CN105975590A - Method and device for determining object type - Google Patents
Method and device for determining object type Download PDFInfo
- Publication number
- CN105975590A CN105975590A CN201610298394.2A CN201610298394A CN105975590A CN 105975590 A CN105975590 A CN 105975590A CN 201610298394 A CN201610298394 A CN 201610298394A CN 105975590 A CN105975590 A CN 105975590A
- Authority
- CN
- China
- Prior art keywords
- data
- characteristic dimension
- characteristic
- type
- dimension
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2216/00—Indexing scheme relating to additional aspects of information retrieval not explicitly covered by G06F16/00 and subgroups
- G06F2216/03—Data mining
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method and a device for determining an object type. The method comprises the following steps: obtaining the feature data of each object on a plurality of feature dimensions in an object set, wherein the virtual resources of the object are consumed when the object in the object set executes a resource operation; on the basis of the feature data on the feature dimension, determining extremum data corresponding to the feature dimension; on the basis of the feature data of each object on each feature dimension and the extremum data on the corresponding feature dimension, determining the category attribute data of each object; and according to a data interval where the category attribute data belongs to, determining the object type of each object. The method solves the technical problem of low efficiency for determining the object type in the prior art.
Description
Technical field
The present invention relates to data processing field, in particular to the determination method and apparatus of a kind of object type.
Background technology
Along with the fast development of Internet technology, big data mining is widely used in every field, by a large number
The process of data can obtain substantial amounts of valuable information, or estimates the development trend in field.As
The bank field, the object that, credit many for number of deposits is big, need to carry out emphasis maintenance, but the most this kind of
Object is small part, in order to excavate the storage potentiality of object, needs to carry out data according to the various information of object
Process and excavate, classify with the storage potentiality according to object, and emphasis safeguards the object that wherein storage potentiality are bigger
Group;For another example, in catering field, the object that consumption is often, spending amount is bigger is high-quality object, but this kind of right
As being all to be transformed by plain objects, accordingly it is also possible to the various information of object is processed and excavates, with
Consumption potentiality according to object is classified, and emphasis safeguards the groups of objects that wherein consumption potentiality is bigger.
At present, when the various information of object is processed, need to use data mining model (such as regression analysis mould
Type, decision-tree model, Bayesian Classification Model, rough set model, supporting vector machine model etc.), but, use this
When the correlation attribute information (such as the type of object) of destination object is predicted by class data mining model, need mould
Type is trained in a large number and could be used, and i.e. needs to expend the longer training time, and the use of data mining model is more multiple
Miscellaneous (relatedness between as more in flow process, flow process is strong), thus lengthen the time carrying out object type differentiation further,
Thus have impact on the efficiency of whole event.
For technical problem inefficient when determining the type of object in correlation technique, effective solution is the most not yet proposed
Certainly scheme.
Summary of the invention
Embodiments provide the determination method and apparatus of a kind of object type, true at least to solve in correlation technique
Determine technical problem inefficient during the type of object.
An aspect according to embodiments of the present invention, it is provided that a kind of determination method of object type, the method includes:
Obtain each object characteristic in multiple characteristic dimension in object set, wherein, the object in object set
When performing resource operation, the virtual resource of object is consumed;Characteristic in feature based dimension determines corresponding to spy
Levy the extreme value data of dimension;Based in each object characteristic in each characteristic dimension and characteristic of correspondence dimension
Extreme value data determine the category attribute data of each object;Determine often according to the data interval belonging to category attribute data
The object type of individual object.
Further, based on each object characteristic in each characteristic dimension and the pole in characteristic of correspondence dimension
Value Data determines that the category attribute data of each object include: special at each to each object based on preset standard model
Levy the characteristic in dimension and the extreme value data in characteristic of correspondence dimension are standardized processing, obtain each object
Standardized data in each characteristic dimension;Each object is read in each characteristic dimension from presetting database
The weight that standardized data is corresponding;Based on each object standardized data in each characteristic dimension and corresponding weight
Determine the category attribute data of each object.
Further, extreme value data include minimum data and maximum data, and preset standard model includes calculating mark
Standardized calculation formula Bi=(D-MIN)/(MAX-MIN) of standardization data Bi, wherein, Bi is that each object is many
The standardized data in the i-th characteristic dimension in individual characteristic dimension, MIN is the minimum data in the i-th characteristic dimension,
MAX is the maximum data in the i-th characteristic dimension.
Further, determine each based on each object standardized data in each characteristic dimension and corresponding weight
The category attribute data of object include: based on each object standardized data in each characteristic dimension and corresponding power
Category attribute data T of each object of re-computation,Wherein, Ki is in the i-th characteristic dimension
The weight that standardized data Bi is corresponding, N is the dimension of multiple characteristic dimension, and i is the positive integer of no more than N.
