CN107330709A - Determine the method and device of destination object - Google Patents
Determine the method and device of destination object Download PDFInfo
- Publication number
- CN107330709A CN107330709A CN201610282775.1A CN201610282775A CN107330709A CN 107330709 A CN107330709 A CN 107330709A CN 201610282775 A CN201610282775 A CN 201610282775A CN 107330709 A CN107330709 A CN 107330709A
- Authority
- CN
- China
- Prior art keywords
- candidate target
- user
- fraction
- candidate
- correspondence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06Q30/0202—Market predictions or forecasting for commercial activities
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a kind of method, device and server for determining destination object.Wherein it is determined that the method for object includes：From the targeted customer of each candidate target of different dimensions acquisition percent information shared in correspondence all users of dimension, and according to the fraction of each candidate target of aforementioned proportion information acquisition, the targeted customer of each candidate target refers to set up the user that business number of times in initial preset time reaches preset times in correspondence candidate target；Obtain customer volume of each candidate target in following preset time period；Fraction is reached into predetermined threshold value and customer volume reaches that the candidate target of predetermined number is defined as destination object.The embodiment of the present application, destination object is determined jointly by obtaining the fraction of each candidate target and combining forecast model, so as to overcome in the case where candidate target historical data is limited, only rely on forecast model and determine the low defect of destination object accuracy rate, substantially increase the degree of accuracy of prediction.
Description
Technical field
The application is related to the communication technology, more particularly to a kind of method and device for determining destination object.
Background technology
With the development of ecommerce, user completes the purchase of commodity by way of on-line payment for convenience
Buy, generate Third-party payment platform, Third-party payment platform can ensure the interests of both parties, because
This, it is deep to be liked by businessman and user.
In order to cooperate with more following high-quality businessmans, Third-party payment platform is needed in existing businessman
Go to the businessman for finding to possess powerful development potentiality.The approach for having now been found that above-mentioned potentiality businessman is then by pre-
Model is surveyed, forecast model can predict the speedup situation of businessman's coming few months by the historical data of businessman,
So as to find potentiality businessman.But, this mode is not particularly suited for just setting up businessman soon, this be because
It is limited for such businessman's historical data, so that the degree of accuracy of prediction can be substantially reduced.
The content of the invention
In view of this, the application provides a kind of method and device for determining destination object.
According to the first aspect of the embodiment of the present application, there is provided a kind of method for determining destination object, the side
Method includes：
From different dimensions obtain the targeted customer of each candidate target in correspondence all users of dimension it is shared
Percent information, and according to the fraction of percent information acquisition each candidate target, each time
The targeted customer of object is selected to refer to that setting up business number of times in initial preset time in correspondence candidate target reaches
The user of preset times；
Obtain customer volume of each candidate target in following preset time period；
The fraction is reached into predetermined threshold value and the customer volume reaches that the candidate target of predetermined number is defined as
Destination object.
According to the second aspect of the embodiment of the present application, there is provided a kind of device for determining destination object, the dress
Put including：
Fraction obtains module, and the targeted customer for obtaining each candidate target from different dimensions ties up in correspondence
Percent information shared in all users is spent, and each candidate target is obtained according to the percent information
Fraction, the targeted customer of each candidate target refers to set up initial default in correspondence candidate target
Business number of times reaches the user of preset times in time；
Customer volume acquisition module, for obtaining user of each candidate target in following preset time period
Amount；
Destination object determining module, the fraction for fraction acquisition module to be obtained reaches default
The customer volume that threshold value and the customer volume acquisition module are obtained reaches that the candidate target of predetermined number is determined
For destination object.
According to the third aspect of the embodiment of the present application there is provided a kind of server, the server includes：
Processor；Memory for storing the processor-executable instruction；
Wherein, the processor is configured as：
From different dimensions obtain the targeted customer of each candidate target in correspondence all users of dimension it is shared
Percent information, and according to the fraction of percent information acquisition each candidate target, each time
The targeted customer of object is selected to refer to that setting up business number of times in initial preset time in correspondence candidate target reaches
The user of preset times；
Obtain customer volume of each candidate target in following preset time period；
The fraction is reached into predetermined threshold value and the customer volume reaches that the candidate target of predetermined number is defined as
Destination object.
In the embodiment of the present application, by obtaining the targeted customer of each candidate target from different dimensions right
Answer percent information shared in all users of dimension, and each candidate according to aforementioned proportion information acquisition
The fraction of object, destination object is determined then in conjunction with forecast model jointly, so as to overcome in candidate couple
As historical data it is limited in the case of, only rely on forecast model and determine the low defect of destination object accuracy rate,
Substantially increase the degree of accuracy of prediction.
