CN109191185A - A kind of visitor's heap sort method and system - Google Patents
A kind of visitor's heap sort method and system Download PDFInfo
- Publication number
- CN109191185A CN109191185A CN201810929565.6A CN201810929565A CN109191185A CN 109191185 A CN109191185 A CN 109191185A CN 201810929565 A CN201810929565 A CN 201810929565A CN 109191185 A CN109191185 A CN 109191185A
- Authority
- CN
- China
- Prior art keywords
- data
- client
- user
- app
- target app
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/52—Network services specially adapted for the location of the user terminal
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/535—Tracking the activity of the user
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
Abstract
The present embodiments relate to a kind of objective heap sort methods, comprising: obtains the user data of each APP in client's electronic mobile device；It analyzes the user data and filter plant cheats list and blacklist, obtain remaining users data；The remaining users data are screened and counted, user behavior data is generated, which includes behavioral data of the user on the APP high using liveness；The corresponding probability value of each client is obtained according to the user behavior data, and with logistic regression algorithm model；After the probability value for obtaining each client, all clients are divided into according to the probability value by different classifications.The invention further relates to a kind of objective heap sort systems.
Description
Technical field
The invention belongs to technical field of data processing more particularly to a kind of objective heap sort method and system.
Background technique
With the further expansion of age and globalization of economy, more and more industry product homogeneity speed are accelerated, market
Competition increasingly sharpens, and the competition between enterprise is not only the competition of energy personnel and technology, and the competition of customer resources is also never
Have and stopped, the client that any enterprise is intended to this enterprise be it is good, higher benefit can be thus brought to enterprise
Profit.However often things turn out contrary to one's wishes, customer demand diversification and personalized feature are also increasingly obvious, therefore for enterprise such as
What identifies client, to divide group tactful for the risk that different clients carries out differentiation, improves customer account management level, mentions significantly
The retention ratio of high corporate client certainly will be very beneficial to the development of enterprise.
In loan industry, it usually needs statistic of classification is carried out to the client of loan, to facilitate business personnel according to client
Classification makes different risks and divides group tactful.But the existing mode classified to client also rests on according to the age, disappears
The stage that the data such as expense volume directly divide.The evaluation condition of which is few, keeps classification results accuracy not high, thus can not give industry
Business personnel do product promotion and provide effective reference frame.
In view of this, nowadays there is an urgent need to design a kind of objective heap sort method, to overcome existing customer's classification method
Shortcoming.
Summary of the invention
It is inadequate to solve client segmentation in the prior art the embodiment of the invention provides a kind of objective heap sort method and system
Accurate technical problem.
The embodiment of the present invention provides a kind of objective heap sort method, comprising the following steps:
Obtain the user data of each APP in client's electronic mobile device；
It analyzes the user data and filter plant cheats list and blacklist, obtain remaining users data；
The remaining users data are screened and counted, user behavior data is generated, which includes
Behavioral data of the user on the target APP high using liveness；
The corresponding probability value of each client is obtained according to the user behavior data, and with logistic regression algorithm model；
After the probability value for obtaining each client, all clients are divided into according to the probability value by different classes
Not.
Further, the user data is obtained according to the agreement reached with affiliate.
Further, the analysis user data and filter plant fraud list and blacklist, obtain remaining users
The step of data, specifically includes:
Find equipment fraud data and the blacklist data in the user data；
Reject all customer data in the equipment fraud data and the corresponding electronic mobile device of blacklist data.
Further, the step of remaining users data being screened and counted, generating user behavior data is specific
Include:
Target APP is filtered out, target APP includes loan class, credit-card type, common reserve fund class, social security class, goes on a tour
Class, star hotel class APP；
The user behavior data of each client is counted according to the user data of the target APP.
Further, the user behavior data includes use duration, frequency of use and the use intensity of target APP.
Further, the user behavior data includes the quantity of installation targets APP and each target APP in specified time
Installation number, the target APP quantity and each target APP that are unloaded in specified time unloading number.
Further, the user behavior data includes the retention quantity of the target APP in specified time, opens day
Number, number and maximum duration.
