CN104168535B - The method for establishing 3G visitor's open model - Google Patents
The method for establishing 3G visitor's open model Download PDFInfo
- Publication number
- CN104168535B CN104168535B CN201410418345.9A CN201410418345A CN104168535B CN 104168535 B CN104168535 B CN 104168535B CN 201410418345 A CN201410418345 A CN 201410418345A CN 104168535 B CN104168535 B CN 104168535B
- Authority
- CN
- China
- Prior art keywords
- rete mirabile
- network users
- user
- call
- visitor
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Mobile Radio Communication Systems (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention discloses a kind of 3G visitor's open model method, including：ARPU value steps, calculate the ARPU value informations of rete mirabile user, then are modified and segment processing；Rete mirabile positioning step, the address information of rete mirabile user is obtained by the judgement screening of the coefficient of variation；Probability step is roamed, collects voice and short message that rete mirabile crosses network users, integral data carries out standard deviation processing, calculates the possibility of user's roaming；Be closely connected people's step, show that the rete mirabile of this network users is closely connected people；Student's step, predicts student group.The invention also discloses a kind of 3G visitor's open model, including long unrestrained model module, ARPU values model module, address location model module, roam probabilistic model module, be closely connected people's model module and student model module.What the present invention more preferably, can be refined more serves user, rete mirabile user is obtained more preferential and better services after Home Network is added.
Description
Technical field
The present invention relates to the communications field, more particularly to a kind of 3G visitor's open model method and 3G visitor's open model.
Background technology
With 3G fast development, customer demand shows obvious new feature, and communication service also shows new trend,
The requirement of customer quantity explosive growth and client to service response speed, accuracy improves constantly, traditional business hall, customer service
Hot line channel can't bear the heavy load, and each operator is while customer retaining is tried every possible means, and for the amount of extending one's service, allow more users
The good service of oneself is enjoyed, starts target to be concentrated one's gaze on user's especially high-end user of rival, 3G visitor, which opens, is exactly
Comply with this needs rete mirabile to grow up that arises at the historic moment and instigate rebellion within enemy camp means.
It is interaction according between different operators user that existing 3G visitor, which opens, extracts the Back ground Information of rete mirabile user, beats
The service framework based on rete mirabile Client view is made, the service of oneself is promoted using telemarketing means and customer communication and produces
Product.A kind of improved procedure is to utilize data processing technique, is collected with computer, record data, then from it is substantial amounts of, be probably mixed and disorderly
Without being extracted in chapter, elusive data and derive that for some specific people be valuable, significant number
According to, and transmit the data delivered and selected after data are analyzed and processed.By pattern analysis technology, this method can be by visitor
The effective information at family is collected, there is provided the user for having production capacity to be worth is serviced.For the step of realizing of this method, at data
Reason process is more single, and customer basis information could not effectively combine reduction client's real demand, in addition artificial subjective factor
Judge that user's value accounting is larger, when the service of carrying out is promoted, the reduction of data utilization rate can be caused, increase operation costs.
Existing 3G visitor's on-mode can not meet growing customer demand and the service to become more meticulous, need to be to user's
Consumption feature and the type of user do more detailed classification, and it is imperative to research and develop new 3G visitor's open model.
The content of the invention
It is an object of the invention to provide a kind of 3G visitor's open model method and 3G visitor's open model, can more preferably, more refine
Serve user, rete mirabile user is obtained more preferential and better services after Home Network is added.
Realizing the technical scheme of above-mentioned purpose is：
A kind of 3G visitor's open model method, comprises the following steps：
ARPU value steps, the information of network users is crossed by collecting rete mirabile, and rete mirabile user is calculated by logistic regression algorithm
ARPU value informations, be modified further according to known this network users ARPU values, finally to ARPU values carry out segment processing；
Rete mirabile positioning step, the call detailed list of network users and Home Network user preset period is crossed according to rete mirabile, match with
The stable several base station informations of Home Network user's communication rule, the address that rete mirabile user is obtained by the judgement screening of the coefficient of variation are believed
Breath；
Probability step is roamed, the rete mirabile by collecting the preset time period crosses the voice and short message of network users, whole
The data for closing the period carry out standard deviation processing, then obtain the possibility size of user's roaming by probability calculation formula；
Be closely connected people's step, by rete mirabile is crossed network users the moon call law and the tickets of all call laws converge
Always, the corresponding coefficient of variation is calculated, show that the rete mirabile of this network users is closely connected people accordingly；
Student's step, by collect this network users and rete mirabile cross network users call and short message it is single in detail, collect making for user
With behavior, associated person information is tightly combined, predicts student group.
