CN104156466B - A kind of resource allocation methods and device based on grade - Google Patents
A kind of resource allocation methods and device based on grade Download PDFInfo
- Publication number
- CN104156466B CN104156466B CN201410418429.2A CN201410418429A CN104156466B CN 104156466 B CN104156466 B CN 104156466B CN 201410418429 A CN201410418429 A CN 201410418429A CN 104156466 B CN104156466 B CN 104156466B
- Authority
- CN
- China
- Prior art keywords
- grade
- user
- dimension
- benchmark
- equation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06313—Resource planning in a project environment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
Abstract
The present embodiments relate to technical field of data processing, more particularly to a kind of resource allocation methods and device based on grade.This method includes：According to the boundary value of the benchmark dimension values of user and the benchmark dimension being previously obtained vector, selection in equation is encouraged to encourage equation suitable for the benchmark dimension grade of user from default benchmark dimension grade；Equation is encouraged according to the benchmark dimension values of the user and the benchmark dimension grade selected, calculates the benchmark dimension grade point of user；According to the benchmark dimension grade point of the user and default various dimensions weight vectors, the various dimensions grade point of user is calculated；It is the user resource allocation according to the various dimensions grade point of the user.This method can avoid the waste of resource so as to reduce cost.
Description
Technical field
The present embodiments relate to technical field of data processing, more particularly to a kind of resource allocation methods based on grade and
Device.
Background technology
Managing customer relation (Customer-Managed Relationship, CMR) is that a kind of widely used division is used
Method, software and the interconnection network means of family grade.
It is main using the model split user gradation provided in CMR in the existing resource allocation methods based on grade, and
It is user resource allocation according to user gradation., may in typing user profile due to not clear and definite grading standard
A grade arbitrarily is divided to user, causes the unreasonable of user gradation.In addition, grading standard is more by manager artificial
Determine, even if there is clear and definite grading standard, but the operating efficiency of artificial determination user gradation is low.
During being user resource allocation according to user gradation, the unreasonable of user gradation division will cause resource point
That matches somebody with somebody is unreasonable, so as to a certain degree of waste of resource, and then increases the cost of resource.
The content of the invention
The purpose of the present invention is to propose to a kind of resource allocation methods and device based on grade, to avoid waste of resource, from
And reduce the cost of resource.
On the one hand, the invention provides a kind of resource allocation methods based on grade, including：
According to the boundary value of the benchmark dimension values of user and the benchmark dimension being previously obtained vector, from default benchmark dimension
Benchmark dimension grade excitation equation of the selection suitable for user in grade excitation equation；
Equation is encouraged according to the benchmark dimension values of the user and the benchmark dimension grade selected, calculates the benchmark of user
Dimension grade point；
According to the benchmark dimension grade point of the user and default various dimensions weight vectors, various dimensions of user etc. are calculated
Level value；
It is the user resource allocation according to the various dimensions grade point of the user.
On the other hand, the invention provides a kind of resource allocation device based on grade, including：
Equation selecting unit, for the benchmark dimension values according to user and the boundary value of benchmark dimension being previously obtained to
Amount, selection in equation is encouraged to encourage equation suitable for the benchmark dimension grade of user from default benchmark dimension grade；
Initial grade computing unit, swash for the benchmark dimension values according to the user and the benchmark dimension grade selected
Equation is encouraged, calculates the benchmark dimension grade point of user；
Final rating calculation unit, for the benchmark dimension grade point according to the user and default various dimensions weight to
Amount, calculate the various dimensions grade point of user；
Resource allocation unit, it is the user resource allocation for the various dimensions grade point according to the user.
The resource allocation methods and device based on grade provided in the embodiment of the present invention, effectively reduce the cost of resource.