In addition, the embodiment of the present invention provides a kind of objective heap sort system simultaneously, comprising:
Module is obtained, for obtaining the user data of each APP in client's electronic mobile device；
First analysis module obtains remaining for analyzing the user data simultaneously filter plant fraud list and blacklist
User data；
Second analysis module generates user behavior data, is somebody's turn to do for the remaining users data to be screened and counted
User behavior data includes user in the behavioral data using the high target APP of liveness；
Computing module, for calculating each client according to the user behavior data, and with logistic regression algorithm model
Corresponding probability value；
Division module, for after the probability value for obtaining each client, according to the probability value by all clients
It is divided into different classifications.
Further, first analysis module specifically includes:
Module is found, for finding the fraud data of the equipment in the user data and blacklist data；
Module is rejected, for rejecting the institute in the equipment fraud data and the corresponding electronic mobile device of blacklist data
There is user data.
Further, second analysis module specifically includes:
Screening module, for filtering out target APP, target APP includes loan class, credit-card type, common reserve fund class, social security
Class, class of going on a tour, star hotel class APP；
Statistical module, for counting the user behavior data of each client according to the user data of the target APP.
The above scheme of the embodiment of the present invention compared with prior art, has the advantages that through crawl client's electricity
The related data of target APP in sub- mobile device, and the related data is excavated, generates the corresponding factor；It is comprehensive to correspond to
Target APP user behavior data, with logistic regression algorithm, thus it is speculated that the home type of client's maximum probability, improve client
The accuracy of classification.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly introduced, it should be apparent that, drawings in the following description are only some embodiments of the invention, for this
For the those of ordinary skill in field, without any creative labor, it can also be obtained according to these attached drawings
His attached drawing.
Fig. 1 is the flow chart of visitor's heap sort method described in the embodiment of the present invention.
Fig. 2 is the method flow that the embodiment of the present invention analyzes the user data and filter plant fraud list and blacklist
Figure.
Fig. 3 is the method flow diagram that the embodiment of the present invention is screened and counted to the remaining users data.
Fig. 4 is the method flow that all clients are divided into different classifications according to the probability value by the embodiment of the present invention
Figure.
Fig. 5 is the structural schematic diagram of visitor's heap sort system described in the embodiment of the present invention.
Icon: 51- obtains module；The first analysis module of 52-；521- finds module；522- rejects module；53- second divides
Analyse module；531- screening module；532- statistical module；54- computing module；55- division module.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with attached drawing to the present invention make into
It is described in detail to one step, it is clear that described embodiments are only a part of the embodiments of the present invention, rather than whole implementation
Example.Based on the embodiments of the present invention, obtained by those of ordinary skill in the art without making creative efforts
All other embodiment, shall fall within the protection scope of the present invention.
The preferred embodiment that the invention will now be described in detail with reference to the accompanying drawings.
Embodiment 1
Fig. 1 is a kind of flow diagram of objective heap sort method provided in an embodiment of the present invention.The method specifically includes
Following steps:
S101 obtains the user data of each APP in each client's electronic mobile device；
Wherein, the acquisition of the user data is carried out according to the related protocol that each APP and affiliate reach
's.That is, the user data is grabbed for the demand of the affiliate.The type of the affiliate
It is unlimited, it can be property firm, car dealer, developer's platform or loan platform etc..In the present embodiment, the affiliate is
Finance company, various loan products of mainly marketing.
In a step 101, it during obtaining the user data of client, can be based on different affiliates, from clothes
It is engaged in obtaining end user's data relevant to affiliate's marketing product in device, is also possible to the end user generated based on client
Data obtain other user data associated with end user's data, here without limitation from server.For example,
When the affiliate is finance company, the data of crawl are required to reflect that the client's borrows loan repayment capacity, as vehicle is borrowed, room
Borrow, consume loan, common reserve fund, social security etc..
The type of the electronic mobile device is unlimited, can be various calculating equipment, such as mobile phone, tablet computer, computer
Deng.In the present embodiment, the electronic mobile device is mobile phone.
S102, analyzes the user data and filter plant cheats list and blacklist, obtains remaining users data；
Wherein, by using user data described in liveness high target APP and equipment Risk dimensional analysis, to filter
Fall rogue device.The rogue device can include but is not limited to that facility registration is excessively frequent, non-commonly used equipment logs in, equipment association
Excessive account information, equipment are simulator etc..The blacklist includes being classified as blacklist by industry.The blacklist can
It is identified with being matched by the data retention grabbed.