Brief description of the drawings
Fig. 1 is a kind of flow chart of the method for determination destination object shown in the exemplary embodiment of the application one；
Fig. 2A is that a kind of target of each candidate target of acquisition shown in the exemplary embodiment of the application one is used
The flow chart at family；
It in Fig. 2A according to user service information and potentiality fraction is that each candidate target determines mesh that Fig. 2 B, which are,
Mark the flow chart of user；
Fig. 3 is the process schematic of another determination destination object shown in the exemplary embodiment of the application one；
Fig. 4 is a kind of hardware structure diagram of equipment where the application determines the device of destination object；
Fig. 5 is a kind of block diagram of the device of determination destination object shown in the exemplary embodiment of the application one；
Fig. 6 A are the frames of the device of another determination destination object shown in the exemplary embodiment of the application one
Figure；
Fig. 6 B are the frames of the device of another determination destination object shown in the exemplary embodiment of the application one
Figure；
Fig. 6 C are the frames of the device of another determination destination object shown in the exemplary embodiment of the application one
Figure；
Fig. 7 is the block diagram of the device of another determination destination object shown in the exemplary embodiment of the application one；
Fig. 8 is the block diagram of the device of another determination destination object shown in the exemplary embodiment of the application one.
Embodiment
Here exemplary embodiment will be illustrated in detail, its example is illustrated in the accompanying drawings.Following
When description is related to accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawings represent same or analogous
Key element.Embodiment described in following exemplary embodiment does not represent the institute consistent with the application
There is embodiment.On the contrary, they are only one be described in detail in such as appended claims, the application
The example of the consistent apparatus and method of a little aspects.
It is the purpose only merely for description specific embodiment in term used in this application, and is not intended to be limiting
The application." one kind ", " institute of singulative used in the application and appended claims
State " and "the" be also intended to including most forms, unless context clearly shows that other implications.Should also
Work as understanding, term "and/or" used herein refers to and associated lists item comprising one or more
Purpose any or all may combine.
It will be appreciated that though may describe various using term first, second, third, etc. in the application
Information, but these information should not necessarily be limited by these terms.These terms only be used for by same type of information that
This is distinguished.For example, in the case where not departing from the application scope, the first information can also be referred to as
Two information, similarly, the second information can also be referred to as the first information.Depending on linguistic context, as in this institute
Use word " if " can be construed to " and ... when " or " when ... when " or " response
In it is determined that ".
In the embodiment of the present application, it is each by obtaining in the case where candidate target historical data is limited
The targeted customer of candidate target, and the targeted customer of each candidate target is obtained in correspondence dimension from different dimensions
Percent information shared in all users is spent, then according to aforementioned proportion information acquisition correspondence candidate target
Fraction, finally determines destination object, so as to improve the degree of accuracy of prediction jointly with reference to Classical forecast model.
The implementation process of the application is described in detail with reference to specific embodiment.
Fig. 1 is a kind of flow chart of the method for determination destination object shown in the exemplary embodiment of the application one,
The embodiment is described from Third-party payment platform side.As shown in figure 1, the side of the determination destination object
Method includes：
Step S101, the targeted customer for obtaining each candidate target from different dimensions is useful in correspondence dimension institute
Shared percent information in family, and according to the fraction of each candidate target of aforementioned proportion information acquisition.
Wherein, candidate target can be just to set up businessman soon, and the targeted customer of each candidate target can
To refer to set up the user that business number of times in initial preset time reaches preset times in correspondence candidate target,
Wherein, preset time and preset times can be arranged as required to, and such as preset time can be half a year,
Preset times can for 2 times, it is 3 inferior, i.e., targeted customer can be forward-looking user, they
Generally begin to initial stage of founding that the preferable business of business model is done shopping and can therefrom found in the businessman in businessman
Family.
Wherein, different dimensions can include but is not limited to business number of times dimension, professional dimension and number of users
Measure dimension etc..In this embodiment, the targeted customer of each candidate target is obtained from different dimensions in correspondence
Shared percent information, can include in all users of dimension：Being obtained from business number of times dimension had multiple
The targeted customer of business record ratio shared in correspondence all targeted customers of candidate target；From quantity dimension
Degree obtains targeted customer's ratio shared in correspondence all users of candidate target；From the acquisition pair of professional dimension
The ratio for answering the targeted customer of candidate target shared in all users of the affiliated industry in affiliated city.
And can be included according to the fraction of each candidate target of aforementioned proportion information acquisition：It is multiple according to having
The targeted customer of business record ratio shared in correspondence all targeted customers of candidate target, targeted customer
The targeted customer of shared ratio and correspondence candidate target is in affiliated city in correspondence all users of candidate target
The maximum of shared ratio in all users of the affiliated industry in city, obtains the fraction of correspondence candidate target.
