CN110110012A - User's expectancy appraisal procedure, device, electronic equipment and readable medium - Google Patents
User's expectancy appraisal procedure, device, electronic equipment and readable medium Download PDFInfo
- Publication number
- CN110110012A CN110110012A CN201910330540.9A CN201910330540A CN110110012A CN 110110012 A CN110110012 A CN 110110012A CN 201910330540 A CN201910330540 A CN 201910330540A CN 110110012 A CN110110012 A CN 110110012A
- Authority
- CN
- China
- Prior art keywords
- data
- user
- timing
- financial modeling
- various dimensions
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000012546 transfer Methods 0.000 claims abstract description 48
- 230000003542 behavioural effect Effects 0.000 claims abstract description 35
- 230000006399 behavior Effects 0.000 claims description 48
- 238000012549 training Methods 0.000 claims description 43
- 238000012360 testing method Methods 0.000 claims description 28
- 238000010801 machine learning Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 description 20
- 238000010586 diagram Methods 0.000 description 13
- 238000012545 processing Methods 0.000 description 13
- 230000015654 memory Effects 0.000 description 9
- 230000009471 action Effects 0.000 description 7
- 238000003066 decision tree Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 238000011161 development Methods 0.000 description 6
- 238000012163 sequencing technique Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 210000004027 cell Anatomy 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000013524 data verification Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000005291 magnetic effect Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000007704 transition Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000000712 assembly Effects 0.000 description 1
- 238000000429 assembly Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000000546 chi-square test Methods 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 210000003127 knee Anatomy 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 238000012954 risk control Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 210000000352 storage cell Anatomy 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/283—Multi-dimensional databases or data warehouses, e.g. MOLAP or ROLAP
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
Abstract
This disclosure relates to a kind of user's expectancy appraisal procedure, device, electronic equipment and computer-readable medium based on timing financial modeling.This method comprises: obtaining the basic data of user, the basic data includes behavioral data and attribute data；Various dimensions characteristic is generated by the behavioral data and the attribute data, the various dimensions characteristic includes duration dimension data, behavior dimension data, frequency dimension data and attribute dimensions data；In the various dimensions characteristic input timing financial modeling, the current value and value Transfer probability of the user will be obtained；And based on user's expectancy described in the current value and the value Transfer probability assessment.This disclosure relates to user's expectancy appraisal procedure, device, electronic equipment and the computer-readable medium based on timing financial modeling, it can predict user expectancy of the user after following a period of time, enterprise can carry out diversification, personalized service to user according to user's expectancy.
Description
Technical field
This disclosure relates to computer information processing field, in particular to a kind of user based on timing financial modeling
Expectancy appraisal procedure, device, electronic equipment and computer-readable medium.
Background technique
User is setting up one's own business originally for internet.The opening of internet and direct contact with user, determine this row
One speciality of industry is exactly all final power to make decision all in user hand.Inside this industry, user is finally and most
Fastidious referee.So the value judgement of user is the key problem of its concern for current company.Due to visitor
The diversity at family, enterprise also want to take various adjustment means for different clients, realize lean operation, are company
Strive for maximum profit, this just needs to carry out user's lean operation to the user of different values, mentions by all kinds of operation means
Liveness, retention ratio and the payment rate of high different types of user in the product.
Currently, RFM model is the classical tool for measuring user's value and user's ability to make profits, element that there are three RFM models,
These three elements constitute the index of data analysis: the last time consumption (Recency), consuming frequency (Frequency), consumption
The amount of money (Monetary).RFM model is by the recent buying behavior of a client, the population frequency of purchase and how much has been spent
This three indexs describe the moneyness of the client.In conjunction with these three indexs, customer can be divided into multiple classifications, to its into
The analysis of row data, then formulates the marketing strategy of enterprise.But traditional RFM model passes through three dimensions in bargain link: R, F,
M refined user group is the assessment with historical data to user's current state.With the development of various electronic technology, advertisement with
Media industry quicklys increase, and user has touched more a greater amount of information.In today's society, the hobby of user and behavior exist
Huge variation will occur in short time, and RFM model is only counted as obtained from historical data analysis user's current state
The demand for quickly developing and changing according to market has been far from satisfying.
Therefore, it is necessary to a kind of new user's expectancy appraisal procedures based on timing financial modeling, device, electronic equipment
And computer-readable medium.
Above- mentioned information are only used for reinforcing the understanding to the background of the disclosure, therefore it disclosed in the background technology part
It may include the information not constituted to the prior art known to persons of ordinary skill in the art.
Summary of the invention
In view of this, the disclosure provides a kind of user's expectancy appraisal procedure based on timing financial modeling, device, electricity
Sub- equipment and computer-readable medium can predict user expectancy of the user after following a period of time, and enterprise can foundation
User's expectancy carries out diversification, personalized service to user.
Other characteristics and advantages of the disclosure will be apparent from by the following detailed description, or partially by the disclosure
Practice and acquistion.
According to the one side of the disclosure, a kind of user's expectancy appraisal procedure based on timing financial modeling is proposed, it should
Method includes: to obtain the basic data of user, and the basic data includes behavioral data and attribute data；Pass through the behavior number
Various dimensions characteristic is generated according to the attribute data, the various dimensions characteristic includes duration dimension data, behavior dimension
Degree evidence, frequency dimension data and attribute dimensions data；By in the various dimensions characteristic input timing financial modeling, obtain
Take the current value and value Transfer probability of the user；And based on the current value and the value Transfer probability assessment
User's expectancy.
In one embodiment of the present disclosure, further includes: pass through the basic data and at least one engineering of historical user
Practise timing financial modeling described in model foundation.
In one embodiment of the present disclosure, it is built by the basic data of historical user and at least one machine learning model
Founding the timing financial modeling includes: the basic data and the finance of timing described in unsupervised learning model foundation by historical user
Model；And/or timing financial modeling described in the basic data and supervised learning model foundation by historical user.
In one embodiment of the present disclosure, it is built by the basic data of historical user and at least one machine learning model
Founding the timing financial modeling includes: to generate history various dimensions characteristic by the basic data of historical user；By described
History various dimensions characteristic generates training set data and test set data；Respectively in training set data and test set data
Each dimension data of the history multi-dimensional data carries out branch mailbox coding；And the training set data input after encoding branch mailbox
In at least one described machine learning model, the test set data after being encoded by branch mailbox are verified to establish the timing gold
Melt model.
In one embodiment of the present disclosure, the training set data after branch mailbox being encoded inputs at least one described engineering
It practises in model, it includes: by branch mailbox that the test set data after being encoded by branch mailbox, which are verified to establish the timing financial modeling,
Training set data after coding inputs at least one described machine learning model, generates various dimensions evaluation index；Pass through branch mailbox
Various dimensions evaluation index described in test set data verification after coding；And referred to after being verified based on various dimensions evaluation
Mark determines the timing financial modeling.