Specifically, in the embodiment of the present invention, as shown in Fig. 2, the analysis user data and filter plant fraud name
List and blacklist, obtain remaining users data the step of include:
S201 finds equipment fraud data and blacklist device data in the user data.Wherein, the blacklist
Data are to carry out analysis based on known blacklist to find.For example, known a batch blacklist, by acquired user data
It is matched with the blacklist grabbed, to weed out the blacklist hit.
S202 rejects all numbers of users in the equipment fraud data and the corresponding electronic mobile device of blacklist data
According to.
The remaining users data is in remaining electronic mobile devices after rejecting filter plant fraud list and blacklist
User data.
S103 is screened and is counted to the remaining users data, and user behavior data, the user behavior data are generated
Behavioral data including user on the target APP high using liveness；
Wherein, the user behavior data mainly includes client in the use duration of target APP, frequency of use and using strong
Degree；In specified time the quantity of installation targets APP and each target APP installation number, the target APP that is unloaded in specified time
The unloading number of quantity and each target APP；Retention number including target APP in consumer electronics device each in specified time
Amount opens number of days, number and maximum duration.
In the embodiment of the present invention, as shown in figure 3, described screened and counted to the remaining users data, generates and use
The step of family behavioral data, specifically includes:
S301 filters out target APP, and target APP includes loan class, credit-card type, common reserve fund class, social security class, departure
It goes on a tour class, the relevant APP of star hotel's class.Specifically, being set after filtering out equipment fraud list and blacklist to remaining electronics
Standby user data carries out secondary analysis, and the user data based on the target APP is analyzed.The target APP can root
According to needs any selection, such as the application program that the requirement based on affiliate selects, client is commonly used etc..
S302 counts the user behavior data of each client according to the user data of the target APP.
Wherein, count the target APP's based on the dimensions such as PUSH message (push), location-based service (LBS) and liveness
User data obtains user behavior data.For example, the target APP is to client's automatic push message, can according to client whether
The PUSH message is clicked, the data such as duration of browsing carry out the behavioral data statistics of the client.
The user behavior data can be used for reflecting the related qualification of client, carry out for subsequent to same class user
Sort out.
S104, according to the user behavior data, and it is corresponding with logistic regression algorithm model to calculate each client
Probability value；
Wherein, the variable in logistic regression algorithm can be determined according to the user behavior data, is calculated according to logistic regression
Which kind of other probability value method prediction client assigns to.In the present embodiment, for class business of providing a loan, can be for being calculated is each
The probability of the following potential promise breaking of client.
In practical applications, logistic regression algorithm includes orderly logistic regression algorithm and unordered logistic regression algorithm, orderly
Logistic regression algorithm is a kind of algorithm developed on two sorted logic regression algorithm bases, by the K kind that will set variable
Cases classification is two classes, obtains orderly more sorted logic regression models using two sorted logic Regression Model Simulators；Unordered logic
Regression algorithm is then the reference value for defining dependent variable first, secondly, utilizing the corresponding dependent variable of different independents variable and reference value phase
Than establishing transformation model, and determine using transformation model the algorithm of the probability value of client.
Multifarious client in internet platform is combined in the embodiment of the present invention on the basis of existing logistic regression algorithm
Information quantifies the user data of different clients, the probability value of each client is calculated using quantized result,
Classify to realize to client.It is specifically chosen any logistic regression algorithm to be calculated, here without limitation.
All clients are divided into not after the probability value for obtaining each client according to the probability value by S105
Same classification.
After step S104 obtains the probability value of each client, it is most general that client can be extrapolated according to the probability value
The home type of rate.
Specifically, as shown in figure 4, the step of all clients are divided into different classifications according to the probability value includes:
S401 sorts from large to small the probability value of each client；
Specifically, for each client, it can all calculate a probability value, i.e., N number of client will correspond to N number of probability value,
Then N number of probability value is sorted from large to small.
Client is divided into M classification using the maximum M client of probability value as reference point by S402；
S403 finds out and is classified as same category with client similar in the probability value of each classification.
