CN116911507A - Urban block vitality evaluation method and storage medium based on space projection pursuit - Google Patents
Urban block vitality evaluation method and storage medium based on space projection pursuit Download PDFInfo
- Publication number
- CN116911507A CN116911507A CN202310923601.9A CN202310923601A CN116911507A CN 116911507 A CN116911507 A CN 116911507A CN 202310923601 A CN202310923601 A CN 202310923601A CN 116911507 A CN116911507 A CN 116911507A
- Authority
- CN
- China
- Prior art keywords
- urban
- block
- projection
- vitality
- index
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 105
- 238000003860 storage Methods 0.000 title claims abstract description 9
- 239000013598 vector Substances 0.000 claims abstract description 52
- 238000000034 method Methods 0.000 claims abstract description 36
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 29
- 230000002068 genetic effect Effects 0.000 claims abstract description 25
- 238000005457 optimization Methods 0.000 claims abstract description 21
- 238000009826 distribution Methods 0.000 claims abstract description 13
- 238000011160 research Methods 0.000 claims abstract description 10
- 230000000694 effects Effects 0.000 claims description 59
- 238000004364 calculation method Methods 0.000 claims description 26
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 7
- 230000035772 mutation Effects 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000005520 cutting process Methods 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims description 3
- 238000012217 deletion Methods 0.000 claims description 3
- 230000037430 deletion Effects 0.000 claims description 3
- 238000011425 standardization method Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 abstract description 2
- 238000004458 analytical method Methods 0.000 abstract 1
- 238000004445 quantitative analysis Methods 0.000 abstract 1
- 238000011161 development Methods 0.000 description 4
- 239000000203 mixture Substances 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 240000002853 Nelumbo nucifera Species 0.000 description 2
- 235000006508 Nelumbo nucifera Nutrition 0.000 description 2
- 235000006510 Nelumbo pentapetala Nutrition 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 2
- 241000272814 Anser sp. Species 0.000 description 1
- 229920002430 Fibre-reinforced plastic Polymers 0.000 description 1
- 230000004308 accommodation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 235000013361 beverage Nutrition 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000011151 fibre-reinforced plastic Substances 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- 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
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Biophysics (AREA)
- Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Biology (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Educational Administration (AREA)
- Physiology (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Genetics & Genomics (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Primary Health Care (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A city block vitality evaluation method based on space projection pursuit and a storage medium, wherein the method utilizes multisource city geographic data to obtain an evaluation index of city block vitality; the space projection pursuit method of multi-objective optimization is provided, two objective functions are defined to extract variation information to the greatest extent and minimize the neighborhood distance with the closer projection value respectively; fusing the two objective functions through a multi-objective genetic algorithm to obtain an optimal projection vector; and calculating a block comprehensive vitality value based on the projection vector and the evaluation index, and analyzing spatial distribution characteristics and influence factors of urban vitality of the research area. According to the method, multidimensional geographic data is utilized for dimension reduction, a one-dimensional optimal projection solution set is obtained, a traditional projection pursuit model is improved, the space influence between street areas is considered, quantitative analysis is carried out on urban vitality by utilizing a multi-objective optimized genetic algorithm, and the accuracy and reliability of urban neighborhood comprehensive vitality analysis are improved.
Description
Technical Field
The invention relates to the technical field of urban research, in particular to a city block vitality evaluation method and a storage medium based on a space projection pursuit model.
Background
Under the background of globalization and rapid promotion of urban progress, population flow is accelerated, urban area is rapidly enlarged, and urban vitality becomes an important index for measuring urban development progress. Jacobs introduced the concept of urban vitality in the book of life and death in the united states major city, and thought that urban vitality comes from the diversity of internal life, and the spatial interaction process of people and their daily activities constitutes the diversity of life, which itself brings and stimulates the generation of more diversity. Urban planners and managers are increasingly interested in quantitatively analyzing urban vitality, and become key factors for promoting urban healthy development and improving human life quality.
In recent years, with the wide application of wireless networks, space positioning technology and intelligent terminal equipment, massive multi-source urban geographic data, such as mobile phone signaling, land utilization data, infrastructure data, social media data and the like, are accumulated and formed, and a data basis is provided for understanding urban development and planning. However, existing research has typically used a few data sources to measure urban vitality, a single data source reflecting only a certain aspect of urban vitality. For example, a community of residents in a metropolitan area may have fewer points of interest, but have a high population density and a high night light index. Meanwhile, urban vitality tends to show a gathering effect, and the closer the blocks are, the more similar the urban vitality values are. However, the spatial correlation between the neighborhood activities is difficult to consider by the traditional projection pursuit, linear regression, entropy weight method and other evaluation methods. Therefore, the spatial influence of the street intervals is considered while the multisource geospatial data is used, so that urban vitality can be measured from multiple angles, deviation caused by a single data source is avoided, and spatial features of urban vitality distribution can be well mined.
Disclosure of Invention
The invention aims to provide a city block vitality evaluation method based on space projection pursuit and a storage medium thereof, which are used for solving the problems in the background technology and realizing the comprehensive vitality evaluation of the city block.