In above-mentioned 3G visitor's open model method, in addition to length is strolled suddenly, and the length is strolled to be included suddenly：
Step S61, we are extracted as called rete mirabile call-information, the ownership place of regular rete mirabile number, ticket spot
With corresponding province；
Step S62, it is segmented after handling the duration of call, frequency；
Step S63, is handled number section, marks excellent number；
Step S64, collect targeted customer's information.
In above-mentioned 3G visitor's open model method, the ARPU values step includes：
Step S11, extract voice and conversational nature information that rete mirabile crosses network users；
Step S12, extract rete mirabile and cross the short message reception of network users and send information；
Step S13, collect voice, call, short message reception and short message sending information that rete mirabile crosses network users, pass through logic and return
Reduction method calculates ARPU values；
Step S14, the ARPU values that step S13 is calculated are modified according to known this network users ARPU values；
Step S15, revised ARPU values are averagely divided into 10 sections, as a result collected.
In above-mentioned 3G visitor's open model method, the rete mirabile positioning step includes：
Step S21, extract preset time period rete mirabile call detailed list；
Step S22, the first district is positioned, reposition first small towns and the second small towns in the district；
Step S23, the second district is positioned, reposition first small towns and the second small towns in the district；
Step S24, the respective call average in two the first small towns and two the second small towns and standard deviation are calculated, tries to achieve variation
Coefficient；
Step S25, screened to obtain the address information of rete mirabile user according to the coefficient of variation.
In above-mentioned 3G visitor's open model method, the roaming probability step includes：
Step S31, collect voice and short message that rete mirabile crosses network users；
Step S32, calculate the average value and standard deviation of the long-distance roaming duration of call in the preset time period；
Step S33, roaming probability is calculated by probability calculation formula；
Step S34, the roaming probability being calculated averagely is divided into 10 sections, end product collects.
In above-mentioned 3G visitor's open model method, the people's step that is closely connected includes：
Step S41, extraction rete mirabile cross the phone number communication ticket of network users；
Step S42, extraction moon rule contact user, mark week situation；
Step S43, extract all rule contact users；
Step S44, seek the coefficient of variation of all rule users；
Step S45, determine that the rete mirabile of Home Network is closely connected people according to the coefficient of variation tried to achieve.
In above-mentioned 3G visitor's open model method, student's step includes：
Step S51, collect the voice messaging of this network users；
Step S52, the duration of call and number are calculated, and averaged and standard deviation；
Step S53, collect the short message of this network users；
Step S54, short message sending number is calculated, is averaged；
Step S55, collect the analysis result of voice and short message, ask for probable value, be tightly combined contact person and predict student group
Body.
In above-mentioned 3G visitor's open model method, the preset time period is two months.
A kind of 3G visitor's open model, including：
Long unrestrained model module, collect local rete mirabile and cross call scenarios of the network users under long-distance and roaming state；
ARPU value model modules, prediction rete mirabile cross the ARPU values of network users, by the mapping with Home Network bill, restore use
The true consumption value at family；
Address location model module, simulation rete mirabile cross the ownership district and small towns of network users；
Roam probabilistic model module, thus it is speculated that the user without roaming the possibility size roamed will occur in future；
Be closely connected people's model module, and the call law of network users and this network users is crossed according to rete mirabile, draws two class users
Contact tightness degree；And
Student model module, transmission situation feature is received according in specific period voice call and short message, is inferred different
Netted the probability that network users are student.
The beneficial effects of the invention are as follows：The present invention, will be with this network users in order to effectively solve the problems, such as rete mirabile user service
There is the rete mirabile user profile of call and short message record to carry out regular, unknown user profile is reduced by related algorithm.
Meanwhile algorithm of the invention reduces and provided the information of user, for service aspect, it is objective to be created to the service of becoming more meticulous
Condition, under considerable resources supplIes and manpower, resource can be made to maximize the use, reduce human cost, and will be excellent
Matter user, which effectively puts together, to be serviced, and has advantageously expanded Home Network customer group.