Each classification corresponds to a customers, and the number of client included in each customers is unlimited, can be identical,
It can not also be identical.After being classified, which can be determined according to the probability value for the client for including in each customers
The value range of the probability value of family group, in this way, for subsequent emerging client, it can be by the value range of probability value, fastly
Speed determines customers belonging to client.
Specifically, for loan class business, the client is sequentially divided into A, B, C, D, E, F six by the embodiment of the present invention
The customers of grade, wherein A grade is optimal client, which refers to the client for having housing loan, vehicle to borrow；B grade is high-quality
Client, the top-tier customer refer to the client for having common reserve fund and social security；C grade is first-class client, which refers to creditable
The client of card；D grade is medium client, which refers to that loan, credit card, social security card and common reserve fund all do not have, but is passed through
The consumption such as often tourism both at home and abroad, discrepancy star hotel；E grade be inferior client, the inferior client refer to have non-housing loan, vehicle borrow with
Outer consumption is borrowed, and platform quantity of providing a loan is less than and is equal to 3；F grade be worst client, the worst client refer to have non-housing loan,
Consumption other than vehicle is borrowed is borrowed, and platform quantity of providing a loan is greater than 3.
Visitor's heap sort method provided in an embodiment of the present invention is carried out by the APP data of crawl client's electronic mobile device
The excavation of data generates the corresponding factor；The user behavior data of comprehensive corresponding main APP is pushed away with logistic regression algorithm
The home type of client's maximum probability is surveyed, the accuracy of objective heap sort is improved.
In addition, the embodiment of the present invention further provides for a kind of objective heap sort system, as shown in Figure 5, comprising:
Module 51 is obtained, for obtaining the user data of each APP in consumer electronics device.Wherein, the user data
Acquisition be to be carried out according to the related protocol that each APP and affiliate reach.That is, the user data is
It is grabbed for the demand of the affiliate.The type of the affiliate is unlimited, can be property firm, automobile
Quotient, developer's platform or loan platform etc..In the present embodiment, the affiliate is finance company, various loans of mainly marketing
Product.
The type of the electronic mobile device is unlimited, can be various calculating equipment, such as mobile phone, tablet computer, computer
Deng.In the present embodiment, the electronic mobile device is mobile phone.
First analysis module 52 is remained for analyzing the user data simultaneously filter plant fraud list and blacklist
Remaining user data.Wherein, by user using user data described in liveness high APP and equipment Risk dimensional analysis, thus
Filter out rogue device.The rogue device can include but is not limited to that facility registration is excessively frequent, non-commonly used equipment logs in, equipment
It is associated with excessive account information, equipment is simulator etc..The blacklist equipment includes being classified as blacklist by industry.It should
Blacklist equipment can be identified by the data retention matching grabbed.The remaining users data are to reject filter plant to take advantage of
User data after swindleness list and blacklist in remaining electronic mobile device.
Specifically, first analysis module 52 includes:
Module 521 is found, for finding the fraud data of the equipment in the user data and blacklist data.Wherein, institute
Stating blacklist data is to carry out analysis based on known blacklist to find.For example, known batch facility blacklist, will be obtained
It takes user data and is matched with the blacklist for having grabbed retention, to weed out the blacklist hit.
Module 522 is rejected, for rejecting in the equipment fraud data and the corresponding electronic mobile device of blacklist data
All customer data.
Second analysis module 53, for the remaining users data to be screened and are counted, generation user behavior data,
The user behavior data includes behavioral data of the user on the target APP high using liveness.Wherein, the user behavior number
According to use duration, frequency of use and use intensity including the target APP；The number of the installation target APP in specified time
The installation number of amount and each target APP unload target APP quantity and the unloading number of each target APP in specified time；Refer to
The retention quantity of target APP, opening number of days, number and maximum duration in interior each client's electronic mobile device of fixing time.
Second analysis module 53 specifically includes:
Screening module 531, for filtering out target APP, target APP include loan class, credit-card type, common reserve fund class,
Social security class, class of going on a tour, the relevant APP of star hotel's class.Specifically, after filtering out equipment fraud list and blacklist,
Secondary analysis is carried out to the user data of remaining electronic mobile device, the user data based on the target APP is analyzed.Institute
Stating target APP can according to need any selection, for example the requirement based on affiliate selects, client is commonly used answers
With program etc..