In one embodiment of the present disclosure, various dimensions characteristic is generated by the behavioral data and the attribute data
According to including: to determine multiple goal behaviors and its corresponding time based on the behavioral data；By the multiple goal behavior according to
Its corresponding time-sequencing；And pass through the multiple goal behavior and the attribute data generation various dimensions after sequence
Characteristic.
In one embodiment of the present disclosure, it is generated by the multiple goal behavior after sequence with the attribute data
The various dimensions characteristic includes: to determine that the duration is tieed up by the interval time of first goal behavior and end goal behavior
Degree evidence；And/or the behavior dimension data is determined by the time corresponding to the end goal behavior；And/or pass through institute
The quantity for stating multiple goal behaviors determines the frequency dimension data；And/or institute is determined by the amount of money in the attribute data
State attribute dimensions data.
In one embodiment of the present disclosure, by the various dimensions characteristic input timing financial modeling, institute is obtained
It states the current value of user and value Transfer probability includes: that the various dimensions characteristic is carried out branch mailbox coding；Branch mailbox is compiled
The various dimensions characteristic after code inputs in the timing financial modeling；And the timing financial modeling is to the multidimensional
Degree characteristic is clustered and is grouped with the current value of the determination user and value Transfer probability.
In one embodiment of the present disclosure, the timing financial modeling to the various dimensions characteristic carry out cluster and
Grouping includes: that the timing financial modeling is evaluated according to various dimensions with value Transfer probability with the current value of the determination user
Index is clustered and is grouped with the current value of the determination user and value Transfer probability to the various dimensions characteristic.
In one embodiment of the present disclosure, the timing financial modeling is according to various dimensions evaluation index to the various dimensions
It includes: the timing finance that characteristic, which is clustered and be grouped with the current value of the determination user and value Transfer probability,
Model carries out Unsupervised clustering to the various dimensions characteristic according to various dimensions evaluation index with the current of the determination user
Value and value Transfer probability；And/or the timing financial modeling according to various dimensions evaluation index to the various dimensions characteristic
It is grouped according to decision tree is carried out with the current value of the determination user and value Transfer probability.
In one embodiment of the present disclosure, the letter based on user described in the current value and value Transfer probability assessment
Borrowing value includes: the charge for credit based on user described in the current value and the value Transfer determine the probability；And/or it is based on
The line of credit of user described in the current value and the value Transfer determine the probability.
In one embodiment of the present disclosure, based on user described in the current value and the value Transfer probability assessment
Expectancy includes: to be worth in quadrant to determine user in multidimensional user based on the current value and the value Transfer probability
Expectancy quadrant.
According to the one side of the disclosure, a kind of user's expectancy assessment device based on timing financial modeling is proposed, it should
Device includes: basic data module, and for obtaining the basic data of user, the basic data includes behavioral data and attribute number
According to；Characteristic module, for generating various dimensions characteristic, the multidimensional by the behavioral data and the attribute data
Spending characteristic includes duration dimension data, behavior dimension data, frequency dimension data and attribute dimensions data；Model calculates
Module, for obtaining the current value and value of the user in the various dimensions characteristic input timing financial modeling
Transition probability；And value assessment module, for the letter based on user described in the current value and value Transfer probability assessment
Borrow value.
In one embodiment of the present disclosure, further includes: model training module, for the basic data by historical user
The timing financial modeling is established at least one machine learning model.
In one embodiment of the present disclosure, the model training module includes: cluster cell, for passing through historical user
Basic data and unsupervised learning model foundation described in timing financial modeling；And/or decision package, for passing through historical user
Basic data and supervised learning model foundation described in timing financial modeling.
In one embodiment of the present disclosure, the model training module includes: historical data unit, for passing through history
The basic data of user generates history various dimensions characteristic；Training test cell, for passing through the history various dimensions feature
Data generate training set data and test set data；Branch mailbox coding unit, for respectively to training set data and test set data
In the history multi-dimensional data each dimension data carry out branch mailbox coding；And training unit, for branch mailbox to be encoded
Training set data afterwards inputs at least one described machine learning model, and the test set data after being encoded by branch mailbox are tested
Card is to establish the timing financial modeling.
In one embodiment of the present disclosure, the training unit includes: input subelement, after encoding branch mailbox
Training set data inputs at least one described machine learning model, generates various dimensions evaluation index；Subelement is verified, for leading to
Various dimensions evaluation index described in test set data verification after crossing branch mailbox coding；And index subelement, for being verified
The timing financial modeling is determined based on the various dimensions evaluation index afterwards.
In one embodiment of the present disclosure, the characteristic module includes: time quantum, for being based on the behavior
Data determine multiple goal behaviors and its corresponding time；Sequencing unit, for corresponding to the multiple goal behavior according to it
Time-sequencing；And feature unit, for generating institute with the attribute data by the multiple goal behavior after sequence
State various dimensions characteristic.
In one embodiment of the present disclosure, the feature unit includes: duration subelement, for passing through first target line
To determine the duration dimension data with the interval time of end goal behavior；And/or behavior subelement, for passing through the end
Time corresponding to tail goal behavior determines the behavior dimension data；And/or frequency subelement, for passing through the multiple mesh
The quantity of mark behavior determines the frequency dimension data；And/or attribute subelement, for passing through the amount of money in the attribute data
Determine the attribute dimensions data.
In one embodiment of the present disclosure, the model computation module includes: processing unit, is used for the various dimensions
Characteristic carries out branch mailbox coding；Model unit, when described for the various dimensions characteristic input after encoding branch mailbox
In sequence financial modeling；And computing unit, for the timing financial modeling to the various dimensions characteristic carry out cluster and
Grouping is with the current value of the determination user and value Transfer probability.
In one embodiment of the present disclosure, the computing unit is also used to the timing financial modeling according to various dimensions
Evaluation index is clustered and is grouped with the current value and value Transfer of the determination user to the various dimensions characteristic
Probability.
In one embodiment of the present disclosure, the computing unit is also used to the timing financial modeling according to various dimensions
Evaluation index carries out Unsupervised clustering to the various dimensions characteristic with the current value and value Transfer of the determination user
Probability；And/or the timing financial modeling carries out decision tree point to the various dimensions characteristic according to various dimensions evaluation index
Group is with the current value of the determination user and value Transfer probability.
In one embodiment of the present disclosure, the value assessment module includes: interest unit, for based on described current
The charge for credit of value and user described in value Transfer determine the probability；And/or amount unit, for based on the current value with
The line of credit of user described in value Transfer determine the probability.
