CN109726233A - For portraying the method, computer system and readable medium of user image - Google Patents
For portraying the method, computer system and readable medium of user image Download PDFInfo
- Publication number
- CN109726233A CN109726233A CN201811654292.5A CN201811654292A CN109726233A CN 109726233 A CN109726233 A CN 109726233A CN 201811654292 A CN201811654292 A CN 201811654292A CN 109726233 A CN109726233 A CN 109726233A
- Authority
- CN
- China
- Prior art keywords
- multidimensional
- user
- index
- data
- portraying
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
This application provides a kind of for portraying the method, computer system and readable medium of user image.This method comprises: being based on user data, the multidimensional index for characterizing the feature of user is determined；The multidimensional index is quantified using Principal Component Analysis, and dimensionality reduction fusion is carried out to the multidimensional index after quantization using logistic regression analysis method, to form quantitative multidimensional label；And clustering processing is carried out to the multidimensional label, to establish the multidimensional model for portraying user image.
Description
Technical field
The present invention relates to the methods, computer system and readable medium for portraying user image.
Background technique
In order to portray user image, traditional statistical model generally uses " it is assumed that-simulation-prediction " this confirmation property data
Analysis method, it is difficult to use ever-changing objective world, can not really find the Inherent relation and regularity of data.When will be above-mentioned
When confirmation property data analysing method is applied to higher-dimension, non-linear, non-normal data prediction modeling, it more difficult to the effect having had
Fruit.
Summary of the invention
According to the one aspect of the application, a kind of method for portraying user image is provided, comprising: be based on number of users
According to determining the multidimensional index for characterizing the feature of user；The multidimensional index is quantified using Principal Component Analysis, and
And dimensionality reduction fusion is carried out to the multidimensional index after quantization using logistic regression analysis method, to form quantitative multidimensional label；And
Clustering processing is carried out to the multidimensional label, to establish the multidimensional model for portraying user image.
According to some embodiments, the multidimensional index quantify using Principal Component Analysis and utilizes logistic regression
It includes: using described more that analytic approach, which carries out dimensionality reduction fusion to the multidimensional index after quantization to be formed the step of quantitative multidimensional label,
It ties up index and forms original multi-dimensional index matrix, and the original multi-dimensional index matrix is standardized, to be standardized
Multidimensional index matrix；The related coefficient in the standardization multidimensional index matrix between corresponding multidimensional index is calculated, to obtain phase
Relationship matrix number；Calculate the characteristic value and feature vector of the correlation matrix；Utilize the standardization multidimensional index matrix
With the described eigenvector of the correlation matrix, principal component scores are calculated；And to the principal component scores application logic
The Return Law is to form quantitative multidimensional label.
According to some embodiments of the present application, determined based on user data the multidimensional index for characterizing user characteristics it
Before, the method also includes: the user data is obtained from multiple sources；And the user data is pre-processed.
According to some embodiments of the present application, the user is tourist, and the user data is multidimensional tourism data, described
Multiple sources include one of the following terms or more: tourist attraction data source, tourism industry data source, public security lodging number
According to source, Unionpay's consumption data source, telecom operators' data source, internet data source.
According to some embodiments of the present application, the multidimensional index includes user basic information index and user behavior data
One of index or more.
According to some embodiments of the present application, clustering processing is carried out to establish for portraying user's shape to the multidimensional label
The step of multidimensional model of elephant includes: to optimize adjustment to the parameter of the multidimensional model using new user data.
According to some embodiments of the present application, clustering processing is carried out to establish for portraying user's shape in the multidimensional label
After the multidimensional model of elephant, the method also includes: it is for statistical analysis to the user image using statistical analysis template.
According to some embodiments of the present application, the method also includes: the result of the statistical analysis is shown as visually
Change figure or chart；Or using the statistical analysis as a result, precisely being recommended to user.
According to a second aspect of the present application, a kind of computer system is provided, comprising: one or more processors；With
And one or more memories, it is configured as storage series of computation machine executable instruction, wherein the series of computation machine
Executable instruction makes one or more processor execute basis when being run by one or more processor
Aforementioned described in any item methods.