Statistical module 532, for counting the user behavior number of each client according to the user data of the target APP
According to.Wherein, the number of users of the target APP is counted based on the dimensions such as PUSH message (push), location-based service (LBS) and liveness
According to acquisition user behavior data.For example, whether the target APP can click this according to client to client's automatic push message
PUSH message, the data such as duration of browsing carry out the behavioral data statistics of the client.
Computing module 54, for calculating each visitor according to the user behavior data, and with logistic regression algorithm model
The corresponding probability value in family.Wherein, the variable in logistic regression algorithm can be determined according to the user behavior data, according to logic
Which kind of other probability value regression algorithm prediction client assigns to.In the present embodiment, for class business of providing a loan, what is be calculated can be with
It is the probability of the following potential promise breaking of each client.Interconnection is combined in the embodiment of the present invention on the basis of existing logistic regression algorithm
Multifarious customer information in net platform, the user data of different clients is quantified, and is calculated often using quantized result
The probability value of one client classifies to client to realize.Any logistic regression algorithm is specifically chosen to be counted
It calculates, here without limitation.
Division module 55, for after the probability value for obtaining each client, according to the probability value by all visitors
Family is divided into different classifications.
Specifically, the division module 55 includes:
The probability value of each client is sorted from large to small.For each client, one can be all calculated generally
Rate value, i.e., N number of client will correspond to N number of probability value, then sort from large to small N number of probability value.
Client is divided into M classification using the maximum M client of probability value as reference point；
It finds out and is classified as same category with client similar in the probability value of each classification.Each classification corresponds to a client
Group, the number of client included in each customers is unlimited, can be identical, it can not also be identical.It, can after being classified
To determine the value range of the probability value of the customers according to the probability value for the client for including in each customers, in this way, right
In subsequent emerging client, customers belonging to client can quickly be determined by the value range of probability value.
Specifically, the client is sequentially divided into A, B, C, D, E, F six for loan class business by the embodiment of the present invention
The customers of grade, wherein A grade is optimal client, which refers to the client for having housing loan, vehicle to borrow；B grade is high-quality
Client, the top-tier customer refer to the client for having common reserve fund and social security；C grade is first-class client, which refers to creditable
The client of card；D grade is medium client, which refers to that loan, credit card, social security card and common reserve fund all do not have, but is passed through
The consumption such as often tourism both at home and abroad, discrepancy star hotel；E grade be inferior client, the inferior client refer to have non-housing loan, vehicle borrow with
Outer consumption is borrowed, and platform quantity of providing a loan is less than and is equal to 3；F grade be worst client, the worst client refer to have non-housing loan,
Consumption other than vehicle is borrowed is borrowed, and platform quantity of providing a loan is greater than 3.
Visitor's heap sort system provided in an embodiment of the present invention is carried out by the APP data of crawl client's electronic mobile device
The excavation of data generates the corresponding factor；The user behavior data of comprehensive corresponding target APP is pushed away with logistic regression algorithm
The home type for surveying client's maximum probability, improves the accuracy of client segmentation.
It will be understood by those skilled in the art that embodiments herein can provide as method, apparatus (equipment) or computer
Program product.Therefore, in terms of the application can be used complete hardware embodiment, complete software embodiment or combine software and hardware
Embodiment form.Moreover, it wherein includes the meter of computer usable program code that the application, which can be used in one or more,
The computer journey implemented in calculation machine usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of sequence product.
The application is flow chart of the reference according to method, apparatus (equipment) and computer program product of the embodiment of the present application
And/or block diagram describes.It should be understood that each process in flowchart and/or the block diagram can be realized by computer program instructions
And/or the combination of the process and/or box in box and flowchart and/or the block diagram.It can provide these computer programs to refer to
Enable the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to generate
One machine so that by the instruction that the processor of computer or other programmable data processing devices executes generate for realizing
The device for the function of being specified in one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Although the preferred embodiment of the application has been described, it is created once a person skilled in the art knows basic
Property concept, then additional changes and modifications may be made to these embodiments.So it includes excellent that the following claims are intended to be interpreted as
It selects embodiment and falls into all change and modification of the application range.
