CN109978411A - A kind of communications and transportation development index building model - Google Patents
A kind of communications and transportation development index building model Download PDFInfo
- Publication number
- CN109978411A CN109978411A CN201910283943.2A CN201910283943A CN109978411A CN 109978411 A CN109978411 A CN 109978411A CN 201910283943 A CN201910283943 A CN 201910283943A CN 109978411 A CN109978411 A CN 109978411A
- Authority
- CN
- China
- Prior art keywords
- index
- transportation
- communications
- development
- unification
- 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
- 238000011161 development Methods 0.000 title claims abstract description 76
- 238000004891 communication Methods 0.000 title claims abstract description 73
- 238000012216 screening Methods 0.000 claims abstract description 23
- 238000004458 analytical method Methods 0.000 claims abstract description 14
- 238000000034 method Methods 0.000 claims description 135
- 238000004364 calculation method Methods 0.000 claims description 47
- 238000011156 evaluation Methods 0.000 claims description 33
- 239000011159 matrix material Substances 0.000 claims description 25
- 238000009826 distribution Methods 0.000 claims description 24
- 238000012545 processing Methods 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 13
- 238000010219 correlation analysis Methods 0.000 claims description 12
- 230000008859 change Effects 0.000 claims description 8
- 238000011160 research Methods 0.000 claims description 7
- 238000004519 manufacturing process Methods 0.000 claims description 6
- 238000000513 principal component analysis Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 5
- 230000008901 benefit Effects 0.000 claims description 4
- LVTKHGUGBGNBPL-UHFFFAOYSA-N Trp-P-1 Chemical compound N1C2=CC=CC=C2C2=C1C(C)=C(N)N=C2C LVTKHGUGBGNBPL-UHFFFAOYSA-N 0.000 claims description 3
- 238000011835 investigation Methods 0.000 claims description 3
- 238000003672 processing method Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 241000406668 Loxodonta cyclotis Species 0.000 claims 1
- 238000013139 quantization Methods 0.000 abstract description 5
- 230000001105 regulatory effect Effects 0.000 abstract description 4
- 230000004075 alteration Effects 0.000 description 2
- 238000000265 homogenisation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000000611 regression analysis Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- Mathematical Physics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Computational Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Computing Systems (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Algebra (AREA)
- Primary Health Care (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of communications and transportation development indexes to construct model, belong to technical field of traffic transportation, include the following steps: the building of (1) communications and transportation index index system, includes four steps in the building of communications and transportation index index system: the essential analysis of step A communications and transportation development；Step B preliminary index selection；Step C index screening；Whether step D judge index system is perfect；(2) criterion, criterionization include three steps: step A index unification and step B achievement data nondimensionalization, step C Index Weights；(3) determination of index weights；(4) determination of communications and transportation development index building model.The present invention is by calculating communications and transportation development index, it can effectively reflect interregional Transportation Development Level and communications and transportation Green Development degree, quantization reference, power-assisted Transportation Sustainable Development are provided for Industry regulatory bodies policies, development Analysis of Policy Making.
Description
Technical field
The present invention relates to technical field of traffic transportation more particularly to a kind of communications and transportation development index to construct model.
Background technique
The sustainable development of communications and transportation, it is necessary to be that the sustainable development of transportation system itself and communications and transportation promote
The collaboration of the sustainable development of socio-economy is unified.One sustainable transportation system is to support and promote region and country can
The necessary basis of sustainable development.Considering from overall national economy, communications and transportation will not only realize the sustainability of its system operation,
Also the quality of macroeconomy development is pushed in the frame of overall national economy, including promote Region homogenization development, mitigate warp
Pressure etc. of the Ji development to resource environment.It cannot be industry pipe currently without a set of construction method for communications and transportation index
Reason department policies carry out Analysis of Policy Making offer quantization reference.
Summary of the invention
(1) the technical issues of solving
In view of the deficiencies of the prior art, the present invention provides a kind of communications and transportation development indexes to construct model, solves mesh
It is preceding without a set of construction method for communications and transportation index, cannot for Industry regulatory bodies policies, carry out Analysis of Policy Making
The problem of quantization reference is provided.
