CN106372207B - The influence power sort method and ordering system of public platform information - Google Patents
The influence power sort method and ordering system of public platform information Download PDFInfo
- Publication number
- CN106372207B CN106372207B CN201610801255.7A CN201610801255A CN106372207B CN 106372207 B CN106372207 B CN 106372207B CN 201610801255 A CN201610801255 A CN 201610801255A CN 106372207 B CN106372207 B CN 106372207B
- Authority
- CN
- China
- Prior art keywords
- public platform
- platform information
- influence power
- information
- public
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
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
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)
Abstract
The present invention provides the influence power sort method and ordering system of a kind of public platform information, and the influence power sort method of public platform information includes: the first Interaction parameters Y and the second Interaction parameters D of the corresponding multiple public platform information of crawl；The first Interaction parameters Y and the second Interaction parameters D based on the public platform information, calculate the influence power of the public platform information in the steps below: influence power W:W=aY (DT)+(1-a) [D of public platform information is calculated as followsm(DT)+Dm(DT-1)-D (DT-1)], wherein a is rational, and Y (DT) is the first Interaction parameters of the current date of public platform information, Dm(DT-1) be the second Interaction parameters of amendment of the public platform information on the day before current date, D (DT-1) be current date on the day before public platform information the second Interaction parameters.The influence power sort method and ordering system of public platform information provided by the invention can accurately calculate the influence power of public platform information by multiple Interaction parameters.
Description
Technical field
The present invention relates to the influence power sort methods and sequence system of field of communication technology more particularly to a kind of public platform information
The sort method and sequence of system, a kind of temperature sort method of public platform information and ordering system and a kind of public platform influence power
System.
Background technique
With the rapid development of social networks and big data era, more and more social networks distinguish user.
By taking wechat as an example, in addition to the registrable general account of general user, also sets up public platform and registered for user.
The user for registering general account usually using the account as personal contact, communication and shares to use.General account
Number chat message can be sent, chat message can be text, picture, audio or view in one-to-one or group chat scenario
Frequently.However, chat message due to its real-time, frequency of interaction is fast the features such as, not will use text, picture, audio or view usually
The combined information of frequency.Meanwhile general account is only capable of issuing shared information, shared information in circle of friends (social networks interaction scenarios)
Can be simultaneously by all " good friends " of the general account, or optionally partially " good friend " is seen.What general account was issued is total to
Enjoying information can be text, picture and small video, and the quantity of text number of words, picture number and small video is all restricted.
And personal, tissue or the registrable public platform of company, directly to issue public platform information, public platform to other users
Information can generally be issued in above-mentioned one-to-one chat scenario, and public platform information can also be issued in circle of friends (social networks friendship
Mutual scene) in.Public platform information can be text, picture, audio, video or their combination.Meanwhile public platform information
The unlimited number of words of text, picture, audio and video are unlimited.
It can be seen that general account is to register the general account for carrying out social action, the interactive object of general account
Good friend, the household of user etc..And public platform is then used to promote, propagate, the interactive object of public platform can be any concern
The people of the public platform.Public platform described herein can also be down to some account types in other social networks.For example, the public
It number can also refer in microblogging plus " V " account.
However, how user chooses public platform to pay close attention to, how content provider chooses public platform to issue content, usually
It is all to be chosen according to the assessed value of several dimensions of public platform.These dimensions may include public platform publication public platform
The liveness of information, the influence power of public platform information, influence power of public platform etc..It is existing by taking the influence power of public platform information as an example
Have in technology, for public platform information influence power according only to read number, thumb up number, comment any one of number parameter is commented
Estimate, there are also the assessment modes of some prior arts according to the simple combination of these parameters.Such assessment mode can not be accurately
Obtain the influence power of public platform information.
Summary of the invention
The present invention provides a kind of influence power sequence side of public platform information to overcome the problems of the above-mentioned prior art
Method and ordering system, a kind of temperature sort method of public platform information and ordering system and a kind of sequence of public platform influence power
Method and ordering system can accurately calculate the influence power of public platform information by multiple Interaction parameters.
The present invention provides a kind of influence power sort method of public platform information, comprising: the corresponding multiple public platform information of crawl
The first Interaction parameters Y and the second Interaction parameters D；Based on the interaction ginseng of the first Interaction parameters Y of the public platform information and second
Number D, calculates the influence power of the public platform information: when the first Interaction parameters Y of the public platform information is greater than in the steps below
When equal to first threshold, the second Interaction parameters of amendment of the public platform information: D are calculatedm(DT)=e[1/(DT+1)]* D (DT),
In, DT is that the first Interaction parameters of the public platform information reach the interval between the date and current date of the first threshold
Number of days, DmIt (DT) is the second Interaction parameters of amendment of the current date of public platform information, D (DT) is that the public platform of current date is believed
Second Interaction parameters of breath；When DT is greater than 0, influence power W:W=aY (DT)+(1- of public platform information is calculated as follows
a)[Dm(DT)+Dm(DT-1)-D (DT-1)], wherein a is rational, Y (DT) be the current date of public platform information first mutually
Dynamic parameter, DmIt (DT-1) is the second Interaction parameters of amendment of the public platform information on the day before current date, D (DT-1) is to work as the day before yesterday
Second Interaction parameters of the public platform information on the day before the phase.
Preferably, it when the first Interaction parameters Y of the public platform information is less than the first threshold, counts as follows
Calculate influence power W:W=aY+ (1-a) D of public platform information.
Preferably, when being equal to 0 for DT, influence power W:W=aY (0)+(1-a) of public platform information is calculated as follows
Dm(0), wherein Y (0) is current first Interaction parameters of the public platform information, DmIt (0) is the current of the public platform information
Correct the second Interaction parameters, wherein Dm(0)=e1* (0) D, D (0) are current second Interaction parameters of the public platform information.
Preferably, the first threshold is the integer in 9000 to 11000.
Preferably, further includes: public platform information is ranked up according to the influence power W of the public platform information；According to institute
The ranking results for stating the influence power W of public platform information will push the public platform information to user.
Preferably, the step of pushing the public platform information to user according to ranking results includes: that will affect before power W comes
The public platform information of N% is pushed to user, and N is the integer in 0 to 30.
Preferably, further includes: the multiple public platform information grabbed are divided into multiple classification, each described classification packet
Include multiple public platform information；Under each described classification, according to the public platform information influence power W to public platform information into
Row sequence；According to the affiliated classification and public platform information of the public platform information influence power W ranking results to user
Push the public platform information.
Preferably, user has one or more labels, each corresponding classification of the label, according to the public affairs
The ranking results of the influence power W of the affiliated classification of crowd's information and the public platform information will push the public platform letter to user
The step of breath include: under a classification, will affect power W come before N% public platform information be pushed to have correspond to
The user of the label of the classification, N are the integer in 0 to 30.
Preferably, first Interaction parameters and second Interaction parameters are to read number, thumb up number, forwarding number, comment
Any two in number, collection number and attention number
Preferably, first Interaction parameters are to read number, and second Interaction parameters are to thumb up number.