In the embodiment of the present invention benchmark dimension grade excitation equation suitable for user, and root are selected according to the benchmark dimension values of user
The benchmark dimension grade of user is calculated with the benchmark dimension grade excitation equation selected according to the benchmark dimension values of the user
Value；And then the benchmark dimension grade point according to user and the various dimensions weight vectors, the various dimensions grade point of user is calculated,
So that it is determined that the grade of user.Because process provides encourage equation, rate range division points by the benchmark dimension grade
The clear and definite grading standard that vector sum rate range division points vector determines, therefore it is able to ensure that the reasonable of user gradation
Property, and then when being user resource allocation according to user gradation, the waste of resource can be avoided, so as to reduce resources costs.
Brief description of the drawings
Accompanying drawing described herein is used for providing further understanding the embodiment of the present invention, forms the embodiment of the present invention
A part, the restriction to the embodiment of the present invention is not formed.In the accompanying drawings：
Fig. 1 is the implementation process figure of the resource allocation methods based on grade provided in first embodiment of the invention；
Fig. 2 is the schematic diagram of the grade excitation model provided in the embodiment of the present invention；
Fig. 3 is the implementation process figure of the resource allocation methods based on grade provided in second embodiment of the invention；
Fig. 4 is the schematic diagram of the grade excitation model provided in second embodiment of the invention；
Fig. 5 is the schematic diagram of the grade excitation model provided in second embodiment of the invention；
Fig. 6 is the schematic diagram of the grade excitation model provided in second embodiment of the invention；
Fig. 7 is the structural representation of the resource allocation device based on grade provided in third embodiment of the invention.
Embodiment
Below in conjunction with the accompanying drawings and specific embodiment the embodiment of the present invention is carried out in further detail with complete explanation.It can manage
Solution, specific embodiment described herein are only used for explaining the embodiment of the present invention, rather than the restriction to the embodiment of the present invention.
It also should be noted that for the ease of description, the part related to the embodiment of the present invention rather than entirely is illustrate only in accompanying drawing
Portion's content.
First embodiment：
Fig. 1 is the implementation process figure of the resource allocation methods based on grade provided in first embodiment of the invention, the party
Method can be by being performed based on the resource allocation device of grade, and described device can be realized by software and/or hardware, can be used as terminal
A part for equipment is built in inside terminal device.As shown in figure 1, the implementation process includes：
Step 11, according to the boundary value of the benchmark dimension values of user and the benchmark dimension being previously obtained vector, from default
Benchmark dimension grade excitation equation of the selection suitable for user in benchmark dimension grade excitation equation.
In the user gradation partition process based on various dimensions, each dimension represents a kind of information of user respectively, will be more
Benchmark dimension values of a kind of value of dimension as user in dimension values.Benchmark dimension boundary value vector s=s1, s2, s3,
S4 ... } value range of benchmark dimension, i.e. the benchmark dimension values according to user and the benchmark corresponding to expression different user grade
The boundary value vector of dimension can determine the benchmark dimension grade of user.
Specifically, exemplified by with the boundary value vector s={ f, h, t, p } of benchmark dimension.If the benchmark dimension values q of user meets
Following relation：0≤q<F, it is determined that user belongs to the first estate；If the benchmark dimension values q of user meets following relation：f≤q<
H, it is determined that user belongs to the second grade；If the benchmark dimension values q of user meets following relation：h≤q<T, it is determined that user belongs to
In the tertiary gradient；If the benchmark dimension values q of user meets following relation：t≤q<P, it is determined that user belongs to the fourth estate.First
Grade, the second grade, the tertiary gradient and the fourth estate can be named as primary, intermediate, advanced and super successively.
Default benchmark dimension grade excitation equation is respectively equation corresponding to each predetermined level.Fig. 2 is implementation of the present invention
The schematic diagram of the grade excitation model provided in example, as shown in Fig. 2 the first estate excitation equation is y=2x；Second grade encourages
Equation is y=x+a/2；Tertiary gradient excitation equation is y=x/2+b/2+a/4；Fourth estate excitation equation is y=x/4+c/2+
b/4+a/8.The slope of wherein each grade represents the excitation factor of each grade, and excitation factor is smaller, represents that grade rises and gets over
It is difficult.
Wherein { a, b, c, d } forms rate range division points vector, i.e. the various dimensions grade point of foundation user and described etc.