According to the third aspect of the application, a kind of non-transient computer-readable medium is provided, calculating is stored thereon with
Machine executable instruction, the computer executable instructions make one or more when being run by one or more processors
Multiple processors are executed according to aforementioned described in any item methods.
According to some embodiments of the present application, user image can be more accurately portrayed.
According to being described below referring to attached drawing, other property features of the invention and advantage be will become apparent.
Detailed description of the invention
Included attached drawing for explanatory purposes, and is merely provided for invention disclosed herein device and incites somebody to action
It is applied to the example for calculating the possibility construction and arrangement of method of equipment.These attached drawings are never limited in those skilled in the art
Embodiment can be carried out under the premise of not departing from the spirit and scope of embodiment any in terms of form and details
Change.The embodiment will become apparent to by specific descriptions with reference to the accompanying drawing, wherein similar appended drawing reference table
Show similar structural detail.
Fig. 1 is the process for schematically showing the process for portraying user image according to some embodiments of the present application
Figure.
Fig. 2 is the process for being used to form quantitative multidimensional label schematically shown according to some embodiments of the present application
Flow chart.
Fig. 3 is the process for schematically showing the process for portraying user image according to some embodiments of the present application
Figure.
Fig. 4 is schematically shown according to some embodiments of the present application for obtaining the process of user data from source
Flow chart.
Fig. 5 is schematically shown according to some embodiments of the present application for carrying out pretreated mistake to user data
The flow chart of journey.
Fig. 6 is schematically shown according to some embodiments of the present application for optimizing to the parameter of multidimensional model
The flow chart of the process of adjustment.
Fig. 7 is the process for schematically showing the process for portraying user image according to some embodiments of the present application
Figure.
Fig. 8 is schematically shown according to some embodiments of the present application for analyzing and counting to user image
The flow chart of process.
Fig. 9 is to show the letter that can be used for implementing the method for portraying user image according to some embodiments of the present application
Cease the schematic block diagram of processing equipment.
Specific embodiment
The representative applications of the device and method according to embodiment described herein are provided in this part.These are provided
Example is merely to adding context and helping to understand the embodiment.For those skilled in the art therefore will it is aobvious and
It is clear to, embodiment of the present invention can be real in the case where not having some or all of these details
It applies.In other cases, it is not described in detail well known processing step, to avoid unnecessarily obscuring implementation of the present invention
Scheme.Other application be also it is possible so that following example be not construed as it is restrictive.
Fig. 1 is schematically shown according to some embodiments of the present application for portraying the process 100 of user image
Flow chart.
As shown in fig. 1, in step s101, it can be based on user data, determine the more of the feature for characterizing user
Tie up index.
According to some embodiments of the present application, multidimensional index may include user basic information index and user behavior data
One of index or more.Note that multidimensional index is not limited to above-mentioned items.
For example, user basic information index may include one of the following terms or more: (1) gender；(2) year
Age；(3) marital status；(4) academic；(5) income level etc..Note that user basic information index is not limited to above-mentioned items.
For example, user behavior data index may include one of the following terms or more: (1) food and drink consumption gold
Volume；(2) food price；(3) number is consumed；(4) lodging consumption price；(5) lodging spending amount；(6) lodging hotel class；
(7) guest room number；(8) room occupancy rate；(9) traffic spending amount；(10) traffic route；(11) type of vehicle；
(12) scenic spot visit consumption；(13) scenic spot ticketing service price；(14) mode is gone sight-seeing；(15) the purchase and consumption amount of money；(16) shopping type；
(17) shopping place；(18) entertainment spending amount；(19) place etc. is consumed.Note that user behavior data index is not limited to
Above-mentioned items.
After step slol, step S103 is proceeded to for portraying the process 100 of user image.In step s 103,
It can use Principal Component Analysis to quantify the multidimensional index, and using logistic regression analysis method to more after quantization
It ties up index and carries out dimensionality reduction fusion, to form quantitative multidimensional label.
The process for being used to form quantitative multidimensional label is described in detail below with reference to Fig. 2.Fig. 2 is to schematically show root
According to the flow chart of the process 200 for being used to form quantitative multidimensional label of some embodiments of the present application.