Further, the type of object set includes the first kind, Second Type and the 3rd type, for the first kind
Object set in the resource operation number of times of object be not less than the first preset value and consumed resource is not less than second and presets
Value, the resource operation number of times for the object in the object set of Second Type is less than the first preset value, is the 3rd type
The consumed resource of the object in object set is less than the second preset value, wherein, if the type of object set is the first kind
Type, resource operation number of times that the most multiple characteristic dimension included in multiple time period in each time period, in each time period
Consumed resource, accumulative resource operation number of times and accumulative consumed resource;If the type of object set is Equations of The Second Kind
Type, the most multiple characteristic dimension include the resource operation number of times in each time period and accumulative resource operation number of times;If object
The type of set is the 3rd type, and the most multiple characteristic dimension include the consumed resource in each time period and accumulative resource
Consumption.
Further, multiple time periods include first time period, the second time period and the 3rd time period, the second time
The length of section is longer than first time period and was shorter than for the 3rd time period.
Further, determine that the object type of each object includes according to the data interval belonging to category attribute data: obtain
Take the interval division data that the object set type belonging to object set is corresponding;According to interval division data to object set
The interval at category attribute data place divide, obtain multiple data interval;By the category attribute number of each object
According to object type corresponding to the data interval at place as the object type of each object.
Another aspect according to embodiments of the present invention, it is provided that the determination device of a kind of object type, this device includes:
Acquiring unit, for obtaining each object characteristic in multiple characteristic dimension in object set, wherein, right
When performing resource operation as the object in set, the virtual resource of object is consumed;First determines unit, for based on
Characteristic in characteristic dimension determines the extreme value data corresponding to characteristic dimension;Second determines unit, for based on often
Individual object characteristic in each characteristic dimension and the extreme value data in characteristic of correspondence dimension determine each object
Category attribute data;3rd determines unit, determines the right of each object according to the data interval belonging to category attribute data
As type.
Further, second determines that unit includes: processing module, is used for based on preset standard model each object
Characteristic in each characteristic dimension and the extreme value data in characteristic of correspondence dimension are standardized processing, and obtain
Each object standardized data in each characteristic dimension;Read module, each for reading from presetting database
The weight that object standardized data in each characteristic dimension is corresponding;Determine module, be used for based on each object respectively
Standardized data in individual characteristic dimension and corresponding weight determine the category attribute data of each object.
Further, extreme value data include minimum data and maximum data, and preset standard model includes calculating mark
Standardized calculation formula Bi=(D-MIN)/(MAX-MIN) of standardization data Bi, wherein, Bi is that each object is many
The standardized data in the i-th characteristic dimension in individual characteristic dimension, MIN is the minimum data in the i-th characteristic dimension,
MAX is the maximum data in the i-th characteristic dimension.
In embodiments of the present invention, by obtaining each object characteristic in multiple characteristic dimension in object set,
When object in object set performs resource operation, the virtual resource of object is consumed;Spy in feature based dimension
Levy data and determine the extreme value data corresponding to characteristic dimension;Based on each object characteristic in each characteristic dimension
With the category attribute data that the extreme value data in characteristic of correspondence dimension determine each object;According to category attribute data institute
The data interval belonged to determines the object type of each object, thus solves the type timeliness determining object in correlation technique
The technical problem that rate is relatively low, by object characteristic in multiple characteristic dimension is processed, such that it is able to according to
Process the category attribute data obtained and quickly determine object type, and associative operation need not be carried out (as training data excavates
Model), thus saved the process time, improve the efficiency of the type determining object.
Accompanying drawing explanation
Accompanying drawing described herein is used for providing a further understanding of the present invention, constitutes the part of the application, this
Bright schematic description and description is used for explaining the present invention, is not intended that inappropriate limitation of the present invention.At accompanying drawing
In:
Fig. 1 is the flow chart of the determination method of object type according to embodiments of the present invention;And
Fig. 2 is the schematic diagram of the determination device of object type according to embodiments of the present invention.
Detailed description of the invention
In order to make those skilled in the art be more fully understood that the present invention program, below in conjunction with in the embodiment of the present invention
Accompanying drawing, is clearly and completely described the technical scheme in the embodiment of the present invention, it is clear that described embodiment
It is only the embodiment of a present invention part rather than whole embodiments.Based on the embodiment in the present invention, ability
The every other embodiment that territory those of ordinary skill is obtained under not making creative work premise, all should belong to
The scope of protection of the invention.
It should be noted that term " first " in description and claims of this specification and above-mentioned accompanying drawing, "
Two " it is etc. for distinguishing similar object, without being used for describing specific order or precedence.Should be appreciated that this
Sample use data can exchange in the appropriate case, in order to embodiments of the invention described herein can with except
Here the order beyond those illustrating or describing is implemented.Additionally, term " includes " and " having " and they
Any deformation, it is intended that cover non-exclusive comprising, such as, contain series of steps or the process of unit, side
Method, system, product or equipment are not necessarily limited to those steps or the unit clearly listed, but can include the clearest
List or for intrinsic other step of these processes, method, product or equipment or unit.
According to embodiments of the present invention, it is provided that the embodiment of the method for a kind of determination method of object type, explanation is needed
It is can to hold in the computer system of such as one group of computer executable instructions in the step shown in the flow chart of accompanying drawing
OK, and, although show logical order in flow charts, but in some cases, can be to be different from herein
Order perform shown or described by step.