Brief description of the drawings
Fig. 1 is the structural representation of 3G visitor's open model of the present invention；
Fig. 2 is the flow chart of 3G visitor's open model method of the present invention；
Fig. 3 is the flow chart of the ARPU value steps of 3G visitor's open model method of the present invention；
Fig. 4 is the flow chart of the rete mirabile positioning step of 3G visitor's open model method of the present invention；
Fig. 5 is the flow chart of the roaming probability step of 3G visitor's open model method of the present invention；
Fig. 6 is the flow chart of the people's step that is closely connected of 3G visitor's open model method of the present invention；
Fig. 7 is the flow chart of student's step of 3G visitor's open model method of the present invention；
Fig. 8 is that the length of 3G visitor's open model method of the present invention strolls rapid flow chart.
Embodiment
Below in conjunction with accompanying drawing, the invention will be further described.
Referring to Fig. 1,3G visitor's open model of the present invention, including：Long unrestrained model module 1 and objective open model module 2, visitor's die sinking
Pattern block 2 include ARPU values model module 21, address location model module 22, roam probabilistic model module 23, be closely connected people
Model module 24 and student model module 25, wherein：
Long unrestrained model module 1 crosses call scenarios of the network users under long-distance and roaming state for collecting local rete mirabile,
User in certain activity extent, which compares roaming demand, to be beaten, therefore the advantage of the model is to can be good at having reflected length
Way roaming demand obtains user, and for rete mirabile 2G user, our unified rate of the long-distance roaming of 3G single deck tape-recorders have very big attraction.
ARPU values model module 21 is used to predict that rete mirabile crosses the ARPU values of network users, by the mapping with Home Network bill, goes back
Original goes out the true consumption value of user, embodies the value of user.Under certain level of consumption, it can targetedly carry out 3G single deck tape-recorders not
With the marketing of product, the model plays a part of indispensable and replaced in whole model system.
Address location model module 22 is used to simulate ownership district and small towns that rete mirabile crosses network users, on the one hand can draw a circle to approve
The user group gone out in the range of certain dispatching, on the other hand can concentrated area marketed, human cost can be saved, acted on
It is huge.
Roaming probabilistic model module 23 is used to speculate that the user without roaming the possibility size roamed will occur in future, with
ARPU models complement each other, and the influence that can obtain prediction roaming to customer consumption value is used in combination, can restore rete mirabile use
The suitable Home Network 3G single deck tape-recorder products in family；
The people's model module 24 that is closely connected crosses the call law of network users and this network users according to rete mirabile, draws two class users
Contact tightness degree, it is contemplated that the influence of population effect, predict this kind of rete mirabile colony being closely connected with this network users and be more easy to
In instigating rebellion within enemy camp.In the case of resource abundance, this crowd of user plays good adjustment effect.
Student model module 25 receives transmission situation feature according in specific period, voice call and short message, infers
Rete mirabile user is the probability of student, is combined in addition with close contact person, on the premise of known Home Network User, Neng Gougeng
Accurately orient rete mirabile User.On the one hand because User consumption is relatively low, loyalty is higher, another aspect student
User profile face is wider, causes this kind of user to instigate rebellion within enemy camp difficulty bigger, therefore needs to be shielded on stream, avoids
The waste of human resources.
Referring to Fig. 2,3G visitor's open model method of the present invention, comprises the following steps：
Step S1, ARPU value step, the information of network users is crossed by collecting rete mirabile, is calculated by logistic regression algorithm different
The ARPU value informations of network users, it is modified further according to known this network users ARPU values, finally ARPU values is carried out at segmentation
Reason, referring to Fig. 3, specifically including：
Step S11, extract voice and conversational nature information that rete mirabile crosses network users；
Step S12, extract rete mirabile and cross the short message reception of network users and send information；
Step S13, collect voice, call, short message reception and short message sending information that rete mirabile crosses network users, pass through logic and return
Reduction method calculates ARPU values；Wherein, logistic regression algorithm is as follows：
Home Network customer consumption data can be inquired, extraction wherein has this month voice SMS number interacted with rete mirabile user
According to, it is collected according to rete mirabile Subscriber Number, classification information under voice SMS collected respectively during combined data, will
Each user and the every summary information (x) included are used as a sample, obtain a sample set A.It can establish
Multiple linear regression model：
ARPU=b0+b1*x1+b2*x2+ ...+bn*xn
The actual ARPU values of rete mirabile user are obtained by survey, substitutes into model and obtains { b1, b2 ..., bn }, by parameter
Substitute into model and obtain the multiple linear regression model for estimating ARPU values.
Step S14, the ARPU values that step S13 is calculated are modified according to known this network users ARPU values, i.e.,：With
Compared by the actual ARPU values and prediction ARPU values of this network users, standard error estimate is obtained, according to error amount amendment
ARPU value estimation results.