As shown in Figure 2, in step s 201, it can use the multidimensional index and form original multi-dimensional index matrix, and
And the original multi-dimensional index matrix is standardized, to obtain standardization multidimensional index matrix.
For example, can use multidimensional index forms original multi-dimensional index matrix X shown in following formula (1):
X=[xnp] formula (1)
Wherein, n is line number, and p is row number, and n and p are the natural number more than or equal to 1.
Above-mentioned original multi-dimensional index matrix X is standardized for example, can use following data-standardizing formula (2),
To obtain standardizing multidimensional index matrix Z shown in following formula (3):
Z=[Znp] formula (3)
Wherein, XijIndicate the original multi-dimensional index of the i-th row jth column in original multi-dimensional index matrix X,Indicate original more
Tie up the average value of whole original multi-dimensional indexs of jth column in index matrix X, SjIndicate jth column in original multi-dimensional index matrix X
The summation of whole original multi-dimensional indexs.ZijIndicate the standardization multidimensional index of the i-th row jth column in standardization multidimensional index matrix Z.
I and j is greater than or equal to 1 natural number, and i is less than or equal to n, and j is less than or equal to p.
After step S201, the process 200 for being used to form quantitative multidimensional label proceeds to step S203.In step
In S203, the related coefficient in the standardization multidimensional index matrix between corresponding multidimensional index can be calculated, to obtain correlation
Coefficient matrix.
For example, can be using following formula (4) come between multidimensional index corresponding in normalized multidimensional index matrix
Related coefficient, to obtain correlation matrix R:
Wherein, Z and Z, respectively standardization multidimensional index matrix, n are the line number for standardizing multidimensional index matrix Z and Z '.
After step S203, the process 200 for being used to form quantitative multidimensional label proceeds to step S205.In step
In S205, the characteristic value and feature vector of the correlation matrix can be calculated.
For example, the p eigenvalue λ of above-mentioned correlation matrix R can be calculated1To λp, and can be according to from small to large
Sequence is arranged as following formula (5):
λ1≥λ2≥…λp>=0 formula (5)
Furthermore it is possible to calculate above-mentioned p eigenvalue λ1To λpFeature vector ti, such as shown in following formula (6):
ti=(tLi,t2i..., tpi) formula (6)
After step S205, the process 200 for being used to form quantitative multidimensional label proceeds to step S207.In step
In S207, it can use the described eigenvector of standardization the multidimensional index matrix and the correlation matrix, calculate master
Component score.
For example, all principal components can not be chosen when choosing principal component, but several principal components before can choosing,
So that the variance contribution ratio of several preceding principal components reaches 70% or more.For example, it is assumed that FiFor extracted i-th it is main at
Get point, then FiIt may be expressed as following formula (7):
Fi=Zij×tiFormula (7)
Wherein, ZijFor the standardization multidimensional index of the i-th row jth column in standardization multidimensional index matrix, tiFor p characteristic value
λ1To λpFeature vector.
After step S207, the process 200 for being used to form quantitative multidimensional label proceeds to step S209.In step
In S209, quantitative multidimensional label can be formed to the principal component scores application logistic regression.
For example, can use Logic Regression Models shown in following formula (8) to form quantitative multidimensional label pi:
Wherein, ziIt may be expressed as following formula (9):
Wherein, FijFor the variation of user's dimensional labels evaluation, β0, βjAnd εiFor predetermined constant, βj(j=0,1,2 ...
M), m is the natural number more than or equal to 1.
The S-type distribution of coefficient object of p, and p is increasing function, and the value range of p is P ∈ (0,1).
For example, (10) the correlation y between multidimensional label and user image can be calculated according to the following formula:
Wherein, for each dimension i (i=1,2 ... n), if yi is approximately equal to 0, then it represents that the label of the dimension is to user
The influence of image is weaker, that is to say, that the correlation between the label of the dimension and user image is poor；If yiIt is approximately equal to 1, then
Indicate that influence of the label of the dimension to user image is stronger, that is to say, that related between the label of the dimension and user image
Property is preferable.