Fig. 1 is the flow chart of the determination method of object type according to embodiments of the present invention, as it is shown in figure 1, the method
Comprise the steps:
Step S101, obtains each object characteristic in multiple characteristic dimension in object set, wherein, right
When performing resource operation as the object in set, the virtual resource of object is consumed.
Step S102, the characteristic in feature based dimension determines the extreme value data corresponding to characteristic dimension.
Step S103, based on each object characteristic in each characteristic dimension and the pole in characteristic of correspondence dimension
Value Data determines the category attribute data of each object.
Step S104, determines the object type of each object according to the data interval belonging to category attribute data.
By above-described embodiment, obtain each object characteristic in multiple characteristic dimension in object set, right
When performing resource operation as the object in set, the virtual resource of object is consumed;Characteristic number in feature based dimension
According to determining the extreme value data corresponding to characteristic dimension;Based on each object characteristic in each characteristic dimension and right
Extreme value data in the characteristic dimension answered determine the category attribute data of each object;Belonging to category attribute data
Data interval determines the object type of each object, thus when solving the type determining object in correlation technique efficiency is relatively
Low technical problem, by object characteristic in multiple characteristic dimension is processed, such that it is able to according to place
The category attribute data that reason obtains quickly determine type, and need not carry out associative operation (such as training data mining model),
Thus saved the process time, improve the efficiency of the type determining object.
The said method of the application can apply to the fields such as bank, food and drink, retail.As, at the bank field, object
Object in set can be depositor, the virtual resource i.e. property of depositor, and property is held by resource operation i.e. depositor
The deposit operation of row, the characteristic in multiple characteristic dimension i.e. with the data deposited in associated plurality of dimension;For another example,
Object in catering field, object set i.e. customer, the virtual resource i.e. cash of client, stored value card, member
The resources such as card, resource operation i.e. customer makes in cash, stored value card, member card etc. carry out the behavior consumed, multiple
Characteristic in characteristic dimension i.e. consumes the data in associated plurality of dimension with client.
It should be noted that in order to targetedly different types of client is analyzed, can first customer group be entered
Row classification, such as be divided three classes (i.e. the first kind, Second Type and the 3rd type), criteria for classification is mainly according to each
User's (i.e. object) resource operation number of times within a period of time (such as consumption number of times or number of deposits etc.) and resource
Consumption (such as spending amount or amount deposited etc.), is not less than first by resource operation number of times (such as consumption number of times) pre-
If value (such as 5 times) and consumed resource (such as spending amount) are not less than the object of the second preset value (such as 2000 yuan)
Putting into as in the object set of the first kind, number of operations and the consumed resource of this class object are the highest, to industry
Contribution rate higher, belong to and be worth higher object, by resource operation number of times less than the object of the first preset value put into into
In the object set of Second Type, consumed resource is put into less than the object of the second preset value the object set of the 3rd type
In conjunction, Equations of The Second Kind and the 3rd class object belong to potential becoming and are worth higher object, can be found by data analysis
Go out the user that wherein probability is higher, thus guided, to become high-quality object.
In the technical scheme of step S101, different types of data can be obtained according to the type of object set, tool
Body is as follows: if the type of object set is the first kind, the most multiple characteristic dimension include each time in multiple time period
Resource operation number of times in Duan, the consumed resource in each time period, accumulative resource operation number of times and accumulative resource
Consumption;If the type of object set is Second Type, the most multiple characteristic dimension include the resource behaviour in each time period
Make number of times and accumulative resource operation number of times;If the type of object set is the 3rd type, the most multiple characteristic dimension include respectively
Consumed resource in the individual time period and accumulative consumed resource.
Above-mentioned multiple time periods include first time period, the second time period and the 3rd time period, the second time period
Length is longer than first time period and was shorter than for the 3rd time period.
Such as, for catering field, first time period can be 30 days, and the second time period can be 60 days, the 3rd
Time period can be 90 days, if the type of object set is the first kind, the most multiple characteristic dimension include 30 days resources
Number of operations, 30 days consumed resources, 90 days resource number of operations, 90 days consumed resources, 180 days resource operations
Number of times, 180 days consumed resources, accumulative resource operation number of times and accumulative consumed resource;If the class of object set
Type is Second Type, and multiple characteristic dimension include 30 days resource number of operations, 90 days resource number of operations, 180 natural gifts
Source number of operations and accumulative resource operation number of times;If the type of object set is the 3rd type, multiple characteristic dimension bags
Include 30 days consumed resources, 90 days consumed resources, 180 days consumed resources and accumulative consumed resource.
In the scheme of step S102, the spy in each characteristic dimension can be determined by methods such as bubbling method, ranking methods
Levying the extreme value data in data, extreme value data include minimum data and maximum data.
