CN107679889B - The recognition methods of potential customers a kind of and terminal device - Google Patents
The recognition methods of potential customers a kind of and terminal device Download PDFInfo
- Publication number
- CN107679889B CN107679889B CN201710807133.3A CN201710807133A CN107679889B CN 107679889 B CN107679889 B CN 107679889B CN 201710807133 A CN201710807133 A CN 201710807133A CN 107679889 B CN107679889 B CN 107679889B
- Authority
- CN
- China
- Prior art keywords
- client
- potential customers
- operation model
- running node
- product
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
Abstract
The present invention provides the recognition methods of potential customers a kind of and terminal devices, are suitable for technical field of data processing, and this method includes：Identify the corresponding N number of running node of product；Carry out the structure of operation model respectively to N number of running node based on historical customer data；The client properties data for needing to be promoted client are read out, client properties data are handled successively using N number of operation model, the client properties data that each operation model filters out can be as the input of next operation model；Client to be promoted in the selection result that n-th operation model obtains is identified as to the potential customers of product.The result screened each time is all subjected to multiple model discrimination as the input of model next time, it ensure that the client to be promoted finally identified is the potential customers that there is larger probability can complete all operations step, so that the embodiment of the present invention can realize the identification to potential customers' high accuracy.
Description
Technical field
The invention belongs to the recognition methods of technical field of data processing more particularly to potential customers and terminal devices.
Background technology
Product is accurately and effectively promoted in order to realize, personal attribute's feature that many enterprises all begin through client is come pair
Different clients analyse in depth, and determine the different consumption demands of different clients, to filter out and have with product more
The potential customers of identical consumption demand, and product push is carried out to potential customers, to realize the accurate popularization to product.
However in actual conditions, when determining popularization of potential customers is being carried out, due to the purchase of some finance and money management products
Operating process is complex, such as may include verification registration and tie up card operation, at this point, even if the consumption demand of client can be with
Finance and money management product matches, and client also not necessarily patiently goes to complete complicated operating process.Such as finance and money management is produced
Fund product in product, since fund product is when being bought, needs to carry out when the consumption demand of client is fund product
It clicks, verifying dynamic password (OTP, One-time Password), registers/log in, ties up the operating procedures such as card and transaction, this
When, although fund product matches with the consumption demand of client, client not necessarily can patiently complete all operations step,
As may when tying up card if lose patience, then abandon follow-up step so that this time sale failure.Therefore,
It identifies that the accuracy of the method for potential customers is relatively low with the finance and money management product goodness of fit according only to client's consumption demand, leads to product
Sale success rate it is relatively low, it is difficult to realize the accurate popularization of product.
In summary, when having the product of complicated operating process in face of such as finance and money management product etc., the prior art pair
The recognition accuracy of potential customers corresponding with product is relatively low, and then is difficult to realize the accurate popularization to product.
Invention content
In view of this, an embodiment of the present invention provides the recognition methods of potential customers a kind of and terminal device, it is existing to solve
Have in technology, the problem relatively low to the corresponding potential customers' recognition accuracy of product with complex operations flow.
The first aspect of the embodiment of the present invention provides a kind of recognition methods of potential customers, including：
Identify the corresponding N number of running node of product；
Based on the historical customer data stored in presetting database, operation mould is carried out respectively to N number of running node of product
The structure of type, to respectively obtain N number of operation model, wherein N is the positive integer more than 1；
The client properties data for needing to be promoted client are read, it is sharp according to the corresponding operation order of the N number of running node
The client properties data are handled successively with N number of operation model, the institute handled according to each operation model
Client to be promoted is stated in the evolutionary operator probability of the corresponding running node, the client to be promoted is screened, wherein will be every
The corresponding client properties data of the client to be promoted that a operation model filters out are as the defeated of next operation model
Enter；
The corresponding the selection result of n-th operation model is obtained, by client's identification to be promoted described in the selection result
For the potential customers of the product.
The second aspect of the embodiment of the present invention provides a kind of identification terminal equipment of potential customers, the potential customers'
Identification terminal equipment includes memory, processor, and the computer that can be run on the processor is stored on the memory
Program, the processor realize following steps when executing the computer program.
Identify the corresponding N number of running node of product；
Based on the historical customer data stored in presetting database, operation mould is carried out respectively to N number of running node of product
The structure of type, to respectively obtain N number of operation model, wherein N is the positive integer more than 1；
The client properties data for needing to be promoted client are read, it is sharp according to the corresponding operation order of the N number of running node
The client properties data are handled successively with N number of operation model, the institute handled according to each operation model
Client to be promoted is stated in the evolutionary operator probability of the corresponding running node, the client to be promoted is screened, wherein will be every
The corresponding client properties data of the client to be promoted that a operation model filters out are as the defeated of next operation model
Enter；
The corresponding the selection result of n-th operation model is obtained, by client's identification to be promoted described in the selection result
For the potential customers of the product.
The third aspect of the embodiment of the present invention provides a kind of computer readable storage medium, including：It is stored with computer
Program, which is characterized in that the computer program realizes the recognition methods of potential customers as described above when being executed by processor
The step of.