After step S209, the process 200 for being used to form quantitative multidimensional label can terminate.
According to some embodiments of the present application, quantitative multidimensional label storage can will be formed by user behavior rule
In library, so as to the sample database called and learnt as subsequent algorithm model.Early period can grade according to expert and audit is discussed
It stores some user behavior rules as initial rule of conduct into user behavior rule base, the later period can be according to autonomous learning
Corresponding user behavior rule is enriched and added to algorithm constantly.
Referring back to Fig. 1, after step s 103, the process 100 for portraying user image proceeds to step S105.?
In step S105, clustering processing can be carried out to the multidimensional label, to establish the multidimensional model for portraying user image.
For example, clustering processing can be carried out to multidimensional label using K mean value (K-means) algorithm, to establish for portraying
The multidimensional model of user image.Note that other than K mean value (K-means) algorithm, can also using it is known in the art other
Clustering algorithm, the application are not particularly limited this.
After step S105, the process 100 for portraying user image can terminate.
It is described below with reference to Fig. 3 according to some embodiments of the present application for portraying the process 300 of user image.Figure
3 be the flow chart for schematically showing the process 300 for portraying user image according to some embodiments of the present application.
As shown in figure 3, in step S301 the user data can be obtained from multiple sources.
According to some embodiments of the present application, the user can be tourist, and the user data can travel for multidimensional
Data, the multiple source may include one of the following terms or more: tourist attraction data source, tourism industry data
Source, public security lodging data source, Unionpay's consumption data source, telecom operators' data source, internet data source etc..
It is described below with reference to Fig. 4 according to some embodiments of the present application for obtaining the process of user data from source
400.Fig. 4 is schematically shown according to some embodiments of the present application for obtaining the process 400 of user data from source
Flow chart.
As shown in Figure 4, in step S401, it can collect and analyze business demand.
After step S401, the process 400 for obtaining user data from source may be advanced to step S403.In step
, can be with design objective and Meta data system in rapid S403, and it can be associated with unified index by various businesses term.
After step S403, the process 400 for obtaining user data from source may be advanced to step S405.In step
It, can be with design data resource hierarchy in rapid S405.
After step S405, the process 400 for obtaining user data from source may be advanced to step S407.In step
In rapid S407, data management can be carried out.
After step S407, the process 400 for obtaining user data from source can terminate.
Referring back to Fig. 3, after step S301, the process 300 for portraying user image proceeds to step S303.?
In step S303, the user data can be pre-processed.
According to some embodiments of the present application, the pretreatment may include being cleaned, being converted to user data, integrated
Etc. processes, to realize the consistency of data format, uniqueness and completeness.
It is described below with reference to Fig. 5 according to some embodiments of the present application for carrying out pretreated mistake to user data
Journey 500.Fig. 5 is schematically shown according to some embodiments of the present application for carrying out pretreated process to user data
500 flow chart.
As described in Figure 5, in step S501, data convergence task can be created.
After step S501, step S503 is proceeded to for carrying out pretreated process 500 to user data.In step
In S503, it can be determined that whether the data to be converged are normal data.
If judging that the data to be converged are normal datas in step S503, for being located in advance to user data
The process 500 of reason proceeds to step S505.In step S505, standard interface docking can be carried out to normal data.In step
After S505, it can terminate for carrying out pretreated process 500 to user data.
It is pre- for being carried out to user data if judging that the data to be converged are not normal datas in step S503
The process 500 of processing proceeds to step S507.In step s 507, nonstandard numbers evidence can be imported.
After step S507, step S509 is proceeded to for carrying out pretreated process 500 to user data.In step
It, can be to the nonstandard numbers imported according to progress data audit in S509.
After step S509, step S511 is proceeded to for carrying out pretreated process 500 to user data.In step
In S511, it can be determined that whether data are correct.
If judging that data are correctly, for carrying out pretreated process 500 to user data in step S511
It can terminate.
If judging data in step S511 not is correctly, for carrying out pretreated process to user data
500 proceed to step S513.In step S513, data point reuse can be carried out.
After step S513, it may return to above-mentioned steps for carrying out pretreated process 500 to user data
S517。
Referring back to Fig. 3, after step S303, the process 300 for portraying user image proceeds to step S305.?