Preferably, first Interaction parameters are to read number, and second Interaction parameters are forwarding number.
Preferably, first Interaction parameters are to read number, and second Interaction parameters are comment number.
Preferably, the value range of a is 0.01 to 0.1.
Preferably, the public platform information is article, the picture, audio that the public platform account of social network-i i-platform is issued
And/or video.
Preferably, the of the public platform information is grabbed by the api interface of one or more social network-i i-platforms
One Interaction parameters and the second Interaction parameters.
According to another aspect of the invention, a kind of influence power ordering system of public platform information is also provided, according to institute as above
The influence power sort method for the public platform information stated is ranked up multiple public platform information, and according to the public platform
The ranking results of influence power push the public platform information to user.
According to another aspect of the invention, a kind of temperature sort method of public platform information is also provided, comprising: according to such as
The influence power sort method of the upper public platform information calculates the influence power W of the public platform information；According to the public platform
Influence power W calculate the temperature H of the public platform information, in which: the influence power W of the public platform information is divided for M section,
M is the integer greater than 2, and for b-th of section in the M section, as b=1, which is [0, Z1], when b is 2 to M-1
In arbitrary integer when, the section be (Zb-1, Zb], when b is equal to M, which is (ZM-1, ∞), when b is 1 any into M
When integer, ZbFor positive integer；It calculates quantity of the influence power W of the public platform information in each section and the public platform is believed
The ratio of the sum of breath, in b-th of section, the ratio of the influence power W of the public platform information is wb；When the public affairs of current date
The influence power W of crowd's informationtThe influence W of public platform information on the day before greater than current dateyWhen, if WyB-th of the section ∈, and b
For greater than 1 be less than or equal to M integer when, H=c* (1/wb)*(Wt-Wy)/Wy, wherein c is numeric parameter.
Preferably, as the influence power W of the public platform information of current datetPublic platform information on the day before greater than current date
Influence WyWhen, if WyWhen=0, H=c* (1/wb)*(Wt)；If WyThe 1st section ∈, and WyWhen ≠ 0, H=c* (1/w1)*(Wt-
Wy)/Wy。
Preferably, as the influence power W of the public platform information of current datetPublic platform on the day before less than or equal to current date
The influence W of informationyWhen, the temperature H=0 of the public platform information.
Preferably, which is characterized in that M is the arbitrary integer in 3 to 6.
Preferably, which is characterized in that when b is 1 arbitrary integer into M, ZbFor 100 multiple.
Preferably, the influence power W of the public platform information is divided into 4 sections, including [0,100], (100,1000],
(1000,5000], and (5000, ∞).
Preferably, further includes: public platform information is ranked up according to the temperature H of the public platform information；According to described
The ranking results of the temperature H of public platform information will push the public platform information to user.
Preferably, the step of pushing the public platform information to user according to ranking results includes: before coming temperature H
The public platform information of P% is pushed to user, and P is the integer in 0 to 30.
Preferably, further includes: the multiple public platform information grabbed are divided into multiple classification, each described classification packet
Include multiple public platform information；Under each described classification, public platform information is carried out according to the temperature H of the public platform information
Sequence；It is pushed according to the ranking results of the temperature H of the affiliated classification and public platform information of the public platform information to user
The public platform information.
Preferably, user has one or more labels, each corresponding classification of the label, according to the public affairs
The ranking results of the temperature H of the affiliated classification of crowd's information and the public platform information will push the public platform letter to user
The step of breath includes: under a classification, and the public platform information of P% is pushed to have to correspond to and be somebody's turn to do before temperature H is come
The user of the label of classification, P are the integer in 0 to 30.
According to another aspect of the invention, a kind of temperature ordering system of public platform information is also provided, according to item institute as above
The temperature sort method for the public platform information stated is ranked up multiple public platform information, and is believed according to the public platform
The ranking results of the temperature of breath push the public platform information to user.
According to another aspect of the invention, a kind of sort method of public platform influence power is also provided, comprising: according to institute as above
The influence power sort method for the public platform information stated calculates the public platform information that the public platform is issued in first time period
Influence power W；Calculate the sum of the influence power W of public platform information that the public platform is issued in first time period；By the public
Influence power Q of the sum of number influence power W of public platform information issued in first time period as the public platform；According to the public affairs
Many numbers influence power Q are ranked up the public platform.
Preferably, further includes: the public platform information that will affect R% before power Q comes is pushed to user, and R is whole in 0 to 30
Number.
According to another aspect of the invention, a kind of ordering system of public platform influence power is also provided, according to as described above
The sort method of public platform influence power is ranked up multiple public platforms, and according to the sequence of the public platform influence power
As a result the public platform information is pushed to user.
Compared with prior art, the present invention has the advantage that
1) present invention passes through two Interaction parameters of acquisition public platform information, when the first Interaction parameters are more than or equal to threshold value
When, one of Interaction parameters are modified, public platform letter is calculated based on the two Interaction parameters and amendment Interaction parameters
The influence power of breath, and assign these parameters different weights enables and calculates resulting influence power and more accurately indicate the public
The influence power of number information；
2) distribution situation of the influence power based on public platform information, the public platform influence power area where public platform information
Between, to calculate the temperature of public platform information, that is, the influence power change rate of public platform information, the present invention believes in view of public platform
Change case difficulty of the influence power of breath in different sections is different, with when calculating the temperature of public platform information, according to different public affairs
Public platform information proportion in the influence power section of crowd's information, assigns different degree-of-difficulty factors, so that calculating institute
The temperature obtained can more accurately indicate the temperature of public platform information；
3) influence power of public platform is calculated based on the influence power of the accurate public platform information of the invention calculated, so that
The influence power of public platform can more accurately be indicated by calculating resulting influence power；
4) influence power of above-mentioned public platform information, the temperature of public platform information are based respectively on to public platform information sorting, is come
Influence power or the higher public platform information of temperature are pushed to user.Influence power based on above-mentioned public platform sorts to public platform, comes
The higher public platform of influence power is pushed to user.User can pay close attention to these public platforms or collection public platform information according to demand, or
Person is released news by the higher public platform of these influence powers, more effectively to obtain information or release information.
Detailed description of the invention
Its example embodiment is described in detail by referring to accompanying drawing, above and other feature of the invention and advantage will become
It is more obvious.
Fig. 1 shows the flow chart of the influence power sort method of public platform information according to an embodiment of the present invention.
Fig. 2 shows the streams of the specific sort method of the influence power according to an embodiment of the invention according to public platform information
Cheng Tu.
Fig. 3 shows the stream of the specific sort method of the influence power according to an embodiment of the invention according to public platform information
Cheng Tu.
Fig. 4 shows the flow chart of the temperature sort method of public platform information according to an embodiment of the present invention.
Fig. 5 shows the flow chart of the influence power sort method of public platform according to an embodiment of the present invention.