For convenience, can be by targeted customer's ratio shared in correspondence all users of candidate target
Represent there will be the targeted customer of multiple shopping story record in correspondence candidate target in the candidate target with Y1
All targeted customers in shared ratio represented with Y2, the targeted customer in correspondence candidate target is existed
Shared ratio is represented with Y3 in all users of the affiliated affiliated industry in city, then can pass through formula
F (y)=(Y1*Y2*Max (Y3)) obtains the fraction of correspondence candidate target, wherein, y represents candidate target
Mark.
In this embodiment, why take targeted customer shared in all users of the affiliated industry in affiliated city
Ratio maximum, be because targeted customer's proportion in all users of the affiliated industry in affiliated city
Highest trade company has extensive customer acceptance degree in the city occupation, and therefore, pole has an opportunity to copy to
With the identical professional user in other cities.
It is assumed that the targeted customer of candidate target 1 is user 1-3, all users of candidate target 1 are use
Family 1-100, user 1 has shopping record twice, and user 2-3 once does shopping record, belonging to user 1-3
City be Shanghai, the industry belonging to user 1 is lawyer, and industry belonging to user 2 is teacher, is used
Industry belonging to family 3 is lawyer, and the lawyer in Shanghai is 400 people, and teacher is 500 people, then target is used
Family ratio shared in all users of candidate target 1 is 3%, has multiple shopping in candidate target 1
The targeted customer of record ratio shared in all targeted customers is the target in 1/3, candidate target 1
The maximum of user's ratio shared in all users of the affiliated industry in affiliated city is 1/200, is being obtained
After these data, the fraction of candidate target 1 can be calculated.
Step S102, obtains customer volume of each candidate target in following preset time period.
In this embodiment, step S102 can include：The variable information of each candidate target is inputted
Forecast model, obtains growth rate of each candidate target in following preset time period；Then according to each
Active user's amount of candidate target and its corresponding growth rate, calculate each candidate target following pre-
If the customer volume of period.
Wherein, the variable information of candidate target can including but not limited to following one or more of information：
Active user's scale, transaction stroke count, dealing money, nearest 6 months speedup rings are than average, user
Retention ratio, new user's accounting, each professional accounting, each professional permeability, ranking are oozed in preceding 3% occupation
Saturating rate speedup average, the city permeability speedup of each city accounting, city permeability, ranking preceding 3%
Average, counties and cities' accounting, counties and cities' permeability and counties and cities' permeability speedup average.
Forecast model can include but is not limited to iteration decision tree (Gradient Boosting Decision Tree,
GBDT) model.
For example, above-mentioned all variables can be inputted into GBDT models, candidate target such as candidate quotient is obtained
Following probability of 3 months speedups more than 70% of family, it is assumed that obtain the following 3 months speedups of candidate target 1 and surpass
The probability for crossing 70% is 10%, then following 3 months customer volume of candidate target 1 is：Active user's amount * 1.07.
As can be seen here, each candidate target can be obtained in following preset time period by the GBDT models
Customer volume.
Step S103, reaches predetermined threshold value by fraction and customer volume reaches that the candidate target of predetermined number is determined
For destination object.
In this embodiment, fraction ranking and customer volume have each self-corresponding predetermined threshold value, for example, can be with
Fraction ranking is reached preceding 5% and customer volume reaches that the candidate target of 500 people is defined as destination object.
Above-described embodiment, by obtaining the targeted customer of each candidate target from different dimensions in correspondence dimension
Shared percent information in all users, and according to the fraction of each candidate target of aforementioned proportion information acquisition,
Destination object is determined jointly then in conjunction with forecast model, so that overcome has in candidate target historical data
In the case of limit, only rely on forecast model and determine the low defect of destination object accuracy rate, substantially increase pre-
The degree of accuracy of survey.
Fig. 2A is that a kind of target of each candidate target of acquisition shown in the exemplary embodiment of the application one is used
The flow chart at family, as shown in Figure 2 A, obtaining the process of the targeted customer of each candidate target includes：
Step S201, the user service information of each candidate target is counted according to order data.
Wherein, the user service information of each candidate target can include correspondence user in current candidate object
Shopping-time first and purchase the frequency.
Step S202, obtains the potentiality fraction of each candidate target.
The potentiality fraction is used for the development potentiality discreet value for representing correspondence candidate target, and the potentiality fraction can be with
Each candidate target is empirically for by expert to set.
Step S203, is that each candidate target determines that target is used according to user service information and potentiality fraction
Family.
Wherein, as shown in Figure 2 B, step S203 may comprise steps of：
Step S2031, for each candidate target, according to the user service information of current candidate object and
Its weight, the potentiality fraction of current candidate object and its weight and each user distribute for current candidate object
Fraction, calculate index of each user relative to current candidate object.
