CN105873102A - Mobile network migration method and system - Google Patents

Mobile network migration method and system Download PDF

Info

Publication number
CN105873102A
CN105873102A CN201610197091.1A CN201610197091A CN105873102A CN 105873102 A CN105873102 A CN 105873102A CN 201610197091 A CN201610197091 A CN 201610197091A CN 105873102 A CN105873102 A CN 105873102A
Authority
CN
China
Prior art keywords
network
moves
user
move
ready
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
Application number
CN201610197091.1A
Other languages
Chinese (zh)
Other versions
CN105873102B (en
Inventor
杨瑞
肖吉
王蓉
王志军
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China United Network Communications Group Co Ltd
Original Assignee
China United Network Communications Group Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China United Network Communications Group Co Ltd filed Critical China United Network Communications Group Co Ltd
Priority to CN201610197091.1A priority Critical patent/CN105873102B/en
Publication of CN105873102A publication Critical patent/CN105873102A/en
Application granted granted Critical
Publication of CN105873102B publication Critical patent/CN105873102B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W24/00Supervisory, monitoring or testing arrangements
    • H04W24/02Arrangements for optimising operational condition

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • User Interface Of Digital Computer (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention provides a mobile network migration method and system, belonging to the technical field of migration of mobile networks. The problems of poor accuracy and low efficiency in the existing mobile network migration method can be solved. The mobile network migration method disclosed by the invention comprises the following steps of: acquiring mobile networking data of a user; extracting a behaviour parameter xi of a potential user from the mobile networking data, wherein the potential user is a user surfing an internet by using the highest-speed mobile network; and the behaviour parameter xi is an a-dimensional vector; and judging whether the potential user wants to perform mobile network migration or not according to the behaviour parameter xi of the potential user, and if so, sending information for performing mobile network migration to the potential user.