Level scope division points vector, can determine the grade of user.
To sum up, according to the boundary value of the benchmark dimension values of user and the benchmark dimension being previously obtained vector, it may be determined that use
Benchmark dimension rate range belonging to family, and then the benchmark dimension grade excitation equation suitable for user can be selected.Need
Illustrate, benchmark dimension grade excitation equation can be with identical corresponding to different benchmark dimension grades, can also be different, can be with
Each benchmark dimension grade corresponds to same benchmark dimension grade equation.
Step 12, according to the benchmark dimension values of the user and the benchmark dimension grade selected equation is encouraged, calculate and use
The benchmark dimension grade point at family.
By the benchmark dimension values of user, substitute into the benchmark dimension grade suitable for user selected and encourage equation, that is, count
Calculate the benchmark dimension grade point of user.For example, the benchmark dimension values of user are q, and benchmark dimension of the user selected etc.
Level excitation equation is y=x+a/2, then the benchmark dimension grade point of user is：q+a/2.
Step 13, the benchmark dimension grade point according to the user and default various dimensions weight vectors, calculate user's
Various dimensions grade point.
In user gradation partition process, each component in default various dimensions weight vectors represents each dimension respectively
Shared proportion.
Wherein, according to the benchmark dimension grade point of the user and default various dimensions weight vectors, the more of user are calculated
Dimension grade point can include：According to equation below, the various dimensions grade point G of user is calculated：Its
In, g is the benchmark dimension grade point of user, and v={ v1, v2, v3, v4 ..., vk } is various dimensions weight vectors, and k weighs for various dimensions
The number of dimensions of weight vector.
For example, v={ 100%, 110%, 80%, 90% }, and the benchmark dimension grade point g=q+a/2 of user, then user
Various dimensions grade point G=(q+a/2) * 0.95.
Step 14, the various dimensions grade point according to the user, it is the user resource allocation.
For example, according to the various dimensions grade point of user, when being that 500 users distribute shuttlecock.If the multidimensional of the user
Spend that grade point is bigger, it is higher using the frequency of shuttlecock to characterize user, then only can exceed preset value for various dimensions grade points
User distributes shuttlecock, without distributing the shuttlecock of identical quantity for each user, so as to cost-effective.
It should be noted that the various dimensions grade of the benchmark dimension grade point of user and user in first embodiment of the invention
It is worth equal round numbers, and can be rounded by the way of rounding up.
Wherein, according to the various dimensions grade point of the user, it is the user resource allocation, can includes：It is it is determined that described
Whether the various dimensions grade point of user is more than preset value, if so, being the user resource allocation；Otherwise, it is not the user point
With resource.
It is the specific of the user resource allocation to the various dimensions grade point according to the user in the embodiment of the present invention
Method is not construed as limiting, as long as there is the distribution principle of determination.
In the resource allocation methods based on grade provided in first embodiment of the invention, there is provided a kind of clearly grade is drawn
Minute mark is accurate, i.e., encourages equation, and default various dimensions according to the benchmark dimension values of user and suitable for the benchmark dimension of user
Weight vectors, the various dimensions grade point of user is obtained, and according to the various dimensions grade point of the user, money is distributed for the user
Source.Because method provides a kind of clear and definite grading standard, therefore it is able to ensure that the reasonability of user gradation division, energy
Enough is reasonably user resource allocation, and then when being user resource allocation according to the various dimensions grade point of the user, is reduced
The waste of resource, so as to cost-effective.
Second embodiment：
Fig. 3 is the implementation process figure of the resource allocation methods based on grade provided in second embodiment of the invention, the party
Method can be by being performed based on the resource allocation device of grade, and described device can be realized by software and/or hardware, can be used as terminal
A part for equipment is built in inside terminal device.As shown in figure 3, the implementation process includes：
Step 21, grade classification dimension vector is set, and the various dimensions are set according to grade classification dimension vector
Weight vectors.
