representation method using shared parameter convolutional neural network |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106021269A (en) * | 2015-03-27 | 2016-10-12 | 国际商业机器公司 | Transforming social media re-shares to track referrer history and identify influencers |
| US20180018709A1 (en) * | 2016-05-31 | 2018-01-18 | Ramot At Tel-Aviv University Ltd. | Information spread in social networks through scheduling seeding methods |
| CN107808067A (en) * | 2017-10-19 | 2018-03-16 | 重庆邮电大学 | Information propagation forecast system and method based on network structure Yu user psychology speciality |
| CN107908673A (en) * | 2017-10-25 | 2018-04-13 | 平安科技（深圳）有限公司 | The real relationship match method, apparatus and readable storage medium storing program for executing of social platform user |
-
2018
- 2018-05-28 CN CN201810522210.5A patent/CN110196955B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106021269A (en) * | 2015-03-27 | 2016-10-12 | 国际商业机器公司 | Transforming social media re-shares to track referrer history and identify influencers |
| US20180018709A1 (en) * | 2016-05-31 | 2018-01-18 | Ramot At Tel-Aviv University Ltd. | Information spread in social networks through scheduling seeding methods |
| CN107808067A (en) * | 2017-10-19 | 2018-03-16 | 重庆邮电大学 | Information propagation forecast system and method based on network structure Yu user psychology speciality |
| CN107908673A (en) * | 2017-10-25 | 2018-04-13 | 平安科技（深圳）有限公司 | The real relationship match method, apparatus and readable storage medium storing program for executing of social platform user |
Non-Patent Citations (1)
| Title |
|---|
| 王晓彤: "结合时间因子的社交网络用户影响力分析", 《中国优秀硕士学位论文全文数据库（信息科技辑）》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112487201A (en) * | 2020-11-26 | 2021-03-12 | 西北工业大学 | Knowledge graph representation method using shared parameter convolutional neural network |
| CN112487201B (en) * | 2020-11-26 | 2022-05-10 | 西北工业大学 | Knowledge graph representation method using shared parameter convolutional neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110196955B (en) | 2023-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Contractor | Some assembly required: leveraging Web science to understand and enable team assembly | |
| Paulavičius et al. | A systematic review and empirical analysis of blockchain simulators | |
| CN110347596A (en) | A kind of test method, device, system, electronic equipment and medium | |
| Murugesan | Web application development: Challenges and the role of web engineering | |
| Behfar et al. | Knowledge management in OSS communities: Relationship between dense and sparse network structures | |
| CN109409738A (en) | Method, the electronic device of deep learning are carried out based on block platform chain | |
| CN106910045A (en) | Design of Workflow method and system | |
| CN101924786A (en) | Dynamic content preference and behavior sharing between computing devices | |
| CN112090079A (en) | Game task running method and device, computer equipment and storage medium | |
| Gonzalez-Pardo et al. | Behaviour-based identification of student communities in virtual worlds | |
| Roy Chowdhury et al. | Complementary assistance mechanisms for end user mashup composition | |
| Wang et al. | Knowledge transmission model with differing initial transmission and retransmission process | |
| CN110942202A (en) | Emergency drilling deduction method, computer storage medium and electronic equipment | |
| CN110392880A (en) | System and method for managing the dynamic design data of virtual environment | |
| US11983219B2 (en) | Instructional design tool | |
| CN110196955A (en) | Information processing method, device and storage medium | |
| Dragoicea et al. | Integrating HLA and service-oriented architecture in a simulation framework | |
| Barrett et al. | An Interaction-Based Approach to Computational Epidemiology. | |
| Liu et al. | Social computing and behavioral modeling | |
| CN116012017A (en) | Resource information processing method, device, computer equipment and storage medium | |
| CN109102061A (en) | A kind of group of subscribers behavior generation system meeting human dynamics rule, equipment and storage medium | |
| CN108683657A (en) | Safety access method, device, terminal device and the readable storage medium storing program for executing of data | |
| Ekyalimpa et al. | A prototype for project management game development using high level architecture | |
| CN113377931A (en) | Language model collaborative learning method, system and terminal of interactive robot | |
| Chen | [Retracted] Intelligent Recommendation System of Dance Art Video Resources Based on the Wireless Network |
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 |