Fig. 6 shows the topological diagram of the influence power ordering system of public platform information according to an embodiment of the invention.
Fig. 7 shows the topological diagram of the influence power ordering system of public platform information according to another embodiment of the present invention.
Specific embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be with a variety of shapes
Formula is implemented, and is not understood as limited to embodiment set forth herein；On the contrary, thesing embodiments are provided so that the present invention will
Fully and completely, and by the design of example embodiment comprehensively it is communicated to those skilled in the art.It is identical attached in figure
Icon note indicates same or similar structure, thus will omit repetition thereof.
In order to solve in the prior art, the not accurate enough defect of the influence power of public platform information, the present invention provides a kind of public affairs
The influence power sort method of crowd's information.Public platform information according to an embodiment of the present invention is shown referring first to Fig. 1, Fig. 1
The flow chart of influence power sort method.In Fig. 1, two steps are shown altogether:
Step S110: the first Interaction parameters Y and the second Interaction parameters D of the corresponding multiple public platform information of crawl.
In the present invention, public platform information can refer to article, the picture, sound of the public platform account publication of social network-i i-platform
Frequency and/or video.Specifically, in step s 110, grabbing each public from the server where multiple public platform information
The real-time first Interaction parameters Y and the second Interaction parameters D of number information.Preferably, pass through one or more social network-i i-platforms
Api interface grabs in the server of one or more social network-i i-platforms, the first Interaction parameters of each public platform information and the
Two Interaction parameters.In some embodiments, grab the first Interaction parameters Y's and the second Interaction parameters D of multiple public platform information
Step can be executed periodically daily.The first Interaction parameters Y and second of multiple public platform information is grabbed in yet other embodiments,
The step of Interaction parameters D, can execute with user demand.
First Interaction parameters Y and the second Interaction parameters D, which can be, to be read number, thumbs up number, forwarding number, comment number, collection number
And any two in attention number.Preferably, the second Interaction parameters D is stronger compared to the first Interaction parameters Y interactivity.For example,
In some embodiments, the first Interaction parameters Y is to read number, and the second Interaction parameters D is to thumb up number；In yet other embodiments,
One Interaction parameters Y is to read number, and the second Interaction parameters D is forwarding number；In further embodiments, the first Interaction parameters Y is to read
Reading, the second Interaction parameters D are comment number.It will be understood by those skilled in the art that above-mentioned thumb up number, forwarding number, comment number phase
It is more stronger than reading number interactivity, it can more show concern of the user for the public platform information.
Step S120: the first Interaction parameters Y and the second Interaction parameters D based on public platform information calculate the public platform
The influence power of information.
Specifically, being to read number with an Interaction parameters Y in the step s 120, the second Interaction parameters D is to thumb up number to be
Example, illustrates the calculating of the influence power of public platform information.First determine whether the reading number Y of public platform information is more than or equal to the first threshold
Value.First threshold can be the integer in 9000 to 11000.For example, in the present embodiment, first threshold takes 10000.
When whether the reading number Y of public platform information is more than or equal to 10000, public platform is calculated by following formula first
The amendment of information thumbs up number (namely correcting the second Interaction parameters):
Dm(DT)=e[1/(DT+1)]* D (DT),
Wherein, DT reaches the interval number of days between 10000 date and current date for the reading number Y of public platform information.
For example, the date Data1 that the reading number Y of public platform information reaches 10000 is 2016-4-20, the reading of public platform information is obtained
Several date Data2 be 2016-4-22, then DT=Data2-Data1=2 days.DmIt (DT) is the current date of public platform information
Amendment thumb up number.D (DT) is that the public platform information of current date thumbs up several D, that is, when Data2, public platform information
Thumb up several D.
It will be understood by those skilled in the art that above-mentioned reading number Y and thumb up several D and can be changed in a day, therefore, institute
" the thumbing up number of the public platform information of current date " stated, " the reading number of the public platform information of current date " refer both to current date
Several D and reading number Y are thumbed up when obtaining public platform information.That is, if obtaining the point of public platform information at 10 points of the 2016-4-22 morning
It praises several D and reads number Y, then the public platform information obtained using 10 points thumbs up several D and reading number Y as the public of 2016-4-22
Number information thumbs up several D and reads number Y；If 2016-4-22 2 pm obtain public platform information thumb up several D and read number
The public platform information for thumbing up several D and reading number Y 10 points of acquisitions of replacement for the public platform information that 2 points obtain then is thumbed up several D by Y
And number Y is read as the public platform information of 2016-4-22 and thumbs up several D and reading number Y.
When reading the interval number of days DT that number Y reaches between 10000 date and current date and being greater than 0, as follows
Calculate the influence power W of public platform information:
W=aY (DT)+(1-a) [Dm(DT)+Dm(DT-1)-D (DT-1)],
Wherein, Y (DT) is the reading number of the current date of public platform information, DmIt (DT-1) is the public affairs on the day before current date
The amendment of crowd's information thumbs up number, and D (DT-1) thumbs up number for the public platform information on the day before current date.A is rational.By
In thumbing up several D, compared to reading, number Y interactivity is stronger, and therefore, the value range of a can be 0.01 to 0.1, to indicate to thumb up several D
In big more of weight for calculating the weight ratio in influence power W and reading number Y.Preferably, a takes 0.027.
Below by taking a takes 0.027 as an example, multiple embodiments of different DT numerical value are described:
For example, when reading number Y and reaching the interval number of days DT=1 between 10000 date and current date,
The amendment of current date thumbs up several Dm(1)=e[1/(1+1)]* D (1)=e(1/2)*D(1)；
Amendment on the day before current date thumbs up several Dm(0)=e[1/(1+0)]* D (0)=e1*D(0)；
Calculate the formula of the influence power W of public platform information are as follows:
W=0.027*Y (1)+0.973* [Dm(1)+Dm(0)-D(0)]。
In another example when reading number Y and reaching the interval number of days DT=2 between 10000 date and current date,
The amendment of current date thumbs up several Dm(2)=e[1/(1+2)]* D (2)=e(1/3)*D(2)；
Amendment on the day before current date thumbs up several Dm(1)=e[1/(1+1)]* D (1)=e(1/2)*D(1)；
Calculate the formula of the influence power W of public platform information are as follows:
W=0.027*Y (2)+0.973* [Dm(2)+Dm(1)-D(1)]。
For another example when reading number Y and reaching the interval number of days DT=k between 10000 date and current date,
The amendment of current date thumbs up several Dm(k)=e[1/(1+k)]*D(k)；
Amendment on the day before current date thumbs up several Dm(k-1)=e[1/(k)]*D(k-1)；
Calculate the formula of the influence power W of public platform information are as follows:
W=0.027*Y (k)+0.973* [Dm(k)+Dm(k-1)-D(k-1)]。
Specifically, when above-mentioned several embodiments illustrate that DT is greater than 0, the calculation formula of the influence power W of public platform information.