Step S15, revised ARPU values are averagely divided into 10 sections, as a result collected.
Step S2, rete mirabile positioning step, the call detailed lists of network users and Home Network user preset period is crossed according to rete mirabile,
The several base station informations stable with Home Network user's communication rule are allotted, obtain rete mirabile user's by the judgement screening of the coefficient of variation
Address information, referring to Fig. 4, specifically including：
Step S21, extracts the rete mirabile call detailed list of preset time period (being two months in the present embodiment), and rete mirabile call is detailed
It is single include opposite-terminal number, one's own side's ticket spot, calling and called, whether be long-distance roaming call.
Step S22, the first district is positioned, reposition first small towns and the second small towns in the district；
Step S23, the second district is positioned, reposition first small towns and the second small towns in the district；
Step S24, the respective call average in two the first small towns and two the second small towns and standard deviation are calculated, i.e.,：Pass through
Call detailed list is dialed, the base station information conversed every time, two most base stations of occurrence number is counted, calculates same base station
In voice duration average and standard deviation, so as to try to achieve the coefficient of variation, i.e.,：Made a variation with token sound difference divided by speech mean
Coefficient.
Step S25, last small towns information being positioned according to the coefficient of variation, i.e. screening obtains the address information of rete mirabile user,
I.e.：Using the minimum base station of the coefficient of variation as the base station oriented, match to obtain the address information of user with base station information.
Step S3, roams probability step, and the rete mirabile by collecting preset time period (in the present embodiment two months) crosses net use
The voice and short message at family, the data for integrating the period carry out standard deviation processing, then are used by probability calculation formula
The possibility size of family roaming, referring to Fig. 5, specifically including：
Step S31, collect voice and short message that rete mirabile crosses network users；
Step S32, calculate long-distance roaming voice duration average value and mark in preset time period (in the present embodiment two months)
It is accurate poor；
Step S33, roaming probability is calculated by probability calculation formula, it is as follows：
The various information such as voice and the short message of user are extracted, obtain a z value：
(wherein x1, x2 ..., xm are the various information of user to z=w0+w1*x1+w2*x2+...+wm*xm, and dimension is
m)；
Afterwards roaming probability is obtained according to the form of sigmoid functions：P=1/ (1+exp (- z)).
Step S34, the roaming probability being calculated averagely is divided into 10 sections, end product collects.
Step S4, be closely connected people's step, by rete mirabile is crossed network users the moon call law and all call laws if
Singly collected, calculate the corresponding coefficient of variation, show that the rete mirabile of this network users is closely connected people accordingly, referring to Fig. 6, tool
Body includes：
Step S41, extraction rete mirabile cross the phone number communication ticket of network users；
Step S42, moon rule contact user, mark week situation, in order to seek are extracted in communicating ticket from phone number
Look for the call law of same contact person；
Step S43, all rule contact users are extracted in communicating ticket from phone number；
Step S44, the coefficient of variation of all rule users is sought, i.e.,：Statistics have call it is all weekly it is several be rule day, try to achieve rule
The standard deviation and average value of in a few days talk times are restrained, the coefficient of variation is standard deviation divided by average value；
Step S45, determine that the rete mirabile of Home Network is closely connected people according to the coefficient of variation tried to achieve, i.e.,：Obtain All Contacts
The coefficient of variation, the coefficient of variation is smaller, contact it is closer.
Step S5, student's step, by collect this network users and rete mirabile cross network users call and short message it is single in detail, collect use
The usage behavior at family, is tightly combined associated person information, predicts student group, referring to Fig. 7, specifically including：
Step S51, collect the voice messaging of this network users；
Step S52, the duration of call and number are calculated, and averaged and standard deviation；
Step S53, collect the short message of this network users；
Step S54, short message sending number is calculated, is averaged；
Step S55, collect the analysis result of voice and short message, ask for probable value by known student's message registration, analysis
Go out the rule of student's call, including air time point and the duration of call, the message registration of user is compared therewith, obtains probability
Value, specific method are：
The various information such as voice and the short message of user are extracted, obtain a z value：
(wherein x1, x2 ..., xm are the various information of user to z=w0+w1*x1+w2*x2+...+wm*xm, and dimension is
m)；
Afterwards the probability for student is obtained according to the form of sigmoid functions：P=1/ (1+exp (- z)), is tightly combined connection
It is that people predicts student group, i.e.,：It is proposed is defined as the user of student, and the people that is closely connected of these users is also defined as into student,
Thus student group is predicted.