In one embodiment of the present disclosure, the value assessment module, be also used to based on the current value with it is described
Value Transfer probability is worth the expectancy quadrant that user is determined in quadrant in multidimensional user.
According to the one side of the disclosure, a kind of electronic equipment is proposed, which includes: one or more processors；
Storage device, for storing one or more programs；When one or more programs are executed by one or more processors, so that one
A or multiple processors realize such as methodology above.
According to the one side of the disclosure, it proposes a kind of computer-readable medium, is stored thereon with computer program, the program
Method as mentioned in the above is realized when being executed by processor.
According to the disclosure by user's expectancy appraisal procedure of timing financial modeling, device, electronic equipment and based on
Calculation machine readable medium generates various dimensions characteristic by the behavioral data and the attribute data, and the various dimensions are special
It levies in data input timing financial modeling, obtains the current value and value Transfer probability of the user；And assess the user
The mode of expectancy, can predict user expectancy of the user after following a period of time, and enterprise can be expected according to user
It is worth and diversification, personalized service is carried out to user.
It should be understood that the above general description and the following detailed description are merely exemplary, this can not be limited
It is open.
Detailed description of the invention
Its example embodiment is described in detail by referring to accompanying drawing, above and other target, feature and the advantage of the disclosure will
It becomes more fully apparent.Drawings discussed below is only some embodiments of the present disclosure, for the ordinary skill of this field
For personnel, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of user's expectancy assessment side based on timing financial modeling shown according to an exemplary embodiment
The application scenarios block diagram of method.
Fig. 2 is a kind of user's expectancy assessment side based on timing financial modeling shown according to an exemplary embodiment
The flow chart of method.
Fig. 3 is a kind of user's expectancy assessment based on timing financial modeling shown according to another exemplary embodiment
The flow chart of method.
Fig. 4 is a kind of user's expectancy assessment based on timing financial modeling shown according to another exemplary embodiment
The schematic diagram of method.
Fig. 5 is a kind of user's expectancy assessment based on timing financial modeling shown according to another exemplary embodiment
The schematic diagram of method.
Fig. 6 is a kind of user's expectancy assessment dress based on timing financial modeling shown according to an exemplary embodiment
The block diagram set.
Fig. 7 is a kind of user's expectancy assessment based on timing financial modeling shown according to another exemplary embodiment
The block diagram of device.
Fig. 8 is the block diagram of a kind of electronic equipment shown according to an exemplary embodiment.
Specific embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be real in a variety of forms
It applies, and is not understood as limited to embodiment set forth herein；On the contrary, thesing embodiments are provided so that the disclosure will be comprehensively and complete
It is whole, and the design of example embodiment is comprehensively communicated to those skilled in the art.Identical appended drawing reference indicates in figure
Same or similar part, thus repetition thereof will be omitted.
In addition, described feature, structure or characteristic can be incorporated in one or more implementations in any suitable manner
In example.In the following description, many details are provided to provide and fully understand to embodiment of the disclosure.However,
It will be appreciated by persons skilled in the art that can with technical solution of the disclosure without one or more in specific detail,
Or it can be using other methods, constituent element, device, step etc..In other cases, it is not shown in detail or describes known side
Method, device, realization or operation are to avoid fuzzy all aspects of this disclosure.
Block diagram shown in the drawings is only functional entity, not necessarily must be corresponding with physically separate entity.
I.e., it is possible to realize these functional entitys using software form, or realized in one or more hardware modules or integrated circuit
These functional entitys, or these functional entitys are realized in heterogeneous networks and/or processor device and/or microcontroller device.
Flow chart shown in the drawings is merely illustrative, it is not necessary to including all content and operation/step,
It is not required to execute by described sequence.For example, some operation/steps can also decompose, and some operation/steps can close
And or part merge, therefore the sequence actually executed is possible to change according to the actual situation.
It should be understood that although herein various assemblies may be described using term first, second, third, etc., these groups
Part should not be limited by these terms.These terms are to distinguish a component and another component.Therefore, first group be discussed herein below
Part can be described as the second component without departing from the teaching of disclosure concept.As used herein, term " and/or " include associated
All combinations for listing any of project and one or more.
It will be understood by those skilled in the art that attached drawing is the schematic diagram of example embodiment, module or process in attached drawing
Necessary to not necessarily implementing the disclosure, therefore it cannot be used for the protection scope of the limitation disclosure.
Fig. 1 is a kind of user's expectancy assessment side based on timing financial modeling shown according to an exemplary embodiment
The application scenarios block diagram of method.
As shown in Figure 1, system architecture 100 may include terminal device 101,102,103, network 104 and server 105.
Network 104 between terminal device 101,102,103 and server 105 to provide the medium of communication link.Network 104 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
User can be used terminal device 101,102,103 and be interacted by network 104 with server 105, to receive or send out
Send message etc..Various telecommunication customer end applications can be installed, such as financial class platform is answered on terminal device 101,102,103
With, shopping class application, web browser applications, searching class application, instant messaging tools, mailbox client, social platform software
Deng.
In embodiment of the disclosure, will by user browse Financial Information platform for, in the disclosure based on timing
User's expectancy appraisal procedure of financial modeling is described in detail.It is noted that the timing finance mould in the disclosure
Type also can be applicable in the platform of multiple application scenarios and different merchandise classifications, and the application is not limited.
Terminal device 101,102,103 can be the various electronic equipments with display screen and supported web page browsing, packet
Include but be not limited to smart phone, tablet computer, pocket computer on knee and desktop computer etc..
Server 105 can be to provide the server of various services, such as utilize terminal device 101,102,103 to user
The financial platform class website browsed provides the back-stage management server supported.Server 105 can be to the user's base received
Number data carry out the processing such as analyzing, and processing result (user behavior estimated data) is fed back to corporate client management terminal.
Server 105 can for example obtain the basic data of user, and the basic data includes behavioral data and attribute data；
Server 105 for example can generate various dimensions characteristic by the behavioral data and the attribute data, and the various dimensions are special
Levying data includes duration dimension data, behavior dimension data, frequency dimension data and attribute dimensions data；Server 105 can example
As will be described in various dimensions characteristic input timing financial modeling, current value and the value Transfer for obtaining the user are general
Rate；Server 105 can be for example based on user's expectancy described in the current value and the value Transfer probability assessment.
Server 105 can also be for example by described in the basic data of historical user and the foundation of at least one machine learning model
Timing financial modeling.
Server 105 can be the server of an entity, also may be, for example, multiple server compositions, needs to illustrate
It is that user's expectancy appraisal procedure based on timing financial modeling provided by the embodiment of the present disclosure can be by server 105
It executes, correspondingly, user's expectancy assessment device based on timing financial modeling can be set in server 105.And it mentions
The finance pages platform end that supply user carries out Financial Information browsing is normally in terminal device 101,102,103.