It is described below as the interval number of days DT=0 between the date and current date that reach 10000 for reading number Y, public platform information
Influence power W calculation formula:
W=aY (0)+(1-a) Dm(0),
Wherein, Y (0) is the reading number of public platform information, Dm(0) number is thumbed up for the current amendment of the public platform information,
Wherein, Dm(0)=e1* (0) D, D (0) are that the current of the public platform information thumbs up number.The value of a can be big with DT in the formula
The value of a is identical in the calculation formula of the influence power W of public platform information when 0.
Further, when the reading number Y of public platform information is less than 10000, public platform information is calculated as follows
Influence power W:
W=aY+ (1-a) D,
Wherein, a in the calculation formula of the influence power W of public platform information when the value of a can be greater than 0 with DT in the formula
Value is identical.
The influence power sort method of public platform information provided by the invention can calculate public platform information according to aforesaid way
Influence power W.It in some embodiments, further include the step of sequence push after the influence power W for calculating each public platform information
Suddenly, as shown in Figure 2.In fig. 2 it is shown that two steps:
Step S210: public platform information is ranked up (from big to small) according to the influence power W of each public platform information.
Step S220: and according to the ranking results of influence power W, the public platform information of N% before pushing to user, N is 0 to 30
Integer.User referred herein can be the user that information is obtained from public platform, is also possible to issue by public platform and believe
The user of breath.The higher multiple public platform information of influence power W can be pushed to user in this way, be obtained with improving user
Effective, valuable, influential information is taken, or the user of release information is made to understand issued public platform informational influence power
To carry out next step decision etc..
Fig. 3 can be referred in above-mentioned some change case according to influence power W sequence push step, in fig. 3 it is shown that 3
A step:
Step S310: being divided into multiple classification for the multiple public platform information grabbed, each described classification includes more
A public platform information.
The division of multiple public platform information can execute in step provided by the invention in above-mentioned steps S310, can also be with
It is obtained from the server where multiple public platform information.Specifically, in some embodiments, public platform issues public platform
When information, the affiliated classification of the public platform information can be increased.It can be sentenced in yet other embodiments, according to the classification of public platform
The affiliated classification of the public platform information of the public platform of breaking publication.In further embodiments, public platform information can be divided
Analysis is to judge classification belonging to the public platform information.For example, according to occurring most keywords in public platform information, believing public platform
Picture in breath analyze and then judges classification belonging to the public platform information by analyzing and training system.
The affiliated classification of public platform information can be the classification of the audient of the public platform information, for example, classification may include
Women, male, child, women white collar, housewife etc..In some change case, the affiliated classification of public platform information be can be
The classification of the public platform information, for example, classification may include that video display, movement, shopping, science and technology, electricity are competing etc..Those skilled in the art
More mode classifications may be implemented, it will not be described here.
Step S320: under each classification, public platform information is ranked up according to the influence power W of public platform information.
Specifically, by taking the mode classification of " video display, movement, shopping, science and technology, electricity are competing etc. " as an example.Respectively to being divided into
The lower multiple public platform information progress influence power W sequence of " video display, movement, shopping, science and technology, electricity are competing etc. " classification.
In some embodiments, same public platform information is divided into multiple classification, and is sorted in multiple classification.
In some change case, same public platform information is only divided into a classification.
Step S330: according to the affiliated classification and public platform information of public platform information influence power W ranking results to
Family pushes public platform information.
Specifically, in some embodiments, user has one or more labels, corresponding one, each label is classified,
Step S330 may include under a classification, and the public platform information that will affect N% before power W (from big to small) comes is pushed to tool
There is the user of the label corresponding to the classification, N is the integer in 0 to 30.Further, the label that user has can be user
The label voluntarily selected.For example, user can choose the public platform information for paying close attention to some or multiple classification.In some change case
In, the label that user has is obtained by user behavior analysis.
When user has multiple labels, when pushing the public platform information of the corresponding multiple classification of multiple labels to user,
And one public platform information belong to multiple classification, then can also include the steps that not repeat push public platform information.
On the basis of the influence power of public platform information, the present invention also provides a kind of temperature sort methods of public platform information.
The temperature H of public platform information indicates the influence power change rate of public platform information.Temperature H value shows more greatly the heat of the public platform information
It spends higher.It will be appreciated by those skilled in the art that the influence power of public platform information is different, the difficulty of (change rate) is continued growing also not
Together.Therefore, the present invention is by assigning degree-of-difficulty factor different when temperature calculates based on Different Effects power section.The influence power section
Interior public platform information accounting is bigger, and degree-of-difficulty factor is smaller, and vice versa.
Specifically, the step of temperature sort method of public platform information, is referring to fig. 4.Two steps are shown in FIG. 4:
Step S410: the shadow of public platform information is calculated according to the influence power sort method of public platform information provided by the invention
Ring power W.
Step S420: the temperature H of public platform information is calculated according to the influence power W of public platform.
Specifically, in the step s 420, firstly, dividing the influence power W of public platform information for M section, M is greater than 2
Integer.For b-th of section in M section:
As b=1, which is [0, Z1], when b is 2 arbitrary integer into M-1, which is (Zb-1, Zb]；
When b is equal to M, which is (ZM-1, ∞)；
When b is 1 arbitrary integer into M, ZbFor positive integer.
In view of the calculation amount and computational accuracy of temperature H, M is the arbitrary integer in 3 to 6.In other words, public platform is believed
The influence power W of breath is divided into 3 to 6 sections.When b is 1 arbitrary integer into M, for ease of calculation, ZbFor 100 times
Number.
After the influence power W for dividing public platform information, calculate quantity of the influence power W in each section of public platform information with
The ratio of the sum of public platform information, in b-th of section, the ratio of the influence power W of public platform information is wb.For example, the public
The sum of number information is 10000, in b-th section (such as section (Zb-1, Zb]) in, the quantity of public platform information is 500, then
In b-th of section, the ratio of the influence power W of public platform information is 500/10000=0.05.
As the influence power W of the public platform information of current datetThe influence W of public platform information on the day before greater than current datey
When:
If WyB-th of the section ∈, and b is H=c* (1/w when being less than or equal to the integer of M greater than 1b)*(Wt-Wy)/Wy,
In, c is numeric parameter；
If WyWhen=0, H=c* (1/wb)*(Wt)；
If WyThe 1st section ∈, and WyWhen ≠ 0, H=c* (1/w1)*(Wt-Wy)/Wy。
Wherein, it calculates for convenience, c takes 100.
As the influence power W of the public platform information of current datetPublic platform information on the day before less than or equal to current date
Influence WyWhen, the temperature H=0 of public platform information.
Above-mentioned calculating step, in this embodiment, the shadow of public platform information are illustrated with a specific embodiment below
It rings power W and is divided into 4 sections, including first section [0,100], and second section (100,1000], third section
(1000,5000] and the 4th section (5000, ∞), and c takes 100.Public platform information sum is 10000, in first section
In [0,100], the quantity of public platform information is 5000, then w1=0.5；Second section (100,1000] in, public platform letter
The quantity of breath is 3000, then w2=0.3；Third section (1000,5000] in, the quantity of public platform information is 1500, then w3
=0.15；In the 4th section (5000, ∞), the quantity of public platform information is 500, then w4=0.05.