(2) technical solution
To achieve the above object, the invention provides the following technical scheme: a kind of communications and transportation development index constructs model, packet
Include following steps:
(1) building of communications and transportation index index system:
Step A communications and transportation development essential analysis: according to communications and transportation essential attribute, communications and transportation develop intension and
Transportation system carrys out the demand of analysis indexes system construction, and according in communications and transportation essential attribute, communications and transportation development
Contain and transportation system carries out preliminary index selection；
Step B preliminary index selection: evaluation index primary election, evaluation index selection principle packet are carried out according to evaluation index selection principle
Scientific principle, scientific principle, feasibility principle, principle of comparability, parsimony principle and independency principle are included, is in addition commented
Valence index also needs empirically to determine that method and teaching method are chosen；
Step C index screening: being screened and examined to the evaluation index chosen in step B, according to " measurable, comparable
Property, independence " standard carry out screening index, wherein the screening technique of comparativity includes Specialist Research method, Minimum Mean Square Error method
And VC Method；The screening technique of independence includes simple correlation analysis method and partial Correlation Analysis；
Whether step D judge index system is perfect, and perfect expression index system establishment is completed, not perfect to be referred to again
Mark primary election；
(2) criterion:
Step A index unification: the index in index system after primary election is subjected to the processing of index unification, the finger
The method for marking unification processing includes unification and subtraction unification reciprocal；
Step B achievement data nondimensionalization: will carry out nondimensionalization by unification treated index, the index without
The processing method of dimension includes standardization with extreme difference method, minimizing method, rank method, indexation method；
Step C Index Weights: Index Weights, the side of Index Weights will be carried out by the achievement data of nondimensionalization
Method includes objective weighted model and subjective weighting method, and wherein subjective weighting method refers to including being researcher according to the judgement of its subjective value
A kind of method of fixed each index weight, wherein subjective weighting method includes expert judging method and analytic hierarchy process (AHP)；The objective tax
Power method is that the statistical indicator of data difference is commonly measured in statistics, and wherein objective weighted model includes VC Method, phase relation
Number method, Information Entropy and Principal Component Analysis；
(3) determination of index weights:
Relative importance of the weight to measure every index after standardization, using analytic hierarchy process (AHP) and carries out weight
Calculating then in consulting industry on the basis of relevant expert, each index is carried out two first by the assessment indicator system established
Two compare, and construct judgment matrix, recycle root method calculate each attribute layer and indicator layer index weights and to judgment matrix into
Consistency check is gone；
(4) determination of communications and transportation development index building model:
Gauge index is carried out using weight aggregate index number method, it is first determined the exponential model of attribute layer isWherein Vi is a certain attribute layer index index, and Yi is value of i-th of indicator layer index after standardization,
Ui is indicator layer index in the corresponding weight of attribute layer, and n is that the attribute layer index is related to indicator layer index item number, is then calculated
The computation model of comprehensive traffic development index, comprehensive traffic development index isWherein ViFor a certain attribute
Layer index index, WiIt is attribute layer index in the corresponding weight of destination layer, r is that destination layer index is related to attribute layer index item number.
Preferably, the essential analysis of the step A communications and transportation development in the building of (1) communications and transportation index index system
In, the communications and transportation essential attribute includes production attribute, industrial attributes and social property；The communications and transportation develops intension
Including productivity and the relations of production；The transportation system includes transportation network and change system, operation and management
System and transportation service system three digest journals, selected evaluation index includes traffic infrastructure in step B preliminary index selection
Index, transportation service capacity index, Green Development index, safety traffic indicators and economic and social benefits index.
Preferably, in the step C index screening of the building of (1) communications and transportation index index system, Specialist Research method is
A kind of method of investigation and study sent a letter, consulted on to industry specialists；In step C index screening, Minimum Mean Square Error method calculation formula is such as
Shown in lower:In formula, SjFor target variable XjMean square deviation；N is for being evaluated object
Number；xijFor j-th of index in i-th of evaluation object；I, j are the serial number for being respectively evaluated object and index；Step C index sieve
It chooses, VC Method calculation formula is as follows:In formula, vjFor target variable XjThe coefficient of variation；N is
It is evaluated the number of object；I, j are the serial number for being respectively evaluated object and index.
Preferably, in the step C index screening of the building of (1) communications and transportation index index system, simple correlation analysis
Method calculation formula is as follows:In formula, r is the simple correlation coefficient of target variable X and Y；Cov
(X, Y) is the covariance of the X and Y of target variable；D (X) is the variance of the X of target variable；D (Y) is the side of the Y of target variable
Difference；In step C index screening, partial Correlation Analysis method calculation formula is as follows:In formula,
r1,2For the partial correlation coefficient of target variable 1 and 2；r1,3For the simple correlation coefficient of target variable 1 and 3；r2,3For target variable 2
With 3 simple correlation coefficient.
Preferably, in the step A index unification in the processing of (2) index, the index pair of the inverse unification processing
As for flyback type index and appropriate type index；For flyback type index, pass through one kind of the reciprocal relationship establishment of positive inverse indicators
Inverse transformation mode, its calculation formula isIn formula, Y, X respectively indicate the index before and after unification.C is normal number, is taken
C=1, i.e.,For appropriate type index, its calculation formula isWherein, before Y, X respectively indicate unification
Index afterwards, the appropriateness value that α is index X.