For convenience, in this embodiment it is possible to by each user in current candidate object first
Shopping-time is represented with X1, and the potentiality fraction of current candidate object is represented with X2, each user is existed
The purchase frequency of current candidate object is represented with X3, is point that current candidate object is distributed by each user
Number represented with i, X1, X2 and X3 weight are represented with a, b and c respectively, wherein, a, b and
C size can also be set by expert, then can pass through formula：F (x)=Σ (aX1i*bX2i*cX3i), is obtained
Index of each user relative to current candidate object is obtained, wherein, x represents the mark of user.
Step S2032, determines the abnormal user of current candidate object.
In order to exclude the interference of the abnormal users such as ox, following at least one can be passed through in this embodiment
Mode determines the abnormal user of current candidate object：
First way：The sale of business total degree and all candidate targets in all candidate targets is total
The ratio between number of times reaches that the user of the first default value is defined as abnormal user.
It is assumed that currently having 100 candidate targets, user 1 is total in the purchase of this 100 candidate targets
The ratio between sale total degree of number of times and this 100 candidate targets reaches the first default value for example preceding 1%,
Then user 1 is abnormal user.
The second way：The sale of business total degree and current candidate object in current candidate object is total
The ratio between number of times reaches that the user of the second default value is defined as abnormal user.
It is assumed that user 2 is always secondary in the sale of the purchase total degree and current candidate object of current candidate object
The ratio between number reaches the second default value for example preceding 1%, then user 2 is abnormal user.
It should be noted that the first default value and the second default value can be with identical, can also be different.
Step S2033, removes abnormal user from all users of current candidate object, and will be all surplus
The index of remaining user reaches that the user of default index threshold is defined as targeted customer.
, can be from all users of current candidate object for the accuracy rate of the targeted customer that improves acquisition
Abnormal user is removed, then according to the index of all remaining users, index ranking is reached into default index threshold
The user of value for example preceding 5% is defined as targeted customer.
The targeted customer of each candidate target can be obtained through the above way.
It should be noted that as user is in the change of candidate target business information, the target of candidate target
User is it can also happen that change, but no matter how business information changes, and can pass through above-mentioned steps
S201-S203 determines the targeted customer of candidate target.Similarly, the change of candidate target targeted customer
The change of destination object may also be caused, still, no matter how candidate target targeted customer changes,
To determine destination object by above-mentioned steps S101-S103.
Above-described embodiment, according to each user current candidate object business information and its weight, current
The potentiality fraction and its weight of candidate target and each user are that the fraction that current candidate object is distributed etc. is multiple
Factor, COMPREHENSIVE CALCULATING goes out index of each user relative to current candidate object, then from current candidate
Removed in all users of object after abnormal user, target is determined according to the index ranking of all remaining users
User, determines that destination object provides condition with very high accuracy rate, and to be follow-up.
Fig. 3 is the process schematic of another determination destination object shown in the exemplary embodiment of the application one,
As shown in figure 3, determining the process of destination object can include：
S301, by the variable information input prediction model of each candidate target, obtains each candidate target and exists
The growth rate of following preset time period.
S302, according to the active user of each candidate target amount and its corresponding growth rate, is calculated every
Customer volume of the individual candidate target in following preset time period.
Wherein, following preset time period can be following 6 months.
S303, it is determined that the targeted customer of each candidate target.
S304, the targeted customer of each candidate target is obtained in correspondence all users of dimension from different dimensions
Shared percent information, and according to the fraction of each candidate target of aforementioned proportion information acquisition.
S305, reaches predetermined threshold value by fraction and customer volume reaches that the candidate target of predetermined number is defined as mesh
Mark object.
For example, fraction ranking can be reached to preceding 6% and customer volume reaches the candidate target of 700 people for example
Candidate target is defined as destination object i.e. destination object.
Pass through above-described embodiment, it can clearly be seen that correspondence is obtained according to the percent information of targeted customer and waited
The fraction of object is selected, and combines the process that forecast model determines destination object jointly, said process overcomes
In the case where candidate target historical data is limited, only relies on forecast model and determine destination object accuracy rate
Low defect, substantially increases the degree of accuracy of prediction.
Embodiment with the method for foregoing determination destination object is corresponding, and present invention also provides determine target
The embodiment of the device of object.
The application determines that the embodiment of the device of destination object can be applied in Third-party payment platform.Dress
Putting embodiment can be realized by software, can also be realized by way of hardware or software and hardware combining.
It is the processor by equipment where it as the device on a logical meaning exemplified by implemented in software
Corresponding computer program instructions in nonvolatile memory are read what operation in internal memory was formed.From hard
For part aspect, as shown in figure 4, one kind of equipment where the device of destination object is determined for the application is hard
Part structure chart, except the processor shown in Fig. 4, internal memory, network interface and nonvolatile memory
Outside, the equipment in embodiment where device can also include it generally according to the actual functional capability of the equipment
His hardware, such as terminal, potentially includes camera, touch-screen, communication component etc., for
For server, forwarding chip of responsible processing message etc. is potentially included.