Description

Mobile network moves shifting method and system
Technical field
The invention belongs to mobile network move and turn technical field, be specifically related to a kind of mobile network and move shifting method and system.
Background technology
Along with the arrival in mobile Internet epoch, user starts more and more to use mobile terminal Internet access.To this end, operation Business increases the dynamics that mobile network builds, and the coverage rate of high-speed mobile network (such as 4G network) improves constantly, and obtains for user Preferably mobile Internet access is experienced provides basis.
But, present many has the user of the high-speed mobile network terminal (such as 3G mobile) and is still using low-speed mobile network (such as 2G network) surfs the Net, and the utilization rate causing high-speed mobile network is low, and its ability can not be fully utilized.To this end, guide user By low-speed mobile network to high-speed mobile network move network move turn just become an important problem.
Existing guide user move network move turn method mainly carry out rate preferential, strengthen advertisement intensity a surname Pass.But, these methods all do not have specific aim, are all towards the public or whole users, and can not be accurately to truly having The user using high-speed mobile network demand pushes, therefore its poor accuracy, efficiency are low.
Summary of the invention
The present invention is directed to existing mobile network and move shifting method poor accuracy, inefficient problem, it is provided that a kind of accuracy The mobile network good, efficiency is high moves shifting method and system.
Solve the technology of the present invention problem and be employed technical scheme comprise that a kind of mobile network moves shifting method, comprising:
Gather the mobile Internet access data of user;
From the behavioral parameters x of mobile Internet access extracting data potential user, described potential user moves the most at a high speed for not using The user of dynamic network online, described behavioral parameters x is a dimensional vector;
Behavioral parameters x according to potential user iiJudge whether it is ready to move network and moves and turn, if then to it Send recommendation to move network and move the information turned.
Preferably, described potential user is mobile network's online of mobile terminal and the second speed using First Speed User, described First Speed be more than second speed;Described recommendation moves network and moves the information turned is that recommendation is moved and gone to the The information of the mobile network of one speed.
Preferably, the vector of described behavioral parameters x includes the one or more of herein below: the online in predetermined period Flow;Online duration in predetermined period;In predetermined period, high network speed the consumed surfing flow of demand business accounts for total surfing flow Ratio;In predetermined period, set meal external flux expense accounts for the ratio of total flow expense.
Preferably, at the behavioral parameters x according to potential user iiJudge whether it is ready to move network and moves and turn it Before, also include:
Take individual the having confirmed that of n and be ready that moving network moves the behavioral parameters x of the user turned, according to formula:Calculate parameter μ1And σ1, then it is ready to move net Network moves the distribution density of the user turned
Take individual the having confirmed that of m and be reluctant that moving network moves the behavioral parameters x of the user turned, according to formula:Calculate parameter μ2And σ2, then it is reluctant to move net Network moves the distribution density of the user turned
Wherein, t represents transposition, the value that | σ | is σ, σ-1Inverse for σ.
It may further be preferable that the described behavioral parameters x according to potential user iiJudge whether it is ready to move net Network moves to subcontract and includes:
Calculate user i according to below equation and be ready that moving network moves the probability P (W turned1|xi) and be unwilling to move Dynamic network moves the probability P (W turned2|xi):
P ( W 1 | x i ) = p ( x i | W 1 ) P ( W 1 ) p ( x i | W 1 ) P ( W 1 ) + p ( x i | W 2 ) P ( W 2 ) ,
P ( W 2 | x i ) = p ( x i | W 2 ) P ( W 2 ) p ( x i | W 1 ) P ( W 1 ) + p ( x i | W 2 ) P ( W 2 ) ,
Wherein P (W1) and P (W2) it is parameter preset;
Relatively P (W1|xi) and P (W2|xi), if P is (W1|xi) more than P (W2|xi) then think that potential user i is ready to move Network moves and turns.
It may further be preferable that the described behavioral parameters x according to potential user iiJudge whether it is ready to move net Network moves to subcontract and includes:
CalculateValue, wherein P (W1) and P (W2) it is parameter preset;
Judge g (xi) whether more than 0, if more than 0, think that potential user i is ready to move network and moves and turn.
Solution the technology of the present invention problem be employed technical scheme comprise that a kind of mobile network moves and transfered from one department to another system, comprising:
Collecting unit, for gathering the mobile Internet access data of user;
Extraction unit, for from the behavioral parameters x of mobile Internet access extracting data potential user, described potential user is not Using the user of high-speed mobile network online, described behavioral parameters x is a dimensional vector;