When calculating the temperature of public platform information, the influence power of the public platform information of the public platform information current date is calculated
WtAnd the influence W of the public platform information on the day before current datey。
The influence power W of the public platform information of current datetThe shadow of public platform information on the day before less than or equal to current date
Ring Wy, the temperature H=0 of the public platform information.
The influence power W of the public platform information of current datetThe influence W of public platform information on the day before greater than current datey
When:
If the influence W of the public platform information on the day before current dateyBelong to first section [0,100], and current date
The influence W of the public platform information of the previous dayy=0, then temperature H=100* (1/0.5) * (W of the public platform informationt)
If the influence W of the public platform information on the day before current dateyBelong to first section [0,100], and current date
The influence W of the public platform information of the previous dayy≠ 0, then temperature H=100* (1/0.5) * (W of the public platform informationt-Wy)/Wy；
If the influence W of the public platform information on the day before current dateyBelong to second section (100,1000], then the public
Temperature H=100* (1/0.3) * (W of number informationt-Wy)/Wy；
If the influence W of the public platform information on the day before current dateyBelong to third section (1000,5000], then the public affairs
Temperature H=100* (1/0.15) * (W of crowd's informationt-Wy)/Wy；
If the influence W of the public platform information on the day before current dateyBelong to the 4th section (5000, ∞), then the public
Temperature H=100* (1/0.05) * (W of number informationt-Wy)/Wy。
The temperature sort method of public platform information provided by the invention can calculate public platform information according to aforesaid way
Temperature H.On the basis of being calculated due to the influence power W that the calculating of the temperature H of public platform information is built upon public platform information, because
This, in the temperature H sort method of public platform information, it is preferable that be updated periodically the influence power W of public platform information each
The ratio of the sum of quantity and public platform information in section.In some change case, the section of the influence power W of public platform information
Division can also be adjusted according to the variation of the influence power W of public platform information.
In some embodiments, after the temperature H for calculating each public platform information, further include the steps that sequence push.
It is similar with the sequence of the influence power W of public platform information push step.
In one embodiment, firstly, the temperature H according to public platform information is ranked up public platform information.Then, it presses
According to the ranking results of the temperature H of public platform information public platform information will be pushed to user.Preferably, temperature H is come into preceding P%
(from big to small) public platform information is pushed to user, and P is the integer in 0 to 30.User referred herein can be from the public
Number obtain information user, be also possible to will by public platform release news user.It in this way can be to user
The higher multiple public platform information of temperature H are pushed, it is higher, valuable, powerful to improve user's acquisition influence power change rate
Information, or the user of release information is made to understand issued public platform heatrate H to carry out next step decision etc..
In a change case of above-described embodiment, firstly, the multiple public platform information grabbed are divided into multiple
Classification, each classification include multiple public platform information.The division of multiple public platform information can be in step provided by the invention
Middle execution can also be obtained from the server where multiple public platform information.Specifically, in some embodiments, it is public
When many numbers publication public platform information, the affiliated classification of the public platform information can be increased.It in yet other embodiments, can basis
The classification of public platform judges the affiliated classification of the public platform information of public platform publication.It in further embodiments, can be to public affairs
Crowd's information is analyzed to judge classification belonging to the public platform information.For example, according to occurring most passes in public platform information
Keyword analyze to the picture in public platform information and then judges to divide belonging to the public platform information by analyzing and training system
Class.Later, under each classification, public platform information is ranked up according to the temperature H of public platform information.
Then, it is pushed according to the ranking results of the affiliated classification of public platform information and the temperature H of public platform information to user
Public platform information.Specifically, in some embodiments, user has one or more labels, each label is one point corresponding
Class, the step may include under a classification, and the public platform information of P% is pushed to have to correspond to and be somebody's turn to do before temperature H is come
The user of the label of classification, P are the integer in 0 to 30.Further, the label that user has can be what user voluntarily selected
Label.For example, user can choose the public platform information for paying close attention to some or multiple classification.In some change case, user has
Label be to be obtained by user behavior analysis.
According to another aspect of the invention, a kind of sort method of public platform influence power is also provided, referring specifically to Fig. 5, Fig. 5
5 steps are shown altogether:
Step S510: the influence power sort method of the public platform information provided according to the present invention calculates public platform first
The influence power W for the public platform information issued in period.
Step S520: the sum of the influence power W of public platform information that public platform is issued in first time period is calculated.When first
Between section can be one week, one month, a season, the periods such as half a year.
Step S530: the sum of influence power W of public platform information that public platform is issued in first time period is used as the public affairs
Many numbers influence power Q.
Step S540: public platform is ranked up according to the influence power Q of public platform.
Step S550: the public platform information that will affect R% before power Q (from big to small) comes is pushed to user, and R is 0 to 30
In integer.
In a specific embodiment of the sort method of public platform influence power, public platform is indicated using discrete star
Influence power Q, star include 0.5,1,1.5,2,2.5,3,3.5,4,4.5,5.Star value shows more greatly the public platform influence power more
It is high.Public platform influence power Q shows as the sum of the influence power W of the public platform sent out public platform information whithin a period of time.One timing
The public platform information content issued in phase is more, and the influence power W of single public platform information is bigger, and public platform influence power Q is got over
Greatly.
All public platforms that public platform influence power Q=Σ W, public platform influence power Q are issued in one month with the public platform
The sum of influence power W of information is calculated.Public platform is ranked up from small to large according to public platform influence power Q, according to row
Tagmeme, which is set, obtains public platform influence power star.For example, the influence power Q of public platform comes preceding 10% as 0.5 star；The shadow of public platform
It rings power Q and comes preceding 10% to preceding 20% as 1 star；The influence power Q of public platform comes preceding 20% to preceding 30% as 1.5 stars；It is public
Many numbers influence power Q come preceding 30% to preceding 40% as 2 stars；It is 2.5 that the influence power Q of public platform, which comes preceding 40% to preceding 50%,
Star；The influence power Q of public platform comes preceding 50% to preceding 60% as 3 stars；The influence power Q of public platform comes preceding 60% to preceding
70% is 3.5 stars；The influence power Q of public platform comes preceding 70% to preceding 80% as 4 stars；Before the influence power Q of public platform comes
80% to preceding 90% is 4.5 stars；The influence power Q of public platform comes preceding 90% to preceding 100% as 5 stars.According to public platform
Star can get information about the influence power of the public platform.
The present invention also provides the influence powers of a kind of influence power of public platform information, the temperature of public platform information and public platform
Integrated application calculates the topic influence and topic temperature of public platform in conjunction with above-mentioned calculated result.Pass through public platform (opinion neck
Sleeve) topic influence and topic temperature can know in the interim time, under a certain group of keyword (topic), certain public platform
The spread scope of issued public platform information and growth and the Decay Rate of the public platform influence power.