In the scheme of step S103, based on each object characteristic in each characteristic dimension and characteristic of correspondence
Extreme value data in dimension determine that the category attribute data of each object can be accomplished in that based on pre-bidding
Each object characteristic in each characteristic dimension and the extreme value data in characteristic of correspondence dimension are entered by standardization model
Column criterionization processes, and obtains each object standardized data in each characteristic dimension;Read from presetting database
The weight that each object standardized data in each characteristic dimension is corresponding;Based on each object in each characteristic dimension
On standardized data and corresponding weight determine the category attribute data of each object.
It should be noted that above-mentioned preset standard model includes the standardized calculation formula of normalized data Bi
Bi=(D-MIN)/(MAX-MIN), wherein, Bi is in each object the i-th characteristic dimension in multiple characteristic dimension
Standardized data, MIN is the minimum data in the i-th characteristic dimension, and MAX is the maximum in the i-th characteristic dimension
Data.
By the characteristic in each dimension is standardized, the value of different range can be amplified to same scope
It is beneficial to calculate, as calculated client's contribution degree (contribution degree includes spending amount and the contribution dynamics of consumption time), owing to disappearing
The numerical value of the expense amount of money significantly greater than consumes number of times, by being standardized processing to it, can the amount of money and number of times all be reflected
It is mapped in the interval of 0 to 1, consequently facilitating calculate.
For the fields such as catering trade, the client that spending amount is the highest is the most valuable, the loyalty that consumption number of times is the highest
The highest, then a top-tier customer should be the highest, if high at client's only one of which attribute, another attribute is not
Gao Shi, then be difficult to attribute and define, when i.e. requiring more than more than one attribute as reference conditions, it is impossible to directly perceived
Client is ranked up, in order to the index (i.e. category attribute data) unified with represents the specified genus of object
Property, the classification of each object is determined based on each object standardized data in each characteristic dimension and corresponding weight
Attribute data can be accomplished in that based on each object standardized data in each characteristic dimension and right
Category attribute data T of each object of weight calculation answered,Wherein, Ki is the i-th feature dimensions
The weight that standardized data Bi on degree is corresponding, N is the dimension of multiple characteristic dimension, and i is the positive integer of no more than N.
As for.By calculating the category attribute data of each object, such that it is able to determine its affiliated class according to its occurrence
Type.
It should be noted that above-mentioned weight can be fixed value, it is also possible to enter according to the importance of each characteristic dimension
Row determines, it is also possible to choose suitable empirical value according to the experience of association area practitioner.
By above-described embodiment, the data in dimension each to user are standardized processing, and according to each dimension
Importance calculates category attribute data, such that it is able to determine the type of user according to category attribute data, in order to silver
Row or food and beverage enterprise improve targetedly according to these data.
Alternatively, in the technical scheme of step S104, determine each according to the data interval belonging to category attribute data
The object type of object includes: obtain the interval division data that the object set type belonging to object set is corresponding;According to
The interval at the category attribute data place of object set is divided by interval division data, obtains multiple data interval;
Using object type corresponding for the data interval at the category attribute data place of each object as the object type of each object.
User for the first kind gathers, and interval division data can be 20%, can will be close to the 20% of Interval Maximum value
Being defined as top-tier customer group, as catering trade, this kind of client is the significant contributor of enterprise, and food and beverage enterprise can be with pin
To this type of visitor group, the most actively promotional activities, keep loyalty and the consumption habit of client, for another example, for bank
Speech, the deposit shared by this kind of client accounts for the major part of whole deposit, and bank is also required to periodically safeguard such client.
User for Equations of The Second Kind gathers, and belongs to low frequency visitor group, can not consider spending amount, and the attribute chosen is:
30 days consumption number of times, 90 days consumption number of times, 180 days consumption number of times, cumulative consumption number of times, category attribute data=disappear
Take weight+other key indexs of the standard value * consumption number of times of number of times, category attribute data are sorted from small to large, district
Between divide data can be 20% to 30%, choose the less designated ratio of data (the most above-mentioned interval division data 20%
To 30%) it is low frequency visitor group, the client of the type typically referred to the client of twice, and mobility is relatively big, number
Accounting is more, and to the contribution of enterprise profit about 50%, can the improving targetedly of client choosing the type disappears
Take number of times, become loyalty customer.Other key indexs are self-defining indexs, select energy when this type of visitor's mass selection takes
The data representing consumption number of times get final product (as twice consumption is spaced).
User for the 3rd class gathers, and belongs to low amount visitor group, can not consider to consume number of times, and the attribute chosen is:
30 days consumption total values, 90 days consumption total values, 180 days consumption total value, cumulative consumption total values, category attribute data=mark
Weight+other key indexs of the quasi-value * spending amount of spending amount, by little for category attribute data to big sequence, interval
Dividing data can be 20% to 30%, chooses less designated ratio (the most above-mentioned interval division data 20% to 30%)
For low amount of money visitor group, the client of the type typically referred to the client of twice, and mobility is relatively big, and accounting is more,
To the contribution of enterprise profit about 50%, a client can belong simultaneously to the objective group of the low frequency and low amount, now
Should preferentially promote consumption number of times.The meaning of other key indexs is self-defining index, selects when this type of visitor's mass selection takes
The data that can represent spending limit get final product (such as the integration amount of consumption, voucher purchase volume).