Existing advantageous effect is the embodiment of the present invention compared with prior art：By distinguishing each running node
Carry out evolutionary operator probability to calculate and screened according to this, ensure that the client to be promoted for screening obtain later every time, be all with compared with
Big possibility can complete the client of the running node respective operations step.The result screened each time is all used as next time simultaneously
The input of model, to ensure that the client to be promoted finally identified, all has larger to carry out multiple model discrimination
Probability can complete the potential customers of all operations step, so that the embodiment of the present invention can realize the standard to potential customers
Really identification, improves the accuracy identified to potential customers, and then ensure that the subsequently accuracy to product promotion.
Description of the drawings
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description be only the present invention some
Embodiment for those of ordinary skill in the art without having to pay creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is the implementation process schematic diagram of the recognition methods for the potential customers that the embodiment of the present invention one provides；
Fig. 2 is the implementation process schematic diagram of the recognition methods of potential customers provided by Embodiment 2 of the present invention；
Fig. 3 is the implementation process schematic diagram of the recognition methods for the potential customers that the embodiment of the present invention three provides；
Fig. 4 is the implementation process schematic diagram of the recognition methods for the potential customers that the embodiment of the present invention four provides；
Fig. 5 is the implementation process schematic diagram of the recognition methods for the potential customers that the embodiment of the present invention five provides；
Fig. 6 is the structural schematic diagram of the identification device for the potential customers that the embodiment of the present invention six provides；
Fig. 7 is the schematic diagram of the identification terminal equipment for the potential customers that the embodiment of the present invention seven provides.
Specific implementation mode
In being described below, for illustration and not for limitation, it is proposed that such as tool of particular system structure, technology etc
Body details, to understand thoroughly the embodiment of the present invention.However, it will be clear to one skilled in the art that there is no these specific
The present invention can also be realized in the other embodiments of details.In other situations, it omits to well-known system, device, electricity
The detailed description of road and method, in case unnecessary details interferes description of the invention.
In order to illustrate technical solutions according to the invention, illustrated below by specific embodiment.
Fig. 1 shows the implementation flow chart of the recognition methods for the potential customers that the embodiment of the present invention one provides, and details are as follows：
S101 identifies the corresponding N number of running node of product.
Wherein, running node refers to the operating procedure of the required progress when client buys product, such as in purchase fund product
It clicked, OTP, registered, tying up the operating procedures such as card and transaction, is i.e. fund product corresponds to click, OTP, registers, ties up
The running nodes such as card and transaction.
Due to the more such as common stock of the type and quantity of finance and money management product, fund, bond and trust, and
To different finance and money management products, client's operating process of required progress in purchase will be different.Therefore, product is being carried out
Before the identification of corresponding potential customers, first have to identify which the corresponding running node of product has, so as to subsequent processing.
S102 grasps N number of running node of product based on the historical customer data stored in presetting database respectively
The structure for making model, to respectively obtain N number of operation model, wherein N is the positive integer more than 1.
Wherein historical customer data, refers to the data of the client once crossed by product promotion, and historical customer data is mainly wrapped
Personal relevant information and client containing client are after expanded product, the operation feelings of each running node corresponding to product
Condition.Such as A client name and the personal information such as telephone number and A client after being pushed fund product, carried out point
It hits, OTP, register, tie up which of card and transaction operating procedure, the operating procedure such as only clicked, or complete
All operations step.In embodiments of the present invention, database can be pre-entered and be stored by technical staff.
In the embodiment of the present invention, in order to ensure that the potential customers identified can have larger patient completion product purchase
All operations step can carry out operation model training and structure after getting historical customer data to each running node
It builds, so that the follow-up possibility probability that can be completed each running node to client using the operation model constructed is calculated
And screening.For example, the click for including for fund product, OTP, registering, tying up the running nodes such as card and transaction, it is respectively trained
Corresponding click model, OTP models are constructed, model is registered, ties up the operation models such as snap gauge type and Trading Model.
It should be understood that, the operation model in the embodiment of the present invention is general in the operation of running node for calculating client
Rate is the prediction model that can carry out operation behavior prediction in running node to client.Therefore, it is being utilized in the embodiment of the present invention
When historical customer data carries out the structure of operation model, should select can carry out the data processing algorithm of data prediction to carry out
The training of operation model and structure.Simultaneously, it is contemplated that the data volume of historical customer data can be increasing more huge, because
This, it is preferable that the optional data processing algorithm that can carry out big data processing is used as required data processing algorithm.
S103 reads the client properties data for needing to be promoted client, according to the corresponding operation order of N number of running node,
Client properties data are handled successively using N number of operation model, popularization visitor is waited for according to what each operation model was handled
It treats popularization client in the evolutionary operator probability of corresponding running node and screens, wherein filter out each operation model in family
Input of the corresponding client properties data of client to be promoted as next operation model.
Client wherein to be promoted is exactly and the higher client of the product goodness of fit, client to be promoted and corresponding client properties
Data being both needed to user and set in advance, being transferred when for using, wherein client properties data, including client to be promoted
Personal relevant information.