On the one hand five steps of the above neutralize can enter on the basis of the customer consumption of reduction and roaming possibility
The rational screening of row is recommended, and on the other hand can filter out high-quality resource according to existing adjusting condition, save existing cost.
Step S6, referring to Fig. 8, long stroll includes suddenly：
Step S61, we are extracted as called rete mirabile call-information, the ownership place of regular rete mirabile number, ticket spot
With corresponding province；
Step S62, it is segmented after handling the duration of call, frequency；
Step S63, is handled number section, marks excellent number；
Step S64, collect targeted customer's information.
The long data drawn suddenly of strolling can be used alone.
Above example is used for illustrative purposes only, rather than limitation of the present invention, the technology people about technical field
Member, without departing from the spirit and scope of the present invention, can also make various conversion or modification, therefore all equivalent
Technical scheme should also belong to scope of the invention, should be limited by each claim.
Claims (6)
- A kind of 1. method for establishing 3G visitor's open model, it is characterised in that comprise the following steps：ARPU value steps, the information of network users is crossed by collecting rete mirabile, calculates rete mirabile user's by logistic regression algorithm ARPU value informations, it is modified further according to known this network users ARPU values, segment processing finally is carried out to ARPU values；Rete mirabile positioning step, the call detailed list of network users and Home Network user preset period is crossed according to rete mirabile, matched and Home Network The stable several base station informations of user's communication rule, the address information of rete mirabile user is obtained by the judgement screening of the coefficient of variation；Probability step is roamed, the rete mirabile by collecting the preset time period crosses the voice and short message of network users, and integrating should The data of period carry out standard deviation processing, then obtain the possibility size of user's roaming by probability calculation formula；Be closely connected people's step, by rete mirabile is crossed network users the moon call law and the tickets of all call laws collect, The corresponding coefficient of variation is calculated, show that the rete mirabile of this network users is closely connected people accordingly；Student's step, by collect this network users and rete mirabile cross network users call and short message it is single in detail, collect the use row of user To be tightly combined associated person information, predicting student group；Also include length to stroll suddenly, the length is strolled to be included suddenly：Step S61, we are extracted as called rete mirabile call-information, the ownership place of regular rete mirabile number, ticket spot and right The province answered；Step S62, it is segmented after handling the duration of call, frequency；Step S63, is handled number section, marks excellent number；Step S64, collect targeted customer's information；ARPU value steps include：Step S11, extract voice and conversational nature information that rete mirabile crosses network users；Step S12, extract rete mirabile and cross the short message reception of network users and send information；Step S13, collect voice, call, short message reception and short message sending information that rete mirabile crosses network users, calculated by logistic regression Method calculates ARPU values；Step S14, the ARPU values that step S13 is calculated are modified according to known this network users ARPU values；Step S15, revised ARPU values are averagely divided into 10 sections, as a result collected.
- 2. the method according to claim 1 for establishing 3G visitor's open model, it is characterised in that the rete mirabile positioning step bag Include：Step S21, extract preset time period rete mirabile call detailed list；Step S22, the first district is positioned, reposition first small towns and the second small towns in the district；Step S23, the second district is positioned, reposition first small towns and the second small towns in the district；Step S24, the respective call average in two the first small towns and two the second small towns and standard deviation are calculated, tries to achieve variation lines Number；Step S25, screened to obtain the address information of rete mirabile user according to the coefficient of variation.
- 3. the method according to claim 1 for establishing 3G visitor's open model, it is characterised in that the roaming probability step bag Include：Step S31, collect voice and short message that rete mirabile crosses network users；Step S32, calculate the average value and standard deviation of the long-distance roaming duration of call in the preset time period；Step S33, roaming probability is calculated by probability calculation formula；Step S34, the roaming probability being calculated averagely is divided into 10 sections, end product collects.
- 4. the method according to claim 1 for establishing 3G visitor's open model, it is characterised in that the people's step bag that is closely connected Include：Step S41, extraction rete mirabile cross the phone number communication ticket of network users；Step S42, extraction moon rule contact user, mark week situation；Step S43, extract all rule contact users；Step S44, seek the coefficient of variation of all rule users；Step S45, determine that the rete mirabile of Home Network is closely connected people according to the coefficient of variation tried to achieve.