By above-described embodiment, visitor group is more segmented or clusters, by client's quantification of targets, it is simple to location core
Heart member visitor group, convenient battalion dealer understands self management state and finds the growth point that can improve.
It should be noted that for aforesaid each method embodiment, in order to be briefly described, therefore it is all expressed as one it be
The combination of actions of row, but those skilled in the art should know, the present invention not limiting by described sequence of movement
System, because according to the present invention, some step can use other orders or carry out simultaneously.Secondly, art technology
Personnel also should know, embodiment described in this description belongs to preferred embodiment, involved action and module
Not necessarily necessary to the present invention.
The embodiment of the present invention additionally provides the determination device of a kind of object type.It should be noted that the embodiment of the present invention
The determination device of object type may be used for performing the determination method of the object type that the embodiment of the present invention is provided.
Fig. 2 is the schematic diagram of the determination device of object type according to embodiments of the present invention.As in figure 2 it is shown, this device
May include that acquiring unit 10, first determine unit 20, second determine that unit 30 and the 3rd determines unit 40.
Acquiring unit 10 is for obtaining each object characteristic in multiple characteristic dimension in object set, wherein,
When object in object set performs resource operation, the virtual resource of object is consumed.
First determines that the unit 20 characteristic in feature based dimension determines the extreme value number corresponding to characteristic dimension
According to.
Second determines that unit 30 is for based on each object characteristic in each characteristic dimension and characteristic of correspondence
Extreme value data in dimension determine the category attribute data of each object.
3rd determines that unit 40 determines the object type of each object according to the data interval belonging to category attribute data.
By above-described embodiment, obtain each object spy in multiple characteristic dimension in object set by acquiring unit
Levying data, when the object in object set performs resource operation, the virtual resource of object is consumed;First determines list
Characteristic in unit's feature based dimension determines the extreme value data corresponding to characteristic dimension;Second determines that unit is based on often
Individual object characteristic in each characteristic dimension and the extreme value data in characteristic of correspondence dimension determine each object
Category attribute data;3rd determines that unit determines the object of each object according to the data interval belonging to category attribute data
Type, thus solve technical problem inefficient during the type determining object in correlation technique, by object is existed
Characteristic in multiple characteristic dimension processes, such that it is able to the most true according to processing the category attribute data obtained
Determine type, and associative operation (such as training data mining model) need not be carried out, thus saved the process time, improve
Determine the efficiency of the type of object.
The said method of the application can apply to the fields such as bank, food and drink, retail.As, at the bank field, object
Object in set can be depositor, the virtual resource i.e. property of depositor, and property is held by resource operation i.e. depositor
The deposit operation of row, the characteristic in multiple characteristic dimension i.e. with the data deposited in associated plurality of dimension;For another example,
Object in catering field, object set i.e. customer, the virtual resource i.e. cash of client, stored value card, member
The resources such as card, resource operation i.e. customer makes in cash, stored value card, member card etc. carry out the behavior consumed, multiple
Characteristic in characteristic dimension i.e. consumes the data in associated plurality of dimension with client.
Alternatively, second determines that unit includes: processing module, for existing each object based on preset standard model
Characteristic in each characteristic dimension and the extreme value data in characteristic of correspondence dimension are standardized processing, and obtain every
Individual object standardized data in each characteristic dimension;Read module, each right for reading from presetting database
As the weight that the standardized data in each characteristic dimension is corresponding;Determine module, be used for based on each object at each
Standardized data in characteristic dimension and corresponding weight determine the category attribute data of each object.
It should be noted that extreme value data include minimum data and maximum data, preset standard model includes meter
Calculating standardized calculation formula Bi=(D-MIN)/(MAX-MIN) of standardized data Bi, wherein, Bi is each object
The standardized data in the i-th characteristic dimension in multiple characteristic dimension, MIN is the minimum in the i-th characteristic dimension
Data, MAX is the maximum data in the i-th characteristic dimension.
By the characteristic in each dimension is standardized, the value of different range can be amplified to same scope
It is beneficial to calculate, as calculated client's contribution degree (contribution degree includes spending amount and the contribution dynamics of consumption time), owing to disappearing
The numerical value of the expense amount of money significantly greater than consumes number of times, by being standardized processing to it, can the amount of money and number of times all be reflected
It is mapped in the interval of 0 to 1, consequently facilitating calculate.
For the fields such as catering trade, the client that spending amount is the highest is the most valuable, the loyalty that consumption number of times is the highest
The highest, then a top-tier customer should be the highest, if high at client's only one of which attribute, another attribute is not
Gao Shi, then be difficult to attribute and define, when i.e. requiring more than more than one attribute as reference conditions, it is impossible to directly perceived
Client is ranked up, in order to the index (i.e. category attribute data) unified with represents the specified genus of object
Property, the classification of each object is determined based on each object standardized data in each characteristic dimension and corresponding weight
Attribute data can be accomplished in that based on each object standardized data in each characteristic dimension and right
Category attribute data T of each object of weight calculation answered,Wherein, Ki is the i-th feature dimensions
The weight that standardized data Bi on degree is corresponding, N is the dimension of multiple characteristic dimension, and i is the positive integer of no more than N.