In step S305, it can be based on user data, determine the multidimensional index for characterizing the feature of user.Note that step S305
Concrete operations can be identical as the step S101 in Fig. 1, and particular content repeats no more.
After step S305, the process 300 for portraying user image proceeds to step S307.In step S307,
It can use Principal Component Analysis to quantify the multidimensional index, and using logistic regression analysis method to more after quantization
It ties up index and carries out dimensionality reduction fusion, to form quantitative multidimensional label.Note that the concrete operations of step S307 can in Fig. 1
Step S103 is identical, and particular content repeats no more.
After step S307, the process 300 for portraying user image proceeds to step S309.In step S309,
Clustering processing can be carried out to the multidimensional label, to establish the multidimensional model for portraying user image.Note that step S309
Concrete operations can be identical as the step S105 in Fig. 1, particular content repeats no more.
It is described below with reference to Fig. 6 according to some embodiments of the present application for being optimized to the parameter of multidimensional model
The process 600 of adjustment.Fig. 6 be schematically show according to some embodiments of the present application for the parameter to multidimensional model into
The flow chart for the process 600 that row is optimized and revised.
As shown in Figure 6, in step s 601, can use new user data, to the parameter of the multidimensional model into
Row is optimized and revised.
After step S601, the process 600 for optimizing adjustment for the parameter to multidimensional model can terminate.
It is described below with reference to Fig. 7 according to some embodiments of the present application for portraying the process 700 of user image.Figure
7 be the flow chart for schematically showing the process 700 for portraying user image according to some embodiments of the present application.
As shown in Figure 7, in step s 701, it can be based on user data, determine the more of the feature for characterizing user
Tie up index.Note that the concrete operations of step S701 can be identical as the step S101 in Fig. 1, details are not described herein.
After step S701, the process 700 for portraying user image proceeds to step S703.In step S703,
It can use Principal Component Analysis to quantify the multidimensional index, and using logistic regression analysis method to more after quantization
It ties up index and carries out dimensionality reduction fusion, to form quantitative multidimensional label.Note that the concrete operations of step S703 can in Fig. 1
Step S103 is identical, and details are not described herein.
After step S703, the process 700 for portraying user image proceeds to step S705.In step S705,
Clustering processing can be carried out to the multidimensional label, to establish the multidimensional model for portraying user image.Note that step S705
Concrete operations can be identical as the step S105 in Fig. 1, details are not described herein.
After step S705, the process 700 for portraying user image proceeds to step S707.In step S707,
It is for statistical analysis to the user image to can use statistical analysis template.
After step S707, the process 700 for portraying user image may be advanced to step S709 or step S711.
In step S709, the result of the statistical analysis can be shown as visualized graphs or chart.It, can be in step S711
Using the statistical analysis as a result, precisely being recommended to user.
After step S709 or step S711, the process 700 for portraying user image can terminate.
It describes below with reference to Fig. 8 according to some embodiments of the present application for being analyzed and counted to user image
Process 800.Fig. 8 is schematically shown according to some embodiments of the present application for analyzing and counting to user image
The flow chart of process 800.
As shown in Figure 8, in step S801, analysis modeling can be carried out to application.
After step S801, the process 800 for analyzing and counting to user image proceeds to step S803.In step
In rapid S803, data can be extracted, be converted, load etc. and handled.
After step S803, the process 800 for analyzing and counting to user image proceeds to step S805.In step
In rapid S805, data analysis result can be obtained.
After step S805, the process 800 for analyzing and counting to user image can terminate.
According to some embodiments of the present application, can more accurately be portrayed by the analysis of user's big data to multidimensional
User image.
According to some embodiments of the present application, the technical solution of the application can be applied to tour field.Using being carved
The more accurately user image drawn can provide to the user of such as tourist etc and more accurately recommend, so as to more preferable
Ground meets tourist market and the diversification and personalized demand of tourist.
Fig. 9 is to show the letter that can be used for implementing the method for portraying user image according to some embodiments of the present application
Cease the schematic block diagram of processing equipment.