Preferably, in the step A index unification in the processing of (2) index, the index pair of the subtraction unification processing
As for flyback type index and appropriate type index；For flyback type index, subtraction unification formula are as follows: Y=M-X, wherein M is index
The upper bound of a permission of X, takes M=0, i.e. Y=-X；For appropriate type index, subtraction unification formula is Y=K- | α-X |,
Middle K is normal number, the appropriateness value that α is index X.
Preferably, in the step B achievement data nondimensionalization in the processing of (2) index, the meter of the standardization with extreme difference method
Calculation mode isWherein i=1,2 ..., n, j=1,2 ..., m, YijRange 0~1 it
Between, each YijThe distribution of value is still identical as the corresponding original distribution of X value, suitable for the nothing in normal distribution or Non-Gaussian Distribution index value
The calculation of dimension, the minimizing method isWherein i=1,2 ..., n；J=1,2 ..., m, Yij
Range between 1~∞, each YijValue distribution it is still identical as the corresponding original distribution of X value, be suitable for be in normal distribution or it is non-just
The nondimensionalization of state distribution index value；The rank method, which refers to, is marked with unification treated index value by sequence from small to large
Corresponding rank then makes each index value be converted into the data between 1~n, and n is sample content, and wherein the calculation formula of rank method is
Yij=x, wherein x=1,2 ... n；The indexation method refers to that indexation method is to remove the value of each report period of initial data
With selected base-period value, the calculation of the indexation method isWherein i=1,2 ..., n；J=1,2 ..., m refer to
Numberization method is by the value of each report period of initial data divided by selected base-period value, with nondimensionalization initial data.
Preferably, in the step C Index Weights in the processing of (2) index, the calculation of the VC Method isWherein m evaluation indexes have n evaluation object, and X is raw data matrix, wherein xijIt is the of i-th of object
J index value,The standard deviation of each index is calculated first, and the calculation of standard deviation isS in formulajIt indicates the standard deviation of j-th of index, then calculates the coefficient of variation of each index, wherein variation lines
Several calculations areThe calculation of the correlation coefficient process isWherein P evaluation refers to
Target correlation matrix is R,The P index XpWith the multiple correlation between other P-1 index
Coefficient ρp, at this timeRP-1For x1, x2... xp-1Between correlation matrix rp=(r1p, r2p... rp-1p)T, institute
With ρp=rp TRp-1 -1rP；The calculation of the Information Entropy isWherein P is the number wherein d of evaluation indexj=1-
ej,Wherein, k > 0, ej>=0, entropy ej indicate jth item index；Principal Component Analysis root first
According to the feature of things, its assessment indicator system X is determined1, X2... Xp；Secondly, being standardized and calculating to initial data
Correlation matrix Z,Again, the characteristic root λ and feature vector A of correlation matrix, and base are asked
Contribution rate T and contribution rate of accumulative total E is calculated in characteristic root；Then, the weight coefficient of principal component scores matrix F and the principal component factor is calculated
B, if Y is generalized variable and overall target, X is each target variable, is expressed in matrix as Y=FX, the weight coefficient B of the principal component factor
It is expressed as B=[b1 b2 L bk],Each index comprehensive score is finally calculated as each index weights and carries out normalizing
Change processing, calculation formula are as follows
(3) beneficial effect
The present invention provides a kind of communications and transportation development indexes to construct model, has following the utility model has the advantages that communications and transportation
Sustainable development, it is necessary to be transportation system itself sustainable development and communications and transportation promote economic society sustainable development
The collaboration of exhibition is unified.One sustainable transportation system is the necessary base for supporting and promoting region and national sustainable development
Plinth.Consider from overall national economy, communications and transportation will not only realize the sustainability of its system operation, will also be in overall national warp
In the frame of Ji, the quality of macroeconomy development is pushed, including promotes Region homogenization development, mitigates economic development to resource environment
Pressure etc..Therefore, by constructing communications and transportation Development Assessment index system, and then communications and transportation development index is calculated, it can
Effectively to reflect interregional Transportation Development Level and communications and transportation Green Development degree, formulated for Industry regulatory bodies
Policy carries out Analysis of Policy Making offer quantization reference, power-assisted Transportation Sustainable Development.