As for.By calculating the category attribute data of each object, such that it is able to determine its affiliated class according to its occurrence
Type.
It should be noted that above-mentioned weight can be fixed value, it is also possible to enter according to the importance of each characteristic dimension
Row determines, it is also possible to choose suitable empirical value according to the experience of association area practitioner.
By above-described embodiment, the data in dimension each to user are standardized processing, and according to each dimension
Importance calculates category attribute data, such that it is able to determine the type of user according to category attribute data, in order to silver
Row or food and beverage enterprise improve targetedly according to these data.
Alternatively, the 3rd determines that unit is additionally operable to obtain the interval division that the object set type belonging to object set is corresponding
Data;According to interval division data, the interval at the category attribute data place of object set is divided, obtain multiple
Data interval;Using object type corresponding for the data interval at the category attribute data place of each object as each object
Object type.
By above-described embodiment, visitor group is more segmented or clusters, by client's quantification of targets, it is simple to location core
Heart member visitor group, convenient battalion dealer understands self management state and finds the growth point that can improve.
The using method that modules provided in the present embodiment step corresponding with embodiment of the method is provided is identical, should
Can also be identical by scene.It is noted, of course, that the scheme that above-mentioned module relates to can be not limited to above-mentioned enforcement
Content in example and scene, and above-mentioned module may operate in terminal or mobile terminal, can by software or
Hardware realizes.
The invention described above embodiment sequence number, just to describing, does not represent the quality of embodiment.
In the above embodiment of the present invention, the description to each embodiment all emphasizes particularly on different fields, and does not has in certain embodiment
The part described in detail, may refer to the associated description of other embodiments.
In several embodiments provided herein, it should be understood that disclosed technology contents, can be passed through other
Mode realize.Wherein, device embodiment described above is only schematically, the division of the most described unit,
Can be that a kind of logic function divides, actual can have other dividing mode, the most multiple unit or assembly when realizing
Can in conjunction with or be desirably integrated into another system, or some features can be ignored, or does not performs.Another point, institute
The coupling each other shown or discuss or direct-coupling or communication connection can be by some interfaces, unit or mould
The INDIRECT COUPLING of block or communication connection, can be being electrical or other form.
The described unit illustrated as separating component can be or may not be physically separate, shows as unit
The parts shown can be or may not be physical location, i.e. may be located at a place, or can also be distributed to
On multiple unit.Some or all of unit therein can be selected according to the actual needs to realize the present embodiment scheme
Purpose.
It addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, it is also possible to
It is that unit is individually physically present, it is also possible to two or more unit are integrated in a unit.Above-mentioned integrated
Unit both can realize to use the form of hardware, it would however also be possible to employ the form of SFU software functional unit realizes.
If described integrated unit is using the form realization of SFU software functional unit and as independent production marketing or use,
Can be stored in a computer read/write memory medium.Based on such understanding, technical scheme essence
On the part that in other words prior art contributed or this technical scheme completely or partially can be with software product
Form embodies, and this computer software product is stored in a storage medium, including some instructions with so that one
Platform computer equipment (can be for personal computer, server or the network equipment etc.) performs each embodiment institute of the present invention
State all or part of step of method.And aforesaid storage medium includes: USB flash disk, read only memory (ROM, Read-Only
Memory), random access memory (RAM, Random Access Memory), portable hard drive, magnetic disc or CD
Etc. the various media that can store program code.
The above is only the preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For Yuan, under the premise without departing from the principles of the invention, it is also possible to make some improvements and modifications, these improve and profit
Decorations also should be regarded as protection scope of the present invention.
Claims (10)
1. the determination method of an object type, it is characterised in that including:
Obtain each object characteristic in multiple characteristic dimension in object set, wherein, at described object
When object in set performs resource operation, the virtual resource of described object is consumed;
The extreme value data corresponding to described characteristic dimension are determined based on the characteristic in described characteristic dimension;
Based on described each object characteristic in characteristic dimension each described and corresponding described characteristic dimension
On extreme value data determine the category attribute data of described each object;
The object type of described each object is determined according to the data interval belonging to described category attribute data.
Method the most according to claim 1, it is characterised in that based on described each object in feature dimensions each described
Characteristic on degree and the extreme value data in corresponding described characteristic dimension determine that the classification of described each object belongs to
Property data include:
Based on preset standard model to described each object characteristic in characteristic dimension each described and right
The extreme value data in described characteristic dimension answered are standardized processing, and obtain described each object described in each
Standardized data in characteristic dimension;
Described each object standardized data in characteristic dimension each described is read corresponding from presetting database
Weight;
Institute is determined based on described each object standardized data in characteristic dimension each described and corresponding weight
State the category attribute data of each object.