Judging unit, for the behavioral parameters x according to potential user iiJudge whether it is ready to move network and moves and turn;
Transmitting element, for moving the potential user turned and send recommendation and move network and move and turn to being ready to move network Information.
Preferably, the vector of described behavioral parameters x includes the one or more of herein below: the online in predetermined period Flow;Online duration in predetermined period;In predetermined period, high network speed the consumed surfing flow of demand business accounts for total surfing flow Ratio;In predetermined period, set meal external flux expense accounts for the ratio of total flow expense.
Preferably, described mobile network moves to transfer from one department to another to unite and also includes pre-calculation unit, and it is used for:
Take individual the having confirmed that of n and be ready that moving network moves the behavioral parameters x of the user turned, according to formula:Calculate parameter μ1And σ1, then it is ready to move net Network moves the distribution density of the user turned
Take individual the having confirmed that of m and be reluctant that moving network moves the behavioral parameters x of the user turned, according to formula:Calculate parameter μ2And σ2, then it is reluctant to move net Network moves the distribution density of the user turned
Wherein, t represents transposition, the value that | σ | is σ, σ-1Inverse for σ.
It may further be preferable that the described behavioral parameters x according to potential user iiJudge whether it is ready to move net Network moves to subcontract and includes:
CalculateValue, wherein P (W1) and P (W2) it is parameter preset;
Judge g (xi) whether more than 0, if more than 0, think that potential user i is ready to move network and moves and turn.
The mobile network of the present invention moves in shifting method, first gather likely move network move turn user behavior ginseng Number, analyzes each user further according to behavioral parameters and is ready to move network and moves the probability turned, and only moves net to being ready Network moves the higher user of probability turned and sends and recommend to move network and move the information turned, so that the accuracy of information pushing Good, efficiency height.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet that a kind of mobile network of embodiments of the invention moves shifting method;
Fig. 2 is the schematic flow sheet that the another kind of mobile network of embodiments of the invention moves shifting method;
Fig. 3 is that a kind of mobile network of embodiments of the invention moves the composition schematic block diagram transfering from one department to another system.
Fig. 4 is that the another kind of mobile network of embodiments of the invention moves the composition schematic block diagram transfering from one department to another system.
Detailed description of the invention
For making those skilled in the art be more fully understood that technical scheme, below in conjunction with the accompanying drawings and specific embodiment party The present invention is described in further detail by formula.
Embodiment 1:
The present embodiment provides a kind of mobile network to move shifting method, comprising:
S101, the mobile Internet access data of collection user.
S102, behavioral parameters x from mobile Internet access extracting data potential user, described potential user is the highest for not using The user of speed mobile network's online, described behavioral parameters x is a dimensional vector.
S103, behavioral parameters x according to potential user iiJudge whether it is ready to move network and moves and turn, if then to Its transmission is recommended to move network and is moved the information turned.
The mobile network of the present embodiment moves in shifting method, first gathers and likely moves network and move the behavior of user turned Parameter, analyzes each user further according to behavioral parameters and is ready to move network and moves the probability turned, and only moves to being ready Network moves the higher user of probability turned and sends and recommend to move network and move the information turned, so that the accuracy of information pushing Good, efficiency height.
Embodiment 2:
The present embodiment provides a kind of mobile network to move shifting method, comprising:
S201, the mobile Internet access data of collection user.
It is to say, by the acquisition node disposed in carrier network, know that whole user is surfed the Net by mobile network Related data.Such as, data mode can be as shown in table 1 below, including: subscriber phone number (demultiplexing family, user area), user make Mobile terminal style (i.e. the what kind of mobile network of the highest support of mobile terminal), user use mobile network's class Type, online time started, online end time, online duration, surfing flow, business of networking type etc..
Table 1, the mobile Internet access data of user
Preferably, according to above mobile Internet access data, in conjunction with the charge system (business support system) of operator, also can obtain Know the consumption of user account, specifically can be as shown in table 2 below, including: subscriber phone number, of that month spending amount, basis set Dinner cost with, set meal external flux, set meal external flux expense, set meal external flux bag, set meal external flux cover all expenses.
Table 2, the consumption of user account