To achieve the purpose, the invention adopts the following technical scheme:
a city block vitality evaluation method based on a space projection pursuit model comprises the following steps:
a multisource geographic data collection and preprocessing step S110:
acquiring required urban activity comprehensive evaluation data, wherein the urban activity comprehensive evaluation data comprises basic geographic data, urban geographic data and remote sensing data, preprocessing the urban activity comprehensive evaluation data, including data cutting, duplicate removal value, deletion value and projection conversion, dividing blocks based on the basic geographic data, and deleting block units with smaller areas as a research area;
city vitality evaluation index construction step S120:
calculating an urban activity evaluation index by taking the block obtained by dividing in the step S110 as a basic unit, and standardizing the urban activity evaluation index according to positive and negative influences;
improved multi-objective optimized spatial projection pursuit model step S130:
constructing a multi-objective optimized projection function, constructing a first objective function maximization inter-class distance function and a second objective function minimization distance function, using the element square sum of projection vectors to meet the constraint condition that the square sum is 1, and solving the multi-objective optimization problem by using a non-dominant order genetic algorithm (NSGA-II) according to the multi-objective optimized projection function, the two objective functions and the constraint condition, and calculating an optimal projection vector;
and (S140) evaluating urban comprehensive activity results:
and calculating the urban comprehensive activity value according to the optimal projection vector and the standardized evaluation index obtained by the calculation in the step S130, dividing the urban street into a plurality of grades by adopting a fractional number method, and evaluating the spatial distribution result of the urban activity according to the grading result.
Optionally, the multisource urban geographic data acquisition substep S111:
the urban activity comprehensive evaluation data mainly comprises basic geographic data, urban geographic data and remote sensing data,
wherein: the basic geographic data comprise administrative division, road network, railway network and water system data; the urban geographic data comprise POIs, buildings, bus stops, subway stops and population density data; the remote sensing data product comprises land utilization data;
street block division substep S112:
dividing an urban area into a plurality of polygonal areas with different sizes according to a highway network, a railway network and a water system, sorting the widths of all levels of roads according to an actual road network of the city, establishing a street space by taking the road widths as buffer radii, and merging buffer data of all levels of road networks; the road buffer area and the river are erased by using the planar research area, and vector data of the city block is preliminarily obtained; blocks that are too small to take on social and economic functions are inspected and deleted.
Optionally, the step S120 of constructing the urban vitality assessment index includes the following sub-steps:
evaluation index calculation substep S121:
the urban vitality evaluation indexes comprise 10 evaluation indexes of POI density, POI mixing degree, land utilization mixing degree, bus station density, distance of nearest subway stations, building occupied area, volume rate, built-up area occupation ratio, population density and greening rate of each block, and the urban vitality evaluation indexes are calculated by utilizing the urban vitality comprehensive evaluation data;
index normalization substep S122:
according to whether the influence direction of the evaluation index on the urban vitality is a positive index or a negative index, the evaluation index with the higher urban vitality and the smaller urban vitality is the negative index, the evaluation index with the higher urban vitality and the larger urban vitality is the positive index, and different standardization methods are selected according to the influence direction of the index on the urban vitality to carry out index standardization.
Optionally, the step S130 of the multi-objective optimized spatial projection tracking model specifically includes:
the projection function sub-step S131 of constructing the multi-objective optimization:
let a= { a 1 ,a 2 ,…,a n The number of the evaluation indexes is represented by the projection vector, n is represented by a j Indicating index x j Corresponding projection value, x= { X ij I=1, 2, m; j=1, 2,..n } is the evaluation index matrix, x ij The j index value representing the i block is obtained by reducing the dimension of the multidimensional evaluation index data and projecting the multidimensional evaluation index data to form a comprehensive index Z= { Z i I=1, 2,..m }, the calculation formula of the projection function is:
wherein z is i A comprehensive activity value, also called comprehensive projection value, a, representing block i j As a vector to be solved, representing a projection value of a j-th evaluation index, and m represents the number of blocks;
building an objective function substep S132:
defining a first objective function Q 1 (a) The calculation formula is as follows:
Q 1 (a)＝S(Z)D(Z)
s (Z) represents the inter-class distance, calculated by the variance of the integrated projection values:
d (Z) represents the inter-class distance, calculated by the distance of the integrated projection value:
wherein n represents the number of evaluation indexes; m represents the number of blocks; z i Representing the integrated projection value of the ith block;representing an average value of the integrated projection values; r is a window width parameter for estimating local scattered point density; u (R-R (i, k)) represents a unit step function, u (·) =1 when R-R (i, k) > 0, otherwise u (·) =0; r (i, k) = |z i -z k The i represents the absolute value of the difference of the integrated projection values between two blocks;
defining a second objective function Q 2 (a) The calculation formula is as follows:
wherein d (pos) i ,pos k ) Representing the geographic distance between neighborhood i and neighborhood k; m represents the number of blocks; beta is a constant; w (w) ik Is a positive function, and the more similar the comprehensive projection values are between two blocks, w ik The smaller a is the projection vector, X i An evaluation index vector indicating the ith block;
the multi-objective genetic algorithm solves projection vector sub-step S133:
according to the projection function, the two objective functions and the limiting condition, solving the multi-objective optimization problem by using a non-dominant sorting genetic algorithm NSGA-II, calculating projection vectors, and finding an optimal solution set for enabling the first objective function to reach the maximum value and enabling the second objective function to reach the minimum value.
Optionally, in the construct objective function sub-step S132,
the optimization problem of converting the search for the optimal projection vector into an objective function, the first objective function being to extract x as large as possible ij Variation information Max { Q } 1 (a) The purpose of the second objective function is to minimize the distance function Min { Q } taking into account the spatial correlation 2 (a) Meanwhile, the sum of squares of elements of the projection vector needs to satisfy the constraint that the sum of squares is 1:
optionally, in the multi-source city geographic data acquisition sub-step S111,
the road network comprises expressways, primary roads, secondary roads and tertiary roads, the POIs comprise a plurality of major categories, and the land utilization data has a plurality of categories.