Wherein, grade classification dimension vector n={ n1, n2, n3, n4, n5 ... }, various dimensions weight vectors v=v1, v2,
v3,v4,v5…}.The number of component is equal in the number of component and various dimensions weight vectors in grade classification dimension vector, and waits
Each component represents a dimension in level partition dimension vector, and a benchmark dimension can be taken in these dimensions.Various dimensions are weighed
Weight vector represents the weight of each dimension corresponding to grade classification dimension vector.That is, the weight shared by n1 is v1；Power shared by n2
Weight is v2；Weight shared by n2 is v3；Weight shared by n4 is v4；Weight shared by n5 is v5.It should be noted that benchmark is tieed up
The weight of degree is 100%.
Wherein, the grade classification dimension vector n can be：N={ spending amount, the last consumption time, consumption frequency
Rate }, wherein dimension on the basis of spending amount.Now, the spending amount of user, the last consumption time and the equal energy of consuming frequency
Enough obtained by statistics.Further, since dimension on the basis of spending amount, therefore the weight of spending amount is 100%, further according to
Actual conditions set the weight of the last consumption time and the weight of consuming frequency, that is, complete setting for various dimensions weight vectors
It is fixed.That is, it is the specific reality of dimension that the embodiment of the present invention, which provides one kind with spending amount, the last consumption time, consuming frequency,
Apply scheme.
Step 22, benchmark dimension grade excitation equation described in the rate range division points vector sum is set, and according to institute
State benchmark dimension grade described in rate range division points vector sum and encourage equation, calculate the boundary value vector of the benchmark dimension.
Wherein, it is user's divided rank according to rate range division points vector r={ r1, r2, r3, r4 ... }.It is each default
The default benchmark dimension grade excitation equation of corresponding one of grade, and the slope of each grade excitation equation represents swashing for the grade
Encourage the factor, excitation factor is smaller, illustrate user rise to next grade difficulty it is bigger.
Each component in the rate range division points vector r is substituted into the benchmark dimension grade excitation equation, can
Enough calculate each component in the boundary value vector s of benchmark dimension.
Still by taking the benchmark dimension rating calculation excitation model provided in Fig. 2 as an example, i.e. rate range division points vector r=
{ a, b, c, d }, benchmark dimension grade excitation equation is respectively y=2x, y=x+a/2, y=x/2+b/2+a/4, y=x/4+c/2+
B/4+a/8, then calculate the boundary value vector s={ a/2, b-a/2,2c-b-a/2,4d-2c-b-a/2 } of benchmark dimension.It is actual
In use, parameter a, b, c and d are replaced with into occurrence.
The distributed number situation of user can meet following relation：Power user's quantity<Naive user quantity<Advanced level user
Quantity<Intermediate users quantity.I.e. line segment length can meet following relation：d-c<a<c-b<b-a.
It should be noted that the type of default benchmark dimension grade excitation equation can convert in the embodiment of the present invention,
And benchmark dimension number of levels can also increase or reduce as needed.In addition, to each class user in the embodiment of the present invention
Quantity between relation be also not especially limited.
Wherein, in the benchmark dimension grade encourages equation, benchmark dimension grade swashs corresponding to each benchmark dimension grade
At least one of exponential function, linear function, logarithmic function and linear function can be included respectively by encouraging the type of equation.
For example, when having four benchmark dimension grade excitation equations, benchmark dimension grade corresponding to the first estate encourages equation
Type can be exponential function, the type of benchmark dimension grade excitation equation corresponding to the second grade can be linear function,
The type of benchmark dimension grade excitation equation can be benchmark dimension corresponding to logarithmic function and the fourth estate corresponding to the tertiary gradient
The type for spending grade excitation equation can be linear function；When having three benchmark dimension grade excitation equations, the first estate is corresponding
The type of benchmark dimension grade excitation equation can be that linear function, benchmark dimension grade corresponding to the second grade encourage equation
Type can be logarithmic function, the type of benchmark dimension grade excitation equation can be exponential function corresponding to the tertiary gradient.
Specifically, in the benchmark dimension grade encourages equation, benchmark dimension grade corresponding to each benchmark dimension grade
It can be same exponential function to encourage equation.