Fig. 5 is a kind of block diagram of the device of determination destination object shown in the exemplary embodiment of the application one,
The device can be applied in Third-party payment platform, as shown in figure 5, the device bag of the determination destination object
Include：Fraction obtains module 51, customer volume acquisition module 52 and destination object determining module 53.
Fraction, which obtains module 51, to be used to obtain the targeted customer of each candidate target in correspondence from different dimensions
Shared percent information in all users of dimension, and according to the fraction of each candidate target of percent information acquisition,
The targeted customer of each candidate target refers to set up business time in initial preset time in correspondence candidate target
Number reaches the user of preset times.
Customer volume acquisition module 52 is used to obtain customer volume of each candidate target in following preset time period.
Destination object determining module 53 is used to the fraction that fraction acquisition module 51 is obtained reaching predetermined threshold value
And the customer volume that customer volume acquisition module 52 is obtained reaches that the candidate target of predetermined number is defined as target pair
As.
In an optional implementation, as shown in Figure 6A, the device can also include：Count mould
Block 54, acquisition module 55 and determining module 56.
Statistical module 54 is used to obtain the target that module obtains each candidate target from different dimensions in fraction
Before user's percent information shared in correspondence all users of dimension, counted according to order data each
The user service information of candidate target.
Acquisition module 55 is used for the potentiality fraction for obtaining each candidate target, and potentiality fraction is used to represent correspondence
The development potentiality discreet value of candidate target.
Determining module 56 is used for the user service information and acquisition module 55 counted according to statistical module 54
The potentiality fraction of acquisition is that each candidate target determines targeted customer.
In an optional implementation, as shown in Figure 6B, determining module 56 may include：Calculate son
Module 561, determination sub-module 562 and removal determination sub-module 563.
Calculating sub module 561 is used to be directed to each candidate target, according to the customer service of current candidate object
Information and its weight, the potentiality fraction of current candidate object and its weight and each user are current candidate pair
As the fraction of distribution, index of each user relative to current candidate object is calculated.
Determination sub-module 562 is used for the abnormal user for determining current candidate object.
Removing determination sub-module 563 is used to remove determination sub-module from all users of current candidate object
562 abnormal users determined, and the index reached for all remaining users that calculating sub module 561 is calculated
User to default index threshold is defined as targeted customer.
In another optional implementation, as shown in Figure 6 C, determination sub-module 562 may include：
At least one unit in first determining unit 5621 and the second determining unit 5622.
First determining unit 5621 is used in the business total degree of all candidate targets and all candidates couple
The ratio between sale total degree of elephant reaches that the user of the first default value is defined as abnormal user.
Second determining unit 5622 is used in the business total degree of current candidate object and current candidate pair
The ratio between sale total degree of elephant reaches that the user of the second default value is defined as abnormal user.
In another optional implementation, it can include as shown in fig. 7, fraction obtains module 51：
First acquisition submodule 511, the second acquisition submodule 512 and the 3rd acquisition submodule 513.
First acquisition submodule 511 is used to obtain the target for having multiple business record from business number of times dimension
User's ratio shared in correspondence all targeted customers of candidate target.
Second acquisition submodule 512 is used in correspondence candidate target own from quantity dimension acquisition targeted customer
Shared ratio in user.
3rd acquisition submodule 513 is used to obtain the targeted customer of correspondence candidate target in institute from professional dimension
Belong to ratio shared in all users of the affiliated industry in city.
In another optional implementation, it can also include as shown in fig. 7, fraction obtains module 51：
Fraction obtains submodule 514.
Fraction, which obtains submodule 514, is used for having multiple business according to what the first acquisition submodule 511 was obtained
The targeted customer of record ratio shared in correspondence all targeted customers of candidate target, second obtain submodule
The targeted customer that block 512 is obtained ratio shared in correspondence all users of candidate target and the 3rd obtains son
The targeted customer for the corresponding candidate target that module 513 is obtained institute in all users of the affiliated industry in affiliated city
The maximum of the ratio accounted for, obtains the fraction of correspondence candidate target.
In another optional implementation, as shown in figure 8, customer volume acquisition module 52 may include：
Input obtains submodule 521 and calculating sub module 522.
Input, which obtains submodule 521, to be used for the variable information input prediction model of each candidate target, is obtained
To each candidate target following preset time period growth rate.
Calculating sub module 522 is used to be measured and inputted according to the active user of each candidate target to obtain submodule
531 obtained corresponding growth rate, calculate user of each candidate target in following preset time period
Amount.
The function of unit and the implementation process of effect specifically refer to correspondence in the above method in said apparatus
The implementation process of step, will not be repeated here.