S202, finding out potential user from mobile Internet access data, potential user is not for using high-speed mobile network online User.
Obviously, only currently the user that high-speed mobile network (temporarily as a example by 4G network) is surfed the Net is not used just can to continue Continue and move network to mobile network more at a high speed and move and turn, just belong to potential and may move the user that network moves turn, Therefore according to the type of the mobile terminal that user uses, these users can be screened as potential user.
Preferably, potential user is the use using the mobile terminal of First Speed and the mobile network of second speed to surf the Net Family, First Speed is more than second speed.
Obviously, user to use to mobile network more at a high speed, it is necessary to use mobile terminal more at a high speed (such as hands simultaneously Machine), and the user of terminal type and the mobile network's type matching (as with 3G mobile network on 3G mobile terminal) for using, General unlikely go to 4G network change 4G mobile terminal specially to move.Therefore, the mobile end of currently used fair speed The user of mobile network's online of end and relatively low velocity the most most possibly moves network and moves and turn, therefore can be used by user These preferred potential users are screened by mobile terminal style and the contrast of mobile network's type.
Wherein, the most also according to the type of mobile terminal, potential user also can be classified again, as used 4G mobile terminal But with the user of 2G or 3G mobile network, and use 3G mobile terminal but with the user of 2G mobile network.Because this two class is used Mobile terminal style that family is held is different, therefore they move network and move the tendency turned and be likely to different, can be as not Same model carries out processing (simply design parameter is different) the most in the same manner.
S203, the behavioral parameters x, behavioral parameters x extracting potential user from mobile Internet access data are a dimensional vector.
It is to say, after selecting potential user, extract the some projects in its mobile Internet access data, form potential user Behavioral parameters x, wherein, if having chosen a project, then x is a dimensional vector.
Preferably, the vector of behavioral parameters x includes the one or more of herein below:
Surfing flow Q in predetermined period: i.e. user is carried out with mobile network (such as one month) within cycle certain time The total flow of online.
Online duration T in predetermined period: i.e. within cycle certain time (such as one month) the actually used mobile network of user Network carries out the total time surfed the Net.
In predetermined period, high network speed the consumed surfing flow of demand business accounts for ratio S of total surfing flow: obviously, relative to Accessing the general business such as webpage, the business such as video, access electricity business, access map of watching are higher for the requirement of network speed, logical Often could obtain more preferable experience, the flow that therefore this kind of business can be used under the mobile network of more speed The ratio accounting for total flow is obtained.Certainly, the partial example of simply high network speed demand business provided above, high network speed demand industry What business specifically includes according to circumstances can be decided in its sole discretion by operator.
In predetermined period, set meal external flux expense accounts for ratio C of total flow expense: when moving online, typically have The inevitable expense that is included in original set meal of expense of a part, but when time of mobile Internet access, flow etc. beyond time, then need Extra mobile Internet access expense outside flow bag to be bought or payment set meal, now can be by this part expense and whole mobile Internet accesses The proportional recording of expense (not including the expense of phone, note etc.) gets off.
Visible, during above every content difference, represent user and be ready to move network to move the probability turned the most different, Therefore they all can be as the optional project of behavioral parameters x.It is to say as a example by 4 dimensional vectors of these 4 contents below according to x Bright, i.e. x=[D, T, S, C], and for concrete user i, then xi=[Di,Ti,Si,Ci].Certainly, example above is not to row Restriction for the project of parameter x.
S204, take n and have confirmed that and to be ready that moving network moves the behavioral parameters x of the user turned, according to formula:Calculate parameter μ1And σ1, then it is ready to move net Network moves the distribution density of the user turnedWherein, t represent turn Put, the value that | σ | is σ, σ-1Inverse for σ.
It has been investigated that, it is believed that if using behavioral parameters x as variable, then user is ready to move network and moves and turn Probability meets normal distribution (Gauss distribution), is i.e. ready that moving network moves the user W turned1Distribution density p (x | W1) ~N (μ11), this p (x | W1) specifically meet below equation:
But the now μ in formula1And σ1The most not Know.
To this end, n can be chosen it has been acknowledged that be ready that moving network moves the user turned (as being complete mobile network before Network moves the user turned) behavioral parameters x, and calculate μ according to the above formula x of these users1And σ1, and for follow-up In calculating.Obviously, the user's sample now chosen is the most (i.e. n is the biggest), the then μ of gained1And σ1Accuracy the highest.Wherein, Owing to x is 4 dimensional vectors, therefore its corresponding σ is then 4*4 covariance matrix, and | σ | and σ-1It it is then the value of corresponding line column and inverse.