According to the user's expectancy appraisal procedure and device based on timing financial modeling of the disclosure, pass through the behavior
Data and the attribute data generate various dimensions characteristic, by the various dimensions characteristic input timing financial modeling,
Obtain the current value and value Transfer probability of the user；And the mode of user's expectancy is assessed, it can predict to use
User expectancy of the family after following a period of time, enterprise can carry out diversification, individual character to user according to user's expectancy
The service of change.
Fig. 2 is a kind of user's expectancy assessment side based on timing financial modeling shown according to an exemplary embodiment
The flow chart of method.As shown in Fig. 2, user's expectancy appraisal procedure 20 based on timing financial modeling includes at least step S202
To S208.
As shown in Fig. 2, obtaining the basic data of user in S202, the basic data includes behavioral data and attribute
Data.Wherein, it may include the financial corelation behaviour data of user in basic data, can be loaning bill behavior, refund behavior etc. belongs to
Property data can be borrowing balance data.
In S204, various dimensions characteristic, the various dimensions are generated by the behavioral data and the attribute data
Characteristic includes duration dimension data, behavior dimension data, frequency dimension data and attribute dimensions data.
In one embodiment, generating various dimensions characteristic with the attribute data by the behavioral data includes:
Multiple goal behaviors and its corresponding time are determined based on the behavioral data；The multiple goal behavior is corresponding according to its
Time-sequencing；And pass through the multiple goal behavior and the attribute data generation various dimensions characteristic after sequence
According to.
More specifically, for example can generate the multiple characteristic by the behavioral data after sequence includes: by first
The interval time of behavioral data and end behavioral data determines the duration characteristics data；And/or pass through the end behavior number
The behavioural characteristic data are determined according to the corresponding time；And/or determine that the frequency is special by the quantity of the behavioral data
Levy data；And/or the attributive character data are determined by the amount of money in the behavioral data.
Corresponding to the last consumption (Recency) in RFM model, consuming frequency (Frequency), spending amount
(Monetary).Different classes of characteristic can be established for user behavior above.It can be for example with user's lend-borrow action
For the relevant time, the relevant behavioral data of lend-borrow action can be divided into, the last time debt-credit borrows or lends money frequency, and borrow
Monetary allowance volume.More specifically duration characteristics data can be generated according to the time interval of lend-borrow action for the first time and last time lend-borrow action
L(Length)；Behavioural characteristic data R (Recency) is determined by the time of last time lend-borrow action, is sent out by lend-borrow action
Raw number determines frequency characterization data F (Frequency), determines attributive character data by the credit amount in nodes ' behavior
M(Monetary)。
It is noted that in attributive character data, it can be using the amount of money of user's last time debt-credit as attributive character
Data, can also be by credit amount attributive character data the most average in the multiple lend-borrow action of user, and concrete condition can be according to model
The difference of focus in calculating and be adjusted, the disclosure is not limited.
In S206, by the various dimensions characteristic input timing financial modeling, obtain the user works as present value
Value and value Transfer probability.
In one embodiment, by the various dimensions characteristic input timing financial modeling, obtain the user's
Current value and value Transfer probability include: that the various dimensions characteristic is carried out branch mailbox coding；Institute after branch mailbox is encoded
Various dimensions characteristic is stated to input in the timing financial modeling；And the timing financial modeling is to the various dimensions characteristic
According to being clustered and be grouped with the current value of the determination user and value Transfer probability.
Wherein, branch mailbox coding techniques (Weight of Evidence, WOE) i.e. evidence weight can turn model data
Scale card format is turned to, WOE is a kind of coding form to original argument, to carry out WOE coding to a variable, need
This variable is grouped processing (being also discretization, branch mailbox) first.In modeling, need to continuous variable discretization,
After feature discretization, model can be more stable, reduces the risk of model over-fitting, needs by means of branch mailbox technology this when.
Branch mailbox technology, which is divided into, supervision branch mailbox and unsupervised branch mailbox: have card side's branch mailbox method (ChiMerge) of supervision from bottom to
On (i.e. based on merging) Method of Data Discretization.It depends on Chi-square Test: the adjacent interval with minimum X2 value is closed
And together, until meeting determining stopping criterion.Basic thought: for accurate discretization, opposite quefrency is in an area
In should be completely the same.Therefore, if there is very similar class to be distributed in two adjacent sections, the two sections can be with
Merge；Otherwise, they should be held apart at.Unsupervised branch mailbox method be using equidistant partition, etc. frequency divide method, data are straight
Connect branch mailbox.
In one embodiment, it after carrying out branch mailbox to feature, needs to every group of carry out WOE coding after branch mailbox, then
Model training can be put into.
In one embodiment, the timing financial modeling is according to various dimensions evaluation index to the various dimensions characteristic
It is clustered and is grouped with the current value of the determination user and value Transfer probability.
Wherein, clustering method can cluster for k-mean, and k-mean cluster is first to randomly select K user base data conduct
Initial cluster centre.Then the distance between each user base data and each seed cluster centre are calculated, each right
As distributing to the cluster centre nearest apart from it.Cluster centre and the object for distributing to them just represent a cluster.
Wherein, grouping can be grouped by decision tree, and decision tree (Decision Tree) is sent out in known various situations
On the basis of raw probability, the desired value that net present value (NPV) is sought by constituting decision tree is more than or equal to zero probability, in the disclosure
In timing financial modeling, decision tree is a prediction model, what he represented be the probability that occurs of basic data and basic data it
Between a kind of mapping relations.A classifier is obtained by study, this classifier can provide emerging basic data
Classification.
In one embodiment, the timing financial modeling is according to various dimensions evaluation index to the various dimensions characteristic
Clustered and be grouped with the current value of the determination user and value Transfer probability include: the timing financial modeling according to
Various dimensions evaluation index carries out Unsupervised clustering to the various dimensions characteristic with the current value and valence of the determination user
It is worth transition probability；And/or the timing financial modeling determines to the various dimensions characteristic according to various dimensions evaluation index
Plan tree is grouped with the current value of the determination user and value Transfer probability.
In S208, based on user's expectancy described in the current value and the value Transfer probability assessment.
In one embodiment, the credit standing packet based on user described in the current value and value Transfer probability assessment
It includes: the charge for credit based on user described in the current value and the value Transfer determine the probability；And/or based on described current
The line of credit of value and user described in the value Transfer determine the probability.
Wherein, the detailed content based on user's expectancy described in the current value and the value Transfer probability assessment
It is specifically described in Fig. 4, the corresponding embodiment of Fig. 5.