Specifically, in the benchmark dimension grade encourages equation, benchmark dimension grade corresponding to each benchmark dimension grade
It can also be same linear function to encourage equation.
Fig. 4-Fig. 6 is the schematic diagram of the grade excitation model provided in second embodiment of the invention respectively, such as Fig. 4 and Fig. 5
It is shown, embody grade in these grades excitation model and rise more and more difficult trend, i.e., it is more high-grade corresponding sharp
It is smaller to encourage the factor.Further, since the grade described in Fig. 5 and Fig. 6 encourages each grade excitation equation in model identical, both grades
Excitation model swashs without the benchmark dimension grade that judged can just to select to the benchmark dimension values of user suitable for user
Equation is encouraged, in the case of less demanding to user gradation division, both models can be selected.
Step 23, according to the boundary value of the benchmark dimension values of user and benchmark dimension vector, from the benchmark dimension
Benchmark dimension grade excitation equation of the selection suitable for user in grade excitation equation.
Obtain the benchmark dimension values q of user, and according to the benchmark dimension values q of user and the boundary value of the benchmark dimension to
S is measured, encourages selection in equation to encourage equation suitable for the benchmark dimension grade of user from the benchmark dimension grade.
Step 24, according to the benchmark dimension values of the user and the benchmark dimension grade selected equation is encouraged, calculate and use
The benchmark dimension grade point at family.
Step 25, the benchmark dimension grade point according to the user and default various dimensions weight vectors, calculate user's
Various dimensions grade point.
Step 26, the various dimensions grade point according to the user, it is the user resource allocation.
It should be noted that in second embodiment of the invention, In Grade partition dimension vector, various dimensions weight vectors, base
The particular content of quasi- dimension grade excitation equation and rate range division points vector is not construed as limiting.Carried in the embodiment of the present invention
The resource allocation methods based on grade supplied are applied to different application scenarios.
For example, grade classification dimension vector n={ sales volume, credibility, liveness, loyalty } is preset with, various dimensions power
Weight vector v={ 100%, 110%, 80%, 90% }, rate range division points vector r={ 10,40,60,65 }, and calculate
The boundary value vector s={ 100,300,700,900 } of benchmark dimension.That is dimension on the basis of selection sales volume.Rate range divides
The vectorial r of point represents to mean that primary grade scope exists in [0,10], intermediate rate range in [11,40], advanced tiers scope
[41,60], and super rate range is in [61,65].The boundary value vector s of benchmark dimension represents to limit corresponding to the division points such as each
Volume, the limit as corresponding to the division points of grade 10 is 1,000,000.If the user of certain grade to be divided, its benchmark dimension grade point is 11,
So its various dimensions grade point G={ 11* (100%+110%+80%+90%)/4 } ≈ 10.
The resource allocation methods based on grade provided in second embodiment of the invention, the intelligence of user gradation can be realized
Change and safeguard, so that it is guaranteed that the reasonability of user gradation, for different grades of user resource allocation when, the wave of resource can be reduced
Take, so as to cost-effective.
It is the device embodiment and system embodiment of the embodiment of the present invention below, the inventive method embodiment, device are implemented
Example and system embodiment belong to same design, and the detail content of not detailed description in device embodiment and system embodiment can
To refer to above method embodiment.
3rd embodiment：
Fig. 7 is the structural representation of the resource allocation device based on grade provided in third embodiment of the invention, such as Fig. 7
Shown, the resource allocation device based on grade described in the present embodiment can include：Equation selecting unit 31, for according to user
Benchmark dimension values, from default benchmark dimension grade encourage equation in selection suitable for user benchmark dimension grade excitation side
Journey；Initial grade computing unit 32, for the benchmark dimension values according to the user and the benchmark dimension grade selected excitation
Equation, calculate the benchmark dimension grade point of user；Final rating calculation unit 33, for benchmark dimension according to the user etc.
Level value and default various dimensions weight vectors, calculate the various dimensions grade point of user；Resource allocation unit 34, for according to
The various dimensions grade point of user, it is the user resource allocation.