Detailed description of the invention
Fig. 1 is the building flow chart of communications and transportation index index system of the invention；
Fig. 2 is the overall development condition diagram of comprehensive traffic index of the invention；
Fig. 3 is the trend graph of comprehensive traffic index and each attribute layer of the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
As shown in Figure 1, it is proposed that following embodiments:
Embodiment one:
A kind of communications and transportation development index building model, includes the following steps:
(1) building of communications and transportation index index system:
Step A communications and transportation development essential analysis: according to communications and transportation essential attribute, communications and transportation develop intension and
Transportation system carrys out the demand of analysis indexes system construction, and according in communications and transportation essential attribute, communications and transportation development
Contain and transportation system carry out preliminary index selection, the communications and transportation essential attribute include production attribute, industrial attributes with
And social property；It includes productivity and the relations of production that the communications and transportation, which develops intension,；The transportation system includes handing over
Logical transportation network and change system, operation and management system and transportation service system three digest journals, the institute in step B preliminary index selection
The evaluation index of selection includes traffic infrastructure index, transportation service capacity index, Green Development index, safety traffic indicators
And economic and social benefits index；
Step B preliminary index selection: evaluation index primary election, evaluation index selection principle packet are carried out according to evaluation index selection principle
Scientific principle, scientific principle, feasibility principle, principle of comparability, parsimony principle and independency principle are included, is in addition commented
Valence index also needs empirically to determine that method and teaching method are chosen；
Step C index screening: being screened and examined to the evaluation index chosen in step B, according to " measurable, comparable
Property, independence " standard carry out screening index, wherein the screening technique of comparativity includes Specialist Research method, Minimum Mean Square Error method
And VC Method, wherein Specialist Research method is a kind of method of investigation and study sent a letter, consulted on to industry specialists；Lowest mean square
Poor method calculation formula is as follows:In formula, SjFor target variable XjMean square deviation；N is
It is evaluated the number of object；xijFor j-th of index in i-th of evaluation object；I, j are the sequence for being respectively evaluated object and index
Number；VC Method calculation formula is as follows:In formula, vjFor target variable XjThe coefficient of variation；N is quilt
The number of evaluation object；I, j are the serial number for being respectively evaluated object and index；The screening technique of independence includes simple correlation
Analysis method and partial Correlation Analysis, wherein simple correlation analysis method calculation formula is as follows:
In formula, r is the simple correlation coefficient of target variable X and Y；Cov (X, Y) is the covariance of the X and Y of target variable；D (X) is to refer to
Mark the variance of the X of variable；D (Y) is the variance of the Y of target variable；In step C index screening, partial Correlation Analysis method calculates public
Formula is as follows:In formula, r1,2For the partial correlation coefficient of target variable 1 and 2；r1,3For index
The simple correlation coefficient of variable 1 and 3；r2,3For the simple correlation coefficient of target variable 2 and 3；
Whether step D judge index system is perfect, and perfect expression index system establishment is completed, not perfect to be referred to again
Primary election is marked, 1 communications and transportation development index index system of table is obtained according to the above method
1 communications and transportation development index index system of table
(2) criterion:
Step A index unification: the index in index system after primary election is subjected to the processing of index unification, the finger
The method for marking unification processing is unification and subtraction unification reciprocal, wherein the index object of the inverse unification processing is
Flyback type index and appropriate type index；For flyback type index, pass through a kind of inversion of the reciprocal relationship establishment of positive inverse indicators
Mode is changed, its calculation formula isIn formula, Y, X respectively indicate the index before and after unification, and C is normal number, take C=
1, i.e.,For appropriate type index, its calculation formula isWherein, before and after Y, X respectively indicate unification
Index, the appropriateness value that α is index X, the index object handled using the subtraction unification are that flyback type index and appropriate type refer to
Mark；For flyback type index, subtraction unification formula are as follows: Y=M-X, the upper bound for the permission that wherein M is index X take M=
0, i.e. Y=-X；For appropriate type index, subtraction unification formula is Y=K- | α-X |, wherein K is normal number, and α is index X's
Appropriateness value, unification and subtraction unification reciprocal are selected and are compared, and the following table 2 is unification and subtraction unification mark reciprocal
Data comparison after standardization；
Tables of data after the unification reciprocal of table 2 and the standardization of subtraction unification
Step B achievement data nondimensionalization: will carry out nondimensionalization by unification treated index, the index without
The processing method of dimension includes the meter of standardization with extreme difference method, minimizing method, rank method, standardization with extreme difference method described in indexation method
Calculation mode isWherein i=1,2 ..., n, j=1,2 ..., m, YijRange 0~1 it
Between, each YijThe distribution of value is still identical as the corresponding original distribution of X value, suitable for the nothing in normal distribution or Non-Gaussian Distribution index value
The calculation of dimension, the minimizing method isWherein i=1,2 ..., n；J=1,2 ..., m, Yij's
Range is between 1~∞, each YijThe distribution of value is still identical as the corresponding original distribution of X value, is suitable for being in normal distribution or abnormal
The nondimensionalization of distribution index value；The rank method, which refers to, is marked with phase by sequence from small to large for unification treated index value