For device embodiment, because it corresponds essentially to embodiment of the method, so related part is joined
See the part explanation of embodiment of the method.Device embodiment described above be only it is schematical,
The unit wherein illustrated as separating component can be or may not be physically separate, be used as list
The part of member display can be or may not be physical location, you can with positioned at a place, or
It can also be distributed on multiple NEs.Part therein can be selected according to the actual needs or complete
Portion's module realizes the purpose of application scheme.Those of ordinary skill in the art are not paying creative work
In the case of, you can to understand and implement.
The device of above-mentioned determination destination object, is used by the target that each candidate target is obtained from different dimensions
Family percent information shared in correspondence all users of dimension, and it is every according to aforementioned proportion information acquisition
The fraction of individual candidate target, destination object is determined then in conjunction with forecast model jointly, so as to overcome
In the case that candidate target historical data is limited, only relies on forecast model and determine that destination object accuracy rate is low
Defect, substantially increases the degree of accuracy of prediction.
Those skilled in the art will readily occur to this after considering specification and putting into practice invention disclosed herein
Other embodiments of application.The application is intended to any modification, purposes or the adaptability of the application
Change, these modifications, purposes or adaptations follow the general principle of the application and including this Shen
Please undocumented common knowledge or conventional techniques in the art.Description and embodiments only by
It is considered as exemplary, the true scope of the application and spirit are pointed out by following claim.
It should be appreciated that the application be not limited to be described above and be shown in the drawings it is accurate
Structure, and various modifications and changes can be being carried out without departing from the scope.Scope of the present application is only by institute
Attached claim is limited.
Claims (15)
1. a kind of method for determining destination object, it is characterised in that methods described includes：
From different dimensions obtain the targeted customer of each candidate target in correspondence all users of dimension it is shared
Percent information, and according to the fraction of percent information acquisition each candidate target, each time
The targeted customer of object is selected to refer to that setting up business number of times in initial preset time in correspondence candidate target reaches
The user of preset times；
Obtain customer volume of each candidate target in following preset time period；
The fraction is reached into predetermined threshold value and the customer volume reaches that the candidate target of predetermined number is defined as
Destination object.
2. according to the method described in claim 1, it is characterised in that obtained often from different dimensions described
Before the targeted customer of individual candidate target percent information shared in correspondence all users of dimension, the side
Method also includes：
The user service information of each candidate target is counted according to order data；
The potentiality fraction of each candidate target is obtained, the potentiality fraction is used to represent correspondence candidate target
Development potentiality discreet value；
It is that each candidate target determines the target according to the user service information and potentiality fraction
User.
3. according to the method described in claim 1, it is characterised in that described to be believed according to the customer service
Breath and potentiality fraction are that each candidate target determines the targeted customer, including：
For each candidate target, according to the user service information and its weight of the current candidate object,
The potentiality fraction and its weight of the current candidate object and each user distribute for current candidate object
Fraction, calculate index of each user relative to current candidate object；
Determine the abnormal user of current candidate object；
Remove the abnormal user from all users of current candidate object, and by all remaining users
Index reaches that the user of default index threshold is defined as the targeted customer.
4. method according to claim 3, it is characterised in that the determination current candidate object
Abnormal user, including：
It will be reached in the ratio between the business total degree of all candidate targets and sale total degree of all candidate targets
The user of first default value is defined as the abnormal user；And/or
It will be reached in the ratio between the business total degree of current candidate object and sale total degree of current candidate object
The user of second default value is defined as the abnormal user.
5. according to the method described in claim 1, it is characterised in that described to obtain each from different dimensions
The targeted customer of candidate target percent information shared in correspondence all users of dimension, including：
The targeted customer that being obtained from business number of times dimension had multiple business record owns in correspondence candidate target
Shared ratio in targeted customer；
Targeted customer's ratio shared in correspondence all users of candidate target is obtained from quantity dimension；
The targeted customer of correspondence candidate target is obtained in all users of the affiliated industry in affiliated city from professional dimension
In shared ratio.
6. method according to claim 5, it is characterised in that described to be obtained according to the percent information
The fraction of each candidate target is obtained, including：
According to the targeted customer for having multiple business record in correspondence all targeted customers of candidate target
Shared ratio, the targeted customer ratio shared in correspondence all users of candidate target and described right
The maximum of the targeted customer of candidate target ratio shared in all users of the affiliated industry in affiliated city is answered,
Obtain the fraction of correspondence candidate target.
7. according to the method described in claim 1, it is characterised in that described to obtain each candidate couple
As the customer volume in following preset time period, including：
By the variable information input prediction model of each candidate target, each candidate target is obtained not
Carry out the growth rate of preset time period；
According to the active user of each candidate target amount and its corresponding growth rate, calculate described
Customer volume of each candidate target in following preset time period.