Wherein, the resource allocation unit specifically can be used for：Determine whether the various dimensions grade point of the user is more than
Preset value, if so, being the user resource allocation；Otherwise, it is not the user resource allocation.
Wherein, final rating calculation unit 33 specifically can be used for：According to equation below, the various dimensions grade of user is calculated
Value G：Wherein, g is the benchmark dimension grade point of user, and v={ v1, v2, v3, v4 ..., vk } is more
Dimension weight vectors, k are the number of dimensions of various dimensions weight vectors.
Wherein, the device can also include：First setting unit, for setting grade classification dimension vectorial, and according to institute
State grade classification dimension vector and the various dimensions weight vectors are set；Second setting unit, for setting the rate range to draw
Benchmark dimension grade described in branch vector sum encourages equation, and the benchmark dimension according to the rate range division points vector sum
Grade encourages equation, calculates the boundary value vector of the benchmark dimension.
Wherein, the grade classification dimension vector n can be：N={ spending amount, the last consumption time, consumption frequency
Rate }, wherein dimension on the basis of spending amount.
Wherein, in the benchmark dimension grade encourages equation, benchmark dimension grade swashs corresponding to each benchmark dimension grade
At least one of exponential function, linear function, logarithmic function and linear function can be included respectively by encouraging the type of equation.
Wherein, in the benchmark dimension grade encourages equation, benchmark dimension grade swashs corresponding to each benchmark dimension grade
It can be same exponential function to encourage equation.
The resource allocation device based on grade provided in third embodiment of the invention, characteristic specific as follows：Use user
Benchmark dimension values calculate user benchmark dimension grade, with reference to various dimensions determine user various dimensions grade, so, grade draw
The comprehensive condition of user can more be embodied by dividing, and formulate rewards and punishments means effectively and have realistic meaning；Made using different excitation factors
Grade classification has suitable variability, inferior grade is quickly excessively arrived greater degree, the rising of each rate range gradually becomes
Difficulty, the intensity of variation of difficulty are embodied by excitation factor, a large number of users can thus be distributed in middle-and-high-ranking, meet statistics rule
Rule；Provide the model criteria and establishment implementation process of a grade classification so that grade classification has model reference and reality
Foundation is applied, model parameter, or even model segment function can be changed according to reality scene so that grade classification closer to reality feelings
Condition；Because this programme has detailed model to establish process and implementation steps so that grade classification can be with intellectually and automatically, no
Artificial interference is needed again.Therefore, the device can realize the intelligent maintenance of user gradation, so that it is guaranteed that user gradation is reasonable
Property, for different grades of user resource allocation when, the waste of resource can be reduced, so as to cost-effective.
The preferred embodiment of the upper only embodiment of the present invention, is not intended to limit the invention embodiment, for ability
For field technique personnel, the embodiment of the present invention can have various changes and change.All spirit and principle in the embodiment of the present invention
Within any modification, equivalent substitution and improvements made etc., should be included within the protection domain of the embodiment of the present invention.
Claims (12)
- A kind of 1. resource allocation methods based on grade, it is characterised in that including：According to the boundary value of the benchmark dimension values of user and the benchmark dimension being previously obtained vector, from default benchmark dimension grade Selection in equation is encouraged to encourage equation suitable for the benchmark dimension grade of user；Equation is encouraged according to the benchmark dimension values of the user and the benchmark dimension grade selected, calculates the benchmark dimension of user Grade point；According to the benchmark dimension grade point of the user and default various dimensions weight vectors, the various dimensions grade of user is calculated Value, wherein, each component in the various dimensions weight vectors represents the proportion shared by each dimension respectively；It is the user resource allocation according to the various dimensions grade point of the user.
- 2. according to the method for claim 1, it is characterised in that be the use according to the various dimensions grade point of the user Resource is distributed at family, including：Determine whether the various dimensions grade point of the user is more than preset value, if so, being the user resource allocation；Otherwise, no For the user resource allocation.