Optionally, in the step S121 of calculating the evaluation index, the method for calculating the urban vitality evaluation index is as follows:
POI density = total number of POIs/block area within a block of 20 meters buffer,
bus stop density = total number of bus stops/block area within a block of 20 meters,
the POI and land utilization mixedness is calculated using shannon entropy,
distance of nearest subway station = euclidean distance of neighborhood center point to nearest subway station;
building footprint = building area within a block/total block area,
build area ratio = build area within a block/total area of the block,
greening rate = greening land area within a block/total block area,
volume ratio = sum of indoor areas of buildings in a block/total area of block, total indoor area of a single building is equal to building floor area multiplied by number of floors,
population density = average of the grid population density values contained within a neighborhood.
Optionally, in the index normalization sub-step S122,
the negative indicators include: the distance between nearest subway stations, the land utilization mixing degree and the greening rate; the other indexes are negative indexes;
the normalized calculation formula of the forward index is:
the standardized calculation formula of the negative index is as follows:
wherein x is max,j Represents the maximum value, x, of the j-th index min,j Represents the minimum value, x, of the j-th index ij The j index value indicating the i-th neighborhood.
Optionally, in the multi-objective genetic algorithm solution projection vector sub-step S133,
in the non-dominant ranking genetic algorithm NSGA-II, parameters to be set include iteration times, initial iteration population numbers, crossover probability and mutation rate,
setting the iteration times to 100 in the experimental process, wherein the initial iteration population numbers are respectively 50, 100, 150 and 200, the crossover probability is 0.7, the mutation rate is 1/n, and n represents the index number.
The invention further discloses a storage medium for storing computer executable instructions that, when executed by a processor, perform the above-described city block vitality assessment method based on spatial projection pursuit.
The invention has the following beneficial effects:
(1) A plurality of acquirable evaluation indexes are extracted from the multi-source geospatial data, so that urban vitality can be measured from a plurality of angles, and deviation caused by a single data source is avoided.
(2) And the projection pursuit model algorithm is adopted to project the high-dimensional data onto the low-dimensional subspace, so as to find out the optimal projection direction capable of reflecting the original high-dimensional data, and the method is favorable for evaluating the urban vitality by adopting multiple sources and multiple indexes.
(3) The traditional projection pursuit model is improved, the space influence of a street interval is considered, and two objective functions are constructed to find the optimal projection vector.
(4) And the multi-objective function is solved by utilizing a multi-objective optimized genetic algorithm, so that the spatial characteristics of urban activity distribution are better mined, and the accuracy and reliability of urban comprehensive activity evaluation are improved.
Drawings
FIG. 1 is a flowchart of a city block vitality assessment method based on a spatial projection pursuit model in accordance with an embodiment of the present invention;
fig. 2 is an example of a spatial distribution of comprehensive activity in a central urban area of the western security city, in accordance with an embodiment of the present invention.
Detailed Description
The invention is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting thereof. It should be further noted that, for convenience of description, only some, but not all of the structures related to the present invention are shown in the drawings.
The invention is characterized in that: widening data sources, acquiring evaluation indexes of urban block vitality by utilizing multi-source urban geographic data, solving the problem of multi-target optimization by utilizing a non-dominant ranking genetic algorithm NSGA-II by utilizing a space projection pursuit method of multi-target optimization, calculating projection vectors, and comprehensively evaluating the block vitality. The invention fuses two objective functions based on a genetic algorithm of multi-objective optimization, reduces the dimension of a multi-dimensional evaluation index to obtain an optimal projection solution set, and obtains the comprehensive activity value of a city block.
Referring to fig. 1, a flow chart of a city block vitality assessment method based on a spatial projection pursuit model is shown in accordance with a specific embodiment of the present invention.
A multisource geographic data collection and preprocessing step S110:
the method comprises the steps of obtaining required urban activity comprehensive evaluation data, wherein the urban activity comprehensive evaluation data comprises basic geographic data, urban geographic data and remote sensing data, preprocessing the urban activity comprehensive evaluation data, comprising data cutting, duplicate removal value, deletion value and projection conversion, dividing blocks based on the basic geographic data, and deleting block units with smaller areas to serve as a research area.
Specifically, the step S110 of collecting and preprocessing the multi-source geographic data includes the following sub-steps:
multisource city geographic data acquisition substep S111:
the urban vitality comprehensive evaluation data mainly comprises basic geographic data, urban geographic data and remote sensing data, and specifically comprises administrative division, road network, railway network, water system, POI, building, bus station, subway station, population density, land utilization data and the like.
Wherein: the basic geographic data comprise administrative division, road network, railway network and water system data, and the basic geographic data are from an open street map OpenStreetMap in 2022 years by way of example;
the urban geographic data includes POI, building, bus stops, subway stops, and population density data. Wherein, the POI, building, bus station and subway station data come from a Goldmap with the time of 2022; population density data is from the world population space dataset of world pop for 2020;
the remote sensing data product includes land utilization data, illustratively global land utilization and land coverage data sets from guard number 2 (Sentinel-2) 2021.
Specifically, the road network comprises expressways, primary roads, secondary roads, tertiary roads and other categories; the POI data is in 14 major categories, including food and beverage, company enterprises, shopping consumption, traffic facilities, financial institutions, hotel accommodations, scientific, teaching and cultural, tourist attractions, automobile correlations, business houses, life services, leisure and entertainment, medical care and sports and fitness; land utilization data is 8 in total, including water bodies, trees, flooded vegetation, crops, built-up areas, bare land, ice and snow, clouds and pastures.