The rank answered then makes each index value be converted into the data between 1~n, and n is sample content, and wherein the calculation formula of rank method is Yij
=x, wherein x=1,2 ... n；The indexation method refers to that indexation method is the value by each report period of initial data divided by choosing
The calculation of fixed base-period value, the indexation method isWherein i=1,2 ..., n；J=1,2 ..., m, indexation
Method is by the value of each report period of initial data divided by selected base-period value, and with nondimensionalization initial data, the following table 3 is various
Method nondimensionalization overall merit；
Comprehensive evaluation result and its sequence under the various dimensionless methods of table 3
Step C Index Weights: Index Weights, the side of Index Weights will be carried out by the achievement data of nondimensionalization
Method includes objective weighted model and subjective weighting method, and wherein subjective weighting method refers to including being researcher according to the judgement of its subjective value
A kind of method of fixed each index weight, wherein subjective weighting method includes expert judging method and analytic hierarchy process (AHP)；The objective tax
Power method is that the statistical indicator of data difference is commonly measured in statistics, and wherein objective weighted model includes VC Method, phase relation
Number method, Information Entropy and Principal Component Analysis, the calculation of the VC Method areWherein m evaluations refer to
Mark, has n evaluation object, X is raw data matrix, wherein xijFor j-th of index value of i-th of object,The standard deviation of each index is calculated first, and the calculation of standard deviation isFormula
Middle SjIt indicates the standard deviation of j-th of index, then calculates the coefficient of variation of each index, wherein the calculation of the coefficient of variation isThe calculation of the correlation coefficient process isThe wherein related coefficient square of P evaluation index
Battle array is R,The P index XpWith the multiple correlation coefficient ρ between other P-1 indexp, at this timeRP-1For x1, x2 ... xp-1Between correlation matrix rp=(r1p,r2p... rp-1p)T, so ρp=
rp TRp-1 -1rP；The calculation of the Information Entropy isWherein P is the number wherein d of evaluation indexj=1-ej,Wherein, k > 0, ej>=0, entropy ej indicate jth item index；The Principal Component Analysis is first according to thing
The feature of object determines its assessment indicator system X1, X2... Xp；Secondly, being standardized to initial data and calculating correlation
Coefficient matrix Z,Again, the characteristic root λ and feature vector A of correlation matrix, and base are asked
Contribution rate T and contribution rate of accumulative total E is calculated in characteristic root；Then, the weight coefficient of principal component scores matrix F and the principal component factor is calculated
B, if Y is generalized variable and overall target, X is each target variable, is expressed in matrix as Y=FX, the weight coefficient B of the principal component factor
It is expressed as B=[b1 b2 L bk],Each index comprehensive score is finally calculated as each index weights and carries out normalizing
Change processing, calculation formula are as follows
(3) determination of index weights:
Relative importance of the weight to measure every index after standardization, using analytic hierarchy process (AHP) and carries out weight
Calculating then in consulting industry on the basis of relevant expert, each index is carried out two first by the assessment indicator system established
Two compare, and construct judgment matrix, recycle root method calculate each attribute layer and indicator layer index weights and to judgment matrix into
Consistency check is gone, the following table 4 is the calculated result of index weights；
The calculated result of 4 index weights of table
(4) determination of communications and transportation development index building model:
Gauge index is carried out using weight aggregate index number method, it is first determined the exponential model of attribute layer isWherein Vi is a certain attribute layer index index, and Yi is value of i-th of indicator layer index after standardization,
Ui is indicator layer index in the corresponding weight of attribute layer, and n is that the attribute layer index is related to indicator layer index item number, is then calculated
The computation model of comprehensive traffic development index, comprehensive traffic development index isWherein ViFor a certain attribute
Layer index index, WiIt is attribute layer index in the corresponding weight of destination layer, r is that destination layer index is related to attribute layer index item number,
The following table 5 is final index calculated result.
5 index calculated result of table
According to the calculated result of above-mentioned index, alteration trend and the country of the Research on formula for calculating index of index can use
Relationship between the alteration trend of total output value,
Transformation relation of the table 6 between comprehensive traffic index and GDP
There are higher positive correlation between ITDI index and GDP (GDP), related coefficient reaches
0.996, very close 1, it indicates the in close relations of the two, can further do regression analysis, disclose and simultaneously determine ITDI index and state
Relationship between interior total output value makes the fitting result of GDP using the regression model of regression analysis, as shown in table 7 below:
The fitting result of 7 GDP of table
According to upper table comprehensive traffic development index one unit of every increase, GDP will increase by 8603.259 hundred million yuan, therefore
Corresponding measure can be taken to accelerate the development progress of comprehensive traffic to promote the development of economy, this and country and relevant industrial department pair
The development orientation of communications and transportation is perfectly in harmony.By the GDP value of Regression Model Simulator it is found that quasi- compared with actual GDP value
Conjunction value and the mean error of true value nearly ten years are 2.5%, and the precision of fitting is higher, therefore can be based on regression model and establishment
Comprehensive traffic development index predict the GDP value in the following year, to reflect the development trend and substantially of national economy level
Scale formulates corresponding policy for country and provides the reference frame of quantification.In conclusion being commented by building communications and transportation development
Valence index index model, and then communications and transportation development index is calculated, it can effectively reflect interregional communications and transportation development
Horizontal and communications and transportation Green Development degree provides quantization reference for Industry regulatory bodies policies, development Analysis of Policy Making, helps
Power Transportation Sustainable Development.