According to the user behavior prediction model generation method based on time series of the disclosure, in the base of traditional RFM model
On plinth, L (Length) evaluation factor is increased.Objective group is subjected to sorting out value by Unsupervised clustering, branch mailbox coding techniques.Together
When, unlike traditional RFM model, the method in the disclosure passes through the dimensions such as a series of behaviors of client, attribute, is based on machine
Device study method establish LRFM model, by LRFM model prediction client for a period of time after customer value transition probability.
It will be clearly understood that the present disclosure describes how to form and use particular example, but the principle of the disclosure is not limited to
These exemplary any details.On the contrary, the introduction based on disclosure disclosure, these principles can be applied to many other
Embodiment.
Fig. 3 is a kind of user's expectancy assessment based on timing financial modeling shown according to another exemplary embodiment
The flow chart of method.Process shown in Fig. 3 is " to be established by the basic data of historical user and at least one machine learning model
The detailed description of the timing financial modeling ".
As shown in figure 3, generating history various dimensions characteristic by the basic data of historical user in S302.It can lead to
The basic data for crossing the registered user in financial platform generates history various dimensions characteristic.
In S304, training set data and test set data are generated by the history various dimensions characteristic.In machine
In study, generally sample is divided into independent three parts training set (train set), verifying collection (validation set) and survey
Examination collection (test set).Wherein, training set is for establishing model.Verifying collection is used to determine that network structure or Controlling model are complicated
The parameter of degree, and the performance for the model that test set then examines final choice optimal how.
It in one embodiment, can also be for example, the multiple characteristic after coding be divided into according to time series more
A data set, the data set include training observation collection, training performance collection, test observation collection, and test performance collection；It will be described
Training observation collection, the training performance collection input in multiple machine learning models, generate various dimensions characteristic index；Pass through the survey
Examination observation collection, the test performance collection verify the various dimensions characteristic index；And the various dimensions are based on after being verified
Characteristic index determines the multiple initial machine learning model.
Wherein, the basic data of user can be divided into training observation collection according to the time as shown in the table, and training performance collection is surveyed
Examination observation collection, and test performance collection.
In S306, respectively to every dimension of the history multi-dimensional data in training set data and test set data
Data carry out branch mailbox coding.
In S308, the training set data after branch mailbox is encoded is inputted at least one described machine learning model, is passed through
Test set data after branch mailbox coding are verified to establish the timing financial modeling.
It in one embodiment, can be for example, the training set data after branch mailbox is encoded inputs at least one described engineering
It practises in model, generates various dimensions evaluation index；Various dimensions evaluation index described in test set data verification after being encoded by branch mailbox；
And the timing financial modeling is determined based on the various dimensions evaluation index after being verified.
In one embodiment of the present disclosure, the problem of being directed to user's debt-credit, during machine learning, can pass through
The basic data of the training observation collection, the user that the training performance is concentrated determines group's interest in black and per capita interest.Its
In, it is observed and is collected by the test, the basic data determination for the user that the test performance is concentrated should averagely go back interest；And it is logical
Crossing described should averagely go back interest and group's interest in black and the interest per capita verifies the various dimensions characteristic index.
More specifically, the stabilization on different dimensions of the model can be also determined by group's interest in black and per capita interest
Property:
According to the user behavior prediction model generation method based on time series of the disclosure, prediction user can be obtained and existed
The behavior prediction model of behavioral data in following a period of time improves the efficiency to user behavior analysis, provides more for enterprise
Efficiently comprehensive customer analysis data so that enterprise can rational deployment marketing advertisement, user service strategy and
Reduce user's bring security risk.
Fig. 4, Fig. 5 are a kind of user's expectancies based on timing financial modeling shown according to another exemplary embodiment
The schematic diagram of appraisal procedure.
As described in Figure 4, wherein according to RFM, each index dimension can be subdivided out different grades by these three indexs, this
Sample can segment different classes of user, exist further according to every class user precision marketing.It can be for example each dimension in the disclosure
Primary two points are done, each dimension is divided into two classes of height, and 8 groups of users can be obtained in tri- dimensions of RFM in this way.In this way
User can analyze according to different dimensions, (numeral order RFM:1 represents height, 0 represent low), only be made with 4 groups of examples
To illustrate.
Important value client (111): nearest consumption time is close, the consumption frequency and spending amount are all very high, may be, for example, by
Such user is defined as top-tier customer.
Important holding client (011): nearest consumption time farther out, but consumes the frequency and the amount of money is all very high, illustrates that this is
The loyalty customer that a period of time does not come needs actively to keep in touch with him.
Important development client (101): nearest consumption time is relatively close, spending amount is high, but the frequency is not high, and loyalty is not high,
Very promising user can give priority to.
It is important to keep client (001): nearest consumption time farther out, the consumption frequency it is not high, but the user that spending amount is high can
It can be the user that be lost or to be lost, should be based on keeping measure.
And after introducing L-dimensional, it also can be obtained after following a period of time, the behavioural characteristic of user, in the disclosure
For example L-dimensional can also be done primary two points, as current and user after 120 days behavioural characteristic, thus user by working as
8 preceding groups extend to 16 groups, in as 16 quadrants.Certainly, L can also do different differentiations, can be for example by L points
For three dimensions, currently, 20 days and 120 days, then user has been divided into 24 dimensions by 8 current dimensions.
As shown in figure 5, user is extended to 16 groups by 8 current groups, the feelings in as 16 quadrants
Under condition, (numeral order RFM, 1 represents height, and 0 represents low, number L, and 1 represents current, and 0 represents future)
Important value client (1111) and important value client (0111), will currently be important value client with future；Weight
Client (1011) and important holding client (0011) are kept, will currently be important holding client with future；Important development client
(1101) with important development client (0101): be currently important development client with future；It is important keep client (1001) with again
Keeping client (0001) will currently be important development client with future.
Can be for example, the quadrant classification of active user be important holding client (1011), 120 days futures showed as important draw
It detains a guest family (0001), then can determine the step of more keeping client, in advance perfecting program according to the analysis to user behavior.
According to the user behavior prediction model generation method based on time series of the disclosure, prediction user can be obtained and existed
The behavior prediction model of behavioral data in following a period of time can formulated migration efficiency in face of client, moved by the model
When branch price, amount adjustment or even risk control, various adjustment means can be taken for different clients, realize essence
Refinement operation strives for maximum profit for enterprise, reaches the demand of better services client.
It will be appreciated by those skilled in the art that realizing that all or part of the steps of above-described embodiment is implemented as being executed by CPU
Computer program.When the computer program is executed by CPU, above-mentioned function defined by the above method that the disclosure provides is executed
Energy.The program can store in a kind of computer readable storage medium, which can be read-only memory, magnetic
Disk or CD etc..