- 5. the method according to claim 1 for establishing 3G visitor's open model, it is characterised in that student's step includes：Step S51, collect the voice messaging of this network users；Step S52, the duration of call and number are calculated, and averaged and standard deviation；Step S53, collect the short message of this network users；Step S54, short message sending number is calculated, is averaged；Step S55, collect the analysis result of voice and short message, ask for probable value, be tightly combined contact person and predict student group.
- 6. the method according to claim 1 for establishing 3G visitor's open model, it is characterised in that the preset time period is two Month.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410418345.9A CN104168535B (en) | 2014-08-22 | 2014-08-22 | The method for establishing 3G visitor's open model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410418345.9A CN104168535B (en) | 2014-08-22 | 2014-08-22 | The method for establishing 3G visitor's open model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104168535A CN104168535A (en) | 2014-11-26 |
| CN104168535B true CN104168535B (en) | 2018-01-19 |
Family
ID=51912131
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410418345.9A Active CN104168535B (en) | 2014-08-22 | 2014-08-22 | The method for establishing 3G visitor's open model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104168535B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105160547A (en) * | 2015-08-07 | 2015-12-16 | 北京思特奇信息技术股份有限公司 | Cross-network identification method and system based on stable contact index |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102215504A (en) * | 2010-04-08 | 2011-10-12 | 中国移动通信集团甘肃有限公司 | Method and system for identifying class of newly network-accessed user |
| CN103607691A (en) * | 2013-11-26 | 2014-02-26 | 中国联合网络通信集团有限公司 | Flow package recommendation method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8762193B2 (en) * | 2005-11-11 | 2014-06-24 | Accenture Global Services Limited | Identifying target customers for campaigns to increase average revenue per user |
-
2014
- 2014-08-22 CN CN201410418345.9A patent/CN104168535B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102215504A (en) * | 2010-04-08 | 2011-10-12 | 中国移动通信集团甘肃有限公司 | Method and system for identifying class of newly network-accessed user |
| CN103607691A (en) * | 2013-11-26 | 2014-02-26 | 中国联合网络通信集团有限公司 | Flow package recommendation method and device |
Non-Patent Citations (2)
| Title |
|---|
| 浅谈ARPU值的细化与分析;张俐;《财经界》;20130420;27-29 * |
| 移动通信企业精细化营销客户细分研究;何帆;《万方在线数据库》;20081106;正文第36-38页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104168535A (en) | 2014-11-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107534884A (en) | Quality based on available network switches between networks | |
| CN109978608A (en) | The marketing label analysis extracting method and system of target user's portrait | |
| CN105007171A (en) | User data analysis system and method based on big data in communication field | |
| CN103905971B (en) | A kind of method and device for recommending traffic set meal | |
| CN101562830A (en) | Customer perception evaluation method and system | |
| US9936081B2 (en) | Determining telecommunication subscriber metrics | |
| EP2608179A1 (en) | Determining a common origin, a common destination and a common route from a network data record | |
| US20130204999A1 (en) | System and Method for Automatic Sub-Panel Creation and Management | |
| CN110445942A (en) | A kind of outer paging system of intelligence and intelligent calling-out method | |
| CN101883133A (en) | Accurate influence marketing system based on signalling analysis and method thereof | |
| CN101021927A (en) | Unified marketing supporting system based on analysis of user behaviour and habit and method thereof | |
| US20110022475A1 (en) | Distribution of promotional data and receipt of customers' reactions to the data | |
| CN104113869B (en) | A kind of potential report user's Forecasting Methodology and system based on signaling data | |
| CN102711162A (en) | Method for monitoring network quality and optimizing user experience in mobile internet | |
| CN107624249A (en) | Method and system for the number in the aggregated data real-time counting crowd by communication network | |
| CN101217758B (en) | A method and device of mobility model for cellular network users | |
| CN102123418A (en) | Ping-pong handover positioning method based on A-interface signaling | |
| CN101406032A (en) | Value-added service network and IVR server and real-time flow path track analysis method | |
| CN107787015A (en) | Network method of adjustment and device based on big data | |
| CN109121006A (en) | A kind of marketing method and platform based on live streaming viewing user | |
| Roszik et al. | Retrial queues in the performance modelling of cellular mobile networks using MOSEL | |
| CN105824818A (en) | Informationized management method, platform and system | |
| CN109040489A (en) | The distribution method and device of telecommunications customer service | |
| CN102149113B (en) | Mobile user perception quantification method | |
| CN104168535B (en) | The method for establishing 3G visitor's open model |
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 |