In Fig. 9, central processing unit (CPU) 901 is according to the program stored in read-only memory (ROM) 902 or from depositing
The program that storage part 908 is loaded into random access memory (RAM) 903 executes various processing.In RAM 903, also according to need
Store the data required when CPU 901 executes various processing etc..CPU 901, ROM 902 and RAM 903 are via bus
904 are connected to each other.Input/output interface 905 is also connected to bus 904.
Components described below is connected to input/output interface 905: importation 906 (including keyboard, mouse etc.), output section
Divide 907 (including display, such as cathode-ray tube (CRT), liquid crystal display (LCD) etc. and loudspeakers etc.), storage section
908 (including hard disks etc.), communications portion 909 (including network interface card such as LAN card, modem etc.).Communications portion 909
Communication process is executed via network such as internet.As needed, driver 910 can be connected to input/output interface 905.
Detachable media 911 such as disk, CD, magneto-optic disk, semiconductor memory etc. is installed in driver 910 as needed
On, so that the computer program read out is mounted to as needed in storage section 908.
It is such as removable from network such as internet or storage medium in the case where series of processes above-mentioned by software realization
Unload the program that the installation of medium 911 constitutes software.
It will be understood by those of skill in the art that this storage medium be not limited to it is shown in Fig. 9 be wherein stored with program,
Separately distribute with equipment to provide a user the detachable media 911 of program.The example of detachable media 911 includes disk
(including floppy disk (registered trademark)), CD (including compact disc read-only memory (CD-ROM) and digital versatile disc (DVD)), magneto-optic disk
(including mini-disk (MD) (registered trademark)) and semiconductor memory.Alternatively, storage medium can be ROM 902, storage section
Hard disk for including in 908 etc., wherein computer program stored, and user is distributed to together with the equipment comprising them.
When described instruction code is read and executed by machine, the above-mentioned method according to the embodiment of the present application can be performed.
It can be write with any combination of one or more programming languages for executing the application various aspects
The computer program code of operation, described program design language include object oriented program language-such as Java,
Smalltalk, C++, python etc. further include conventional procedural programming language one such as " C " language or similar journey
Sequence design language.Program code can be executed fully on the user computer, partly be executed on the user computer, conduct
One independent software package executes, part executes on the remote computer or completely long-range on the user computer for part
It is executed on computer or server.In situations involving remote computers, remote computer can pass through the net of any kind
Network --- it is connected to subscriber computer including local area network (LAN) or wide area network (WAN)-, or, it may be connected to outside calculates
Machine (such as being connected using ISP by internet).
It should be appreciated that the combination of each box in each box and flowchart and or block diagram of flowchart and or block diagram,
It can be realized by computer program instructions.These computer program instructions can be supplied to general purpose computer, special purpose computer
Or the processor of other programmable data processing units, so that a kind of machine is produced, so that these computer program instructions exist
When being executed by computer or the processor of other programmable data processing units, produce in implementation flow chart and/or block diagram
One or more boxes specified in function action device.
Can also these computer program instructions store in computer-readable medium, these instruct so that computer,
Other programmable data processing units or other equipment work in a specific way, thus, it stores in computer-readable medium
Instruction just produces the instruction including function action specified in one or more boxes in implementation flow chart and/or block diagram
Manufacture (article of manufacture).
Computer program instructions can also be loaded into computer, other programmable data processing units or other equipment
On, so that series of operation steps are executed in computer, other programmable data processing units or other equipment, in terms of generating
The process that calculation machine is realized, so that the instruction executed on a computer or other programmable device is capable of providing implementation flow chart
And/or function/operation process specified in the box in block diagram.
The flow chart and block diagram in the drawings show system, method and the computer journeys according to multiple embodiments of the application
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, section or code of table, a part of the module, section or code include one or more use
The executable instruction of the logic function as defined in realizing.It should also be noted that in some implementations as replacements, being marked in box
The function of note can also occur in a different order than that indicated in the drawings.For example, two continuous boxes can actually base
Originally it is performed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.It is also noted that
It is the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart, can uses and execute rule
The dedicated hardware based system of fixed function or movement is realized, or can use the group of specialized hardware and computer instruction
It closes to realize.