Due to being to have certain logical operation sequence between the running node of product, as the click of fund product, OTP,
It registers, tie up the running nodes such as card and transaction, the operations such as subsequent OTP can not be just carried out when being not carried out clicking operation, because
This, between these running nodes must by click, OTP, register, tie up card, transaction sequence execute.In embodiments of the present invention,
Operation model is also evolutionary operator probability calculating to be carried out to client properties data, according to the corresponding operation order of running node with base
For golden product, and with click model, OTP models, register model, tie up snap gauge type, the sequence of Trading Model successively to client
What attribute data was handled.It, in embodiments of the present invention, can be right in order to ensure the accuracy of the potential customers finally identified
What each operation model calculated, client to be promoted screens in the evolutionary operator probability of respective operations node, and will operation
The client properties data of the highest part of probability client to be promoted are handled again as the input of next operation model.By
The highest part of evolutionary operator probability client to be promoted is as pair handled next time after being to have chosen operation model processing every time
As client, to ensure that the potential customers for finally screening out, there is higher evolutionary operator probability in each running node,
And then ensure that there is the potential customers identified higher probability can complete the operating process entirely bought, that is, it ensure that identification
The accuracy of the potential customers gone out.
S104 obtains the corresponding the selection result of n-th operation model, the client to be promoted in the selection result is identified as producing
The potential customers of product.
All operation models in front are repeatedly sieved in the completion of the last one operation model (i.e. n-th operation model)
Choosing, the L obtained client to be promoted is after the calculating of the evolutionary operator probability of the last one running node, according to calculated operation
Probability screens this L clients to be promoted, and wherein the highest part of probability client to be promoted will be identified as potential customers.
In embodiments of the present invention, not to treating the screening technique progress promoted client and screened according to evolutionary operator probability
It limits, either being screened according to default fixed number, it is highest that evolutionary operator probability is such as filtered out from click model
1000 clients can also be to be screened according to default screening ratio, and the screening ratio that click model is such as arranged is 40%,
When input click model wait promote client quantity be 2000 when, it is 2000*40%=800 highest therefrom to filter out probability
The client properties data of the client to be promoted filtered out are finally input to next operation model by client, in fund product,
The client properties data that will click on the client to be promoted that model discrimination goes out are input in OTP models, carry out the processing of next step with
Screening.Specific screening technique can be set by technical staff according to actual demand.Likewise, being to wait promoting to L in S104
Can be that the client to be promoted of the default fixed number of selection operation maximum probability is used as when client carries out evolutionary operator probability screening
Potential customers can also be that client to be promoted in the default screening ratio of selection operation maximum probability is used as potential customers.
It is further understood that the embodiment of the present invention for the ease of reader, below by taking fund product as an example, illustrate in detail
Explanation：
In inventive embodiments, the finance and money management product of required popularization is fund product, corresponding running node have click,
OTP, it registers, tie up card and transaction, the client to be promoted of required processing totally 2000 needs therefrom to select 50 or so latent
Product promotion is carried out in client.
There are at least two screening techniques available at this time：
The first, is arranged each operation model treated that screening conditions are that selection operation probability highest presets fixed number
Screening, be such as arranged clicks, OTP, register, tie up card and the default fixed number of transaction screening be respectively 1000,500,250,120 with
And 50, the client properties data input OTP models of maximum preceding 1000 clients to be promoted of evolutionary operator probability can be will click at this time, it will
The client properties data input registration model of maximum preceding 500 clients to be promoted of OTP evolutionary operator probabilities, most by registration evolutionary operator probability
Snap gauge type is tied up in the client properties data input of big preceding 250 clients to be promoted, will be tied up maximum first 120 of card evolutionary operator probability and is waited for
The client properties data for promoting client input Trading Model, are finally used as potential customers by before transactional operation maximum probability 50,
Complete the screening to potential customers.In embodiments of the present invention, the screening mode for using default fixed number, to each behaviour
Make node and be all provided with a default fixed number, the behaviour of client to be promoted is calculated in the corresponding operation model of the running node
After making probability, by evolutionary operator probability before maximum the client to be promoted of default fixed number screen, and by its corresponding client
Attribute data is input in next operation model and is handled.Wherein, each running node corresponding default fixed number
Concrete numerical value can be by technical staff's sets itself according to demand.
Second, each operation model is set treated that screening conditions are that selection operation probability highest screens ratio sieve
Choosing, it is 48% that click, which is such as arranged, OTP, registers, tie up card and transaction screening ratio, only can select operation every time at this time
The corresponding client properties data of 48% client to be promoted, are input in next operation model before probability highest, final to merchandise
Model discrimination goes out the highest preceding 2000*48%*48%*48%*48%*48% ≈ 50 of evolutionary operator probability, and (actual result is
50.961,50 are taken at this time or takes 51, in view of final 50 can more meet actual demand in the embodiment of the present invention, therefore
It has chosen 50) client to be promoted and completes the screening to potential customers as potential customers.