Further, it should be noted that above-mentioned attached drawing is only the place according to included by the method for disclosure exemplary embodiment
Reason schematically illustrates, rather than limits purpose.It can be readily appreciated that above-mentioned processing shown in the drawings is not indicated or is limited at these
The time sequencing of reason.In addition, be also easy to understand, these processing, which can be, for example either synchronously or asynchronously to be executed in multiple modules.
Following is embodiment of the present disclosure, can be used for executing embodiments of the present disclosure.It is real for disclosure device
Undisclosed details in example is applied, embodiments of the present disclosure is please referred to.
Fig. 6 is a kind of user's expectancy assessment dress based on timing financial modeling shown according to an exemplary embodiment
The block diagram set.As shown in fig. 6, user's expectancy assessment device 60 based on timing financial modeling includes: basic data module
602, characteristic module 604, model computation module 606 and value assessment module 608.
Basic data module 602 is used to obtain the basic data of user, and the basic data includes behavioral data and attribute
Data；
Characteristic module 604 is used to generate various dimensions characteristic by the behavioral data and the attribute data,
The various dimensions characteristic includes duration dimension data, behavior dimension data, frequency dimension data and attribute dimensions data；
Model computation module 606 is used to obtain the use in the various dimensions characteristic input timing financial modeling
The current value and value Transfer probability at family；And
Value assessment module 608 is used for the credit valence based on user described in the current value and value Transfer probability assessment
Value.
Fig. 7 is a kind of user's expectancy assessment based on timing financial modeling shown according to another exemplary embodiment
The block diagram of device.User's expectancy assessment device 70 based on timing financial modeling is pre- in the user based on timing financial modeling
On the basis of phase value assessment device 60 further include: model training module 702.
Model training module 702 is used to establish institute by the basic data and at least one machine learning model of historical user
State timing financial modeling.
User's expectancy according to the disclosure based on timing financial modeling assesses device, by the behavioral data with
The attribute data generates various dimensions characteristic, by the various dimensions characteristic input timing financial modeling, obtains institute
State the current value and value Transfer probability of user；And the mode of user's expectancy is assessed, user can be predicted not
User's expectancy after carrying out a period of time, enterprise can carry out diversification, personalized clothes to user according to user's expectancy
Business.
Fig. 8 is the block diagram of a kind of electronic equipment shown according to an exemplary embodiment.
The electronic equipment 200 of this embodiment according to the disclosure is described referring to Fig. 8.The electronics that Fig. 8 is shown
Equipment 200 is only an example, should not function to the embodiment of the present disclosure and use scope bring any restrictions.
As shown in figure 8, electronic equipment 200 is showed in the form of universal computing device.The component of electronic equipment 200 can wrap
It includes but is not limited to: at least one processing unit 210, at least one storage unit 220, (including the storage of the different system components of connection
Unit 220 and processing unit 210) bus 230, display unit 240 etc..
Wherein, the storage unit is stored with program code, and said program code can be held by the processing unit 210
Row, so that the processing unit 210 executes described in this specification above-mentioned electronic prescription circulation processing method part according to this
The step of disclosing various illustrative embodiments.For example, the processing unit 210 can be executed such as Fig. 2, walked shown in Fig. 3
Suddenly.
The storage unit 220 may include the readable medium of volatile memory cell form, such as random access memory
Unit (RAM) 2201 and/or cache memory unit 2202 can further include read-only memory unit (ROM) 2203.
The storage unit 220 can also include program/practical work with one group of (at least one) program module 2205
Tool 2204, such program module 2205 includes but is not limited to: operating system, one or more application program, other programs
It may include the realization of network environment in module and program data, each of these examples or certain combination.
Bus 230 can be to indicate one of a few class bus structures or a variety of, including storage unit bus or storage
Cell controller, peripheral bus, graphics acceleration port, processing unit use any bus structures in a variety of bus structures
Local bus.
Electronic equipment 200 can also be with one or more external equipments 300 (such as keyboard, sensing equipment, bluetooth equipment
Deng) communication, can also be enabled a user to one or more equipment interact with the electronic equipment 200 communicate, and/or with make
Any equipment (such as the router, modulation /demodulation that the electronic equipment 200 can be communicated with one or more of the other calculating equipment
Device etc.) communication.This communication can be carried out by input/output (I/O) interface 250.Also, electronic equipment 200 can be with
By network adapter 260 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network,
Such as internet) communication.Network adapter 260 can be communicated by bus 230 with other modules of electronic equipment 200.It should
Understand, although not shown in the drawings, other hardware and/or software module can be used in conjunction with electronic equipment 200, including but unlimited
In: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and number
According to backup storage system etc..
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to the disclosure
The technical solution of embodiment can be embodied in the form of software products, which can store non-volatile at one
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculating
Equipment (can be personal computer, server or network equipment etc.) executes the above method according to disclosure embodiment.
Described program product can be using any combination of one or more readable mediums.Readable medium can be readable letter
Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to electricity, magnetic, optical, electromagnetic, infrared ray or
System, device or the device of semiconductor, or any above combination.The more specific example of readable storage medium storing program for executing is (non exhaustive
List) include: electrical connection with one or more conducting wires, portable disc, hard disk, random access memory (RAM), read-only
Memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory
(CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
The computer readable storage medium may include in a base band or the data as the propagation of carrier wave a part are believed
Number, wherein carrying readable program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetism
Signal, optical signal or above-mentioned any appropriate combination.Readable storage medium storing program for executing can also be any other than readable storage medium storing program for executing
Readable medium, the readable medium can send, propagate or transmit for by instruction execution system, device or device use or
Person's program in connection.The program code for including on readable storage medium storing program for executing can transmit with any suitable medium, packet
Include but be not limited to wireless, wired, optical cable, RF etc. or above-mentioned any appropriate combination.
Can with any combination of one or more programming languages come write for execute the disclosure operation program
Code, described program design language include object oriented program language-Java, C++ etc., further include conventional
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in user
It calculates and executes in equipment, partly executes on a user device, being executed as an independent software package, partially in user's calculating
Upper side point is executed on a remote computing or is executed in remote computing device or server completely.It is being related to far
Journey calculates in the situation of equipment, and remote computing device can pass through the network of any kind, including local area network (LAN) or wide area network
(WAN), it is connected to user calculating equipment, or, it may be connected to external computing device (such as utilize ISP
To be connected by internet).