Obviously, μ is once calculated1And σ1, then this μ all be can be used directly during all potential users of post analysis1And σ1, and Need not the most individually calculate.
Concrete, if as it was previously stated, think use 4G mobile terminal but with the user of 2G or 3G mobile network, and use 3G mobile terminal but be different with the user of 2G mobile network, the most now can from both users, selected part be respectively Confirm to be ready to move network and move the user turned as sample, calculate the μ that two sets are different respectively1And σ1.Accordingly, with Under in each step, the most all two kinds of users can be respectively calculated with different parameters in the same manner, owing to it calculates Method identical (the most concrete data, parameter are different), therefore be no longer respectively described below.
S205, take m and have confirmed that and to be reluctant that moving network moves the behavioral parameters x of the user turned, according to formula:Calculate parameter μ2And σ2, then it is reluctant to move Network moves the distribution density of the user turned
Similar with step S204, it is believed that to be unwilling to move network and move the user W turned2Also comply with normal distribution (Gauss Distribution), therefore m can be chosen it has been acknowledged that be unwilling to move network and move the user turned and (moved as pushed recommendation before Dynamic network moves the information but the user that clearly refused turned) behavioral parameters x, calculate corresponding parameter by the same way and go out μ2 And σ2
S206, behavioral parameters x according to potential user iiJudge whether it is ready to move network and moves and turn.
It is to say, judge whether each potential user is ready to move network and moves and turn one by one according to above behavioral parameters x, I.e. judge that it is ready and is unwilling to move network to move the probability turned.
Preferably, as a kind of mode of the present embodiment, this step specifically comprises the steps that
Calculate user i according to below equation and be ready that moving network moves the probability P (W turned1|xi) and be unwilling to move Dynamic network moves the probability P (W turned2|xi):
P ( W 1 | x i ) = p ( x i | W 1 ) P ( W 1 ) p ( x i | W 1 ) P ( W 1 ) + p ( x i | W 2 ) P ( W 2 ) , P ( W 2 | x i ) = p ( x i | W 2 ) P ( W 2 ) p ( x i | W 1 ) P ( W 1 ) + p ( x i | W 2 ) P ( W 2 ) ,
Wherein, P (W1) and P (W2) it is parameter preset;
Relatively P (W1|xi) and P (W2|xi), if P is (W1|xi) more than P (W2|xi) then think that potential user i is ready to move Network moves and turns.
As before, be ready and be unwilling to move network to move the distribution density of the potential user turned and all meet above normal state Distribution (obtaining before parameter), is thus directed towards certain and has and determine behavioral parameters xi=[Di,Ti,Si,Ci] user i, it is willing to Meaning moves network and moves and turn and be unwilling to move network and move the value P (W of the probability turned1|xi) and P (W2|xi) can lead to respectively Cross above formula to obtain.Thus, by comparing P (W1|xi) and P (W2|xi) size, i.e. may know that this user i is to be ready to carry out Mobile network moves the probability turned and is the most still unwilling to move network to move the probability turned big.
Wherein, P (W1) and P (W2) it is scale parameter, can be according to it has been determined that be ready and be unwilling to move network to move The user turned carries out statistical analysis and draws, it is possible to rule of thumb set.
Or, it is preferred that as the another way of the present embodiment, this step may also comprise:
CalculateValue, wherein P (W1) and P (W2) it is parameter preset;
Judge g (xi) whether more than 0, if more than 0, think that potential user i is ready to move network and moves and turn.
Obviously, with P (W1|xi) deduct P (W2|xi), then more than 0, its result means that user i is ready that moving network moves The probability turned is bigger, otherwise is then to be unwilling to move network to move the probability turned bigger.As before, P (W1|xi) and P (W2|xi) Formula respectively as follows:
P ( W 1 | x i ) = p ( x i | W 1 ) P ( W 1 ) p ( x i | W 1 ) P ( W 1 ) + p ( x i | W 2 ) P ( W 2 ) , P ( W 2 | x i ) = p ( x i | W 2 ) P ( W 2 ) p ( x i | W 1 ) P ( W 1 ) + p ( x i | W 2 ) P ( W 2 ) .
Visible, the denominator of the two is identical, therefore whether the difference comparing the two is more than 0, is the most just equivalent to compareWhether more than 0.Wherein, P (W1) and P (W2) it is parameter preset, thereforeAlso it is predetermined value, AndThen can be calculated.Obviously, according to the manner, calculate p (x as long as actuali|W1) and p (xi|W2) two values are i.e. Can, fairly simple, easily realize.
Move turn if S207 user is ready to move network, be then sent to recommend to move network and move the information turned.
It is to say, by the result of calculation of above step S206, if drawing, user i is ready to move network and moves and turn Probability is bigger, then judge that it is ready to move network and moves and turn, and be sent to recommend to move network move turn information (as Advertisement), guide its move network move turn.