In the embodiment of the present invention, by carrying out evolutionary operator probability calculating respectively to each running node, and according to setting
Screening obtain carrying out client's screening to be promoted, ensure that the client to be promoted for screening obtain later every time, be all have it is larger
Possibility can complete the client of the running node respective operations step.All it regard the result screened each time as mould next time simultaneously
The input of type, to carry out multiple model discrimination, to ensure that the client to be promoted finally identified, be all have it is larger general
Rate can complete the potential customers of all operations step, so that the embodiment of the present invention can be realized to the accurate of potential customers
Identification, and then ensure that the subsequently accuracy to product promotion.
As a preferred embodiment of the present invention two, as shown in Fig. 2, including：
S1021 handles historical customer data using logistic regression algorithm, is corresponded in each running node
Operation model.
In view of logistic regression algorithm has many advantages, such as that technology maturation, prediction accuracy are higher and training speed is fast, this
In inventive embodiments, selects logistic regression algorithm to handle historical customer data, carry out training and the structure of operation model
It builds, to obtain the corresponding operation model of each running node.
As a preferred embodiment of the present invention three, as shown in figure 3, including：
S201 receives tag extension instruction input by user, and is increased in historical customer data according to tag extension instruction
Add corresponding extended attribute label.
Include the personal relevant information of client in historical customer data, these people's relevant informations also correspond to client's
Attribute tags one by one are the specific data content of the attribute tags of client, such as the name of client, gender and phone information
Personal information is the corresponding specific data content of name attribute label, gender attribute label and call attribute label of client.
When user wishes to increase new extended attribute label for historic customer, the operation model generated with enhancing is general to operating
When the accuracy that rate calculates, corresponding tag extension instruction can be inputted.The embodiment of the present invention is receiving user's input
Tag extension instruction after, corresponding extended attribute label can be generated according to tag extension instruction in historical customer data.Example
Such as, when user wishes to increase the extended attribute label of VIP important levels, VIP grade label extended instructions need to only be inputted.The present invention
Embodiment can generate one in historical customer data after receiving VIP grade label extended instructions according to tag extension instruction
A level attributed labels of corresponding VIP.
S202 obtains the corresponding data of extended attribute label, and records to historical customer data.
Since increased extended attribute label is only merely an attribute tags, it is also necessary to specific data therein
Content, which is configured, could be used for subsequent model training.In embodiments of the present invention, not to the corresponding number of extended attribute label
It is defined according to setting method, can also be according to other attribute tags handle either inputting to obtain by user
It arrives, e.g., when extended attribute label label level attributed for VIP, can be bought according to the client recorded in client properties data
The total amount of product is divided to obtain VIP grades.
S203 operates each running node according to the historical customer data after increase extended attribute label respectively
The training of model and structure obtain corresponding operation model.
After the completion of extended attribute label and its corresponding specific data content record, to obtained new historic customer
Data carry out training and the structure of operation model, and obtain operation model corresponding with each running node.In the present invention
In embodiment, it is preferable that using logistic regression algorithm come carry out historical customer data processing and operation model training and
Structure.
As a preferred embodiment of the present invention four, as shown in figure 4, including：
S105, reads out the contact method of potential customers from client properties data, and according to contact method by product pair
The purchase link push answered is to potential customers.
It after identifying potential customers, needs product pushing to potential customers, to complete the accurate popularization to product.
In the embodiment of the present invention, the contact method from client properties digital independent potential customers, such as phone number, email address are understood,
And the corresponding purchase link of product is generated, link push will be bought to potential customers finally by the contact method got.
As a preferred embodiment of the present invention, in the corresponding purchase link of generation product, for the ease of according to chain
The acquisition for carrying out potential customers' nodal operation data is fetched, each potential customers can be directed to and generate unique corresponding purchase chain
It connects.Meanwhile this purchase link is either disposable link, can also be that each client corresponds to a permanent unique chain
It connects.
As a preferred embodiment of the present invention five, as shown in figure 5, including：
S106 obtains potential customers in the nodal operation data of each running node and is recorded to the visitor of potential customers
Family attribute data.
In embodiments of the present invention, the accuracy calculated evolutionary operator probability in order to further improve operation model, can be right
Potential customers record in the nodal operation data of each running node, if whether potential user A clicks purchase link, are
It is no to have carried out OTP verifying dynamic passwords etc..
In order to realize the nodal operation data acquisition to each potential user, it is necessary first to confirm the identity of operator,
As a preferred embodiment of the present invention, on the basis of the embodiment of the present invention four, each potential customers are generated only in S105
When one corresponding purchase link, as long as the link is clicked opening at this time, you can identify the identity of corresponding potential customers.As
The another preferred embodiment of the present invention, S105 are opened without generating unique corresponding purchase link in purchase connection
When, the automatic cell-phone number for reading potential customers, and determined by cell-phone number to carry out the identity of potential customers.
Meanwhile if in the preset time after buying link push, if not detecting, potential customers have carried out clicking behaviour
Make, then it is assumed that potential customers are not carried out the operation of any running node, and are recorded.The wherein concrete numerical value of preset time
It can be set according to actual conditions by technical staff.
S107 is trained update according to the client properties data of the potential customers of record to N number of operation model.