- 3. according to the method for claim 1, it is characterised in that according to the benchmark dimension grade point of the user and default Various dimensions weight vectors, calculating the various dimensions grade point of user includes：According to equation below, the various dimensions grade point G of user is calculated：Wherein, the benchmark that g is user is tieed up Grade point is spent, v={ v1, v2, v3, v4 ..., vk } is various dimensions weight vectors, and k is the number of dimensions of various dimensions weight vectors.
- 4. according to the method for claim 1, it is characterised in that encouraged from default benchmark dimension grade and select to fit in equation Before the benchmark dimension grade excitation equation of user, in addition to：Grade classification dimension vector is set, and the various dimensions weight vectors are set according to grade classification dimension vector；Benchmark dimension grade excitation equation described in rate range division points vector sum is set, and according to the rate range division points Benchmark dimension grade described in vector sum encourages equation, calculates the boundary value vector of the benchmark dimension.
- 5. according to the method for claim 4, it is characterised in that the grade classification dimension vector n=spending amount, most Nearly one-time-consumption time, consuming frequency }, wherein dimension on the basis of spending amount.
- 6. according to the method described in claim any one of 1-5, it is characterised in that encourage equation in the benchmark dimension grade In, the type of benchmark dimension grade excitation equation corresponding to each benchmark dimension grade includes exponential function, linear function, right respectively Number at least one of function and linear function.
- 7. according to the method described in claim any one of 1-5, it is characterised in that encourage equation in the benchmark dimension grade In, benchmark dimension grade excitation equation is same exponential function corresponding to each benchmark dimension grade.
- A kind of 8. resource allocation device based on grade, it is characterised in that including：Equation selecting unit, it is vectorial for the boundary value of the benchmark dimension values according to user and the benchmark dimension being previously obtained, from Benchmark dimension grade excitation equation of the selection suitable for user in default benchmark dimension grade excitation equation；Initial grade computing unit, for the benchmark dimension values according to the user and the benchmark dimension grade excitation side selected Journey, calculate the benchmark dimension grade point of user；Final rating calculation unit, for the benchmark dimension grade point according to the user and default various dimensions weight vectors, The various dimensions grade point of user is calculated, wherein, each component in the various dimensions weight vectors represents each dimension institute respectively The proportion accounted for；Resource allocation unit, it is the user resource allocation for the various dimensions grade point according to the user.
- 9. device according to claim 8, it is characterised in that the resource allocation unit is specifically used for：Determine whether the various dimensions grade point of the user is more than preset value, if so, being the user resource allocation；Otherwise, no For the user resource allocation.
- 10. device according to claim 8, it is characterised in that final rating calculation unit is specifically used for：According to equation below, the various dimensions grade point G of user is calculated：Wherein, the benchmark that g is user is tieed up Grade point is spent, v={ v1, v2, v3, v4 ..., vk } is various dimensions weight vectors, and k is the number of dimensions of various dimensions weight vectors.
- 11. device according to claim 8, it is characterised in that also include：First setting unit, for setting grade classification dimension vectorial, and according to being set grade classification dimension vector Various dimensions weight vectors；Second setting unit, for setting described in rate range division points vector sum benchmark dimension grade to encourage equation, and according to Benchmark dimension grade described in the rate range division points vector sum encourages equation, calculate the boundary value of the benchmark dimension to Amount.