8. a kind of device for determining destination object, it is characterised in that described device includes：
Fraction obtains module, and the targeted customer for obtaining each candidate target from different dimensions ties up in correspondence
Percent information shared in all users is spent, and each candidate target is obtained according to the percent information
Fraction, the targeted customer of each candidate target refers to set up initial default in correspondence candidate target
Business number of times reaches the user of preset times in time；
Customer volume acquisition module, for obtaining user of each candidate target in following preset time period
Amount；
Destination object determining module, the fraction for fraction acquisition module to be obtained reaches default
The customer volume that threshold value and the customer volume acquisition module are obtained reaches that the candidate target of predetermined number is determined
For destination object.
9. device according to claim 8, it is characterised in that described device also includes：
Statistical module, for obtaining the mesh that module obtains each candidate target from different dimensions in the fraction
Mark before user's percent information shared in correspondence all users of dimension, counted often according to order data
The user service information of individual candidate target；
Acquisition module, the potentiality fraction for obtaining each candidate target, the potentiality fraction is used to represent
The development potentiality discreet value of correspondence candidate target；
Determining module, for the user service information that is gone out according to the statistical module counts and described is obtained
The potentiality fraction that modulus block is obtained determines the targeted customer for each candidate target.
10. device according to claim 8, it is characterised in that the determining module includes：
Calculating sub module, for for each candidate target, according to user's industry of the current candidate object
Business information and its weight, the potentiality fraction of the current candidate object and its weight and each user are
The fraction of current candidate object distribution, calculates index of each user relative to current candidate object；
Determination sub-module, the abnormal user for determining current candidate object；
Determination sub-module is removed, for removing the determination submodule from all users of current candidate object
The abnormal user that block is determined, and the index for all remaining users that the calculating sub module is calculated
Reach that the user of default index threshold is defined as the targeted customer.
11. device according to claim 10, it is characterised in that the determination sub-module includes：
First determining unit, for by the business total degree of all candidate targets and all candidate targets
The ratio between sale total degree reaches that the user of the first default value is defined as the abnormal user；And/or
Second determining unit, for by the business total degree of current candidate object and current candidate object
The ratio between sale total degree reaches that the user of the second default value is defined as the abnormal user.
12. device according to claim 8, it is characterised in that the fraction, which obtains module, to be included：
First acquisition submodule, is used for obtaining the target for having multiple business record from business number of times dimension
Family ratio shared in correspondence all targeted customers of candidate target；
Second acquisition submodule, it is useful in correspondence candidate target institute for obtaining targeted customer from quantity dimension
Shared ratio in family；
3rd acquisition submodule, for obtaining the targeted customer of correspondence candidate target from professional dimension affiliated
Shared ratio in all users of the affiliated industry in city.
13. device according to claim 12, it is characterised in that the fraction obtains module and also wrapped
Include：
Fraction obtains submodule, for having multiple industry according to first acquisition submodule acquisition
The targeted customer of business record ratio shared in correspondence all targeted customers of candidate target, described second are obtained
Take the targeted customer that submodule is obtained ratio shared in correspondence all users of candidate target and described
The targeted customer for the corresponding candidate target that 3rd acquisition submodule is obtained is useful in the affiliated industry institute in affiliated city
The maximum of shared ratio in family, obtains the fraction of correspondence candidate target.
14. device according to claim 8, it is characterised in that the customer volume acquisition module bag
Include：
Input obtains submodule, by the variable information input prediction model of each candidate target, obtains described
Growth rate of each candidate target in following preset time period；
Calculating sub module, for being obtained according to the active user of each candidate target amount and the input
The corresponding growth rate that submodule is obtained, calculates each candidate target in following preset time period
Customer volume.