Otherwise, if judging, user i is unwilling to move network and moves and turn, then terminate the process to this potential user, no longer It is sent to recommend to move network and moves the information turned.
Wherein, it is preferred that the mobile terminal of First Speed used above and the mobile network of second speed are surfed the Net Potential user, then above recommendation moves network and moves the information turned is to recommend to move the letter of the mobile network going to First Speed Breath.
It is to say, for mobile network's online of the mobile terminal of use fair speed described before and relatively low velocity User, it may be that recommend it to be moved the mobile network going to its mobile terminal by the mobile network of relatively low velocity, i.e. recommend to hold The user of 3G mobile terminal moves and goes to 3G network, and recommends the user holding 4G mobile terminal to move and go to 4G network.
S208, for confirming that being ready to move network moves the potential user turned, move network by its requirements and move turn.
It is to say, to potential user send recommend move network move turn information after, if receive its reply, really Recognize it to be ready to move network and move and turn, then moved by the requirement of this potential user and go to corresponding mobile network.
The mobile network of the present embodiment moves in shifting method, finds that user is ready/is unwilling to move network and moves turn general Rate all meets normal distribution, and proposes to use specific formulation to calculate user to be ready/be unwilling to move network and move turn general Rate, thus the accuracy of information pushing can be made more preferable, in hgher efficiency.
Embodiment 3:
As it is shown on figure 3, the present embodiment provides a kind of mobile network to move transfers from one department to another system, comprising:
Collecting unit, for gathering the mobile Internet access data of user.
Extraction unit, for from the behavioral parameters x of mobile Internet access extracting data potential user, potential user is not for use The user of high-speed mobile network online, behavioral parameters x is a dimensional vector.
Judging unit, for the behavioral parameters x according to potential user iiJudge whether it is ready to move network and moves and turn.
Transmitting element, for moving the potential user turned and send recommendation and move network and move and turn to being ready to move network Information.
The present embodiment provides a kind of mobile network to move to transfer from one department to another system, and it can move network according to above method and move and turn, Thus its accuracy is good, efficiency is high.
Embodiment 4:
As shown in Figure 4, a kind of mobile network of the present embodiment offer moves and transfers from one department to another system, comprising:
Collecting unit, for gathering the mobile Internet access data of user.
Extraction unit, for from the behavioral parameters x of mobile Internet access extracting data potential user, potential user is not for use The user of high-speed mobile network online, behavioral parameters x is a dimensional vector.
Judging unit, for the behavioral parameters x according to potential user iiJudge whether it is ready to move network and moves and turn.
Transmitting element, for moving the potential user turned and send recommendation and move network and move and turn to being ready to move network Information.
Preferably, the vector of behavioral parameters x includes the one or more of herein below:
Surfing flow in predetermined period;
Online duration in predetermined period;
In predetermined period, high network speed the consumed surfing flow of demand business accounts for the ratio of total surfing flow;
In predetermined period, set meal external flux expense accounts for the ratio of total flow expense.
Preferably, above mobile network moves to transfer from one department to another to unite and also includes pre-calculation unit, and it is used for:
Take individual the having confirmed that of n and be ready that moving network moves the behavioral parameters x of the user turned, according to formula:Calculate parameter μ1And σ1, then it is ready to move net Network moves the distribution density of the user turned
Take individual the having confirmed that of m and be reluctant that moving network moves the behavioral parameters x of the user turned, according to formula:Calculate parameter μ2And σ2, then it is reluctant to move net Network moves the distribution density of the user turned
Wherein, t represents transposition, the value that | σ | is σ, σ-1Inverse for σ.
It is further preferred that above according to the behavioral parameters x of potential user iiJudge whether it is ready to move network Move to subcontract and include:
CalculateValue, wherein P (W1) and P (W2) it is parameter preset;
Judge g (xi) whether more than 0, if more than 0, think that potential user i is ready to move network and moves and turn.
It is understood that the principle that is intended to be merely illustrative of the present of embodiment of above and the exemplary enforcement that uses Mode, but the invention is not limited in this.For those skilled in the art, in the essence without departing from the present invention In the case of god and essence, can make various modification and improvement, these modification and improvement are also considered as protection scope of the present invention.