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or equipment including the element.
It although an embodiment of the present invention has been shown and described, for the ordinary skill in the art, can be with
A variety of variations, modification, replacement can be carried out to these embodiments without departing from the principles and spirit of the present invention by understanding
And modification, the scope of the present invention is defined by the appended.
Claims (8)
1. a kind of communications and transportation development index constructs model, characterized by the following steps:
(1) building of communications and transportation index index system:
The essential analysis of step A communications and transportation development: intension and traffic are developed according to communications and transportation essential attribute, communications and transportation
Transportation system carrys out the demand of analysis indexes system construction, and according to communications and transportation essential attribute, communications and transportation develop intension with
And transportation system carries out preliminary index selection；
Step B preliminary index selection: evaluation index primary election is carried out according to evaluation index selection principle, evaluation index selection principle includes section
The property learned principle, scientific principle, feasibility principle, principle of comparability, parsimony principle and independency principle, in addition evaluation refers to
Mark also needs empirically to determine that method and teaching method are chosen；
Step C index screening: being screened and examined to the evaluation index chosen in step B, according to " can measure, comparativity, solely
The standard of vertical property " carries out screening index, and wherein the screening technique of comparativity includes Specialist Research method, Minimum Mean Square Error method and change
Different Y-factor method Y；The screening technique of independence includes simple correlation analysis method and partial Correlation Analysis；
Whether step D judge index system is perfect, and perfect expression index system establishment is completed, at the beginning of the not perfect index of progress again
Choosing；
(2) criterion:
Step A index unification: the index in index system after primary election is subjected to the processing of index unification, the index one
The method of causeization processing includes unification and subtraction unification reciprocal；
Step B achievement data nondimensionalization: nondimensionalization, the index dimensionless will be carried out by unification treated index
The processing method of change includes standardization with extreme difference method, minimizing method, rank method, indexation method；
Step C Index Weights: Index Weights, the method packet of Index Weights will be carried out by the achievement data of nondimensionalization
Objective weighted model and subjective weighting method are included, wherein subjective weighting method judges including being researcher according to its subjective value come specified each
A kind of method of index weight, wherein subjective weighting method includes expert judging method and analytic hierarchy process (AHP)；The objective weighted model
That the statistical indicator of data difference is commonly measured in statistics, wherein objective weighted model include VC Method, correlation coefficient process,
Information Entropy and Principal Component Analysis；
(3) determination of index weights:
Relative importance of the weight to measure every index after standardization, the meter of weight is carried out using analytic hierarchy process (AHP)
It calculates, first by the assessment indicator system established, then in consulting industry on the basis of relevant expert, each index is compared two-by-two
Compared with constructing judgment matrix, recycle root method to calculate each attribute layer and indicator layer index weights and carried out to judgment matrix
Consistency check；
(4) determination of communications and transportation development index building model:
Gauge index is carried out using weight aggregate index number method, it is first determined the exponential model of attribute layer isIts
Middle Vi is a certain attribute layer index index, and Yi is value of i-th of indicator layer index after standardization, and Ui is that indicator layer index exists
The corresponding weight of attribute layer, n are that the attribute layer index is related to indicator layer index item number, then calculate comprehensive traffic development and refer to
Number, the computation model of comprehensive traffic development index areWherein ViFor a certain attribute layer index index, WiFor
For attribute layer index in the corresponding weight of destination layer, r is that destination layer index is related to attribute layer index item number.
2. a kind of communications and transportation development index according to claim 1 constructs model, it is characterised in that: transported in (1) traffic
In the essential analysis of step A communications and transportation development in the building of defeated index index system, the communications and transportation essential attribute packet
Include production attribute, industrial attributes and social property；It includes productivity and the relations of production that the communications and transportation, which develops intension,；Institute
Stating transportation system includes transportation network and change system, operation and management system and transportation service system three system greatly
System, in step B preliminary index selection selected evaluation index include traffic infrastructure index, it is transportation service capacity index, green
Chromogenic development index, safety traffic indicators and economic and social benefits index.