After the completion of the client properties data of record update potential customers, the client properties data of record update completion are utilized
All operation models are trained, the evolutionary operator probability that operation model operates client in running node is promoted with update
The accuracy of calculating is promoted to promote the accuracy of the identification to potential customers subsequently to the accuracy of product promotion.
In the embodiment of the present invention, operation model structure is carried out using logistic regression algorithm, it is right to pass through using operation model
Each running node carries out evolutionary operator probability calculating respectively, and is once screened according to the screening technique of setting, ensure that
The client to be promoted obtained later is screened every time, and all there is larger possibility can complete the running node respective operations step
Client.Input by the result screened each time all as model next time simultaneously, to carry out multiple model discrimination, to ensure
The client to be promoted finally identified, is the potential customers that there is larger probability can complete all operations step, from
And the embodiment of the present invention is realized, potential customers are accurately identified, and then ensure that subsequently to the accurate of product promotion
Property.Meanwhile increasing extended attribute label setting function so that promotion operation model can be optimized according to the actual demand of user
Accuracy, the actual node operation data of running node is recorded finally by the potential customers that will identify that, and profit
With these data carry out operation model update so that operation model calculates client in the evolutionary operator probability of each running node
It is promoted to further, ensure that the accuracy next time using these operation models when identification to carry out potential customers, from
And the accuracy of the identification to potential customers is improved, improve the accuracy to product promotion.
Corresponding to the method for foregoing embodiments, Fig. 6 shows the identification device of potential customers provided in an embodiment of the present invention
Structure diagram illustrate only and the relevant part of the embodiment of the present invention for convenience of description.The exemplary potential customers' of Fig. 6
Identification device can be the executive agent of the recognition methods for the potential customers that previous embodiment one provides.
With reference to Fig. 6, the identification device of the potential customers includes：
Node identification module 61 goes out the corresponding N number of running node of product for identification.
Model construction module 62, for based on the historical customer data stored in presetting database, N number of operation to product
Node carries out the structure of operation model respectively, and to respectively obtain N number of operation model, wherein N is the positive integer more than 1.
Client's screening module 63 needs to be promoted the client properties data of client for reading, and is saved according to N number of operation
The corresponding operation order of point, is successively handled the client properties data using N number of operation model, according to each behaviour
The client to be promoted obtained as model treatment the corresponding running node evolutionary operator probability, to the client to be promoted
Screened, wherein using each operation model filter out described in the corresponding client properties data of client to be promoted as
The input of next operation model.
Client identification module 64 obtains the corresponding the selection result of n-th operation model, described in the selection result
Client to be promoted is identified as the potential customers of the product.
Further, the model construction module, including：
In each running node, the historical customer data is handled using logistic regression algorithm, is obtained pair
The operation model answered.
Further, the model construction module further includes：
Tag extension submodule for receiving tag extension instruction input by user, and is instructed according to the tag extension
Increase corresponding extended attribute label in the historical customer data.
Label fills submodule, for obtaining the corresponding data of the extended attribute label, and records to history visitor
User data.
Model construction submodule is used for according to the historical customer data after the increase extended attribute label, to every
A running node carries out training and the structure of the operation model respectively, obtains the corresponding operation model.
Further, the identification device of the potential customers further includes：
Pushing module, the contact method for reading out the potential customers from the client properties data, and according to
The contact method is by the corresponding purchase link push of the product to the potential customers.
Further, the identification device of the potential customers further includes：
Logging modle, for obtain the potential customers the nodal operation data of each running node and recorded to
The client properties data of the potential customers.
Model modification module is used for the client properties data of the potential customers according to record, to N number of behaviour
It is trained update as model.
Each module realizes the process of respective function in the identification device of potential customers provided in an embodiment of the present invention, specifically may be used
With reference to the description of aforementioned embodiment illustrated in fig. 1 one, details are not described herein again.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
Although will also be appreciated that term " first ", " second " etc. are used in some embodiment of the present invention in the text
Various elements are described, but these elements should not be limited by these terms.These terms are used only to an element
It is distinguished with another element.For example, the first contact can be named as the second contact, and similarly, the second contact can be by
It is named as the first contact, without departing from the range of various described embodiments.First contact and the second contact are all contacts, but
Be them it is not same contact.
Fig. 7 is the schematic diagram of the identification terminal equipment for the potential customers that one embodiment of the invention provides.As shown in fig. 7, should
The identification terminal equipment 7 of the potential customers of embodiment includes：Processor 70, memory 71, being stored in the memory 71 can
The computer program 72 run on the processor 70.The processor 70 is realized above-mentioned when executing the computer program 72
Step in the recognition methods embodiment of each potential customers, such as step 101 shown in FIG. 1 is to 104.Alternatively, the processing
Device 70 realizes the function of each module/unit in above-mentioned each device embodiment when executing the computer program 72, such as shown in Fig. 6
The function of module 61 to 64.
The identification terminal equipment 7 of the potential customers can be desktop PC, notebook, palm PC and high in the clouds clothes
The computing devices such as business device.The identification terminal equipment of the potential customers may include, but be not limited only to, processor 70, memory 71.