Claims (10)

1. a mobile network moves shifting method, it is characterised in that including:
Gather the mobile Internet access data of user;
From the behavioral parameters x of mobile Internet access extracting data potential user, described potential user is not for use high-speed mobile net The user of network online, described behavioral parameters x is a dimensional vector;
Behavioral parameters x according to potential user iiJudge whether it is ready to move network and moves and turn, if being then sent to recommend Move network and move the information turned.
Mobile network the most according to claim 1 moves shifting method, it is characterised in that
Described potential user is the user of the mobile network's online using the mobile terminal of First Speed and second speed, described the One speed is more than second speed;
Described recommendation moves network and moves the information turned is the information recommending to move the mobile network going to First Speed.
Mobile network the most according to claim 1 moves shifting method, it is characterised in that the vector of described behavioral parameters x includes Herein below one or more:
Surfing flow in predetermined period;
Online duration in predetermined period;
In predetermined period, high network speed the consumed surfing flow of demand business accounts for the ratio of total surfing flow;
In predetermined period, set meal external flux expense accounts for the ratio of total flow expense.
Mobile network the most according to claim 1 moves shifting method, it is characterised in that join in the behavior according to potential user i Number xiJudge whether it is ready to move before network moves and turn, also include:
Take individual the having confirmed that of n and be ready that moving network moves the behavioral parameters x of the user turned, according to formula:Calculate parameter μ1And σ1, then it is ready to move net Network moves the distribution density of the user turned
Take individual the having confirmed that of m and be reluctant that moving network moves the behavioral parameters x of the user turned, according to formula:Calculate parameter μ2And σ2, then it is reluctant to move net Network moves the distribution density of the user turned
Wherein, t represents transposition, the value that | σ | is σ, σ-1Inverse for σ.
Mobile network the most according to claim 4 moves shifting method, it is characterised in that the described behavior according to potential user i Parameter xiJudge whether it is ready to move network and moves to subcontract and include:
Calculate user i according to below equation and be ready that moving network moves the probability P (W turned1|xi) and be unwilling to move net Network moves the probability P (W turned2|xi):
P ( W 1 | x i ) = p ( x i | W 1 ) P ( W 1 ) p ( x i | W 1 ) P ( W 1 ) + p ( x i | W 2 ) P ( W 2 ) ,
P ( W 2 | x i ) = p ( x i | W 2 ) P ( W 2 ) p ( x i | W 1 ) P ( W 1 ) + p ( x i | W 2 ) P ( W 2 ) ,
Wherein P (W1) and P (W2) it is parameter preset;
Relatively P (W1|xi) and P (W2|xi), if P is (W1|xi) more than P (W2|xi) then think that potential user i is ready to move network Move and turn.
Mobile network the most according to claim 4 moves shifting method, it is characterised in that the described behavior according to potential user i Parameter xiJudge whether it is ready to move network and moves to subcontract and include:
CalculateValue, wherein P (W1) and P (W2) it is parameter preset;
Judge g (xi) whether more than 0, if more than 0, think that potential user i is ready to move network and moves and turn.
7. a mobile network moves and transfers from one department to another system, it is characterised in that including:
Collecting unit, for gathering the mobile Internet access data of user;
Extraction unit, for from the behavioral parameters x of mobile Internet access extracting data potential user, described potential user is not for use The user of high-speed mobile network online, described behavioral parameters x is a dimensional vector;
Judging unit, for the behavioral parameters x according to potential user iiJudge whether it is ready to move network and moves and turn;
Transmitting element, for moving the potential user turned and send and recommend to move network and move the letter turned to being ready to move network Breath.
Mobile network the most according to claim 7 moves and transfers from one department to another system, it is characterised in that the vector of described behavioral parameters x includes Herein below one or more:
Surfing flow in predetermined period;
Online duration in predetermined period;
In predetermined period, high network speed the consumed surfing flow of demand business accounts for the ratio of total surfing flow;
In predetermined period, set meal external flux expense accounts for the ratio of total flow expense.
Mobile network the most according to claim 7 moves and transfers from one department to another system, it is characterised in that also including pre-calculation unit, it is used for:
Take individual the having confirmed that of n and be ready that moving network moves the behavioral parameters x of the user turned, according to formula:Calculate parameter μ1And σ1, then it is ready to move net Network moves the distribution density of the user turned
Take individual the having confirmed that of m and be reluctant that moving network moves the behavioral parameters x of the user turned, according to formula:Calculate parameter μ2And σ2, then it is reluctant to move net Network moves the distribution density of the user turned
Wherein, t represents transposition, the value that | σ | is σ, σ-1Inverse for σ.
Mobile network the most according to claim 9 moves and transfers from one department to another system, it is characterised in that the described behavior according to potential user i Parameter xiJudge whether it is ready to move network and moves to subcontract and include:
CalculateValue, wherein P (W1) and P (W2) it is parameter preset;
Judge g (xi) whether more than 0, if more than 0, think that potential user i is ready to move network and moves and turn.
CN201610197091.1A 2016-03-31 2016-03-31 Mobile network moves shifting method and system Active CN105873102B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610197091.1A CN105873102B (en) 2016-03-31 2016-03-31 Mobile network moves shifting method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610197091.1A CN105873102B (en) 2016-03-31 2016-03-31 Mobile network moves shifting method and system