Note that not describing some details known in the field in order to avoid covering the design of the application.This field skill
Art personnel as described above, completely it can be appreciated how implementing technical solution disclosed herein.
Claims (10)
1. a kind of method for portraying user image, comprising:
Based on user data, the multidimensional index for characterizing the feature of user is determined；
The multidimensional index is quantified using Principal Component Analysis, and using logistic regression analysis method to more after quantization
It ties up index and carries out dimensionality reduction fusion, to form quantitative multidimensional label；And
Clustering processing is carried out to the multidimensional label, to establish the multidimensional model for portraying user image.
2. according to the method described in claim 1, wherein, using Principal Component Analysis to the multidimensional index carry out quantization and
The step of dimensionality reduction is merged to form quantitative multidimensional label packet is carried out to the multidimensional index after quantization using logistic regression analysis method
It includes:
Original multi-dimensional index matrix is formed using the multidimensional index, and standard is carried out to the original multi-dimensional index matrix
Change, to obtain standardization multidimensional index matrix；
The related coefficient in the standardization multidimensional index matrix between corresponding multidimensional index is calculated, to obtain related coefficient square
Battle array；
Calculate the characteristic value and feature vector of the correlation matrix；
Using the described eigenvector of standardization the multidimensional index matrix and the correlation matrix, calculates principal component and obtain
Point；And
Quantitative multidimensional label is formed to the principal component scores application logistic regression.
3. according to the method described in claim 1, wherein, referring to being determined based on user data for characterizing the multidimensional of user characteristics
Before mark, the method also includes:
The user data is obtained from multiple sources；And
The user data is pre-processed.
4. according to the method described in claim 3, wherein, the user is tourist, the user data is multidimensional tourism data,
The multiple source includes one of the following terms or more: tourist attraction data source, tourism industry data source, public security are lived
Place data source, Unionpay's consumption data source, telecom operators' data source, internet data source.
5. according to the method described in claim 1, wherein,
The multidimensional index includes one of user basic information index and user behavior data index or more.
6. according to the method described in claim 1, wherein, carrying out clustering processing to the multidimensional label to establish for portraying use
The step of multidimensional model of family image includes:
Using new user data, adjustment is optimized to the parameter of the multidimensional model.
7. according to the method described in claim 1, wherein, carrying out clustering processing in the multidimensional label to establish for portraying use
After the multidimensional model of family image, the method also includes:
It is for statistical analysis to the user image using statistical analysis template.
8. according to the method described in claim 7, further include:
The result of the statistical analysis is shown as visualized graphs or chart；Or
Using the statistical analysis as a result, precisely being recommended to user.
9. a kind of computer system, comprising:
One or more processors；And
One or more memories are configured as storage series of computation machine executable instruction,
Wherein the series of computation machine executable instruction makes described one when being run by one or more processor
A or more processor executes method described in any one of -8 according to claim 1.