The topic influence of public platform there are two key factor, i.e., public platform publication (a certain group crucial with certain topic
Word) relevant public platform informational influence power, with the influence power of the public platform itself.The two values are bigger, the topic of public platform
Influence power is bigger.But it is different based on significance level, their different weights are assigned, wherein the weight of the influence power of public platform information is big
In the weight of public platform influence power itself.
The topic influence of public platform finds relevant one or more public platform letters with some keyword or crucial phrase
Breath, and the topic influence of public platform is calculated as follows:
Topic influence=0.99*sum of public platform be (the public platform information relevant to topic that the public platform is issued
Influence power)+0.01* the public platform influence power.
The topic temperature of public platform is only dependent upon the sum of the public platform heatrate relevant to topic of public platform publication.
Public platform heatrate is bigger, and the topic temperature of public platform is bigger.The topic temperature of public platform is calculated as follows:
Topic temperature=sum (temperature with topic relevant public information that the public platform is issued) of public platform.
Preferably, the present invention also provides the public platform of the topic temperature of topic influence and public platform based on public platform rows
Sequence and method for pushing, the influence power sort method with the influence power of above-mentioned public platform information, the temperature of public platform information and the public
Similar, it will not be described here.
The present invention also provides the public platform information sorting system calculated based on above-mentioned public platform informational influence power, based on above-mentioned
The public platform information sorting system that public platform heatrate calculates, the public platform sequence system based on the calculating of above-mentioned public platform influence power
System.By taking the public platform ordering system calculated based on above-mentioned public platform influence power as an example, it is described.It is influenced based on above-mentioned public platform
The public platform ordering system that power calculates uses the influence power sort method of public platform as described above, arranges multiple public platforms
Sequence, and public platform is pushed to user according to the ranking results of the influence power of public platform.Specifically, Fig. 6 and Fig. 7 are respectively illustrated
Two embodiments of the influence power ordering system push public platform of public platform.
The influence power ordering system push of public platform according to a first embodiment of the present invention is shown referring first to Fig. 6, Fig. 6
The topological diagram of public platform.Fig. 6 shows ordering system 310, server 320 and multiple terminals 330.Ordering system 310, server
320 and multiple terminals 330 be in communication with each other by network.Multiple terminals 330 have registered public platform on server 320 respectively, and
Its public platform information is issued respectively.Ordering system 310 obtains the public platform publication that multiple terminals 330 are registered from server 320
Public platform information data, and according to the present invention provided by public platform influence power sort method calculate public platform influence
Power is ranked up public platform according to the influence power for calculating resulting public platform.By sequence, ordering system 310 passes through service
Device 320 will affect the general account that the higher multiple public platforms of power are pushed to the registration of terminal 330.
Fig. 7 shows the influence power ordering system push public platform of public platform account according to a second embodiment of the present invention
Topological diagram.Similar with topological diagram shown in fig. 6 in Fig. 7, multiple terminal 330A register public platform account on server 320.
Ordering system 310 obtains the data of the public platform information of public platform publication from server 320, calculates the influence power of public platform,
And public platform is ranked up according to the influence power for calculating resulting public platform.In the present embodiment, ordering system 310 directly to
Terminal 330B pushes the higher multiple public platforms of influence power.Terminal 330B can be the end of the not register account number on server 320
End.Terminal 330B is also possible to register the terminal of general account on server 320.Terminal 330B can be according to the public affairs pushed
Many numbers obtain public platform information, or the public platform by being pushed to release news.
Above-mentioned Fig. 6 and Fig. 7 is only the influence power ordering system push for schematically showing public platform provided by the invention
The topological diagram of public platform.The quantity of ordering system, server and terminal is not limited thereto, and those skilled in the art can also be real
Mode is now more communicated to connect, it will not be described here.The public platform information row calculated based on above-mentioned public platform informational influence power
Sequence system, the public platform information sorting system calculated based on above-mentioned public platform heatrate can also be similarly arranged.In some changes
Change in example, the public platform information sorting system that is calculated based on above-mentioned public platform informational influence power, based on above-mentioned public platform information heat
Spend the public platform information sorting system calculated, the public platform ordering system based on the calculating of above-mentioned public platform influence power is all integrated in one
In a processing system.In other change case, the public platform information sorting system based on the calculating of above-mentioned public platform informational influence power
System, based on above-mentioned public platform heatrate calculate public platform information sorting system, based on above-mentioned public platform influence power calculate
Public platform ordering system can be processing system individually.Those skilled in the art can also realize more variation sides
Formula, it will not be described here.
Compared with prior art, the present invention has the advantage that
1) present invention passes through two Interaction parameters of acquisition public platform information, when the first Interaction parameters are more than or equal to threshold value
When, one of Interaction parameters are modified, public platform letter is calculated based on the two Interaction parameters and amendment Interaction parameters
The influence power of breath, and assign these parameters different weights enables and calculates resulting influence power and more accurately indicate the public
The influence power of number information；
2) distribution situation of the influence power based on public platform information, the public platform influence power area where public platform information
Between, to calculate the temperature of public platform information, that is, the influence power change rate of public platform information, the present invention believes in view of public platform
Change case difficulty of the influence power of breath in different sections is different, with when calculating the temperature of public platform information, according to different public affairs
Public platform information proportion in the influence power section of crowd's information, assigns different degree-of-difficulty factors, so that calculating institute
The temperature obtained can more accurately indicate the temperature of public platform information；
3) influence power that public platform is calculated based on the influence power of the accurate public platform information of the invention calculated, makes to succeed in one's scheme
The influence power of public platform can more accurately be indicated by calculating resulting influence power；
4) influence power of above-mentioned public platform information, the temperature of public platform information are based respectively on to public platform information sorting, is come
Influence power or the higher public platform information of temperature are pushed to user.Influence power based on above-mentioned public platform sorts to public platform, comes
The higher public platform of influence power is pushed to user.User can pay close attention to these public platforms or collection public platform information according to demand, or
Person is released news by the higher public platform of these influence powers, more effectively to obtain information or release information.
It is particularly shown and described exemplary embodiments of the present invention above.It should be understood that the present invention is not limited to institute
Disclosed embodiment, on the contrary, it is intended to cover comprising various modifications within the scope of the appended claims and equivalent set
It changes.