Street block division substep S112:
since the block is an area surrounded by roads and rivers, lakes, etc. are natural dividing elements, the urban area is divided into a plurality of polygonal areas having different sizes according to road networks, railway networks, and water systems. The width of the roads of different levels is different.
The invention takes the city district of the western security city as an example, and arranges the width of each level of road according to the actual road network of the city. The width of the railway and the expressway is 50 meters, the width of the primary road is 40 meters, the width of the secondary road is 30 meters, and the width of the tertiary road is 20 meters.
Because the road space does not belong to the block range, the road width is taken as the radius of the buffer area to establish the street space, and the buffer area data of each level of road network are combined; and (5) using the planar research area to erase the road, railway network buffer area and river area, and preliminarily obtaining the planar vector data of the city block. Finally, blocks with too small an area to take on social and economic functions are inspected and deleted. In the example of the present invention, 1399 blocks are obtained in the central urban area of western security.
City vitality evaluation index construction step S120:
and (2) calculating urban vitality evaluation indexes by taking the blocks obtained by dividing in the step (S110) as basic units, wherein the urban vitality evaluation indexes comprise 10 evaluation indexes such as POI density, POI mixing degree, land utilization mixing degree, bus station density, distance of nearest subway stations, building occupied area, volume rate, built-up area occupation ratio, population density, greening rate and the like of each block, and the urban vitality evaluation indexes are standardized according to positive and negative influences.
Specifically, the city vitality evaluation index construction step S120 includes the following sub-steps:
evaluation index calculation substep S121:
the urban vitality evaluation index comprises 10 evaluation indexes of POI density, POI mixing degree, land utilization mixing degree, bus station density, distance of nearest subway stations, building occupied area, volume rate, built-up area occupation ratio, population density and greening rate of each block, and the urban vitality comprehensive evaluation data is utilized to calculate the urban vitality evaluation index.
Table 1 evaluation index and data source
POI density = total number of POIs/block area within a block 20 meter buffer;
bus stop density = total number of bus stops/block area in block 20 meters buffer;
the POI and land utilization mixedness is calculated using shannon entropy,
when the POI mix is calculated,p i representing the ratio of the number of i-th POIs in a 20-meter buffer area of the neighborhood to the total number of POIs in the buffer area;
when the degree of land use mix is calculated,p i representing the ratio of the ith land use type area in the neighborhood to the area of the neighborhood;
distance of nearest subway station = euclidean distance of neighborhood center point to nearest subway station;
building footprint = building area within a block/total block area;
build area ratio = build area within a block/total area of the block;
greening rate = greening land area within a neighborhood/total neighborhood area;
volume ratio = sum of indoor areas of buildings within a block/total area of block, the total indoor area of a single building being equal to the building footprint multiplied by the number of floors.
Population density = average of the grid population density values contained within a neighborhood.
The POI density and the bus stop density. Because the road space does not belong to the neighborhood, and many POIs and bus stops are located in the road space, the direct use of the POIs or bus stop data in the neighborhood can cause data loss. Meanwhile, the POIs and bus stops in the road space have service functions on nearby blocks, so that the number of POIs or bus stops in a 20-meter buffer area of the block can be used, and the POI density and the bus stop density can be obtained by dividing the area of the block. The world pop global population space dataset is kilometer grid data, so the population density of a block is represented using an average of the grid population density values contained within the block.
Index normalization substep S122:
and judging whether the index is a positive index or a negative index according to the influence of the evaluation index on the urban vitality. The evaluation index with the higher urban activity index being smaller is a negative index, and the evaluation index with the higher urban activity index being larger is a positive index. And selecting different standardization methods according to the influence direction of the index on the urban vitality to carry out index standardization.
The distance of the nearest subway station, the land utilization mixing degree and the greening rate in the evaluation indexes are negative indexes, and other indexes are positive indexes. This is because urban activity is closely related to human activities and the built environment, and the more distant from subway stations, the more complex the land utilization and the higher the greening rate, the less human activities are likely to be, the lower the urban construction level and the lower the urban activity.
Optionally, the normalized calculation formula of the forward index is:
optionally, the normalized calculation formula of the negative indicator is:
wherein the method comprises the steps of，x max,j Represents the maximum value, x, of the j-th index min,j Represents the minimum value, x, of the j-th index ij The j index value indicating the i-th neighborhood.
Improved multi-objective optimized spatial projection pursuit model step S130:
the projection pursuit model is a statistical method for processing and analyzing high-dimensional data, projects the high-dimensional data onto a low-dimensional subspace, and finds out the projection reflecting the structure or the characteristic of the original high-dimensional data, so that the projection pursuit model is applied to urban vitality assessment. Urban vitality presents a spatial aggregation distribution pattern, communities with high vitality have positive effects on surrounding areas, and surrounding communities also present higher vitality levels. Meanwhile, the evaluation index of the comprehensive urban activity plays a role in forming the spatial distribution mode. However, the conventional projection model does not consider space factors, and only uses the evaluation index to calculate urban comprehensive activity.
Therefore, the invention provides an improved multi-target optimized space projection tracking model, a second objective function is added on the basis of the traditional projection tracking model, the influence of space factors is embedded, and the reliability of comprehensive activity value calculation is improved.
Constructing a multi-objective optimized projection function, constructing a first objective function maximization inter-class distance function and a second objective function minimization distance function, taking the sum of squares of the element squares of projection vectors as a limiting condition, solving the multi-objective optimization problem by using a Non-dominant ordered genetic algorithm (Non-dominated Sorting Genetic Algorithms, NSGA-II) according to the multi-objective optimized projection function, the two objective functions and the limiting condition, and calculating the optimal projection vector.