Method the most according to claim 2, it is characterised in that described extreme value data include that minimum data are with very big
Value Data, described preset standard model includes the standardized calculation formula Bi=calculating described standardized data Bi
(D-MIN)/(MAX-MIN), wherein, Bi is described each object i-th in multiple described characteristic dimension
Standardized data in characteristic dimension, MIN is the minimum data in described i-th characteristic dimension, and MAX is described
Maximum data in i-th characteristic dimension.
Method the most according to claim 3, it is characterised in that based on described each object in feature dimensions each described
Standardized data on degree and corresponding weight determine that the category attribute data of described each object include:
Based on described each object standardized data in characteristic dimension each described and corresponding weight calculation institute
State category attribute data T of each object,Wherein, Ki is described i-th characteristic dimension
On weight corresponding to standardized data Bi, N is the dimension of multiple described characteristic dimension, and i is no more than N's
Positive integer.
Method the most as claimed in any of claims 1 to 4, it is characterised in that the type of described object set
Including the first kind, Second Type and the 3rd type, right in the described object set of the described first kind
The resource operation number of times of elephant is not less than the first preset value and consumed resource is not less than the second preset value, for described
The resource operation number of times of the object in the described object set of two types is less than described first preset value, for described the
The consumed resource of the object in the described object set of three types is less than described second preset value, wherein,
If the type of described object set is the described first kind, the most multiple described characteristic dimension include multiple time
Resource operation number of times in each time period, the consumed resource in each time period described, accumulative resource in Duan
Number of operations and accumulative consumed resource;
If the type of described object set is described Second Type, the most multiple described characteristic dimension include described each
Resource operation number of times in time period and accumulative resource operation number of times;
If the type of described object set is described 3rd type, the most multiple described characteristic dimension include described each
Consumed resource in time period and accumulative consumed resource.
Method the most according to claim 5, it is characterised in that the plurality of time period include first time period,
Two time periods and the 3rd time period, the length of described second time period is longer than described first time period and is shorter than institute
Stated for the 3rd time period.
Method the most according to claim 5, it is characterised in that according to the data field belonging to described category attribute data
Between determine that the object type of described each object includes:
Obtain the interval division data that the object set type belonging to described object set is corresponding;
According to described interval division data, the interval at the category attribute data place of described object set is divided,
Obtain multiple described data interval;
Using object type corresponding for the described data interval at the category attribute data place of described each object as institute
State the object type of each object.
8. the determination device of an object type, it is characterised in that including:
Acquiring unit, for obtaining each object characteristic in multiple characteristic dimension in object set, its
In, when the object in described object set performs resource operation, the virtual resource of described object is consumed;
First determines unit, for determining corresponding to described feature dimensions based on the characteristic in described characteristic dimension
The extreme value data of degree;
Second determines unit, for based on described each object characteristic in characteristic dimension each described and
The corresponding extreme value data in described characteristic dimension determine the category attribute data of described each object;
3rd determines unit, determines described each object according to the data interval belonging to described category attribute data
Object type.
Device the most according to claim 8, it is characterised in that described second determines that unit includes:
Processing module, for based on preset standard model to described each object in characteristic dimension each described
Characteristic and corresponding described characteristic dimension on extreme value data be standardized processing, obtain described each
Object standardized data in characteristic dimension each described;
Read module, for reading described each object in characteristic dimension each described from presetting database
The weight that standardized data is corresponding;
Determine module, for based on described each object standardized data in characteristic dimension each described and right
The weight answered determines the category attribute data of described each object.
Device the most according to claim 9, it is characterised in that described extreme value data include that minimum data are with very big
Value Data, described preset standard model includes the standardized calculation formula Bi=calculating described standardized data Bi
(D-MIN)/(MAX-MIN), wherein, Bi is described each object i-th in multiple described characteristic dimension
Standardized data in characteristic dimension, MIN is the minimum data in described i-th characteristic dimension, and MAX is described
Maximum data in i-th characteristic dimension.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610298394.2A CN105975590A (en) | 2016-05-03 | 2016-05-03 | Method and device for determining object type |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610298394.2A CN105975590A (en) | 2016-05-03 | 2016-05-03 | Method and device for determining object type |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105975590A true CN105975590A (en) | 2016-09-28 |
Family
ID=56991374
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610298394.2A Pending CN105975590A (en) | 2016-05-03 | 2016-05-03 | Method and device for determining object type |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105975590A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110363897A (en) * | 2019-07-25 | 2019-10-22 | 新奥(中国)燃气投资有限公司 | A kind of client's temperature drawing generating method and device |
CN111709296A (en) * | 2020-05-18 | 2020-09-25 | 北京奇艺世纪科技有限公司 | Scene identification method and device, electronic equipment and readable storage medium |
CN113077292A (en) * | 2021-04-20 | 2021-07-06 | 北京沃东天骏信息技术有限公司 | User classification method and device, storage medium and electronic equipment |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101340463A (en) * | 2008-08-22 | 2009-01-07 | 深圳市迅雷网络技术有限公司 | Method and apparatus for determining network resource type |
CN104239324A (en) * | 2013-06-17 | 2014-12-24 | 阿里巴巴集团控股有限公司 | Methods and systems for user behavior based feature extraction and personalized recommendation |
CN104699717A (en) * | 2013-12-10 | 2015-06-10 | 中国银联股份有限公司 | Data mining method |
CN104699702A (en) * | 2013-12-09 | 2015-06-10 | 中国银联股份有限公司 | Data mining and classifying method |
CN104778173A (en) * | 2014-01-10 | 2015-07-15 | 腾讯科技(深圳)有限公司 | Determination method, device and equipment of objective user |
CN105225135A (en) * | 2015-10-31 | 2016-01-06 | 广州华多网络科技有限公司 | Potentiality customer recognition method and device |
-
2016
- 2016-05-03 CN CN201610298394.2A patent/CN105975590A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101340463A (en) * | 2008-08-22 | 2009-01-07 | 深圳市迅雷网络技术有限公司 | Method and apparatus for determining network resource type |
CN104239324A (en) * | 2013-06-17 | 2014-12-24 | 阿里巴巴集团控股有限公司 | Methods and systems for user behavior based feature extraction and personalized recommendation |
CN104699702A (en) * | 2013-12-09 | 2015-06-10 | 中国银联股份有限公司 | Data mining and classifying method |
CN104699717A (en) * | 2013-12-10 | 2015-06-10 | 中国银联股份有限公司 | Data mining method |
CN104778173A (en) * | 2014-01-10 | 2015-07-15 | 腾讯科技(深圳)有限公司 | Determination method, device and equipment of objective user |
CN105225135A (en) * | 2015-10-31 | 2016-01-06 | 广州华多网络科技有限公司 | Potentiality customer recognition method and device |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110363897A (en) * | 2019-07-25 | 2019-10-22 | 新奥(中国)燃气投资有限公司 | A kind of client's temperature drawing generating method and device |
CN110363897B (en) * | 2019-07-25 | 2021-04-27 | 新奥(中国)燃气投资有限公司 | Client heat map generation method and device |
CN111709296A (en) * | 2020-05-18 | 2020-09-25 | 北京奇艺世纪科技有限公司 | Scene identification method and device, electronic equipment and readable storage medium |
CN113077292A (en) * | 2021-04-20 | 2021-07-06 | 北京沃东天骏信息技术有限公司 | User classification method and device, storage medium and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Bijak et al. | Does segmentation always improve model performance in credit scoring? | |
Rekarti et al. | Improving business performance: A proposed model for SMEs | |
CN110490729B (en) | Financial user classification method based on user portrait model | |
Kao et al. | A Bayesian latent variable model with classification and regression tree approach for behavior and credit scoring | |
US20080215470A1 (en) | Methods and apparatus for use in association with payment card accounts | |
CN105956122A (en) | Object attribute determining method and device | |
WO2011112981A2 (en) | Methods, computer-accessible medium and systems for construction of and inference with networked data, for example, in a financial setting | |
CN111626766A (en) | Mobile banking marketing customer screening method integrating multiple machine learning models | |
CN106874355A (en) | The collaborative filtering method of social networks and user's similarity is incorporated simultaneously | |
CN101719147A (en) | Rochester model-naive Bayesian model-based data classification system | |
CN111325248A (en) | Method and system for reducing pre-loan business risk | |
Djurisic et al. | Bank CRM optimization using predictive classification based on the support vector machine method | |
Satheesh et al. | Applications of artificial intelligence on customer experience and service quality of the banking sector | |
US20210125272A1 (en) | Using Inferred Attributes as an Insight into Banking Customer Behavior | |
CN105975590A (en) | Method and device for determining object type | |
Stewart | A profit-based scoring system in consumer credit: making acquisition decisions for credit cards | |
CN113781139A (en) | Item recommendation method, item recommendation device, equipment and medium | |
Tsai et al. | Two-stage replenishment policies for deteriorating items at Taiwanese convenience stores | |
Lu et al. | A Hybrid Sales Forecasting Scheme by Combining Independent Component Analysis with K‐Means Clustering and Support Vector Regression | |
Moslehi et al. | Analyzing and investigating the use of electronic payment tools in Iran using data mining techniques | |
Hallam et al. | Semiparametric density forecasts of daily financial returns from intraday data | |
CN116361542A (en) | Product recommendation method, device, computer equipment and storage medium | |
Gupta et al. | Segmentation of retail customers based on cluster analysis in building successful CRM | |
Mabe et al. | Determinants of Corporate Failure: The Case of the Johannesburg Stock Exchange | |
Mundargi et al. | Bank Fixed Term Deposit analysis using Bayesian Logistic Regression |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
CB02 | Change of applicant information | ||
CB02 | Change of applicant information |
Address after: Wuxi District of Jiangsu city in Wuxi Province, Zhenze Road No. 18, Wuxi (National) Software Park Dolphin C seat 2, 3 floor Applicant after: Wuxi private online Polytron Technologies Inc Address before: Wuxi District of Jiangsu city in Wuxi Province, Zhenze Road No. 18, Wuxi (National) Software Park Dolphin C seat 2, 3 floor Applicant before: Wuxi Yazuo Online Technology Development Co., Ltd. |
|
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160928 |