Above-mentioned computer-readable medium carries one or more program, when said one or multiple programs are by one
When the equipment executes, so that the computer-readable medium implements function such as:: obtain the basic data of user, the basis number
According to including behavioral data and attribute data；Various dimensions characteristic, institute are generated by the behavioral data and the attribute data
Stating various dimensions characteristic includes duration dimension data, behavior dimension data, frequency dimension data and attribute dimensions data；It will
In the various dimensions characteristic input timing financial modeling, the current value and value Transfer probability of the user are obtained；With
And based on user's expectancy described in the current value and the value Transfer probability assessment.
It will be appreciated by those skilled in the art that above-mentioned each module can be distributed in device according to the description of embodiment, it can also
Uniquely it is different from one or more devices of the present embodiment with carrying out corresponding change.The module of above-described embodiment can be merged into
One module, can also be further split into multiple submodule.
By the description of above embodiment, those skilled in the art is it can be readily appreciated that example embodiment described herein
It can also be realized in such a way that software is in conjunction with necessary hardware by software realization.Therefore, implemented according to the disclosure
The technical solution of example can be embodied in the form of software products, which can store in a non-volatile memories
In medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) or on network, including some instructions are so that a calculating equipment (can
To be personal computer, server, mobile terminal or network equipment etc.) it executes according to the method for the embodiment of the present disclosure.
It is particularly shown and described the exemplary embodiment of the disclosure above.It should be appreciated that the present disclosure is not limited to
Detailed construction, set-up mode or implementation method described herein；On the contrary, disclosure intention covers included in appended claims
Various modifications and equivalence setting in spirit and scope.
Claims (10)
1. a kind of user's expectancy appraisal procedure based on timing financial modeling characterized by comprising
The basic data of user is obtained, the basic data includes behavioral data and attribute data；
Various dimensions characteristic is generated by the behavioral data and the attribute data, when the various dimensions characteristic includes
Long dimension data, behavior dimension data, frequency dimension data and attribute dimensions data；
By in the various dimensions characteristic input timing financial modeling, current value and the value Transfer for obtaining the user are general
Rate；And
Based on user's expectancy described in the current value and the value Transfer probability assessment.
2. the method as described in claim 1, which is characterized in that further include:
The timing financial modeling is established by the basic data and at least one machine learning model of historical user.
3. method according to claim 2, which is characterized in that pass through the basic data and at least one engineering of historical user
Practising timing financial modeling described in model foundation includes:
Timing financial modeling described in basic data and unsupervised learning model foundation by historical user；And/or
Timing financial modeling described in basic data and supervised learning model foundation by historical user.
4. method according to claim 2, which is characterized in that pass through the basic data and at least one engineering of historical user
Practising timing financial modeling described in model foundation includes:
History various dimensions characteristic is generated by the basic data of historical user；
Training set data and test set data are generated by the history various dimensions characteristic；
Branch mailbox is carried out to each dimension data of the history multi-dimensional data in training set data and test set data respectively
Coding；And
Training set data after branch mailbox is encoded inputs at least one described machine learning model, the survey after being encoded by branch mailbox
Examination collection data are verified to establish the timing financial modeling.
5. a kind of user's expectancy based on timing financial modeling assesses device characterized by comprising
Basic data module, for obtaining the basic data of user, the basic data includes behavioral data and attribute data；
Characteristic module is described more for generating various dimensions characteristic by the behavioral data and the attribute data
Dimensional characteristics data include duration dimension data, behavior dimension data, frequency dimension data and attribute dimensions data；
Model computation module, for obtaining working as the user in the various dimensions characteristic input timing financial modeling
Preceding value and value Transfer probability；And
Value assessment module, for the credit standing based on user described in the current value and value Transfer probability assessment.
6. device as claimed in claim 5, which is characterized in that further include:
Model training module establishes the timing at least one machine learning model for the basic data by historical user
Financial modeling.
7. device as claimed in claim 5, which is characterized in that the model training module includes:
Cluster cell, for timing financial modeling described in the basic data and unsupervised learning model foundation by historical user；
And/or
Decision package, for timing financial modeling described in the basic data and supervised learning model foundation by historical user.
8. device as claimed in claim 5, which is characterized in that the model training module includes:
Historical data unit, for generating history various dimensions characteristic by the basic data of historical user；
Training test cell, for generating training set data and test set data by the history various dimensions characteristic；
Branch mailbox coding unit, for respectively to each of training set data and the history multi-dimensional data in test set data
Dimension data carries out branch mailbox coding；And
Training unit inputs at least one described machine learning model for the training set data after encoding branch mailbox, passes through
Test set data after branch mailbox coding are verified to establish the timing financial modeling.
9. a kind of electronic equipment characterized by comprising
One or more processors；
Storage device, for storing one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
The now method as described in any in claim 1-4.
10. a kind of computer-readable medium, is stored thereon with computer program, which is characterized in that described program is held by processor
The method as described in any in claim 1-4 is realized when row.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910330540.9A CN110110012A (en) | 2019-04-23 | 2019-04-23 | User's expectancy appraisal procedure, device, electronic equipment and readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910330540.9A CN110110012A (en) | 2019-04-23 | 2019-04-23 | User's expectancy appraisal procedure, device, electronic equipment and readable medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110110012A true CN110110012A (en) | 2019-08-09 |
Family
ID=67486361
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910330540.9A Pending CN110110012A (en) | 2019-04-23 | 2019-04-23 | User's expectancy appraisal procedure, device, electronic equipment and readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110110012A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111080338A (en) * | 2019-11-11 | 2020-04-28 | 中国建设银行股份有限公司 | User data processing method and device, electronic equipment and storage medium |