Claims (30)
1. a kind of influence power sort method of public platform information characterized by comprising
The the first Interaction parameters Y and the second Interaction parameters D of the corresponding multiple public platform information of crawl；
The first Interaction parameters Y and the second Interaction parameters D based on the public platform information, calculate the public platform in the steps below
The influence power of information:
When the first Interaction parameters Y of the public platform information is more than or equal to first threshold,
Calculate the second Interaction parameters of amendment of the public platform information:
Dm(DT)=e[1/(DT+1)]* D (DT),
Wherein, DT is that the first Interaction parameters of the public platform information reached between the date and current date of the first threshold
Interval number of days, DmIt (DT) is the second Interaction parameters of amendment of the current date of public platform information, D (DT) is the public affairs of current date
Second Interaction parameters of crowd's information；
When DT is greater than 0, the influence power W of public platform information is calculated as follows:
W=aY (DT)+(1-a) [Dm(DT)+Dm(DT-1)-D (DT-1)],
Wherein, a is rational, and Y (DT) is the first Interaction parameters of the current date of public platform information, DmIt (DT-1) is to work as the day before yesterday
The second Interaction parameters of amendment of public platform information on the day before phase, D (DT-1) are the public platform information on the day before current date
Second Interaction parameters.
2. the influence power sort method of public platform information as described in claim 1, which is characterized in that
When the first Interaction parameters Y of the public platform information is less than the first threshold, public platform letter is calculated as follows
The influence power W of breath:
W=aY+ (1-a) D.
3. the influence power sort method of public platform information as described in claim 1, which is characterized in that when being equal to 0 for DT, press
Following formula calculates the influence power W of public platform information:
W=aY (0)+(1-a) Dm(0),
Wherein, Y (0) is current first Interaction parameters of the public platform information, Dm(0) currently repairing for the public platform information
Positive second Interaction parameters, wherein Dm(0)=e1* (0) D, D (0) are current second Interaction parameters of the public platform information.
4. the influence power sort method of public platform information as described in any one of claims 1 to 3, which is characterized in that described
One threshold value is the integer in 9000 to 11000.
5. the influence power sort method of public platform information as described in any one of claims 1 to 3, which is characterized in that further include:
Public platform information is ranked up according to the influence power W of the public platform information；
According to the ranking results of the influence power W of the public platform information public platform information will be pushed to user.
6. the influence power sort method of public platform information as claimed in claim 5, which is characterized in that according to ranking results to
Family push the public platform information the step of include:
The public platform information that will affect N% before power W comes is pushed to user, and N is the integer in 0 to 30.
7. the influence power sort method of public platform information as described in any one of claims 1 to 3, which is characterized in that further include:
The multiple public platform information grabbed are divided into multiple classification, each described classification includes multiple public platform information；
Under each described classification, public platform information is ranked up according to the influence power W of the public platform information；
It is pushed according to the ranking results of the influence power W of the affiliated classification and public platform information of the public platform information to user
The public platform information.
8. the influence power sort method of public platform information as claimed in claim 7, which is characterized in that user has one or more
A label, each corresponding classification of the label, according to the affiliated classification and the public platform of the public platform information
The ranking results of the influence power W of information will to user push the public platform information the step of include:
Under a classification, the public platform information that will affect N% before power W comes is pushed to the mark corresponding to the classification
The user of label, N are the integer in 0 to 30.
9. the influence power sort method of public platform information as described in any one of claims 1 to 3, which is characterized in that described
One Interaction parameters and second Interaction parameters are to read number, thumb up in number, forwarding number, comment number, collection number and attention number
Any two.
10. the influence power sort method of public platform information as claimed in claim 9, which is characterized in that the first interaction ginseng
For number to read number, second Interaction parameters are to thumb up number.
11. the influence power sort method of public platform information as claimed in claim 9, which is characterized in that the first interaction ginseng
For number to read number, second Interaction parameters are forwarding number.
12. the influence power sort method of public platform information as claimed in claim 9, which is characterized in that the first interaction ginseng
For number to read number, second Interaction parameters are comment number.
13. the influence power sort method of public platform information as described in any one of claims 1 to 3, which is characterized in that a's takes
Being worth range is 0.01 to 0.1.
14. the influence power sort method of public platform information as described in any one of claims 1 to 3, which is characterized in that the public affairs
Crowd's information is article, picture, audio and/or the video that the public platform account of social network-i i-platform is issued.
15. the influence power sort method of public platform information as described in any one of claims 1 to 3, which is characterized in that pass through one
The api interface of a or multiple social network-i i-platforms grabs the first Interaction parameters and the second Interaction parameters of the public platform information.
16. a kind of influence power ordering system of public platform information, which is characterized in that according to any one of such as claim 1 to 15 institute
The influence power sort method for the public platform information stated is ranked up multiple public platform information, and according to the public platform
The ranking results of influence power push the public platform information to user.
17. a kind of temperature sort method of public platform information characterized by comprising
According to the public platform letter as described in calculating the influence power sort method of the described in any item public platform information of claim 1 to 15
The influence power W of breath；
The temperature H of the public platform information is calculated according to the influence power W of the public platform, in which:
The influence power W of the public platform information is divided for M section, M is the integer greater than 2, for b in the M section
A section, as b=1, which is [0, Z1], when b is 2 arbitrary integer into M-1, which is (Zb-1, Zb], work as b
When equal to M, which is (ZM-1, ∞), when b is 1 arbitrary integer into M, ZbFor positive integer；
Calculate the ratio of the sum of quantity of the influence power W of the public platform information in each section and the public platform information
Example, in b-th of section, the ratio of the influence power W of the public platform information is wb；
As the influence power W of the public platform information of current datetThe influence W of public platform information on the day before greater than current dateyWhen,
If WyB-th of the section ∈, and b is H=c* (1/w when being less than or equal to the integer of M greater than 1b)*(Wt-Wy)/Wy, wherein c is
Numeric parameter.
18. the temperature sort method of public platform information as claimed in claim 17, which is characterized in that
As the influence power W of the public platform information of current datetThe influence W of public platform information on the day before greater than current dateyWhen,
If WyWhen=0, H=c* (1/wb)*(Wt)；
If WyThe 1st section ∈, and WyWhen ≠ 0, H=c* (1/w1)*(Wt-Wy)/Wy。
19. the temperature sort method of public platform information as claimed in claim 17, which is characterized in that
As the influence power W of the public platform information of current datetThe influence W of public platform information on the day before less than or equal to current datey
When, the temperature H=0 of the public platform information.
20. the temperature sort method of public platform information as claimed in claim 17, which is characterized in that M is any in 3 to 6
Integer.
21. the temperature sort method of public platform information as claimed in claim 17, which is characterized in that when b was 1 appointing into M
When meaning integer, ZbFor 100 multiple.
22. the temperature sort method of public platform information as claimed in claim 17, which is characterized in that the public platform information
Influence power W is divided into 4 sections, including [0,100], and (100,1000], (1000,5000], and (5000, ∞).
23. the temperature sort method of public platform information as claimed in claim 17, which is characterized in that further include:
Public platform information is ranked up according to the temperature H of the public platform information；
According to the ranking results of the temperature H of the public platform information public platform information will be pushed to user.
24. the temperature sort method of public platform information as claimed in claim 23, which is characterized in that according to ranking results to
Family push the public platform information the step of include:
The public platform information of P% is pushed to user before temperature H is come, and P is the integer in 0 to 30.