Specifically, the improved multi-objective optimized spatial projection tracking model step S130 includes the following sub-steps:
the projection function sub-step S131 of constructing the multi-objective optimization:
let a= { a 1 ,a 2 ,…,a n The number of the evaluation indexes is represented by the projection vector, n is represented by a j Indicating index x j Corresponding projection values. X= {x ij I=1, 2, m; j=1, 2,..n } is the evaluation index matrix, x ij The j index value indicating the i-th neighborhood. The target of space projection pursuit of multi-target optimization is to reduce the dimension of multi-dimensional evaluation index data, and the projection forms a comprehensive index Z= { Z i I=1, 2,..m }. The calculation formula of the projection function is as follows:
wherein z is i A comprehensive activity value, also called comprehensive projection value, a, representing block i j The vector to be solved is a projection value representing the j-th evaluation index, and m represents the number of blocks.
Illustratively, in the embodiment of the present invention, n represents the number of evaluation indexes, which is 10, m represents the number of blocks, which is 1399.
a＝{a 1 ,a 2 ,…,a 10 Is projection vector, a j Indicating index x j Corresponding projection values. X= { X ij I=1, 2, 1399; j=1, 2,..10 } is the evaluation index matrix, x ij The j index value indicating the i-th neighborhood. The target of space projection pursuit of multi-target optimization is to reduce the dimension of multi-dimensional evaluation index data, and the projection forms a comprehensive index Z= { Z i I=1, 2,..1399 }. The calculation formula of the projection function is as follows:
wherein z is i A comprehensive activity value representing a neighborhood i, also referred to as a comprehensive projection value; a, a j Indicating index x j Corresponding projection values.
Building an objective function substep S132:
defining a first objective function Q 1 (a) In calculating the projection vector, the projection value z is required i Can extract x as large as possible ij The variation information in (a) is that the local projection values are concentrated as much as possible to form a plurality of pointsThe clusters as a whole are as dispersed as possible. First objective function Q 1 (a) The calculation formula of (2) is as follows:
Q 1 (a)＝S(Z)D(Z)
wherein S (Z) represents the inter-class distance, calculated by the variance of the integrated projection values:
d (Z) represents the inter-class distance, calculated by the distance of the integrated projection value:
wherein n represents the number of evaluation indexes, and the value is 10; m represents the number of blocks, here the value 1399; z i Representing the integrated projection value of the ith block; z represents the average value of the integrated projection values; r is a window width parameter for estimating local scattered point density, the value of the window width parameter is related to an index data structure, and the principle that at least one point is included in the width is required to be satisfied; u (R-R (i, k)) represents a unit step function, u (·) =1 when R-R (i, k) > 0, otherwise u (·) =0; r (i, k) = |z i -z k The i represents the absolute value of the difference in the integrated projection values between two blocks.
Defining a second objective function Q 2 (a) A. The invention relates to a method for producing a fibre-reinforced plastic composite According to the first law of geography, anything is related to other things, and similar things are more closely related. The more likely the urban vitality values between adjacent blocks are similar, the higher vitality blocks tend to radiate the surrounding blocks. Based on the assumption, a second objective function is constructed, and the calculation formula is as follows:
wherein d (pos) i ,pos k ) Representing the geographic distance between the block i and the block k, and m represents the number of blocks and takes on the value of 1399; beta is a constant, and the value is determined to be 2 through experiments; w (w) ik Is a positive function, and the more similar the comprehensive projection values are between two blocks, w ik The smaller; a is a projection vector; x is X i An evaluation index vector indicating the i-th block.
The optimization problem of converting the found optimal projection vector into an objective function, S132 in the sub-step of constructing the objective function, the objective of the first objective function is to extract x as large as possible ij Variation information Max { Q } 1 (a) The purpose of the second objective function is to minimize the distance function Min { Q } taking into account the spatial correlation 2 (a) And (3) is performed. Meanwhile, the sum of squares of elements of the projection vector needs to satisfy the constraint that the sum of squares is 1:
the multi-objective genetic algorithm solves projection vector sub-step S133:
and solving the multi-objective optimization problem by using a non-dominant ordering genetic algorithm NSGA-II according to the projection function, the two objective functions and the limiting condition, and calculating to obtain an optimal projection vector.
The traditional genetic algorithm is difficult to solve the multi-objective optimization problem, the non-dominant ranking genetic algorithm NSGA-II reduces the complexity of the non-inferior ranking genetic algorithm, has the advantages of high running speed and good convergence of solution sets, and becomes a benchmark for the performance of other multi-objective optimization algorithms. The core of NSGA-II is to coordinate the relationships between the objective functions, find the optimal solution set that maximizes the first objective function and minimizes the second objective function.
In the NSGA-II algorithm, parameters to be set include iteration times, initial iteration population numbers, crossover probability and mutation rate. Because the genetic algorithm is difficult to obtain the unique optimal solution, the iteration times are set to 100 in the experimental process, the initial iteration population numbers are respectively 50, 100, 150 and 200, the crossover probability is 0.7, the mutation rate is 1/n, n represents the index number, and the value is 10. Multiple calculations are performed under each initial iterative population.
Preferably, the above-mentioned multi-objective optimized spatial projection pursuit model can be implemented by Matlab. The invention takes the central urban area of the western security city as a research area. Calculating optimal projection vectors by taking 10 evaluation indexes as input variables, wherein table 2 is an optimal projection vector list:
table 2 list of optimal projection vectors
Note that: x1: POI density; x2: functional mix density; x3: land utilization mixing degree; x4: population density; x5: density of bus stops; x6: distance (m) from nearest subway station; x7: greening rate; x8: building area ratio; x9: volume rate; x10: area ratio of the built-up area.