Obviously, those skilled in the art can carry out various modification and variations without departing from the essence of the application to the application
Mind and range.In this way, if these modifications and variations of the application belong to the range of the claim of this application and its equivalent technologies
Within, then the application is also intended to include these modifications and variations.
Claims (10)
1. a kind of visitor's heap sort method characterized by comprising
Obtain the user data of each APP in client's electronic mobile device；
It analyzes the user data and filter plant cheats list and blacklist, obtain remaining users data；
The remaining users data are screened and counted, generate user behavior data, which includes user
In the behavioral data using the high target APP of liveness；
The corresponding probability value of each client is obtained according to the user behavior data, and with logistic regression algorithm model；?
To after the probability value of client described in each, all clients are divided into according to the probability value by different classifications.
2. visitor's heap sort method as described in claim 1, which is characterized in that the user data is that basis is reached with affiliate
At agreement obtained.
3. visitor's heap sort method as described in claim 1, which is characterized in that described to analyze the user data and filter plant
The step of cheating list and blacklist, obtaining remaining users data specifically includes:
Find equipment fraud data and the blacklist data in the user data；
Reject all customer data in the equipment fraud data and the corresponding electronic mobile device of blacklist data.
4. visitor's heap sort method as described in claim 1, which is characterized in that the remaining users data are screened and united
The step of meter, generation user behavior data, specifically includes:
Target APP is filtered out, target APP includes loan class, credit-card type, common reserve fund class, social security class, go on a tour class, star
Grade hotel class APP；
The user behavior data of each client is counted according to the user data of the target APP.
5. visitor's heap sort method as described in claim 1, which is characterized in that the user behavior data includes target APP
Use duration, frequency of use and use intensity.
6. visitor's heap sort method as described in claim 1, which is characterized in that the user behavior data includes in specified time
The installation number of the quantity of installation targets APP and each target APP, the target APP quantity unloaded in specified time and each mesh
Mark the unloading number of APP.
7. visitor's heap sort method as described in claim 1, which is characterized in that the user behavior data includes in specified time
The retention quantity of the target APP opens number of days, number and maximum duration.
8. a kind of visitor's heap sort system characterized by comprising
Module is obtained, for obtaining the user data of each APP in client's electronic mobile device；
First analysis module obtains remaining users for analyzing the user data simultaneously filter plant fraud list and blacklist
Data；
Second analysis module generates user behavior data, the user for the remaining users data to be screened and counted
Behavioral data includes user in the behavioral data using the high target APP of liveness；
Computing module, for being corresponded to according to the user behavior data, and with each client of logistic regression algorithm model calculating
Probability value；
Division module, for being divided all clients according to the probability value after the probability value for obtaining each client
For different classifications.
9. visitor's heap sort system as claimed in claim 8, which is characterized in that first analysis module specifically includes: finding
Module, for finding the fraud data of the equipment in the user data and blacklist data；
Module is rejected, it is useful for rejecting the institute in the equipment fraud data and the corresponding electronic mobile device of blacklist data
User data.