25. the temperature sort method of public platform information as claimed in claim 17, which is characterized in that further include:
The multiple public platform information grabbed are divided into multiple classification, each described classification includes multiple public platform information；
Under each described classification, public platform information is ranked up according to the temperature H of the public platform information；
Institute is pushed to user according to the ranking results of the temperature H of the affiliated classification and public platform information of the public platform information
State public platform information.
26. the temperature sort method of public platform information as claimed in claim 25, which is characterized in that user has one or more
A label, each corresponding classification of the label, according to the affiliated classification and the public platform of the public platform information
The ranking results of the temperature H of information will to user push the public platform information the step of include:
Under a classification, the public platform information of P% is pushed to the label corresponding to the classification before temperature H is come
User, P be 0 to 30 in integer.
27. a kind of temperature ordering system of public platform information, which is characterized in that according to as described in any one of claim 17 to 26
Public platform information temperature sort method, multiple public platform information are ranked up, and according to the public platform information
The ranking results of temperature push the public platform information to user.
28. a kind of sort method of public platform influence power characterized by comprising
Existed according to the public platform as described in calculating the influence power sort method of the described in any item public platform information of claim 1 to 15
The influence power W for the public platform information issued in first time period；
Calculate the sum of the influence power W of public platform information that the public platform is issued in first time period；
Influence of the sum of the influence power W of public platform information that the public platform is issued in first time period as the public platform
Power Q；
The public platform is ranked up according to the influence power Q of the public platform.
29. public platform influence power sort method as claimed in claim 28, which is characterized in that further include:
The public platform information that will affect R% before power Q comes is pushed to user, and R is the integer in 0 to 30.
30. a kind of ordering system of public platform influence power, which is characterized in that described in any item according to such as claim 28 to 29
The sort method of public platform influence power is ranked up multiple public platforms, and according to the sequence of the public platform influence power
As a result the public platform information is pushed to user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610801255.7A CN106372207B (en) | 2016-09-05 | 2016-09-05 | The influence power sort method and ordering system of public platform information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610801255.7A CN106372207B (en) | 2016-09-05 | 2016-09-05 | The influence power sort method and ordering system of public platform information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106372207A CN106372207A (en) | 2017-02-01 |
| CN106372207B true CN106372207B (en) | 2019-07-16 |
Family
ID=57900465
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610801255.7A Active CN106372207B (en) | 2016-09-05 | 2016-09-05 | The influence power sort method and ordering system of public platform information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106372207B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108416684B (en) * | 2017-02-10 | 2021-09-07 | 腾讯科技（深圳）有限公司 | Method and device for evaluating credibility of account main body and server |
| CN110019780A (en) * | 2017-09-15 | 2019-07-16 | 腾讯科技（深圳）有限公司 | Method, the method for information processing and the relevant apparatus of text information sequence |
| CN108521460B (en) * | 2018-04-04 | 2021-04-16 | Oppo广东移动通信有限公司 | Information pushing method and device, mobile terminal and computer readable storage medium |
| CN109614542B (en) * | 2018-12-11 | 2024-05-14 | 平安科技（深圳）有限公司 | Public number recommendation method, device, computer equipment and storage medium |
| CN109710857A (en) * | 2018-12-27 | 2019-05-03 | 杭州启迪万华科技产业发展有限公司 | A kind of public platform recommended method and device |
| CN110275745A (en) * | 2019-04-11 | 2019-09-24 | 上海盛付通电子支付服务有限公司 | A kind of method and apparatus of overhead account |
| CN110119476A (en) * | 2019-04-26 | 2019-08-13 | 广州美术学院 | A kind of account auto recommending method, device, terminal device and storage medium |
| CN112528196B (en) * | 2020-11-20 | 2023-06-23 | 四川新网银行股份有限公司 | Automatic monitoring system and method for real-time generation of internet public opinion heat index |
| CN114328558B (en) * | 2021-12-30 | 2022-12-27 | 北京达佳互联信息技术有限公司 | List updating method, apparatus, device and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102663101A (en) * | 2012-04-13 | 2012-09-12 | 北京交通大学 | Sina microblog-based user grade sequencing algorithm |
| CN105260474A (en) * | 2015-10-29 | 2016-01-20 | 俞定国 | Microblog user influence computing method based on information interaction network |
| CA2906865A1 (en) * | 2014-10-01 | 2016-04-01 | Amadeus S.A.S. | Automated task handling |
-
2016
- 2016-09-05 CN CN201610801255.7A patent/CN106372207B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102663101A (en) * | 2012-04-13 | 2012-09-12 | 北京交通大学 | Sina microblog-based user grade sequencing algorithm |
| CA2906865A1 (en) * | 2014-10-01 | 2016-04-01 | Amadeus S.A.S. | Automated task handling |
| CN105260474A (en) * | 2015-10-29 | 2016-01-20 | 俞定国 | Microblog user influence computing method based on information interaction network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106372207A (en) | 2017-02-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106372207B (en) | The influence power sort method and ordering system of public platform information | |
| Gjoka et al. | Poking facebook: characterization of osn applications | |
| Kim et al. | Discovering hot topics using Twitter streaming data: social topic detection and geographic clustering | |
| Ratkiewicz et al. | Detecting and tracking political abuse in social media | |
| Ahn et al. | Analysis of topological characteristics of huge online social networking services | |
| Watanabe et al. | Jasmine: a real-time local-event detection system based on geolocation information propagated to microblogs | |
| CN109063010B (en) | Opinion leader mining method based on PageRank | |
| CN103678613B (en) | Method and device for calculating influence data | |
| CN105512326B (en) | A kind of method and system that picture is recommended | |
| CN109636481A (en) | User's portrait construction method and device towards domestic consumer | |
| CN105550275B (en) | A kind of microblogging transfer amount prediction technique | |
| CN110264284A (en) | New media marketing attributive analysis prediction technique, apparatus and system | |
| CN101136869A (en) | Method for generating search intention based contacts group of instant communication system | |
| KR20150046431A (en) | Auto-learning system and method for derive effective marketing | |
| CN106708796A (en) | Text-based key personal name extraction method and system | |
| CN110297967B (en) | Method, device and equipment for determining interest points and computer readable storage medium | |
| JP3669167B2 (en) | Information providing method and information providing apparatus using others group preference information, and recording medium recording information providing program | |
| Hansen et al. | EventGraphs: Charting collections of conference connections | |
| CN107463551A (en) | The analysis method and device of social networks interpersonal relationships | |
| Ying et al. | Followee recommendation in asymmetrical location-based social networks | |
| CN106157150A (en) | Information processing method and information processor | |
| Cai et al. | Extremely low reciprocity and strong Homophily in the World Largest MSM Social Network | |
| Yan et al. | The small-world and scale-free structure of an internet technological community | |
| Wang et al. | Predicting the popularity of online content based on the weak ties theory | |
| Abdullah et al. | Reputation measurement based on a hybrid sentiment analysis approach for Saudi telecom companies |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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 |