It can be seen that the area occupation ratio of the built-up area, the greening rate and the land utilization mixing degree are the largest among the 10 indexes, so that the three evaluation indexes have the largest contribution to the comprehensive activity.
And (S140) evaluating urban comprehensive activity results:
and calculating the urban comprehensive activity value according to the optimal projection vector and the standardized evaluation index obtained by the calculation in the step S130, dividing the urban street into a plurality of grades by adopting a fractional number method, and evaluating the spatial distribution result of the urban activity according to the grading result.
Specifically, the method comprises the following substeps:
urban comprehensive activity calculation substep S141:
obtaining an optimal projection characteristic value z of each block in a one-dimensional linear space according to the optimal projection vector a calculated in S130 i Comprising:
z i ＝a×x i
wherein z is i The optimal projection characteristic value of index data representing the block i in a one-dimensional linear space, namely the comprehensive activity value; a represents the most significantAnd optimizing the projection vector.
Urban neighborhood comprehensive activity evaluation substep S142:
dividing the block vitality into five grades by using a quantile method according to the calculated comprehensive vitality value: high activity, medium activity, low activity and low activity. And correlating the comprehensive vitality value with the block space data, and analyzing the space distribution characteristics of the vitality of the city block.
Referring to fig. 2, a spatial distribution of comprehensive activity in the central urban area of the western security city is shown. Taking the optimal projection vector with the number 1 in table 2 as an example, the projection vector is divided into five levels according to comprehensive vitality values, wherein the high vitality [1.855,2.411 ], the higher vitality [1.834,1.855), the medium vitality [1.783,1.834 ], the lower vitality [1.222,1.783) and the low vitality [0.222,1.222 ]. It can be seen that the area with the highest urban activity value is located in the lotus and lake area, the tombstone area, the new urban area and the Yanta tower area, and in addition, a high-value gathering area of urban activity exists near the second line of the non-central area, in the east three rings of the bridge area and in the north part of the Changan area. Urban vitality in the central urban area of the western city is higher in the economically developed and densely populated areas, and gradually decreases from the higher areas outwards. Wherein, wild goose tower district Datang lotus garden and Qu Jiang site park belong to medium activity district and are park scenic spot, and POI is less, population density is lower, is surrounded by high activity street district. The method can correctly reflect the urban vitality distribution rule of the central urban area of the western security city.
The invention further discloses a storage medium for storing computer executable instructions which, when executed by a processor, perform the above-described city block vitality assessment method based on a spatial projection pursuit model.
In summary, the invention utilizes the multi-source urban geographic data to acquire the evaluation index of urban block vitality, and provides a space projection pursuit method of multi-objective optimization to comprehensively evaluate the block vitality. The method defines two objective functions which are respectively used for extracting variation information to the greatest extent and minimizing the neighborhood distance with a relatively close projection value, the two objective functions are fused through a multi-objective genetic algorithm, and the multi-dimensional evaluation index is subjected to dimension reduction to obtain an optimal projection solution set. The method can well quantitatively evaluate the urban vitality, analyze the contributions of different indexes and improve the accuracy and reliability of calculating the urban neighborhood comprehensive vitality value; further provides scientific decisions for city planning and construction, and promotes the high-quality development of cities.
The invention has the following beneficial effects:
(1) A plurality of acquirable evaluation indexes are extracted from the multi-source geospatial data, so that urban vitality can be measured from a plurality of angles, and deviation caused by a single data source is avoided.
(2) And the projection pursuit model algorithm is adopted to project the high-dimensional data onto the low-dimensional subspace, so as to find out the optimal projection direction capable of reflecting the original high-dimensional data, and the method is favorable for evaluating the urban vitality by adopting multiple sources and multiple indexes.
(3) The traditional projection pursuit model is improved, the space influence of a street interval is considered, and two objective functions are constructed to find the optimal projection vector.
(4) And the multi-objective function is solved by utilizing a multi-objective optimized genetic algorithm, so that the spatial characteristics of urban activity distribution are better mined, and the accuracy and reliability of urban comprehensive activity evaluation are improved.
It will be apparent to those skilled in the art that the elements or steps of the invention described above may be implemented in a general purpose computing device, they may be concentrated on a single computing device, or they may alternatively be implemented in program code executable by a computer device, such that they may be stored in a storage device for execution by the computing device, or they may be separately fabricated into individual integrated circuit modules, or a plurality of modules or steps in them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
While the invention has been described in detail in connection with specific preferred embodiments thereof, it is not to be construed as limited thereto, but rather as a result of a simple deduction or substitution by a person having ordinary skill in the art without departing from the spirit of the invention, which is to be construed as falling within the scope of the invention defined by the appended claims.
Claims (10)
1. A city block vitality evaluation method based on a space projection pursuit model is characterized by comprising the following steps:
a multisource geographic data collection and preprocessing step S110:
acquiring required urban activity comprehensive evaluation data, wherein the urban activity comprehensive evaluation data comprises basic geographic data, urban geographic data and remote sensing data, preprocessing the urban activity comprehensive evaluation data, including data cutting, duplicate removal value, deletion value and projection conversion, dividing blocks based on the basic geographic data, and deleting block units with smaller areas as a research area;
city vitality evaluation index construction step S120:
calculating an urban activity evaluation index by taking the block obtained by dividing in the step S110 as a basic unit, and standardizing the urban activity evaluation index according to positive and negative influences;
improved multi-objective optimized spatial projection pursuit model step S130:
constructing a multi-objective optimized projection function, constructing a first objective function maximization inter-class distance function and a second objective function minimization distance function, using the element square sum of projection vectors to meet the constraint condition that the square sum is 1, and solving the multi-objective optimization problem by using a non-dominant order genetic algorithm (NSGA-II) according to the multi-objective optimized projection function, the two objective functions and the constraint condition, and calculating an optimal projection vector;
and (S140) evaluating urban comprehensive activity results:
and calculating the urban comprehensive activity value according to the optimal projection vector and the standardized evaluation index obtained by the calculation in the step S130, dividing the urban street into a plurality of grades by adopting a fractional number method, and evaluating the spatial distribution result of the urban activity according to the grading result.
2. The method for evaluating urban block vitality according to claim 1, wherein,
multisource city geographic data acquisition substep S111:
the urban activity comprehensive evaluation data mainly comprises basic geographic data, urban geographic data and remote sensing data,
wherein: the basic geographic data comprise administrative division, road network, railway network and water system data; the urban geographic data comprise POIs, buildings, bus stops, subway stops and population density data; the remote sensing data product comprises land utilization data;
street block division substep S112:
dividing an urban area into a plurality of polygonal areas with different sizes according to a highway network, a railway network and a water system, sorting the widths of all levels of roads according to an actual road network of the city, establishing a street space by taking the road widths as buffer radii, and merging buffer data of all levels of road networks; the road buffer area and the river are erased by using the planar research area, and vector data of the city block is preliminarily obtained; blocks that are too small to take on social and economic functions are inspected and deleted.
3. The method for evaluating urban block vitality according to claim 1, wherein,
the city vitality evaluation index construction step S120 includes the following sub-steps:
evaluation index calculation substep S121:
the urban vitality evaluation indexes comprise 10 evaluation indexes of POI density, POI mixing degree, land utilization mixing degree, bus station density, distance of nearest subway stations, building occupied area, volume rate, built-up area occupation ratio, population density and greening rate of each block, and the urban vitality evaluation indexes are calculated by utilizing the urban vitality comprehensive evaluation data;
index normalization substep S122:
according to whether the influence direction of the evaluation index on the urban vitality is a positive index or a negative index, the evaluation index with the higher urban vitality and the smaller urban vitality is the negative index, the evaluation index with the higher urban vitality and the larger urban vitality is the positive index, and different standardization methods are selected according to the influence direction of the index on the urban vitality to carry out index standardization.
4. The method for evaluating urban block vitality according to claim 1, wherein,
the step S130 of the multi-objective optimized spatial projection tracking model specifically includes:
the projection function sub-step S131 of constructing the multi-objective optimization:
let a= { a 1 ,a 2 ,…,a n The number of the evaluation indexes is represented by the projection vector, n is represented by a j Indicating index x j Corresponding projection value, x= { X ij I=1, 2, m; j=1, 2,..n } is the evaluation index matrix, x ij The j index value representing the i block is obtained by reducing the dimension of the multidimensional evaluation index data and projecting the multidimensional evaluation index data to form a comprehensive index Z= { Z i I=1, 2,..m }, the calculation formula of the projection function is:
wherein z is i A comprehensive activity value, also called comprehensive projection value, a, representing block i j As a vector to be solved, representing a projection value of a j-th evaluation index, and m represents the number of blocks;
building an objective function substep S132:
defining a first objective function Q 1 (a) The calculation formula is as follows:
Q 1 (a)＝S(Z)D(Z)
s (Z) represents the inter-class distance, calculated by the variance of the integrated projection values:
d (Z) represents the inter-class distance, calculated by the distance of the integrated projection value:
wherein n represents the number of evaluation indexes; m represents the number of blocks; z i Representing the integrated projection value of the ith block;representing an average value of the integrated projection values; r is a window width parameter for estimating local scattered point density; u (R-R (i, k)) represents a unit step function, u (·) =1 when R-R (i, k) > 0, otherwise u (·) =0; r (i, k) = |z i -z k The i represents the absolute value of the difference of the integrated projection values between two blocks;
defining a second objective function Q 2 (a) The calculation formula is as follows:
wherein d (pos) i ,pos k ) Representing the geographic distance between neighborhood i and neighborhood k; m represents the number of blocks; beta is a constant; w (w) ik Is a positive function, and the more similar the comprehensive projection values are between two blocks, w ik The smaller a is the projection vector, X i An evaluation index vector indicating the ith block;
the multi-objective genetic algorithm solves projection vector sub-step S133:
according to the projection function, the two objective functions and the limiting condition, solving the multi-objective optimization problem by using a non-dominant sorting genetic algorithm NSGA-II, calculating projection vectors, and finding an optimal solution set for enabling the first objective function to reach the maximum value and enabling the second objective function to reach the minimum value.
5. The method for evaluating urban block vitality according to claim 1, wherein,
in the build objective function substep S132,
the optimization problem of converting the search for the optimal projection vector into an objective function, the first objective function being to extract x as large as possible ij Variation information Max { Q } 1 (a) The purpose of the second objective function is to minimize the distance function Min { Q } taking into account the spatial correlation 2 (a) Meanwhile, the sum of squares of elements of the projection vector needs to satisfy the constraint that the sum of squares is 1:
6. the method for evaluating urban block vitality according to claim 2, wherein,
in the multi-source urban geographical data acquisition sub-step S111,
the road network comprises expressways, primary roads, secondary roads and tertiary roads, the POIs comprise a plurality of major categories, and the land utilization data has a plurality of categories.
7. The method for evaluating urban block vitality according to claim 3, wherein,
in the evaluation index calculation sub-step S121, the method for calculating the urban vitality evaluation index is as follows:
POI density = total number of POIs/block area within a block of 20 meters buffer,
bus stop density = total number of bus stops/block area within a block of 20 meters,
the POI and land utilization mixedness is calculated using shannon entropy,
distance of nearest subway station = euclidean distance of neighborhood center point to nearest subway station;
building footprint = building area within a block/total block area,
build area ratio = build area within a block/total area of the block,
greening rate = greening land area within a block/total block area,
volume ratio = sum of indoor areas of buildings in a block/total area of block, total indoor area of a single building is equal to building floor area multiplied by number of floors,
population density = average of the grid population density values contained within a neighborhood.
8. The method for evaluating urban block vitality according to claim 3, wherein,
in the index normalization sub-step S122,
the negative indicators include: the distance between nearest subway stations, the land utilization mixing degree and the greening rate; the other indexes are negative indexes;
the normalized calculation formula of the forward index is:
the standardized calculation formula of the negative index is as follows:
wherein x is max,j Represents the maximum value, x, of the j-th index min,j Represents the minimum value, x, of the j-th index ij The j index value indicating the i-th neighborhood.
9. The method for evaluating urban block vitality according to claim 4, wherein,
in the multi-objective genetic algorithm solution projection vector sub-step S133,
in the non-dominant ranking genetic algorithm NSGA-II, the set parameters comprise iteration times, initial iteration population numbers, crossover probability and mutation rate,
setting the iteration times to 100, wherein the initial iteration population numbers are respectively 50, 100, 150 and 200, the crossover probability is 0.7, the mutation rate is 1/n, and n represents the index number.
10. A storage medium storing computer-executable instructions, characterized by:
the computer-executable instructions, when executed by a processor, perform the spatial projection pursuit-based city block vitality assessment method of any of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310923601.9A CN116911507A (en) | 2023-07-25 | 2023-07-25 | Urban block vitality evaluation method and storage medium based on space projection pursuit |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310923601.9A CN116911507A (en) | 2023-07-25 | 2023-07-25 | Urban block vitality evaluation method and storage medium based on space projection pursuit |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116911507A true CN116911507A (en) | 2023-10-20 |
Family
ID=88357951
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310923601.9A Pending CN116911507A (en) | 2023-07-25 | 2023-07-25 | Urban block vitality evaluation method and storage medium based on space projection pursuit |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116911507A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117314198A (en) * | 2023-10-25 | 2023-12-29 | 北京华清安地建筑设计有限公司 | Comprehensive analysis method and system for historical cultural block function update |
-
2023
- 2023-07-25 CN CN202310923601.9A patent/CN116911507A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117314198A (en) * | 2023-10-25 | 2023-12-29 | 北京华清安地建筑设计有限公司 | Comprehensive analysis method and system for historical cultural block function update |
| CN117314198B (en) * | 2023-10-25 | 2024-03-05 | 北京华清安地建筑设计有限公司 | Comprehensive analysis method and system for historical cultural block function update |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Foroozesh et al. | Assessment of sustainable urban development based on a hybrid decision-making approach: Group fuzzy BWM, AHP, and TOPSIS–GIS | |
| CA2561939C (en) | Method and system for forecasting events and results based on geospatial modeling | |
| CN106780089B (en) | Permanent basic farmland planning method based on neural network cellular automaton model | |
| CN101673369A (en) | Projection pursuit-based method for evaluating flooding risk of drainage pipe network | |
| Lin et al. | Fine-scale mapping of urban ecosystem service demand in a metropolitan context: A population-income-environmental perspective | |
| Zhang et al. | Using street view images to identify road noise barriers with ensemble classification model and geospatial analysis | |
| CN116911507A (en) | Urban block vitality evaluation method and storage medium based on space projection pursuit | |
| CN115809378A (en) | Medical shortage area identification and layout optimization method based on mobile phone signaling data | |
| CN115129802A (en) | Population spatialization method based on multi-source data and ensemble learning | |
| Wang et al. | Morphological characteristics of rural settlements from morphogenesis perspective: A case study of rural settlements in Heilongjiang Province, China | |
| CN114154880A (en) | Method for evaluating walking accessibility of public service facility on street unit level | |
| Qi et al. | Land intensification use scenarios based on urban land suitability assessment of the national park | |
| CN116720750B (en) | Comprehensive energy station equipment capacity planning method, device, terminal and storage medium | |
| CN115146990B (en) | Urban activity quantitative evaluation method integrating multisource geographic big data | |
| Xu et al. | A framework for the evaluation of roof greening priority | |
| CN116523189A (en) | Soil moisture content site planning method, device and storage medium considering hydrologic characteristics | |
| Zhang et al. | A spatial projection pursuit model for identifying comprehensive urban vitality on blocks using multisource geospatial data | |
| Dong et al. | The spectral dimension of human mobility | |
| Castiglione et al. | Multi-source Data-driven Procedure for Traffic Analysis Zones Definition | |
| CN117474352B (en) | Land utilization redevelopment identification and optimization method and device | |
| Kim et al. | Population Allocation at the Building level for Micro-level Urban Simulation: A Case of Jeonju, Korea | |
| Flores et al. | Comparative Spatial Analysis Between Inner-City Socialized Housing and Private Housing Developments in Metro Manila, the Philippines | |
| Kumar et al. | Development of a Land Price Model for a Medium Sized Indian City | |
| CN118278607A (en) | Disaster relief material reserve warehouse location method and device based on natural disasters | |
| Dong et al. | Research on population distribution model based on real estate big data |
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 |