It will be understood by those skilled in the art that Fig. 7 is only the example of the identification terminal equipment 7 of potential customers, do not constitute to potential
The restriction of the identification terminal equipment 7 of client may include components more more or fewer than diagram, or combine certain components, or
The different component of person, such as the identification terminal equipment of the potential customers can also be set including input-output equipment, network insertion
Standby, bus etc..
Alleged processor 70 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), application-specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor can also be any conventional processor
Deng.
The memory 71 is the computer readable storage medium of at least one type, can be the knowledge of the potential customers
The internal storage unit of other terminal device 7, for example, the identification terminal equipment 7 of potential customers hard disk or memory.The memory
71 can also be the External memory equipment of the identification terminal equipment 7 of the potential customers, such as the identification end of the potential customers
The plug-in type hard disk being equipped in end equipment 7, intelligent memory card (Smart Media Card, SMC), secure digital (Secure
Digital, SD) card, flash card (Flash Card) etc..Further, the memory 71 can also both include described potential
The internal storage unit of the identification terminal equipment 7 of client also includes External memory equipment.The memory 71 is described for storing
Other programs needed for computer program and the identification terminal equipment of the potential customers and data.The memory 71 may be used also
For temporarily storing the data that has exported or will export.
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each work(
Can unit, module division progress for example, in practical application, can be as needed and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of described device are divided into different functional units or module, more than completion
The all or part of function of description.Each functional unit, module in embodiment can be integrated in a processing unit, also may be used
It, can also be above-mentioned integrated during two or more units are integrated in one unit to be that each unit physically exists alone
The form that hardware had both may be used in unit is realized, can also be realized in the form of SFU software functional unit.In addition, each function list
Member, the specific name of module are also only to facilitate mutually distinguish, the protection domain being not intended to limit this application.Above system
The specific work process of middle unit, module, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, is not described in detail or remembers in some embodiment
The part of load may refer to the associated description of other embodiments.
Those of ordinary skill in the art may realize that lists described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, depends on the specific application and design constraint of technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
The scope of the present invention.
In embodiment provided by the present invention, it should be understood that disclosed device/terminal device and method, it can be with
It realizes by another way.For example, device described above/terminal device embodiment is only schematical, for example, institute
The division of module or unit is stated, only a kind of division of logic function, formula that in actual implementation, there may be another division manner, such as
Multiple units or component can be combined or can be integrated into another system, or some features can be ignored or not executed.Separately
A bit, shown or discussed mutual coupling or direct-coupling or communication connection can be by some interfaces, device
Or INDIRECT COUPLING or the communication connection of unit, can be electrical, machinery or other forms.
The unit illustrated as separating component may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, you can be located at a place, or may be distributed over multiple
In network element.Some or all of unit therein can be selected according to the actual needs to realize the mesh of this embodiment scheme
's.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, it can also
It is that each unit physically exists alone, it can also be during two or more units be integrated in one unit.Above-mentioned integrated list
The form that hardware had both may be used in member is realized, can also be realized in the form of SFU software functional unit.
If the integrated module/unit be realized in the form of SFU software functional unit and as independent product sale or
In use, can be stored in a computer read/write memory medium.Based on this understanding, the present invention realizes above-mentioned implementation
All or part of flow in example method, can also instruct relevant hardware to complete, the meter by computer program
Calculation machine program can be stored in a computer readable storage medium, the computer program when being executed by processor, it can be achieved that on
The step of stating each embodiment of the method.Wherein, the computer program includes computer program code, the computer program generation
Code can be source code form, object identification code form, executable file or certain intermediate forms etc..The computer-readable medium
May include：Any entity or device, recording medium, USB flash disk, mobile hard disk, magnetic of the computer program code can be carried
Dish, CD, computer storage, read-only memory (ROM, Read-Only Memory), random access memory (RAM,
Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium etc..It should be noted that described
The content that computer-readable medium includes can carry out increasing appropriate according to legislation in jurisdiction and the requirement of patent practice
Subtract, such as in certain jurisdictions, according to legislation and patent practice, computer-readable medium does not include electric carrier signal and electricity
Believe signal.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although with reference to aforementioned reality
Applying example, invention is explained in detail, it will be understood by those of ordinary skill in the art that：It still can be to aforementioned each
Technical solution recorded in embodiment is modified or equivalent replacement of some of the technical features；And these are changed
Or replace, so that the essence of corresponding technical solution is detached from the spirit and scope of various embodiments of the present invention technical solution, it should all
It is included within protection scope of the present invention.