10. a kind of non-transient computer-readable medium, is stored thereon with computer executable instructions, the computer is executable
Instruction makes one or more processor execute according to claim 1-8 when being run by one or more processors
Any one of described in method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811654292.5A CN109726233A (en) | 2018-12-28 | 2018-12-28 | For portraying the method, computer system and readable medium of user image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811654292.5A CN109726233A (en) | 2018-12-28 | 2018-12-28 | For portraying the method, computer system and readable medium of user image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109726233A true CN109726233A (en) | 2019-05-07 |
Family
ID=66299570
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811654292.5A Pending CN109726233A (en) | 2018-12-28 | 2018-12-28 | For portraying the method, computer system and readable medium of user image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109726233A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112508439A (en) * | 2020-12-18 | 2021-03-16 | 威海天鑫现代服务技术研究院有限公司 | Data analysis method, system, computer equipment and storage medium |
| CN111861174B (en) * | 2020-07-09 | 2021-04-13 | 北京睿知图远科技有限公司 | Credit assessment method for user portrait |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7069258B1 (en) * | 2002-09-26 | 2006-06-27 | Bothwell Phillip D | Weather prediction method for forecasting selected events |
| CN102654860A (en) * | 2011-03-01 | 2012-09-05 | 北京彩云在线技术开发有限公司 | Personalized music recommendation method and system |
| CN103744928A (en) * | 2013-12-30 | 2014-04-23 | 北京理工大学 | Network video classification method based on historical access records |
| CN105095477A (en) * | 2015-08-12 | 2015-11-25 | 华南理工大学 | Recommendation algorithm based on multi-index grading |
| CN109063931A (en) * | 2018-09-06 | 2018-12-21 | 盈盈（杭州）网络技术有限公司 | A kind of model method for predicting freight logistics driver Default Probability |
-
2018
- 2018-12-28 CN CN201811654292.5A patent/CN109726233A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7069258B1 (en) * | 2002-09-26 | 2006-06-27 | Bothwell Phillip D | Weather prediction method for forecasting selected events |
| CN102654860A (en) * | 2011-03-01 | 2012-09-05 | 北京彩云在线技术开发有限公司 | Personalized music recommendation method and system |
| CN103744928A (en) * | 2013-12-30 | 2014-04-23 | 北京理工大学 | Network video classification method based on historical access records |
| CN105095477A (en) * | 2015-08-12 | 2015-11-25 | 华南理工大学 | Recommendation algorithm based on multi-index grading |
| CN109063931A (en) * | 2018-09-06 | 2018-12-21 | 盈盈（杭州）网络技术有限公司 | A kind of model method for predicting freight logistics driver Default Probability |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111861174B (en) * | 2020-07-09 | 2021-04-13 | 北京睿知图远科技有限公司 | Credit assessment method for user portrait |
| CN112508439A (en) * | 2020-12-18 | 2021-03-16 | 威海天鑫现代服务技术研究院有限公司 | Data analysis method, system, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Shmueli et al. | Data mining for business analytics: concepts, techniques and applications in Python | |
| US9098564B2 (en) | Domain-specific syntactic tagging in a functional information system | |
| CN113822494A (en) | Risk prediction method, device, equipment and storage medium | |
| US8712955B2 (en) | Optimizing federated and ETL'd databases with considerations of specialized data structures within an environment having multidimensional constraint | |
| Viallard et al. | Assessing the evolution of transit user behavior from smart card data | |
| US11367117B1 (en) | Artificial intelligence system for generating network-accessible recommendations with explanatory metadata | |
| US20210357699A1 (en) | Data quality assessment for data analytics | |
| CN109726233A (en) | For portraying the method, computer system and readable medium of user image | |
| Shmueli et al. | Machine learning for business analytics: Concepts, techniques, and applications with analytic solver data mining | |
| Matseliukh et al. | Development of Intelligent System for Visual Passenger Flows Simulation of Public Transport in Smart City Based on Neural Network. | |
| Akande et al. | Application of XGBoost Algorithm for Sales Forecasting Using Walmart Dataset | |
| Peng et al. | Bank financial risk prediction model based on big data | |
| Alsawan et al. | The application of artificial intelligence in real estate valuation: a systematic review | |
| CN111930944B (en) | File label classification method and device | |
| Poornima et al. | Prediction of water consumption using machine learning algorithm | |
| US11809375B2 (en) | Multi-dimensional data labeling | |
| Lugert | Creating a digital twin to the online promotion process for small businesses | |
| Chaitongrat et al. | Comparing data mining methods for predicting cost construction projects: A case study of cost management datasets from Thailand | |
| Bhuvaneswari et al. | Predicting periodical sales of products using a machine learning algorithm | |
| Behera et al. | Predictive loan approval model using logistic regression | |
| Çelikbilek et al. | Multi-criteria Assessment of Sustainability for Energy Systems Under Uncertainty: Grey-Based Approach | |
| CN118260347B (en) | Data acquisition and analysis method and system based on artificial intelligence | |
| Chen et al. | Performance Evaluation of Data Mining Technologies: An Example of ERP System Adoption | |
| Arbenina | Spatial data mining and machine learning techniques to understand cross-border relocations of headquarters in Europe | |
| Gniewkowski et al. | Assessment of document similarity visualisation methods |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |