CN107944750A - A kind of poverty depth analysis method and system - Google Patents

A kind of poverty depth analysis method and system Download PDF

Info

Publication number
CN107944750A
CN107944750A CN201711318156.4A CN201711318156A CN107944750A CN 107944750 A CN107944750 A CN 107944750A CN 201711318156 A CN201711318156 A CN 201711318156A CN 107944750 A CN107944750 A CN 107944750A
Authority
CN
China
Prior art keywords
mrow
index
poor
dimension
msub
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
Application number
CN201711318156.4A
Other languages
Chinese (zh)
Inventor
何亚文
孙凯
孙翊腾
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Qingdao Zhongke Randy Mdt Infotech Ltd
China University of Petroleum East China
Institute of Geographic Sciences and Natural Resources of CAS
Original Assignee
Qingdao Zhongke Randy Mdt Infotech Ltd
China University of Petroleum East China
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Qingdao Zhongke Randy Mdt Infotech Ltd, China University of Petroleum East China filed Critical Qingdao Zhongke Randy Mdt Infotech Ltd
Priority to CN201711318156.4A priority Critical patent/CN107944750A/en
Publication of CN107944750A publication Critical patent/CN107944750A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—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)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Economics (AREA)
  • Tourism & Hospitality (AREA)
  • General Physics & Mathematics (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Theoretical Computer Science (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Game Theory and Decision Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Cosmetics (AREA)

Abstract

The invention discloses a kind of poor depth analysis method and system, it realizes that process is：Administrative village data are obtained first, obtain at village level misery index；Then poor user data is obtained, obtains family level misery index；Spatialization is carried out to poor depth：The specific location of each poor household is obtained by high definition remote sensing image, the misery index of acquisition is associated with poor household position, so as to obtain regional poor household's poverty depth map.The poverty depth analysis method and system are compared with prior art, the Measure Indexes of poverty-stricken area poor village and poor household can precisely be shown, it is smaller to the measurement results error of poor household and poor village, as a result accuracy rate is high, and its measurement results not only presents the space distribution situation of at village level scale, the distribution to each family is also embodied, it is highly practical, it is applied widely, it is easy to spread.

Description

A kind of poverty depth analysis method and system
Technical field
The present invention relates to Computer Applied Technology field, specifically a kind of highly practical, poor depth analysis method And system.
Background technology
Accurate poverty alleviation is the symmetrical of extensive poverty alleviation, is referred to for different pocket of poverty environment, different Poor Farmers Household situations, fortune Implement accurate identification, accurate helping, the eliminate-poverty mode accurately managed to poverty alleviation object with scientific and effective program.In general, it is smart Mainly for Residents In Poverty, whom whose poverty just helps for quasi- poverty alleviation.
And how to obtain specific poor data and analyze it processing, have in the prior art very much Correlation technique, wherein " Chen Yefeng, Wang Yanhui, Wang little Lin China poor village estimate with Spatial Distribution Characteristics Geographical Studies, 2016,35(12):In 2298-2308. ", it is poor that multidimensional is carried out to the poor village in the whole country using integrated multidimensional misery index It is tired to estimate, and poor village is analyzed in Spatial Distribution Pattern with reference to GIS technology, from quantitative measurement and spatialization expression two Aspect explores the distribution characteristics of Chinese poor village.
" the at village level population below the poverty line multidimensional measuring and calculating of Wang Yanhui, Qian Leyi, Duan Fuzhou, Zhao Wen Ji and its poverty feature analysis --- Populations are with economical by taking Henan Province Neixiang County as an example, and 2014,5:With Qin_Ba mountain areas exceptionally poverty-stricken area's poverty alleviation emphasis in flakes in 114-120. " Exemplified by county, structure aims at the at village level poor identification technology system of population, to multidimensional poverty results of measuring and poverty feature space point Cloth carries out spatialization processing and analysis.The real population below the poverty line and poverty feature distributed areas are identified with this.
The above-mentioned Measure Indexes to poverty-stricken area poor village and poor household are since data etc. limit, to poor household and poor village Measurement results have certain deviation, while its measurement results only presents the space distribution situation of at village level scale, without body Now arrive the distribution at each family.
Based on this, the present invention proposes a kind of poor depth analysis method and system, to solve the above problems.
The content of the invention
The technical assignment of the present invention is to be directed to above shortcoming, there is provided a kind of highly practical, poor depth analysis method And system.
A kind of poverty depth analysis method, it realizes that process is：
First, administrative village data are obtained first, obtain at village level misery index；
Two and then poor user data is obtained, obtain family level misery index；
3rd, spatialization is carried out to poor depth：The specific location of each poor household is obtained by high definition remote sensing image, will be walked The misery index obtained in rapid one, two is associated with poor household position, so as to obtain regional poor household's poverty depth map.
In the step 1, the process for establishing at village level misery index is：
1) at village level poor Measure Indexes system is initially set up, i.e., according to the administrative village data of acquisition, is classified as some fingers Mark, simulates all index multiple correlation by multiple correlation coefficient method, according to the correlation of the index after simulation and discrimination to referring to Mark is screened；
2) weight setting is carried out to index and dimension；
3) according to index and dimension after weighing is assigned in step 2), at village level multidimensional misery index VPI is calculated, i.e., poor depth.
In step 1), when carrying out associated analog by multiple correlation coefficient method, when multiple correlation coefficient is not 0, and return When probability is 0, represent that linear model is set up；Index degree of distinguishing of the multiple correlation coefficient more than 0.5 is examined, discrimination Minimum is rejected；Multiple correlation simulation is repeated, multiple correlation coefficient reduces and below 0.5, shows correlation between index It is smaller.
The negative relations act used in the step 1) refers to measure an index item Xij in the following manner and other are more A index X11, Xij-1, Xij+1 ..., the related coefficient between Xm ' n ', and one is constructed on X11, X12 ..., Xm ' n ' Linear combination, by calculate the simple correlation coefficient between the linear combination and Xij be used as index Xij and X11, X12 ..., Multiple correlation coefficient between Xm ' n '：
X11, X12 ..., Xm ' n ' are returned with Xij first, construct following linear combination：
Simple correlation coefficient, i.e. complex phase relation between Xij and X11, X12 ..., Xm ' n ' are calculated by the following formula Number：
In above-mentioned formulaExpression is the vector value that the variable carries out linear regression with other each variables,Table Show the average value of the variable.
Corresponding, the calculating process of at village level multidimensional misery index VPI is in step 3)：
In formula：20 be constant, for eliminating decimal position influence, increases difference between data；N represents dimension number；M represents phase Answer the index number under dimension；IijRepresent the desired value after standardization；ωijRepresent index weights；ωiRepresent dimension weight.
The step 2 establish family level misery index process be：
(1) the poor data of family level are obtained first, and the poor measuring and calculating dimension of family level and index system are established according to the data；
(2) carry out the poor individual of overall merit by using double critical value multidimensional poverty measuring methods in constructed dimension to refer to The poverty status of each dimension index in mark system, double critical values refer to deprive critical value and poor critical value；
(3) dimension adds up, and calculates the synthesis misery index MPI of poor individual ownership dimension index.
The family poor measuring and calculating dimension of level multidimensional established in step (1) is with index system, assigning each dimension and index Weight, and the processing to each dimension and index weights uses equal weight method：Weight shared by each dimension is equal, all dimension power The sum of weight values are 1, and the weight of each base values is equal in every dimension, i.e. the weighted value of the decile dimension.
Family level multidimensional misery index MPI is calculated by the following formula in step (2)：
In formula：N represents dimension number；M represents the index number under respective dimensions；JijRepresent the desired value after standardization； vijRepresent index weights；viRepresent dimension weight.
It is described poverty deep space detailed process be：
High definition remote sensing image after being handled first by geometric correction, obtains the specific location of each poor household；
Then it is poor to be obtained by the way that multidimensional misery index is associated with poor household position by instrument by regional poor household Tired depth profile, the instrument are the cuclear density analysis tool in Arcgis, and minimum pixel unit is arranged to 0.001, search half Footpath is arranged to 0.02, shows poor depth Nesting Zone and clear area.
A kind of poverty depth analysis system, including：
Administrative at village level poor metric module, by obtaining administrative village data, splits data into some indexs, passes through multiple correlation Y-factor method Y simulates all index multiple correlation, establishes at village level poor Measure Indexes system, then assigns power index and weight, calculating obtain Take at village level multidimensional misery index VPI；
The poor metric module of family level, by obtaining the poor data of family level, establishes the poor measuring and calculating dimension of family level and index system, By using double critical value multidimensional poverty measuring methods come the poor individual of overall merit in constructed dimension index system it is each The poverty status of a dimension index, double critical values refer to deprive critical value and poor critical value, all dimensions are added and are converged Always, the synthesis misery index MPI of poor individual ownership dimension index is calculated；
Display module, it is poor from administrative at village level poor metric module, the at village level multidimensional of the poor metric module of family level to receive Index VPI, comprehensive misery index MPI, then by its with handled by geometric correction after high definition remote sensing image obtain it is each Poor household's specific location is associated, and is then shown.
The at village level poor metric module of the administration obtains at village level multidimensional misery index VPI in the following manner：
Associated analog is carried out by multiple correlation coefficient method again to all indexs of administrative village data of acquisition, after simulation The correlation of index screens index with discrimination：When multiple correlation coefficient is not 0, and recurrence probability is 0, represent Linear model is set up；Index degree of distinguishing of the multiple correlation coefficient more than 0.5 is examined, discrimination minimum is rejected；Again Multiple correlation simulation is repeated, multiple correlation coefficient reduces and below 0.5, and correlation is smaller between showing index；
Then an index item Xij and other multiple index X11, Xij-1, Xij+1 ... are measured in the following manner, Related coefficient between Xm ' n ', constructs the linear combination on X11, X12 ..., Xm ' n ', by calculating this linear group The simple correlation coefficient between Xij is closed as the multiple correlation coefficient between index Xij and X11, X12 ..., Xm ' n ', specifically Process is：
A, X11, X12 ..., Xm ' n ' are returned with Xij first, constructs following linear combination：
B, simple correlation coefficient, i.e. complex phase relation between Xij and X11, X12 ..., Xm ' n ' are calculated by the following formula Number：
In above-mentioned formulaExpression is the vector value that the variable carries out linear regression with other each variables,Table Show the average value of the variable.
C, at village level multidimensional misery index VPI is calculated by the following formula：
In formula：20 be constant, for eliminating decimal position influence, increases difference between data；N represents dimension number；M represents phase Answer the index number under dimension；IijRepresent the desired value after standardization；ωijRepresent index weights；ωiRepresent dimension weight.
The poor metric module of family level obtains family level multidimensional misery index MPI in the following manner：
A) the poor data of family level are obtained first, are established the poor measuring and calculating dimension of family level and index system according to the data, are being built The vertical poor measuring and calculating dimension of family level multidimensional to each dimension and index with index system, assigning weight, and to each dimension and refer to The processing of mark weight uses equal weight method：Weight shared by each dimension is equal, and the sum of all dimension weighted values are 1, per one-dimensional The weight of each base values is equal in degree, i.e. the weighted value of the decile dimension；
B) carry out the poor individual of overall merit by using double critical value multidimensional poverty measuring methods in constructed dimension to refer to The poverty status of each dimension index in mark system；
C) all dimensions are added and collected, calculate the synthesis misery index MPI of poor individual ownership dimension index：
In formula：N represents dimension number；M represents the index number under respective dimensions；JijRepresent the desired value after standardization； vijRepresent index weights；viRepresent dimension weight.
A kind of poor depth analysis method and system of the present invention, have the following advantages：
A kind of poor depth analysis method and system proposed by the present invention, can be to poverty-stricken area poor village and poor household Measure Indexes are precisely shown, smaller to the measurement results error of poor household and poor village, and as a result accuracy rate is high, and it is measured As a result the space distribution situation of at village level scale is not only presented, also embodies the distribution to each family, it is highly practical, it is applied widely It is general, it is easy to spread.
Embodiment
In order to make those skilled in the art more fully understand the present invention program, with reference to embodiment to this hair It is bright to be described in further detail.Obviously, described embodiment be only part of the embodiment of the present invention, rather than whole Embodiment.Based on the embodiments of the present invention, those of ordinary skill in the art are obtained without making creative work The every other embodiment obtained, belongs to the scope of protection of the invention.
A kind of poverty depth analysis method, it realizes that process is：
First, administrative village data are obtained first, obtain at village level misery index；
Two and then poor user data is obtained, obtain family level misery index；
3rd, spatialization is carried out to poor depth：The specific location of each poor household is obtained by high definition remote sensing image, will be walked The misery index obtained in rapid one, two is associated with poor household position, so as to obtain regional poor household's poverty depth map.
In the step 1, the process for establishing at village level misery index is：
1) at village level poor Measure Indexes system is initially set up, i.e., according to the administrative village data of acquisition, is classified as some fingers Mark, simulates all index multiple correlation by multiple correlation coefficient method, according to the correlation of the index after simulation and discrimination to referring to Mark is screened；
It is theoretical to instruct with space Poverty Theories and Man Land relationship system using administrative village as basic research unit, consider certainly The influences of the non-artificial factor to feeling effect such as right environment, and poverty and phase between geographical environment, resource, each key element of social economy Mutually influence, the dynamic relationship of interaction, build the administration including the indexs such as nature, ecological environment, economy, social security Village's multidimensional poverty assessment indicator system Candidate Set.
2) weight setting is carried out to index and dimension；
3) according to index and dimension after weighing is assigned in step 2), at village level multidimensional misery index VPI is calculated, i.e., poor depth.
In step 1), when carrying out associated analog by multiple correlation coefficient method, when multiple correlation coefficient is not 0, and return When probability is 0, represent that linear model is set up；Index degree of distinguishing of the multiple correlation coefficient more than 0.5 is examined, discrimination Minimum is rejected；Multiple correlation simulation is repeated, multiple correlation coefficient reduces and below 0.5, shows correlation between index It is smaller.
The negative relations act used in the step 1) refers to measure an index item Xij in the following manner and other are more A index X11, Xij-1, Xij+1 ..., the related coefficient between Xm ' n ', and one is constructed on X11, X12 ..., Xm ' n ' Linear combination, by calculate the simple correlation coefficient between the linear combination and Xij be used as index Xij and X11, X12 ..., Multiple correlation coefficient between Xm ' n '：
X11, X12 ..., Xm ' n ' are returned with Xij first, construct following linear combination：
Simple correlation coefficient, i.e. complex phase relation between Xij and X11, X12 ..., Xm ' n ' are calculated by the following formula Number：
In above-mentioned formulaExpression is the vector value that the variable carries out linear regression with other each variables,Table Show the average value of the variable.
Corresponding, the calculating process of at village level multidimensional misery index VPI is in step 3)：
In formula：20 be constant, for eliminating decimal position influence, increases difference between data；N represents dimension number；M represents phase Answer the index number under dimension；IijRepresent the desired value after standardization；ωijRepresent index weights；ωiRepresent dimension weight.
The step 2 establish family level misery index process be：
(1) the poor data of family level are obtained first, and the poor measuring and calculating dimension of family level and index system are established according to the data；
(2) carry out the poor individual of overall merit by using double critical value multidimensional poverty measuring methods in constructed dimension to refer to The poverty status of each dimension index in mark system, double critical values refer to deprive critical value and poor critical value；
(3) dimension adds up, and calculates the synthesis misery index MPI of poor individual ownership dimension index.
The family poor measuring and calculating dimension of level multidimensional established in step (1) is with index system, assigning each dimension and index Weight, and the processing to each dimension and index weights uses equal weight method：Weight shared by each dimension is equal, all dimension power The sum of weight values are 1, and the weight of each base values is equal in every dimension, i.e. the weighted value of the decile dimension.
Family level multidimensional misery index MPI is calculated by the following formula in step (2)：
In formula：N represents dimension number；M represents the index number under respective dimensions；JijRepresent the desired value after standardization； vijRepresent index weights；viRepresent dimension weight.
It is described poverty deep space detailed process be：
High definition remote sensing image after being handled first by geometric correction, obtains the specific location of each poor household；
Then it is poor to be obtained by the way that multidimensional misery index is associated with poor household position by instrument by regional poor household Tired depth profile.
Embodiment, below illustrates the method for the present invention with instantiation.
First, the poor measurement of administrative at village level multidimensional is carried out first：
1st, the at village level multidimensional poverty Measure Indexes system in administrative village is established：
Obtain including below figure X by the above method1~X6、X11~X61The at village level multidimensional of " 6 dimensions, 20 indexs " inside Poor measurement indicator system.
Multiple correlation coefficient is the index for measuring linearly related degree between a variable and other multiple variables.It cannot be straight Measuring and calculating is connect, certain method can only be taken to carry out indirect measuring.Multiple correlation coefficient is bigger, shows linear between key element or variable Degree of correlation is closer.
Specific calculating process is as follows：In order to measure an index item Xij and other multiple index X11Xij-1, Xij+1X61 Between related coefficient, construct the linear combination on X11, X12 ..., X61, by calculating the linear combination and Xij Between simple correlation coefficient as the multiple correlation coefficient between index Xij and X11, X12 ..., X61.Specific calculating process is such as Under：
The first step, returns X11, X12 ..., X61 with Xij, obtains：
Second step, it is Xij and X11 to calculate simple correlation coefficient, the multiple correlation coefficient between X12 ..., X61.Complex phase The calculation formula of relation number is：
2nd, criterion and weight setting：
It is fixed to grade in grade classification Primary Reference country poverty alleviation planning outline, economic development outline, existing literature to index Each metrics-thresholds in index system are divided into 1~5 grade by the research of level and the true horizon of data, and numerical value is bigger, poor It is deeper.The subjective and objective combination weights method being combined using analytic hierarchy process (AHP) with entropy assessment, carries out tax power to dimension and index respectively, Tax power method can use the prior art, for example " Jiang Yuxi, slow Cathay, tight beautiful person of outstanding talent are based on principle of maximum entropy referring to open source literature Linear combination assign power method Operations research and mamagement science, 2011,20 (1):53-59”.Policymaker had generally both been taken into account to the inclined of attribute It is good, and reduce entitled subjective random.
3rd, at village level multidimensional misery index calculates：
At village level multidimensional misery index (VPI) is calculated by formula, i.e., poor depth：
In formula：20 be constant, for eliminating decimal position influence, increases difference between data；N represents dimension number；M represents phase Answer the index number under dimension；IijRepresent the desired value after standardization；ωijRepresent index weights；ωiRepresent dimension weight.
At village level misery index score is calculated according to formula, is 5 poor grades according to equidistant regular partition, grade Poor village's poverty depth is represented from low to high from shallow to deep.
2nd, the poor measurement of poor household's multidimensional is established：
1st, dimension and index are calculated first：
It is poor with global multidimensional for the business demand of the current development for poverty relief strategy in China based on multidimensional poverty theory Dimension and index system be frame, by national office of poverty alleviation file it is vertical be caught in family survey data based on, it is poor to establish family grade multidimensional Tired measuring and calculating dimension and index system.
Since effect of each dimension played in poor identification is different, so needing to consider during multidimensional poverty totalling each The weight of dimension and index.Proved by real examples such as correlation analysis and consistency checks, under conditions of different weights are selected, Multidimensional misery index is a sane index.So the processing to each dimension and index weights uses equal weight method, that is, pass through Welfare, living standard, health, the weight shared by each dimension of education of helping are equal；The sum of all dimension weighted values are 1, per dimension The weight of interior each base values is equal, i.e. the weighted value of the decile dimension.Such as index " drinking-water feelings in " living standard " dimension The weight (1/4) that the weighted value (1/20) of condition " is equal to " living standard " dimension is multiplied by " drinking water " index weights (1/5).
2nd, multidimensional poverty measuring method：
Measurement of poverty must comply with two steps：Identify the population below the poverty line in total population and the quantitative measurment side of structure poverty Method.Herein on the basis of dimension index system is built, use " double critical values " (depriving critical value+poverty critical value) multidimensional poor Tired measuring method carrys out poverty status of the poor individual of overall merit in constructed dimension index system.Wherein, dimension adds up Synthesis misery index-MPI of poor individual ownership dimension index can be calculated, dimension, which is decomposed, can then calculate each dimension Spend percentage contribution of the index to comprehensive misery index.
Family level multidimensional misery index (MPI) is calculated by formula, i.e., poor depth：
In formula：N represents dimension number；M represents the index number under respective dimensions；JijRepresent the desired value after standardization； vijRepresent index weights；viRepresent dimension weight.
At village level misery index score is calculated according to formula, is 5 poor grades according to equidistant regular partition, grade Poor household's poverty depth is represented from low to high from shallow to deep.
3rd, the spatialization of poor depth.
Poor household and the acquisition of poor village position：
Using the high definition remote sensing image after geometric correction is handled, obtained by priori from high definition remote sensing image The specific location of each poor household.
The spatialization displaying of poor depth：
By the way that multidimensional misery index is associated with poor household position, regional poor household's poverty depth profile is obtained, Here we use the cuclear density analysis tool in Arcgis, and minimum pixel unit is arranged to 0.001, and search radius is arranged to 0.02 display poverty depth Nesting Zone more directly perceived and clear area.
A kind of poverty depth analysis system, including：
Administrative at village level poor metric module, by obtaining administrative village data, splits data into some indexs, passes through multiple correlation Y-factor method Y simulates all index multiple correlation, establishes at village level poor Measure Indexes system, then assigns power index and weight, calculating obtain Take at village level multidimensional misery index VPI；
The poor metric module of family level, by obtaining the poor data of family level, establishes the poor measuring and calculating dimension of family level and index system, By using double critical value multidimensional poverty measuring methods come the poor individual of overall merit in constructed dimension index system it is each The poverty status of a dimension index, double critical values refer to deprive critical value and poor critical value, all dimensions are added and are converged Always, the synthesis misery index MPI of poor individual ownership dimension index is calculated；
Display module, it is poor from administrative at village level poor metric module, the at village level multidimensional of the poor metric module of family level to receive Index VPI, comprehensive misery index MPI, then by its with handled by geometric correction after high definition remote sensing image obtain it is each Poor household's specific location is associated, and is then shown.
The at village level poor metric module of the administration obtains at village level multidimensional misery index VPI in the following manner：
Associated analog is carried out by multiple correlation coefficient method again to all indexs of administrative village data of acquisition, after simulation The correlation of index screens index with discrimination：When multiple correlation coefficient is not 0, and recurrence probability is 0, represent Linear model is set up；Index degree of distinguishing of the multiple correlation coefficient more than 0.5 is examined, discrimination minimum is rejected；Again Multiple correlation simulation is repeated, multiple correlation coefficient reduces and below 0.5, and correlation is smaller between showing index；
Then an index item Xij and other multiple index X11, Xij-1, Xij+1 ... are measured in the following manner, Related coefficient between Xm ' n ', constructs the linear combination on X11, X12 ..., Xm ' n ', by calculating this linear group The simple correlation coefficient between Xij is closed as the multiple correlation coefficient between index Xij and X11, X12 ..., Xm ' n ', specifically Process is：
A, X11, X12 ..., Xm ' n ' are returned with Xij first, constructs following linear combination：
B, simple correlation coefficient, i.e. complex phase relation between Xij and X11, X12 ..., Xm ' n ' are calculated by the following formula Number：
In above-mentioned formulaExpression is the vector value that the variable carries out linear regression with other each variables,Table Show the average value of the variable.
C, at village level multidimensional misery index VPI is calculated by the following formula：
In formula：20 be constant, for eliminating decimal position influence, increases difference between data；N represents dimension number；M represents phase Answer the index number under dimension；IijRepresent the desired value after standardization；ωijRepresent index weights；ωiRepresent dimension weight.
The poor metric module of family level obtains family level multidimensional misery index MPI in the following manner：
A) the poor data of family level are obtained first, are established the poor measuring and calculating dimension of family level and index system according to the data, are being built The vertical poor measuring and calculating dimension of family level multidimensional to each dimension and index with index system, assigning weight, and to each dimension and refer to The processing of mark weight uses equal weight method：Weight shared by each dimension is equal, and the sum of all dimension weighted values are 1, per one-dimensional The weight of each base values is equal in degree, i.e. the weighted value of the decile dimension；
B) carry out the poor individual of overall merit by using double critical value multidimensional poverty measuring methods in constructed dimension to refer to The poverty status of each dimension index in mark system；
C) all dimensions are added and collected, calculate the synthesis misery index MPI of poor individual ownership dimension index：
In formula：N represents dimension number；M represents the index number under respective dimensions；JijRepresent the desired value after standardization； vijRepresent index weights；viRepresent dimension weight.
Above-mentioned embodiment is only the specific case of the present invention, and scope of patent protection of the invention includes but not limited to Above-mentioned embodiment, it is any to meet a kind of the claims of poor depth analysis method and system of the invention and appoint The appropriate change or replacement that the those of ordinary skill of what technical field does it, should all fall into the patent protection of the present invention Scope.

Claims (10)

  1. A kind of 1. poverty depth analysis method, it is characterised in that it realizes that process is：
    First, administrative village data are obtained first, obtain at village level misery index；
    Two and then poor user data is obtained, obtain family level misery index；
    3rd, spatialization is carried out to poor depth：The specific location of each poor household is obtained by high definition remote sensing image, by step First, the misery index obtained in two is associated with poor household position, so as to obtain regional poor household's poverty depth map.
  2. 2. a kind of poor depth analysis method according to claim 1, it is characterised in that in the step 1, establish village Level misery index process be：
    1) at village level poor Measure Indexes system is initially set up, i.e., according to the administrative village data of acquisition, is classified as some indexs, leads to Cross multiple correlation coefficient method to simulate all index multiple correlation, index is carried out according to the correlation of the index after simulation and discrimination Screening；
    2) weight setting is carried out to index and dimension；
    3) according to index and dimension after weighing is assigned in step 2), at village level multidimensional misery index VPI is calculated, i.e., poor depth.
  3. 3. a kind of poor depth analysis method according to claim 2, it is characterised in that in step 1), pass through complex phase When closing Y-factor method Y and carrying out associated analog, when multiple correlation coefficient is not 0, and return probability when being 0, represent linear model into It is vertical；Index degree of distinguishing of the multiple correlation coefficient more than 0.5 is examined, discrimination minimum is rejected；Repeat multiple correlation Simulation, multiple correlation coefficient reduce and below 0.5, and correlation is smaller between showing index.
  4. 4. a kind of poor depth analysis method according to Claims 2 or 3, it is characterised in that used in the step 1) Negative relations act refer to measure an index item Xij and other multiple index X11, Xij-1, Xij+ in the following manner Related coefficient between 1 ..., Xm ' n ', and the linear combination on X11, X12 ..., Xm ' n ' is constructed, pass through calculating Simple correlation coefficient between the linear combination and Xij is as the complex phase relation between index Xij and X11, X12 ..., Xm ' n ' Number：
    X11, X12 ..., Xm ' n ' are returned with Xij first, construct following linear combination：
    Simple correlation coefficient, i.e. multiple correlation coefficient between Xij and X11, X12 ..., Xm ' n ' are calculated by the following formula：
    In above-mentioned formulaExpression is the vector value that the variable carries out linear regression with other each variables,Representing should The average value of variable.
    Corresponding, the calculating process of at village level multidimensional misery index VPI is in step 3)：
    <mrow> <mi>V</mi> <mi>P</mi> <mi>I</mi> <mo>=</mo> <mn>20</mn> <msubsup> <mi>&amp;Sigma;</mi> <mrow> <mi>i</mi> <mo>-</mo> <mn>1</mn> </mrow> <mi>n</mi> </msubsup> <mrow> <mo>(</mo> <msubsup> <mi>&amp;Sigma;</mi> <mrow> <mi>j</mi> <mo>-</mo> <mn>1</mn> </mrow> <mi>m</mi> </msubsup> <msub> <mi>I</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <msub> <mi>&amp;omega;</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <mo>)</mo> </mrow> <msub> <mi>&amp;omega;</mi> <mi>i</mi> </msub> <mo>;</mo> </mrow>
    In formula：20 be constant, for eliminating decimal position influence, increases difference between data；N represents dimension number；M represents respective dimension Index number under degree；IijRepresent the desired value after standardization；ωijRepresent index weights；ωiRepresent dimension weight.
  5. 5. a kind of poor depth analysis method according to claim 1, it is characterised in that it is poor that the step 2 establishes family level The process of tired index is：
    (1) the poor data of family level are obtained first, and the poor measuring and calculating dimension of family level and index system are established according to the data；
    (2) the poor individual of overall merit is carried out in constructed dimension index body by using double critical value multidimensional poverty measuring methods The poverty status of each dimension index in system, double critical values refer to deprive critical value and poor critical value；
    (3) dimension adds up, and calculates the synthesis misery index MPI of poor individual ownership dimension index.
  6. A kind of 6. poor depth analysis method according to claim 5, it is characterised in that the family level established in step (1) The poor measuring and calculating dimension of multidimensional is with index system, assigning each dimension and index weight, and to each dimension and index weights Processing uses equal weight method：Weight shared by each dimension is equal, and the sum of all dimension weighted values are 1, per dimension Nei Geji The weight of plinth index is equal, i.e. the weighted value of the decile dimension.
  7. A kind of 7. poor depth analysis method according to claim 5 or 6, it is characterised in that in step (2) by with Lower formula calculates family level multidimensional misery index MPI：
    <mrow> <mi>M</mi> <mi>P</mi> <mi>I</mi> <mo>=</mo> <msubsup> <mi>&amp;Sigma;</mi> <mrow> <mi>i</mi> <mo>-</mo> <mn>1</mn> </mrow> <mi>n</mi> </msubsup> <mrow> <mo>(</mo> <msubsup> <mi>&amp;Sigma;</mi> <mrow> <mi>j</mi> <mo>-</mo> <mn>1</mn> </mrow> <mi>m</mi> </msubsup> <msub> <mi>J</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <msub> <mi>v</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <mo>)</mo> </mrow> <msub> <mi>v</mi> <mi>i</mi> </msub> <mo>;</mo> </mrow>
    In formula：N represents dimension number；M represents the index number under respective dimensions；JijRepresent the desired value after standardization；vijGeneration Table index weights；viRepresent dimension weight.
  8. A kind of 8. poverty depth analysis system, it is characterised in that including：
    Administrative at village level poor metric module, by obtaining administrative village data, splits data into some indexs, passes through multiple correlation coefficient Method simulates all index multiple correlation, establishes at village level poor Measure Indexes system, then assigns power index and weight, calculate and obtain village Level multidimensional misery index VPI；
    The poor metric module of family level, by obtaining the poor data of family level, establishes the poor measuring and calculating dimension of family level and index system, passes through Carry out the poor individual each dimension in constructed dimension index system of overall merit using double critical value multidimensional poverty measuring methods The poverty status of index is spent, double critical values refer to deprive critical value and poor critical value, all dimensions are added and are collected, are counted Calculate the synthesis misery index MPI of poor individual ownership dimension index；
    Display module, receives from administrative at village level poor metric module, the at village level multidimensional misery index of the poor metric module of family level VPI, comprehensive misery index MPI, then by its with handled by geometric correction after each poverty that obtains of high definition remote sensing image Family specific location is associated, and is then shown.
  9. A kind of 9. poor depth analysis system according to claim 8, it is characterised in that the at village level poor measurement of the administration Module obtains at village level multidimensional misery index VPI in the following manner：
    Associated analog is carried out by multiple correlation coefficient method again to all indexs of administrative village data of acquisition, according to the index after simulation Correlation index is screened with discrimination：When multiple correlation coefficient is not 0, and recurrence probability is 0, represent linear Model is set up；Index degree of distinguishing of the multiple correlation coefficient more than 0.5 is examined, discrimination minimum is rejected；Repeat Multiple correlation is simulated, and multiple correlation coefficient reduces and below 0.5, and correlation is smaller between showing index；
    Then an index item Xij and other multiple index X11, Xij-1, Xij+1 ..., Xm ' n ' are measured in the following manner Between related coefficient, construct the linear combination on X11, X12 ..., Xm ' n ', by calculate the linear combination with Simple correlation coefficient between Xij is as the multiple correlation coefficient between index Xij and X11, X12 ..., Xm ' n ', detailed process For：
    A, X11, X12 ..., Xm ' n ' are returned with Xij first, constructs following linear combination：
    B, simple correlation coefficient, i.e. multiple correlation coefficient between Xij and X11, X12 ..., Xm ' n ' are calculated by the following formula：
    <mrow> <mi>R</mi> <mo>=</mo> <mfrac> <mrow> <mi>&amp;Sigma;</mi> <mrow> <mo>(</mo> <msub> <mi>X</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <mo>-</mo> <mover> <msub> <mi>X</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <mo>&amp;OverBar;</mo> </mover> <mo>)</mo> </mrow> <mrow> <mo>(</mo> <msub> <mover> <mi>X</mi> <mo>^</mo> </mover> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <mo>-</mo> <mover> <msub> <mi>X</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <mo>&amp;OverBar;</mo> </mover> <mo>)</mo> </mrow> </mrow> <msqrt> <mrow> <mi>&amp;Sigma;</mi> <msup> <mrow> <mo>(</mo> <msub> <mi>X</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <mo>-</mo> <mover> <msub> <mi>X</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <mo>&amp;OverBar;</mo> </mover> <mo>)</mo> </mrow> <mn>2</mn> </msup> <msup> <mrow> <mo>(</mo> <msub> <mover> <mi>X</mi> <mo>^</mo> </mover> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <mo>-</mo> <mover> <msub> <mi>X</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <mo>&amp;OverBar;</mo> </mover> <mo>)</mo> </mrow> <mn>2</mn> </msup> </mrow> </msqrt> </mfrac> <mo>;</mo> </mrow>
    In above-mentioned formulaExpression is the vector value that the variable carries out linear regression with other each variables,Representing should The average value of variable.
    C, at village level multidimensional misery index VPI is calculated by the following formula：
    <mrow> <mi>V</mi> <mi>P</mi> <mi>I</mi> <mo>=</mo> <mn>20</mn> <msubsup> <mi>&amp;Sigma;</mi> <mrow> <mi>i</mi> <mo>-</mo> <mn>1</mn> </mrow> <mi>n</mi> </msubsup> <mrow> <mo>(</mo> <msubsup> <mi>&amp;Sigma;</mi> <mrow> <mi>j</mi> <mo>-</mo> <mn>1</mn> </mrow> <mi>m</mi> </msubsup> <msub> <mi>I</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <msub> <mi>&amp;omega;</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <mo>)</mo> </mrow> <msub> <mi>&amp;omega;</mi> <mi>i</mi> </msub> <mo>;</mo> </mrow>
    In formula：20 be constant, for eliminating decimal position influence, increases difference between data；N represents dimension number；M represents respective dimension Index number under degree；IijRepresent the desired value after standardization；ωijRepresent index weights；ωiRepresent dimension weight.
  10. A kind of 10. poor depth analysis system according to claim 8, it is characterised in that the poor measurement mould of family level Block obtains family level multidimensional misery index MPI in the following manner：
    A) the poor data of family level are obtained first, the poor measuring and calculating dimension of family level and index system are established according to the data, in foundation Level multidimensional poor measuring and calculating dimension in family to each dimension and index with index system, assigning weight, and each dimension and index are weighed The processing of weight uses equal weight method：Weight shared by each dimension is equal, and the sum of all dimension weighted values are 1, in every dimension The weight of each base values is equal, i.e. the weighted value of the decile dimension；
    B) the poor individual of overall merit is carried out in constructed dimension index body by using double critical value multidimensional poverty measuring methods The poverty status of each dimension index in system；
    C) all dimensions are added and collected, calculate the synthesis misery index MPI of poor individual ownership dimension index：
    <mrow> <mi>M</mi> <mi>P</mi> <mi>I</mi> <mo>=</mo> <msubsup> <mi>&amp;Sigma;</mi> <mrow> <mi>i</mi> <mo>-</mo> <mn>1</mn> </mrow> <mi>n</mi> </msubsup> <mrow> <mo>(</mo> <msubsup> <mi>&amp;Sigma;</mi> <mrow> <mi>j</mi> <mo>-</mo> <mn>1</mn> </mrow> <mi>m</mi> </msubsup> <msub> <mi>J</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <msub> <mi>v</mi> <mrow> <mi>i</mi> <mi>j</mi> </mrow> </msub> <mo>)</mo> </mrow> <msub> <mi>v</mi> <mi>i</mi> </msub> <mo>;</mo> </mrow>
    In formula：N represents dimension number；M represents the index number under respective dimensions；JijRepresent the desired value after standardization；vijGeneration Table index weights；viRepresent dimension weight.
CN201711318156.4A 2017-12-12 2017-12-12 A kind of poverty depth analysis method and system Pending CN107944750A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711318156.4A CN107944750A (en) 2017-12-12 2017-12-12 A kind of poverty depth analysis method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711318156.4A CN107944750A (en) 2017-12-12 2017-12-12 A kind of poverty depth analysis method and system

Publications (1)

Publication Number Publication Date
CN107944750A true CN107944750A (en) 2018-04-20

Family

ID=61942728

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711318156.4A Pending CN107944750A (en) 2017-12-12 2017-12-12 A kind of poverty depth analysis method and system

Country Status (1)

Country Link
CN (1) CN107944750A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108805396A (en) * 2018-04-23 2018-11-13 中国农业大学 The poor coupled relation evaluation method with natural calamity in area based on GIS
CN111415057A (en) * 2019-12-04 2020-07-14 信阳师范学院 Generation method and device of regional poverty degree grading diagram
WO2021248335A1 (en) * 2020-06-09 2021-12-16 中山大学 Method and system for measuring urban poverty spaces based on street view images and machine learning
CN114282934A (en) * 2021-03-30 2022-04-05 华南理工大学 Urban low-income crowd distribution prediction method and system based on mobile phone signaling data and storage medium

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
孙林 等: "内蒙古自治区农村人口多维贫困特征测算与分析", 《人文地理》 *
王艳慧: "村级贫困人口多维测算及其贫困特征分析--以河南省内乡县为例", 《人口与经济》 *
陈烨烽 等: "中国贫困村测度与空间分布特征分析", 《地理研究》 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108805396A (en) * 2018-04-23 2018-11-13 中国农业大学 The poor coupled relation evaluation method with natural calamity in area based on GIS
CN111415057A (en) * 2019-12-04 2020-07-14 信阳师范学院 Generation method and device of regional poverty degree grading diagram
CN111415057B (en) * 2019-12-04 2024-02-20 信阳师范学院 Method and device for generating regional poverty degree grading diagram
WO2021248335A1 (en) * 2020-06-09 2021-12-16 中山大学 Method and system for measuring urban poverty spaces based on street view images and machine learning
CN114282934A (en) * 2021-03-30 2022-04-05 华南理工大学 Urban low-income crowd distribution prediction method and system based on mobile phone signaling data and storage medium

Similar Documents

Publication Publication Date Title
Niu et al. Measuring urban poverty using multi-source data and a random forest algorithm: A case study in Guangzhou
González-García et al. Embedding environmental, economic and social indicators in the evaluation of the sustainability of the municipalities of Galicia (northwest of Spain)
Chen et al. Improving assessment of groundwater sustainability with analytic hierarchy process and information entropy method: a case study of the Hohhot Plain, China
CN107944750A (en) A kind of poverty depth analysis method and system
Fernando et al. Modified factor analysis to construct composite indices: illustration on urbanization index
CN106097222A (en) The communal facility spatial accessibility taking user characteristics into account analyzes method and device
CN103577888A (en) Improved entropy weight AHP and application thereof
CN105893770A (en) Method for quantifying influence on basin water resources by climate change and human activities
Paolotti et al. Territorial sustainability evaluation for policy management: The case study of Italy and Spain
CN114548771A (en) Method for evaluating development potential of country travel
CN104679942A (en) Construction land bearing efficiency measuring method based on data mining
Kaurova et al. Cross-country comparison of statistical indicators
Haara et al. Analyzing uncertainties and estimating priorities of landscape sensitivity based on expert opinions
Wang et al. Multidimensional spatiotemporal evolution detection on China’s rural poverty alleviation
CN104424373B (en) A kind of fine expression of space variable correlation
Zhang et al. Multi-hierarchical spatial clustering for characteristic towns in China: An Orange-based framework to integrate GIS and Geodetector
CN116663779B (en) Multi-depth fertility point-surface conversion method and device for cultivated land soil
Ameen et al. Environmental, social and economic challenges for urban development: Stakeholder’s perception in a developing economy
CN117010933A (en) Real estate market feature evaluation method based on model
CN114881309B (en) Method for measuring characteristic correlation between urban activity and carbon evacuation
Yu et al. Potential change of spatial accessibility to health services with the opening of private streets in Shenzhen, China
He et al. Applying a spatial decision support system to the integrated regional planning of China
Xiaolan et al. Determination of the weight values of assessment indexes of website based on AHP-take the website of university library as an example
Zhang et al. A method to determine the spatial allocation standard of social ecological compensation
Su et al. Improvement of a land fragmentation measurement model based on natural surface elements and road network

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
TA01 Transfer of patent application right

Effective date of registration: 20190516

Address after: 257045 China University of Petroleum (East China), 271 North Second Road, Dongying City, Shandong Province

Applicant after: China Petroleum University (East China)

Applicant after: Qingdao Zhongke Randy Mdt InfoTech Ltd

Applicant after: Inst of Geographic Science and Resources, Chiense Academy of Sciences

Address before: 266580 No. 66 Changjiang West Road, Qingdao economic and Technological Development Zone, Shandong

Applicant before: China Petroleum University (East China)

Applicant before: Qingdao Zhongke Randy Mdt InfoTech Ltd

TA01 Transfer of patent application right
RJ01 Rejection of invention patent application after publication

Application publication date: 20180420

RJ01 Rejection of invention patent application after publication