3. a kind of communications and transportation development index according to claim 1 constructs model, it is characterised in that: transported in (1) traffic
In the step C index screening of the building of defeated index index system, Specialist Research method is a kind of to send a letter, consult on to industry specialists
Method of investigation and study；In step C index screening, Minimum Mean Square Error method calculation formula is as follows:In formula, SjFor target variable XjMean square deviation；N is the number for being evaluated object；xijFor
J-th of index in i-th of evaluation object；I, j are the serial number for being respectively evaluated object and index；In step C index screening, become
Different Y-factor method Y calculation formula is as follows:In formula, vjFor target variable XjThe coefficient of variation；N is to be evaluated pair
The number of elephant；I, j are the serial number for being respectively evaluated object and index.
4. a kind of communications and transportation development index according to claim 1 constructs model, it is characterised in that: transported in (1) traffic
In the step C index screening of the building of defeated index index system, simple correlation analysis method calculation formula is as follows:In formula, r is the simple correlation coefficient of target variable X and Y；Cov (X, Y) is the X's and Y of target variable
Covariance；D (X) is the variance of the X of target variable；D (Y) is the variance of the Y of target variable；In step C index screening, partial correlation
Analysis method calculation formula is as follows:In formula, r1,2For the partial correlation of target variable 1 and 2
Coefficient；r1,3For the simple correlation coefficient of target variable 1 and 3；r2,3For the simple correlation coefficient of target variable 2 and 3.
5. a kind of communications and transportation development index according to claim 1 constructs model, it is characterised in that: at (2) index
In step A index unification in reason, the index object of the inverse unification processing is flyback type index and appropriate type index；
For flyback type index, by a kind of inverse transformation mode of the reciprocal relationship establishment of positive inverse indicators, its calculation formula isIn formula, Y, X respectively indicate the index before and after unification.C is normal number, takes C=1, i.e.,For appropriateness
Type index, its calculation formula isWherein, Y, X respectively indicate the index before and after unification, and α is the appropriateness of index X
Value.
6. a kind of communications and transportation development index according to claim 1 constructs model, it is characterised in that: at (2) index
In step A index unification in reason, the index object of the subtraction unification processing is flyback type index and appropriate type index；
For flyback type index, subtraction unification formula are as follows: Y=M-X, the upper bound for the permission that wherein M is index X take M=0, i.e.,
Y=-X；For appropriate type index, subtraction unification formula is Y=K- | α-X |, wherein K is normal number, and α is the appropriateness of index X
Value.
7. a kind of communications and transportation development index according to claim 1 constructs model, it is characterised in that: at (2) index
In step B achievement data nondimensionalization in reason, the calculation of the standardization with extreme difference method isWherein i=1,2 ..., n, j=1,2 ..., m, YijRange between 0~1, each YijValue
Distribution it is still identical as the corresponding original distribution of X value, suitable for being in the nondimensionalization of normal distribution or Non-Gaussian Distribution index value, institute
The calculation for stating minimizing method isWherein i=1,2 ..., n；J=1,2 ..., m, YijRange 1
Between~∞, each YijThe distribution of value is still identical as the corresponding original distribution of X value, is suitable for being in normal distribution or Non-Gaussian Distribution index
The nondimensionalization of value；The rank method, which refers to, is marked with corresponding order by sequence from small to large for unification treated index value
It is secondary, then so that each index value is converted into the data between 1~n, n is sample content, and wherein the calculation formula of rank method is Yij=x,
Middle x=1,2 ... n；The indexation method refers to that indexation method is the value by each report period of initial data divided by selected base
The calculation of time value, the indexation method isWherein i=1,2 ..., n；J=1,2 ..., m, indexation method be by
The value of each report period of initial data is divided by selected base-period value, with nondimensionalization initial data.