| CN111178692A (en) * | 2019-12-12 | 2020-05-19 | 上海淇玥信息技术有限公司 | Resource usage amount estimation method and device and electronic equipment |
| CN111190967A (en) * | 2019-12-16 | 2020-05-22 | 北京淇瑀信息科技有限公司 | User multi-dimensional data processing method and device and electronic equipment |
| CN111199418A (en) * | 2019-12-16 | 2020-05-26 | 北京淇瑀信息科技有限公司 | Data propagation method and device based on graph data and back propagation algorithm and electronic equipment |
| CN111210255A (en) * | 2019-12-16 | 2020-05-29 | 北京淇瑀信息科技有限公司 | Advertisement pushing method and device and electronic equipment |
| CN111738331A (en) * | 2020-06-19 | 2020-10-02 | 北京同邦卓益科技有限公司 | User classification method and device, computer-readable storage medium and electronic device |
| CN111985773A (en) * | 2020-07-15 | 2020-11-24 | 北京淇瑀信息科技有限公司 | User resource allocation strategy determining method and device and electronic equipment |
| CN112529628A (en) * | 2020-12-16 | 2021-03-19 | 平安科技（深圳）有限公司 | Client label generation method and device, computer equipment and storage medium |
| CN113570204A (en) * | 2021-07-06 | 2021-10-29 | 北京淇瑀信息科技有限公司 | User behavior prediction method, system and computer equipment |
| CN113657945A (en) * | 2021-08-27 | 2021-11-16 | 建信基金管理有限责任公司 | User value prediction method, device, electronic equipment and computer storage medium |
| CN111190967B (en) * | 2019-12-16 | 2024-04-26 | 北京淇瑀信息科技有限公司 | User multidimensional data processing method and device and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070022120A1 (en) * | 2005-07-25 | 2007-01-25 | Microsoft Corporation | Caching and modifying portions of a multi-dimensional database on a user device |
| CN107705207A (en) * | 2017-11-07 | 2018-02-16 | 广发证券股份有限公司 | Method, apparatus, equipment and the computer-readable storage medium that customer value is assessed |
| CN109583651A (en) * | 2018-12-03 | 2019-04-05 | 焦点科技股份有限公司 | A kind of method and apparatus for insuring electric business platform user attrition prediction |
| CN109598300A (en) * | 2018-11-30 | 2019-04-09 | 成都数联铭品科技有限公司 | A kind of assessment system and method |
-
2019
- 2019-04-23 CN CN201910330540.9A patent/CN110110012A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070022120A1 (en) * | 2005-07-25 | 2007-01-25 | Microsoft Corporation | Caching and modifying portions of a multi-dimensional database on a user device |
| CN107705207A (en) * | 2017-11-07 | 2018-02-16 | 广发证券股份有限公司 | Method, apparatus, equipment and the computer-readable storage medium that customer value is assessed |
| CN109598300A (en) * | 2018-11-30 | 2019-04-09 | 成都数联铭品科技有限公司 | A kind of assessment system and method |
| CN109583651A (en) * | 2018-12-03 | 2019-04-05 | 焦点科技股份有限公司 | A kind of method and apparatus for insuring electric business platform user attrition prediction |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111080338A (en) * | 2019-11-11 | 2020-04-28 | 中国建设银行股份有限公司 | User data processing method and device, electronic equipment and storage medium |
| CN111178692A (en) * | 2019-12-12 | 2020-05-19 | 上海淇玥信息技术有限公司 | Resource usage amount estimation method and device and electronic equipment |
| CN111190967A (en) * | 2019-12-16 | 2020-05-22 | 北京淇瑀信息科技有限公司 | User multi-dimensional data processing method and device and electronic equipment |
| CN111199418A (en) * | 2019-12-16 | 2020-05-26 | 北京淇瑀信息科技有限公司 | Data propagation method and device based on graph data and back propagation algorithm and electronic equipment |
| CN111210255A (en) * | 2019-12-16 | 2020-05-29 | 北京淇瑀信息科技有限公司 | Advertisement pushing method and device and electronic equipment |
| CN111190967B (en) * | 2019-12-16 | 2024-04-26 | 北京淇瑀信息科技有限公司 | User multidimensional data processing method and device and electronic equipment |
| CN111738331A (en) * | 2020-06-19 | 2020-10-02 | 北京同邦卓益科技有限公司 | User classification method and device, computer-readable storage medium and electronic device |
| CN111985773A (en) * | 2020-07-15 | 2020-11-24 | 北京淇瑀信息科技有限公司 | User resource allocation strategy determining method and device and electronic equipment |
| CN112529628A (en) * | 2020-12-16 | 2021-03-19 | 平安科技（深圳）有限公司 | Client label generation method and device, computer equipment and storage medium |
| CN112529628B (en) * | 2020-12-16 | 2024-04-09 | 平安科技（深圳）有限公司 | Client label generation method and device, computer equipment and storage medium |
| CN113570204A (en) * | 2021-07-06 | 2021-10-29 | 北京淇瑀信息科技有限公司 | User behavior prediction method, system and computer equipment |
| CN113657945A (en) * | 2021-08-27 | 2021-11-16 | 建信基金管理有限责任公司 | User value prediction method, device, electronic equipment and computer storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110110012A (en) | User's expectancy appraisal procedure, device, electronic equipment and readable medium | |
| CN110111198A (en) | User's financial risks predictor method, device, electronic equipment and readable medium | |
| Wang et al. | Adaboost-based security level classification of mobile intelligent terminals | |
| CN110111139A (en) | Behavior prediction model generation method, device, electronic equipment and readable medium | |
| CN109657805A (en) | Hyper parameter determines method, apparatus, electronic equipment and computer-readable medium | |
| Zhou et al. | Internet financial fraud detection based on a distributed big data approach with node2vec | |
| CN112148987B (en) | Message pushing method based on target object activity and related equipment | |
| CN112348660B (en) | Method and device for generating risk warning information and electronic equipment | |
| Liang et al. | Credit risk and limits forecasting in e-commerce consumer lending service via multi-view-aware mixture-of-experts nets | |
| CN110135976A (en) | User's portrait generation method, device, electronic equipment and computer-readable medium | |
| WO2020023647A1 (en) | Privacy preserving ai derived simulated world | |
| CN112163963B (en) | Service recommendation method, device, computer equipment and storage medium | |
| CN110348977A (en) | Financial Risk Analysis method, apparatus and electronic equipment based on multilayered model structure | |
| CN110163661A (en) | Marketing message promotion method, device, electronic equipment and computer-readable medium | |
| CN110363417A (en) | Financial risks strategy-generating method, device and electronic equipment | |
| CN110135978A (en) | User's financial risks appraisal procedure, device, electronic equipment and readable medium | |
| CN110148053A (en) | User's credit line assessment method, apparatus, electronic equipment and readable medium | |
| CN110348208A (en) | A kind of risk control method based on user behavior and neural network, device and electronic equipment | |
| CN110363575A (en) | A kind of credit user moves branch wish prediction technique, device and equipment | |
| CN111583018A (en) | Credit granting strategy management method and device based on user financial performance analysis and electronic equipment | |
| CN110363656A (en) | Financial service request processing method, device and electronic equipment | |
| CN110363653A (en) | Financial service request response method, device and electronic equipment | |
| CN110363654A (en) | A kind of favor information method for pushing, device and electronic equipment | |
| CN110348897A (en) | Financial service product marketing method, apparatus and electronic equipment | |
| CN111198967A (en) | User grouping method and device based on relational graph and electronic equipment |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Country or region after: China Address after: Room 1109, No. 4, Lane 800, Tongpu Road, Putuo District, Shanghai, 200062 Applicant after: Shanghai Qiyue Information Technology Co.,Ltd. Address before: Room a2-8914, 58 Fumin Branch Road, Hengsha Township, Chongming District, Shanghai, 201500 Applicant before: Shanghai Qiyue Information Technology Co.,Ltd. Country or region before: China |