10. visitor's heap sort system as claimed in claim 8, which is characterized in that second analysis module specifically includes: screening
Module, for filtering out target APP, target APP includes loan class, credit-card type, common reserve fund class, social security class, goes on a tour
Class, star hotel class APP；
Statistical module, for counting the user behavior data of each client according to the user data of the target APP.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810929565.6A CN109191185A (en) | 2018-08-15 | 2018-08-15 | A kind of visitor's heap sort method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810929565.6A CN109191185A (en) | 2018-08-15 | 2018-08-15 | A kind of visitor's heap sort method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109191185A true CN109191185A (en) | 2019-01-11 |
Family
ID=64917978
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810929565.6A Pending CN109191185A (en) | 2018-08-15 | 2018-08-15 | A kind of visitor's heap sort method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109191185A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110234133A (en) * | 2019-05-13 | 2019-09-13 | 中国联合网络通信集团有限公司 | A kind of network control method and device |
| CN111325580A (en) * | 2020-02-26 | 2020-06-23 | 支付宝(杭州)信息技术有限公司 | User account management method, device, equipment and storage medium |
| CN112288444A (en) * | 2020-10-23 | 2021-01-29 | 翼果（深圳）科技有限公司 | Cross-border SAAS client analysis method and system based on big data |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014075018A2 (en) * | 2012-11-12 | 2014-05-15 | Treiser Adam | Systems and methods for analyzing and displaying data |
| CN106056444A (en) * | 2016-05-25 | 2016-10-26 | 腾讯科技（深圳）有限公司 | Data processing method and device |
| CN106126597A (en) * | 2016-06-20 | 2016-11-16 | 乐视控股（北京）有限公司 | User property Forecasting Methodology and device |
| CN108256537A (en) * | 2016-12-28 | 2018-07-06 | 北京酷我科技有限公司 | A kind of user gender prediction method and system |
-
2018
- 2018-08-15 CN CN201810929565.6A patent/CN109191185A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014075018A2 (en) * | 2012-11-12 | 2014-05-15 | Treiser Adam | Systems and methods for analyzing and displaying data |
| CN106056444A (en) * | 2016-05-25 | 2016-10-26 | 腾讯科技（深圳）有限公司 | Data processing method and device |
| CN106126597A (en) * | 2016-06-20 | 2016-11-16 | 乐视控股（北京）有限公司 | User property Forecasting Methodology and device |
| CN108256537A (en) * | 2016-12-28 | 2018-07-06 | 北京酷我科技有限公司 | A kind of user gender prediction method and system |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110234133A (en) * | 2019-05-13 | 2019-09-13 | 中国联合网络通信集团有限公司 | A kind of network control method and device |
| CN111325580A (en) * | 2020-02-26 | 2020-06-23 | 支付宝(杭州)信息技术有限公司 | User account management method, device, equipment and storage medium |
| CN111325580B (en) * | 2020-02-26 | 2022-11-08 | 支付宝(杭州)信息技术有限公司 | User account management method, device, equipment and storage medium |
| CN112288444A (en) * | 2020-10-23 | 2021-01-29 | 翼果（深圳）科技有限公司 | Cross-border SAAS client analysis method and system based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111291816B (en) | Method and device for carrying out feature processing aiming at user classification model | |
| CN108256691A (en) | Refund Probabilistic Prediction Model construction method and device | |
| CN105931068A (en) | Cardholder consumption figure generation method and device | |
| CN108921686A (en) | A kind of credit-graded approach and device of personal user | |
| CN110162566A (en) | Association analysis method, device, computer equipment and the storage medium of business datum | |
| CN107784517A (en) | A kind of customer information screening method and terminal device | |
| CN111932130B (en) | Service type identification method and device | |
| CN109325845A (en) | A kind of financial product intelligent recommendation method and system | |
| CN109191185A (en) | A kind of visitor's heap sort method and system | |
| CN109508901A (en) | Allocating method, device and the computer equipment for examination & approval task of providing a loan | |
| CN107622326A (en) | User's classification, available resources Forecasting Methodology, device and equipment | |
| CN112686746A (en) | Credit flow configuration method, device and equipment | |
| KR20210137604A (en) | Automatic data analysis method and system using artificial intelligence | |
| CN110288460A (en) | Collection prediction technique, device, equipment and storage medium based on propagated forward | |
| CN110197426B (en) | Credit scoring model building method, device and readable storage medium | |
| CN113379530A (en) | User risk determination method and device and server | |
| CN110930218A (en) | Method and device for identifying fraudulent customer and electronic equipment | |
| CN110728301A (en) | Credit scoring method, device, terminal and storage medium for individual user | |
| CN113205403A (en) | Method and device for calculating enterprise credit level, storage medium and terminal | |
| CN110516713A (en) | A kind of target group's recognition methods, device and equipment | |
| CN109783381A (en) | A kind of test data generating method, apparatus and system | |
| CN112950347A (en) | Resource data processing optimization method and device, storage medium and terminal | |
| CN110348983B (en) | Transaction information management method and device, electronic equipment and non-transitory storage medium | |
| CN114418736A (en) | Bank retail credit customer layering method, storage medium and server | |
| CN111160987A (en) | Information display method, device and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190111 |
|
| RJ01 | Rejection of invention patent application after publication |