8. a kind of communications and transportation development index according to claim 1 constructs model, it is characterised in that: at (2) index
In step C Index Weights in reason, the calculation of the VC Method isWherein m evaluation indexes,
There is n evaluation object, X is raw data matrix, wherein xijFor j-th of index value of i-th of object,The standard deviation of each index is calculated first, and the calculation of standard deviation isFormula
Middle SjIt indicates the standard deviation of j-th of index, then calculates the coefficient of variation of each index, wherein the calculation of the coefficient of variation isThe calculation of the correlation coefficient process isThe wherein related coefficient square of P evaluation index
Battle array is R,The P index XpWith the multiple correlation coefficient ρ between other P-1 indexp, at this timeRP-1For x1, x2... xp-1Between correlation matrix rp=(r1p, r2p... rp-1p)T, so ρp=rp TRp-1 - 1rP；The calculation of the Information Entropy isWherein P is the number wherein d of evaluation indexj=1-ej,Wherein, k > 0, ej>=0, entropy ej indicate jth item index；The Principal Component Analysis is first according to thing
The feature of object determines its assessment indicator system X1, X2... Xp；Secondly, being standardized to initial data and calculating correlation
Coefficient matrix Z,Again, the characteristic root λ and feature vector A of correlation matrix, and base are asked
Contribution rate T and contribution rate of accumulative total E is calculated in characteristic root；Then, the weight coefficient of principal component scores matrix F and the principal component factor is calculated
B, if Y is generalized variable and overall target, X is each target variable, is expressed in matrix as Y=FX, the weight coefficient B of the principal component factor
It is expressed as B=[b1 b2 L bk],Each index comprehensive score is finally calculated as each index weights and carries out normalizing
Change processing, calculation formula are as follows
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910283943.2A CN109978411A (en) | 2019-04-10 | 2019-04-10 | A kind of communications and transportation development index building model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910283943.2A CN109978411A (en) | 2019-04-10 | 2019-04-10 | A kind of communications and transportation development index building model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109978411A true CN109978411A (en) | 2019-07-05 |
Family
ID=67083910
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910283943.2A Pending CN109978411A (en) | 2019-04-10 | 2019-04-10 | A kind of communications and transportation development index building model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109978411A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110675083A (en) * | 2019-10-08 | 2020-01-10 | 国家计算机网络与信息安全管理中心 | Comprehensive recommendation method and device in scientific and technological field |
| CN112381560A (en) * | 2020-10-23 | 2021-02-19 | 东北石油大学 | Shared equipment product market prediction system and method |
| CN113902098A (en) * | 2021-09-30 | 2022-01-07 | 云天弈(广州)智能科技有限公司 | Multi-type data parallel learning method and device, computer equipment and medium |
| CN114418389A (en) * | 2022-01-17 | 2022-04-29 | 安徽省道路运输管理服务中心 | Construction method of traffic transportation development index model based on evaluation index system |
-
2019
- 2019-04-10 CN CN201910283943.2A patent/CN109978411A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110675083A (en) * | 2019-10-08 | 2020-01-10 | 国家计算机网络与信息安全管理中心 | Comprehensive recommendation method and device in scientific and technological field |
| CN112381560A (en) * | 2020-10-23 | 2021-02-19 | 东北石油大学 | Shared equipment product market prediction system and method |
| CN113902098A (en) * | 2021-09-30 | 2022-01-07 | 云天弈(广州)智能科技有限公司 | Multi-type data parallel learning method and device, computer equipment and medium |
| CN114418389A (en) * | 2022-01-17 | 2022-04-29 | 安徽省道路运输管理服务中心 | Construction method of traffic transportation development index model based on evaluation index system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109978411A (en) | A kind of communications and transportation development index building model | |
| Dong et al. | Carbon emissions, the industrial structure and economic growth: Evidence from heterogeneous industries in China | |
| CN102930482A (en) | Investment effect evaluation method for county power distribution networks | |
| CN106682809A (en) | Enterprise BIM technology application capability quantification assessment method | |
| CN104318482A (en) | Comprehensive assessment system and method of smart distribution network | |
| CN103632203A (en) | Distribution network power supply area division method based on comprehensive evaluation | |
| CN103617371A (en) | Method for comprehensively evaluating electric energy quality based on grey theory | |
| CN104837184A (en) | Heterogeneous wireless network selection method based on interval triangular fuzzy number | |
| CN105512465A (en) | Cloud platform safety quantitative evaluation method based on improved VIKOR method | |
| CN109003010A (en) | The evaluation method of power grid project investment benefit | |
| Mingran | Measurement and spatial statistical analysis of green science and technology innovation efficiency among Chinese Provinces | |
| CN108461150A (en) | A kind of occupational health forecasting research method | |
| CN101739614A (en) | Hierarchy-combined prediction method for communication service | |
| CN111401701A (en) | Comprehensive evaluation method for comprehensive transportation system | |
| Du et al. | A hybrid group-making decision framework for regional distribution network outage loss assessment based on fuzzy best-worst and MARCOS methods | |
| CN107145995A (en) | Production environment safety prediction methods, devices and systems | |
| CN102201106A (en) | Technical evaluation method for fermenting or chemical synthesis based pharmaceutical wastewater treatment | |
| Motaghifard et al. | Introducing a conceptual model for evaluating health safety environmental performance of residential buildings using the fuzzy decision-making approach | |
| CN106485466A (en) | A kind of project management system | |
| El Hadidi et al. | Evaluation of a building Life Cycle Cost (LCC) criteria in Egypt using the Analytic Hierarchy Process (AHP) | |
| CN109657967A (en) | A kind of confirmation method and system of Transmission Expansion Planning in Electric evaluating indexesto scheme weight | |
| CN114647947A (en) | Unit cost prediction method, device, electronic device and computer readable storage medium | |
| Liu et al. | Research into the dynamic development trend of the competitiveness of China’s regional construction industry | |
| CN114298598A (en) | Urban high-reliability medium-voltage distribution network wiring mode comprehensive evaluation method | |
| CN108694527B (en) | Power distribution network evaluation method |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190705 |