Claims (7)
1. a kind of recognition methods of potential customers, which is characterized in that including：
Identify that the corresponding N number of running node of product, the running node are the behaviour that client buys required progress when the product
Make step；
Based on the historical customer data stored in presetting database, operation model is carried out respectively to N number of running node of product
Structure, to respectively obtain N number of operation model, wherein N is the positive integer more than 1；
The client properties data for needing to be promoted client are read, according to the corresponding operation order of the N number of running node, utilize institute
N number of operation model is stated successively to handle the client properties data, according to each operation model handle described in wait for
Client is promoted in the evolutionary operator probability of the corresponding running node, the client to be promoted is screened, wherein will each grasp
Input of the corresponding client properties data of the client to be promoted gone out as model discrimination as next operation model；
The corresponding the selection result of n-th operation model is obtained, client to be promoted described in the selection result is identified as institute
State the potential customers of product；
It is described based on the historical customer data stored in presetting database, operation mould is carried out respectively to N number of running node of product
The structure of type, to respectively obtain N number of operation model, including：
In each running node, the historical customer data is handled using logistic regression algorithm, is obtained corresponding
The operation model；
It is described based on the historical customer data stored in presetting database, operation mould is carried out respectively to N number of running node of product
The structure of type further includes to respectively obtain N number of operation model：
Tag extension instruction input by user is received, and is increased in the historical customer data according to tag extension instruction
Corresponding extended attribute label；
The corresponding data of the extended attribute label are obtained, and are recorded to the historical customer data；
According to the historical customer data after the increase extended attribute label, institute is carried out respectively to each running node
Training and the structure for stating operation model obtain the corresponding operation model.
2. recognition methods as described in claim 1, which is characterized in that further include：
The contact method of the potential customers is read out from the client properties data, and will be described according to the contact method
The corresponding purchase link push of product is to the potential customers.
3. recognition methods as claimed in claim 1 or 2, which is characterized in that further include：
The potential customers are obtained in the nodal operation data of each running node and are recorded to the institute of the potential customers
State client properties data；
According to the client properties data of the potential customers of record, update is trained to N number of operation model.
4. a kind of identification terminal equipment of potential customers, which is characterized in that the identifying processing terminal device packet of the potential customers
Memory, processor are included, the computer program that can be run on the processor, the processor are stored on the memory
Following steps are realized when executing the computer program：
Identify that the corresponding N number of running node of product, the running node are the behaviour that client buys required progress when the product
Make step；
Based on the historical customer data stored in presetting database, operation model is carried out respectively to N number of running node of product
Structure, to respectively obtain N number of operation model, wherein N is the positive integer more than 1；
The client properties data for needing to be promoted client are read, according to the corresponding operation order of the N number of running node, utilize institute
N number of operation model is stated successively to handle the client properties data, according to each operation model handle described in wait for
Client is promoted in the evolutionary operator probability of the corresponding running node, the client to be promoted is screened, wherein will each grasp
Input of the corresponding client properties data of the client to be promoted gone out as model discrimination as next operation model；
The corresponding the selection result of n-th operation model is obtained, client to be promoted described in the selection result is identified as institute
State the potential customers of product；
It is described based on the historical customer data stored in presetting database, operation mould is carried out respectively to N number of running node of product
The structure of type is specifically included with respectively obtaining N number of operation model：
In each running node, the historical customer data is handled using logistic regression algorithm, is obtained corresponding
The operation model；
It is described based on the historical customer data stored in presetting database, operation mould is carried out respectively to N number of running node of product
The structure of type further includes to respectively obtain N number of operation model：
Tag extension instruction input by user is received, and is increased in the historical customer data according to tag extension instruction
Corresponding extended attribute label；
The corresponding data of the extended attribute label are obtained, and are recorded to the historical customer data；
According to the historical customer data after the increase extended attribute label, institute is carried out respectively to each running node
Training and the structure for stating operation model obtain the corresponding operation model.
5. identification terminal equipment as claimed in claim 4, which is characterized in that when the processor executes the computer program
Also realize following steps：
The contact method of the potential customers is read out from the client properties data, and will be described according to the contact method
The corresponding purchase link push of product is to the potential customers.
6. identification terminal equipment as described in claim 4 or 5, which is characterized in that the processor executes the computer journey
Following steps are also realized when sequence：
The potential customers are obtained in the nodal operation data of each running node and are recorded to the institute of the potential customers
State client properties data；
According to the client properties data of the potential customers of record, update is trained to N number of operation model.
7. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, feature to exist
In when the computer program is executed by processor the step of any one of such as claims 1 to 3 of realization the method.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710807133.3A CN107679889B (en) | 2017-09-08 | 2017-09-08 | The recognition methods of potential customers a kind of and terminal device |
| PCT/CN2017/108620 WO2019047350A1 (en) | 2017-09-08 | 2017-10-31 | Potential customer identification method, device and electronic device and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710807133.3A CN107679889B (en) | 2017-09-08 | 2017-09-08 | The recognition methods of potential customers a kind of and terminal device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107679889A CN107679889A (en) | 2018-02-09 |
| CN107679889B true CN107679889B (en) | 2018-09-11 |
Family
ID=61135847
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710807133.3A Active CN107679889B (en) | 2017-09-08 | 2017-09-08 | The recognition methods of potential customers a kind of and terminal device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN107679889B (en) |
| WO (1) | WO2019047350A1 (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110659922B (en) * | 2018-06-28 | 2021-01-26 | 马上消费金融股份有限公司 | Client screening method, device, server and computer readable storage medium |
| CN112561555A (en) * | 2019-09-26 | 2021-03-26 | 北京国双科技有限公司 | Product data processing method and device |
| TWI722774B (en) * | 2020-01-17 | 2021-03-21 | 智泓科技股份有限公司 | Marketing object decision-making method and marketing system using mobile phone number |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104809637A (en) * | 2015-05-18 | 2015-07-29 | 北京京东尚科信息技术有限公司 | Commodity recommending method and system realized by computer |
| US9147159B2 (en) * | 2011-12-30 | 2015-09-29 | Certona Corporation | Extracting predictive segments from sampled data |
| CN106407349A (en) * | 2016-09-06 | 2017-02-15 | 北京三快在线科技有限公司 | Product recommendation method and device |
| CN106980991A (en) * | 2017-04-06 | 2017-07-25 | 百度在线网络技术（北京）有限公司 | A kind of method for pushing of marketing message, device, equipment and storage medium |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101075303A (en) * | 2006-05-18 | 2007-11-21 | 河北全通通信有限公司 | Data unearch model for pedicting service potential customers |
| US9195743B2 (en) * | 2007-10-04 | 2015-11-24 | Yahoo! Inc. | System and method for creating and applying predictive user click models to predict a target page associated with a search query |
| US9652776B2 (en) * | 2012-06-18 | 2017-05-16 | Greg Olsen | Visual representations of recurring revenue management system data and predictions |
| CN105488697A (en) * | 2015-12-09 | 2016-04-13 | 焦点科技股份有限公司 | Potential customer mining method based on customer behavior characteristics |
| CN106776757B (en) * | 2016-11-15 | 2020-03-27 | 中国银行股份有限公司 | Method and device for indicating user to complete online banking operation |
| CN106650273B (en) * | 2016-12-28 | 2019-08-23 | 东方网力科技股份有限公司 | A kind of behavior prediction method and apparatus |
| CN106971321B (en) * | 2017-04-06 | 2021-01-08 | 百度在线网络技术（北京）有限公司 | Marketing information pushing method, marketing information pushing device, marketing information pushing equipment and storage medium |
-
2017
- 2017-09-08 CN CN201710807133.3A patent/CN107679889B/en active Active
- 2017-10-31 WO PCT/CN2017/108620 patent/WO2019047350A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9147159B2 (en) * | 2011-12-30 | 2015-09-29 | Certona Corporation | Extracting predictive segments from sampled data |
| CN104809637A (en) * | 2015-05-18 | 2015-07-29 | 北京京东尚科信息技术有限公司 | Commodity recommending method and system realized by computer |
| CN106407349A (en) * | 2016-09-06 | 2017-02-15 | 北京三快在线科技有限公司 | Product recommendation method and device |
| CN106980991A (en) * | 2017-04-06 | 2017-07-25 | 百度在线网络技术（北京）有限公司 | A kind of method for pushing of marketing message, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2019047350A1 (en) | 2019-03-14 |
| CN107679889A (en) | 2018-02-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107590688A (en) | The recognition methods of target customer and terminal device | |
| CN108062629A (en) | Processing method, terminal device and the medium of transaction event | |
| CN107784504A (en) | Client pays a return visit the generation method and terminal device of event | |
| CN107679889B (en) | The recognition methods of potential customers a kind of and terminal device | |
| CN106326248A (en) | A storage method and device for data of databases | |
| CN109472568A (en) | A kind of block chain method of commerce, device, management system, equipment and storage medium | |
| CN107844867A (en) | Data processing method, device and equipment | |
| CN107844698A (en) | Financial APP authority setting method, device, equipment and storage medium | |
| CN107784063B (en) | Algorithm generation method and terminal equipment | |
| CN107909330A (en) | Work stream data processing method, device, storage medium and computer equipment | |
| CN107133856A (en) | The control method and device of risk order | |
| CN107862352A (en) | A kind of Quick Response Code sharing method and Quick Response Code share equipment | |
| CN111694841A (en) | Order mark generation method, device, server and storage medium | |
| CN110135984A (en) | Exchange management method, device, computer equipment and storage medium | |
| CN106600082A (en) | Processing method and device of task in service system, and service system construction system | |
| CN109670835A (en) | Air control method, apparatus, equipment and readable storage medium storing program for executing based on service node | |
| CN108255936A (en) | A kind of edit methods of webpage, system and editing machine | |
| CN107944870A (en) | Transaction business processing method, system and terminal device based on e-commerce | |
| CN109767110A (en) | A kind of risk control system optimization method, device, equipment and storage medium | |
| CN109461069A (en) | Air control method, apparatus, equipment and readable storage medium storing program for executing based on service node | |
| CN106920168A (en) | Futures point valency exchange information processing method and device | |
| CN108364230A (en) | A kind of account is withdrawn deposit method, apparatus, terminal device and storage medium | |
| CN110275903A (en) | Improve the method and system of the feature formation efficiency of machine learning sample | |
| CN110852809A (en) | Data processing method, device, equipment and medium | |
| CN110288488A (en) | Medical insurance Fraud Prediction method, apparatus, equipment and readable storage medium storing program for executing |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: DE Ref document number: 1247400 Country of ref document: HK |