- 12. device according to claim 11, it is characterised in that the grade classification dimension vector n=spending amount, The last consumption time, consuming frequency }, wherein dimension on the basis of spending amount.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410418429.2A CN104156466B (en) | 2014-08-22 | 2014-08-22 | A kind of resource allocation methods and device based on grade |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410418429.2A CN104156466B (en) | 2014-08-22 | 2014-08-22 | A kind of resource allocation methods and device based on grade |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104156466A CN104156466A (en) | 2014-11-19 |
| CN104156466B true CN104156466B (en) | 2017-12-12 |
Family
ID=51881964
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410418429.2A Active CN104156466B (en) | 2014-08-22 | 2014-08-22 | A kind of resource allocation methods and device based on grade |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104156466B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105391758B (en) * | 2015-10-09 | 2019-07-02 | 天脉聚源（北京）教育科技有限公司 | The method and apparatus of resource allocation in a kind of local area network |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6993401B1 (en) * | 2001-11-07 | 2006-01-31 | Autodesk, Inc. | Method and apparatus for simplified determination of a design schedule utilizing computer aided design (CAD) model information |
| CN101477552A (en) * | 2009-02-03 | 2009-07-08 | 辽宁般若网络科技有限公司 | Website user rank division method |
| CN102663101A (en) * | 2012-04-13 | 2012-09-12 | 北京交通大学 | Sina microblog-based user grade sequencing algorithm |
-
2014
- 2014-08-22 CN CN201410418429.2A patent/CN104156466B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6993401B1 (en) * | 2001-11-07 | 2006-01-31 | Autodesk, Inc. | Method and apparatus for simplified determination of a design schedule utilizing computer aided design (CAD) model information |
| CN101477552A (en) * | 2009-02-03 | 2009-07-08 | 辽宁般若网络科技有限公司 | Website user rank division method |
| CN102663101A (en) * | 2012-04-13 | 2012-09-12 | 北京交通大学 | Sina microblog-based user grade sequencing algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104156466A (en) | 2014-11-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kim et al. | A probabilistic approach for determining the control mode in CREAM | |
| Wei et al. | A comparative study of robust efficiency analysis and data envelopment analysis with imprecise data | |
| Hosoda et al. | A unified theory of the dynamics of closed-loop supply chains | |
| Hashemi et al. | Ant-colony optimization of pumping schedule to minimize the energy cost using variable-speed pumps in water distribution networks | |
| CN108833458B (en) | Application recommendation method, device, medium and equipment | |
| Lahdelma et al. | Reference point approach for multiple decision makers | |
| CN106875027A (en) | The Forecasting Methodology and device of resource request value, the Forecasting Methodology of trading volume | |
| CN109583468A (en) | Training sample acquisition methods, sample predictions method and corresponding intrument | |
| CN106204087A (en) | For the method and apparatus selecting advertising media | |
| CN106846071A (en) | Data processing method and device | |
| CN108268534A (en) | Propagating influence computational methods and device | |
| Dauvin et al. | Estimating broadband diffusion in the EU using NUTS 1 regional data | |
| Varma et al. | Marketing resource allocation in duopolies over social networks | |
| CN115759602A (en) | Method, device and medium for adjusting scheduling | |
| CN104156466B (en) | A kind of resource allocation methods and device based on grade | |
| CN105096161B (en) | It is a kind of enter row information displaying method and apparatus | |
| Linss et al. | The ADVIAN® classification—A new classification approach for the rating of impact factors | |
| CN112001786B (en) | Method and device for configuring credit card limit of customer based on knowledge graph | |
| CN107909500A (en) | Information exchange method and electronic equipment | |
| CN108847956B (en) | Multi-dimensional intelligent capacity expansion and contraction method and system for telecommunication network security service VNF | |
| Pentapalli | A comparative study of Roth-Erev and modified Roth-Erev reinforcement learning algorithms for uniform-price double auctions | |
| CN110069708A (en) | A kind of promotion effect predictor method, device, medium and equipment promoted across medium | |
| CN109960572A (en) | Equipment resource management method and device and intelligent terminal | |
| CN115185606A (en) | Method, device, equipment and storage medium for obtaining service configuration parameters | |
| CN107733846A (en) | A kind of method and device of distributing user permission |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20191125 Address after: 100176 room 222, 2f, building C, No. 18, Kechuang 11th Street, Beijing Economic and Technological Development Zone, Daxing District, Beijing Patentee after: Beijing Jingdong three hundred and sixty degree e-commerce Co., Ltd. Address before: 100080 Beijing city Haidian District xingshikou Road No. 65 building 11C Creative Park West West west Shan East 1-4 layer 1-4 layer Patentee before: Beijing Jingdong Shangke Information Technology Co., Ltd. |
|
| TR01 | Transfer of patent right |