15. a kind of server, it is characterised in that including：
Processor；Memory for storing the processor-executable instruction；
Wherein, the processor is configured as：
From different dimensions obtain the targeted customer of each candidate target in correspondence all users of dimension it is shared
Percent information, and according to the fraction of percent information acquisition each candidate target, each time
The targeted customer of object is selected to refer to that setting up business number of times in initial preset time in correspondence candidate target reaches
The user of preset times；
Obtain customer volume of each candidate target in following preset time period；
The fraction is reached into predetermined threshold value and the customer volume reaches that the candidate target of predetermined number is defined as
Destination object.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610282775.1A CN107330709B (en) | 2016-04-29 | 2016-04-29 | Method and device for determining target object |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610282775.1A CN107330709B (en) | 2016-04-29 | 2016-04-29 | Method and device for determining target object |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107330709A true CN107330709A (en) | 2017-11-07 |
| CN107330709B CN107330709B (en) | 2020-05-05 |
Family
ID=60192419
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610282775.1A Active CN107330709B (en) | 2016-04-29 | 2016-04-29 | Method and device for determining target object |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107330709B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109191176A (en) * | 2018-07-31 | 2019-01-11 | 国政通科技有限公司 | A kind of method and device for precisely hitting high-end food and drink potential user |
| CN110059244A (en) * | 2019-02-01 | 2019-07-26 | 阿里巴巴集团控股有限公司 | Audient's extended method and device |
| CN110197389A (en) * | 2019-03-04 | 2019-09-03 | 腾讯科技（深圳）有限公司 | A kind of user identification method and device |
| CN112348587A (en) * | 2020-11-16 | 2021-02-09 | 脸萌有限公司 | Information pushing method and device and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100010878A1 (en) * | 2004-04-16 | 2010-01-14 | Fortelligent, Inc. | Predictive model development |
| CN103164481A (en) * | 2011-12-16 | 2013-06-19 | 盛乐信息技术（上海）有限公司 | Recommendation method and system of video with largest rising trend |
| CN104915734A (en) * | 2015-06-25 | 2015-09-16 | 深圳市腾讯计算机系统有限公司 | Commodity popularity prediction method based on time sequence and system thereof |
-
2016
- 2016-04-29 CN CN201610282775.1A patent/CN107330709B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100010878A1 (en) * | 2004-04-16 | 2010-01-14 | Fortelligent, Inc. | Predictive model development |
| CN103164481A (en) * | 2011-12-16 | 2013-06-19 | 盛乐信息技术（上海）有限公司 | Recommendation method and system of video with largest rising trend |
| CN104915734A (en) * | 2015-06-25 | 2015-09-16 | 深圳市腾讯计算机系统有限公司 | Commodity popularity prediction method based on time sequence and system thereof |
Non-Patent Citations (1)
| Title |
|---|
| 段鸿轩 等: ""关于用户交互网站产品销售潜能预测仿真研究"", 《计算机仿真》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109191176A (en) * | 2018-07-31 | 2019-01-11 | 国政通科技有限公司 | A kind of method and device for precisely hitting high-end food and drink potential user |
| CN110059244A (en) * | 2019-02-01 | 2019-07-26 | 阿里巴巴集团控股有限公司 | Audient's extended method and device |
| CN110197389A (en) * | 2019-03-04 | 2019-09-03 | 腾讯科技（深圳）有限公司 | A kind of user identification method and device |
| CN112348587A (en) * | 2020-11-16 | 2021-02-09 | 脸萌有限公司 | Information pushing method and device and electronic equipment |
| CN112348587B (en) * | 2020-11-16 | 2024-04-23 | 脸萌有限公司 | Information pushing method and device and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107330709B (en) | 2020-05-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110033252A (en) | A kind of channel of disbursement recommended method and device | |
| CN108537568A (en) | A kind of information recommendation method and device | |
| WO2019196255A1 (en) | Time period selection method and device for telephone sales, terminal equipment and medium | |
| CN107330709A (en) | Determine the method and device of destination object | |
| CN107392645A (en) | Usage mining method, apparatus and its equipment | |
| CN109493113A (en) | A kind of providing method and device of favor information | |
| CN107993088A (en) | A kind of Buying Cycle Forecasting Methodology and device, electronic equipment | |
| CN106611321B (en) | False mobile phone number identification method and device | |
| CN108777701A (en) | A kind of method and device of determining receiver | |
| CN109600344A (en) | Identify the method, apparatus and electronic equipment of risk group | |
| US20150073889A1 (en) | Dynamic Retailer Rewards Based on Attributes of Historical Transactions and Calculated Values | |
| CN110009365A (en) | User group's detection method, device and the equipment of improper transfer electronic asset | |
| CN110298508A (en) | Behavior prediction method, device and equipment | |
| CN109450963B (en) | Message pushing method and terminal equipment | |
| KR20110132792A (en) | System for managing regular customer, application selling apparatus and method for managing regular customer of the apparatus | |
| US7533095B2 (en) | Data mining within a message handling system | |
| CN106485521A (en) | User credit degree appraisal procedure and device | |
| CN111753386B (en) | Data processing method and device | |
| US20130144695A1 (en) | Designing viral marketing strategies for up-selling and cross-selling | |
| CN112330373A (en) | User behavior analysis method and device and computer readable storage medium | |
| CN111143546A (en) | Method and device for obtaining recommendation language and electronic equipment | |
| CN111192045A (en) | Anti-cheating method, device and system based on transaction record information | |
| CN110930226A (en) | Financial product recommendation method and device, electronic equipment and storage medium | |
| JP2019046465A (en) | Presentation apparatus, presentation method, and presentation program | |
| CN110009440A (en) | A kind of data processing method and device based on Trading Model |
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 | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 1246466 Country of ref document: HK |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20200922 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Patentee after: Innovative advanced technology Co.,Ltd. Address before: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Patentee before: Advanced innovation technology Co.,Ltd. Effective date of registration: 20200922 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Patentee after: Advanced innovation technology Co.,Ltd. Address before: A four-storey 847 mailbox in Grand Cayman Capital Building, British Cayman Islands Patentee before: Alibaba Group Holding Ltd. |