Publications (2)

Publication Number Publication Date
CN105873102A true CN105873102A (en) 2016-08-17
CN105873102B CN105873102B (en) 2019-06-21

Family

ID=56627527

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610197091.1A Active CN105873102B (en) 2016-03-31 2016-03-31 Mobile network moves shifting method and system

Country Status (1)

Country Link
CN (1) CN105873102B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104581832A (en) * 2013-10-21 2015-04-29 中国移动通信集团北京有限公司 Method and system for realizing data service shunting
CN105430676A (en) * 2015-11-06 2016-03-23 中国联合网络通信集团有限公司 Method and device for reducing GSM network load

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104581832A (en) * 2013-10-21 2015-04-29 中国移动通信集团北京有限公司 Method and system for realizing data service shunting
CN105430676A (en) * 2015-11-06 2016-03-23 中国联合网络通信集团有限公司 Method and device for reducing GSM network load

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
邓博: "基于数据挖掘技术构建电信4G客户预测模型的研究", 《中国优秀硕士学位论文全文数据库》 *

Also Published As

Publication number Publication date
CN105873102B (en) 2019-06-21

Similar Documents

Publication Publication Date Title
Puspitasari et al. Digital divides and mobile Internet in Indonesia: Impact of smartphones
CN108537578A (en) Advertisement sending method based on big data and device
CN103927324B (en) The method and device that a kind of information is pushed
CN106202534A (en) A kind of content recommendation method based on community users behavior and system
CN109816440A (en) Marketing method, apparatus and system
CN107404481B (en) User information recognition methods and device
CN108510303A (en) Advertisement placement method and device
CN106127505A (en) The single recognition methods of a kind of brush and device
CN103475717A (en) Method and system for recommending friends based on social network
CN105592150A (en) Method, device, and system for acquiring push data
CN109902713A (en) Building recommended method, equipment, storage medium and device based on data analysis
CN106341312A (en) Social contact information display method, system and server
CN110766507A (en) Resource allocation method and device
CN103870538A (en) Method, user modeling equipment and system for carrying out personalized recommendation for users
CN105335515A (en) Information recommendation method and information recommendation device
CN106650760A (en) Method and device for recognizing user behavioral object based on flow analysis
CN108282393A (en) A kind of good friend's adding method, device, computer equipment and readable storage medium storing program for executing
CN110392155A (en) It has been shown that, processing method, device and the equipment of notification message
CN103365842B (en) A kind of page browsing recommends method and device
CN108846708A (en) User's buying behavior prediction technique, device, equipment and storage medium
CN106202465A (en) The method for pushing of a kind of terminal wallpaper, device and mobile terminal
CN103095945A (en) Charging method and charging system based on bill classification and classification charging device
CN109086289A (en) A kind of media data processing method, client, medium and equipment
CN113037510A (en) Charging method, charging device and computer readable storage medium
CN103902596A (en) High-frequency page content clustering method and system

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant