CN117649063B - Public service facility site selection planning method based on demographic big data - Google Patents
Public service facility site selection planning method based on demographic big data Download PDFInfo
- Publication number
- CN117649063B CN117649063B CN202410122857.4A CN202410122857A CN117649063B CN 117649063 B CN117649063 B CN 117649063B CN 202410122857 A CN202410122857 A CN 202410122857A CN 117649063 B CN117649063 B CN 117649063B
- Authority
- CN
- China
- Prior art keywords
- grid
- facility
- candidate facility
- candidate
- future time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000013439 planning Methods 0.000 title claims abstract description 24
- 238000011156 evaluation Methods 0.000 claims abstract description 89
- 230000008859 change Effects 0.000 claims abstract description 84
- 239000003016 pheromone Substances 0.000 claims abstract description 27
- 238000010276 construction Methods 0.000 claims description 18
- 238000011161 development Methods 0.000 abstract description 7
- 230000000694 effects Effects 0.000 description 9
- 230000008569 process Effects 0.000 description 7
- 230000018109 developmental process Effects 0.000 description 6
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 241000257303 Hymenoptera Species 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 241000287828 Gallus gallus Species 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007728 cost analysis Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013079 data visualisation Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000547 structure data 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
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of public service, in particular to a public service facility site selection planning method based on demographic data, which comprises the following steps: acquiring actual population data of each grid, predicted population data in preset different future time periods, each candidate facility and coverage range of the candidate facility in the urban grid map; obtaining travel cost evaluation according to the position distribution between each grid and the grids of the candidate facilities in the coverage area of each candidate facility and the distribution condition of different age structures in actual population data; obtaining a change trend evaluation according to the age structure distribution condition of the predicted population data of each grid in each future time period and the predicted population data change condition of each grid in each future time period; and determining a heuristic function and a pheromone updating mode in the ant colony algorithm, and acquiring the optimal site selection scheme of the public service facility by using the ant colony algorithm. The optimal site selection scheme of the invention can more accord with the future population development trend.
Description
Technical Field
The invention relates to the technical field of public service, in particular to a public service facility site selection planning method based on demographic data.
Background
In urban planning and management, the rational location of public service facilities is directly related to the quality of life of urban residents and the sustainable development of the whole city. A scientific and reasonable site selection scheme can meet demands of residents to the greatest extent, improves service efficiency, promotes social fairness and inclusion, and high-quality public service facilities can remarkably improve living standards of the residents. Therefore, the site selection planning of public service facilities occupies a vital position in city planning and management, and is an important link for realizing the sustainable development of cities and improving the life quality of residents. At present, the coverage range of site selection and positioning and the path cost among all areas are generally considered, an ant colony algorithm is used for site selection planning of public service facilities, when a heuristic function of the ant colony algorithm and an updating mode of pheromones are constructed, diversified development conditions of population structures are ignored, consideration factors are relatively incomplete, and the effect of a site selection planning scheme of the public service facilities is poor.
Disclosure of Invention
In order to solve the technical problem of poor effect of public service facility site selection planning schemes, the invention aims to provide a public service facility site selection planning method based on population big data, and the adopted technical scheme is as follows:
Acquiring actual population data of each grid, predicted population data in preset different future time periods, each candidate facility and coverage range of the candidate facility in the urban grid map;
Obtaining travel cost evaluation of each candidate facility according to the position distribution between each grid and the grid where the candidate facility is located in the coverage area of each candidate facility and the distribution situation of different age structures in the actual population data of each grid in the coverage area of each candidate facility;
Obtaining the change trend evaluation of each grid according to the difference between the age structure distribution conditions of the predicted population data of each grid in every two adjacent future time periods and the predicted population data change condition of each grid in every future time period;
And determining a heuristic function and a pheromone updating mode in an ant colony algorithm according to travel cost evaluation of each candidate facility, change trend evaluation of grids of each candidate facility and grids in a coverage area, and acquiring the optimal site proposal of the public service facility by using the ant colony algorithm.
Preferably, the step of obtaining the travel cost evaluation of each candidate facility according to the position distribution between each grid and the grid where the candidate facility is located in the coverage area of each candidate facility and the distribution of different age structures in the actual population data of each grid in the coverage area of each candidate facility specifically includes:
acquiring different age levels according to the traveling capacities of different age population, and marking each grid in the coverage range of any candidate facility as a reference grid for any candidate facility;
obtaining the facility construction cost of each reference grid according to the distance between each reference grid and the grid of the candidate facility and population quantity distribution condition of each age level in the actual population data of each reference grid;
And obtaining travel cost evaluation of the candidate facilities according to the total number of the actual population data of each reference grid and the facility construction cost.
Preferably, the obtaining the facility construction cost of each reference grid according to the distance between each reference grid and the grid where the candidate facility is located and population quantity distribution condition under each age level in the actual population data of each reference grid specifically includes:
And marking any one reference grid as a target reference grid, calculating the accumulated sum of the product of the population quantity under each age level and the travel cost weight preset under the age level in the actual population data of the target reference grid, and taking the product of the accumulated sum and the distance between the target reference grid and the grid of the candidate facility as the facility construction cost of the target reference grid.
Preferably, the step of obtaining travel cost evaluation of candidate facilities according to the total number of the actual population data of each reference grid and the facility construction cost specifically includes:
And taking the accumulated sum of the ratio of the total number of the actual population data of each reference grid corresponding to the candidate facility to the facility construction cost as the travel cost evaluation of the candidate facility.
Preferably, the method further includes obtaining a change trend evaluation of each grid according to a difference between the age structure distribution conditions of the predicted population data of each grid in every two adjacent future time periods and the predicted population data change conditions of each grid in every future time period, and specifically includes:
Marking any grid as a selected grid, calculating the difference between each future time period of the selected grid and the total number of people in the predicted population data of the adjacent previous future time period, and obtaining the global predicted difference of each future time period of the selected grid; calculating the difference between the population number ratio of each age level in the predicted population data of each future time period of the selected grid and the adjacent previous future time period to obtain the local predicted difference of each age level in each future time period of the selected grid;
obtaining a first characteristic coefficient according to the distribution condition and the fluctuation condition of the global prediction difference of each future time period of the selected grid; obtaining a second characteristic coefficient according to the local prediction difference of each future time period of the selected grid at each age level and the preset travel cost weight;
And obtaining the change trend evaluation of the selected grid according to the first characteristic coefficient and the second characteristic coefficient, wherein the first characteristic coefficient and the change trend evaluation are in positive correlation, and the second characteristic coefficient and the change trend evaluation are in negative correlation.
Preferably, the obtaining the first characteristic coefficient according to the distribution condition and the fluctuation condition of the global prediction difference of each future time period of the selected grid specifically includes:
calculating the average value of the global prediction differences of all future time periods of the selected grid to obtain a first coefficient, calculating the product of the variance and the range of the global prediction differences of all future time periods of the selected grid to obtain a second coefficient, and obtaining a first characteristic coefficient according to the first coefficient and the second coefficient, wherein the first coefficient and the first characteristic coefficient are in positive correlation, and the second coefficient and the first characteristic coefficient are in negative correlation.
Preferably, the obtaining the second characteristic coefficient according to the local prediction difference of each future time period of the selected grid at each age level and the preset trip cost weight specifically includes:
calculating the accumulated sum of the products of the local prediction difference of each future time period of the selected grid at each age level and the travel cost weight of the corresponding age level to obtain travel change evaluation of each future time period of the selected grid; taking the mean value of travel change evaluation of all future time periods of the selected grid as a second characteristic coefficient.
Preferably, the determining the heuristic function and the pheromone updating mode in the ant colony algorithm according to the travel cost evaluation of each candidate facility, the change trend evaluation of the grid where each candidate facility is located and the grid within the coverage area specifically includes:
For any one candidate facility, obtaining a heuristic function value of the candidate facility according to travel cost evaluation of the candidate facility and change trend evaluation of each grid in the coverage range of the candidate facility;
and determining a pheromone updating mode according to the ratio situation of the change trend evaluation of all grids belonging to the grids in the coverage area of the candidate facility on the ant driving path.
Preferably, the obtaining the heuristic function value of the candidate facility according to the travel cost evaluation of the candidate facility and the change trend evaluation of each grid in the coverage area of the candidate facility specifically includes:
And calculating the product of the average value of the change trend evaluations of all grids in the coverage area of the candidate facility and the travel cost evaluation of the candidate facility to obtain the heuristic function value of the candidate facility.
Preferably, the pheromone updating mode specifically includes:
Wherein, For the updated pheromone concentration from path i to j,/>Is the pheromone concentration from path i to j at time t,/>Is the volatile factor of pheromone,/>For the current iteration number,/>Evaluation of the trend of variation of the kth grid in the coverage of the (r) th candidate facility between paths i to j,/>Representing the total number of grids contained within the coverage of the r-th candidate facility between paths i to j,/>Representing the trend evaluation of the s-th grid in the urban grid map,/>Representing the total number of grids contained in the urban raster image.
The embodiment of the invention has at least the following beneficial effects:
The invention firstly acquires population data of each grid in the urban grid graph, including actual population data and future forecast population data, provides a data basis for the subsequent feature analysis of the site selection scheme by combining the change condition of the future population data, and simultaneously acquires each candidate facility and the coverage range thereof. And then, analyzing the distribution condition of the actual population data of the grids in the coverage area of each candidate facility, and combining the distribution condition of different age structures to obtain travel cost evaluation, wherein the travel cost evaluation of the candidate facility reflects the people average travel cost condition of all the grids in the coverage area of the candidate facility. Further, the distribution situation of the future forecast population data of each grid is analyzed, meanwhile, the age structure distribution situation in the forecast population data is combined to obtain the change trend evaluation, and the change trend evaluation is utilized to reflect the change trend of the future population data and the change situation of the future population trip cost. Finally, combining the distribution characteristics of candidate facilities in the actual population data and the distribution characteristics of the predicted population data, determining a heuristic function and a pheromone updating mode, fully considering the diversified development condition and the variation condition of the population structure data, and considering the actual population data and the predicted population data into an ant colony algorithm, wherein the obtained optimal site proposal has better effect, can better accord with the future population development trend, and has more profound effect on public service facilities.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of a method for public service facility site selection planning method based on demographic data.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following description refers to the specific implementation, structure, characteristics and effects of the public service facility site selection planning method based on demographic data according to the invention in combination with the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The invention provides a public service facility site selection planning method based on demographic data, which is specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a method flowchart of a public service facility site selection planning method based on demographic data according to an embodiment of the present invention is shown, and the method includes the following steps:
Step one, acquiring actual population data of each grid, predicted population data in preset different future time periods, each candidate facility and coverage range of the candidate facility in the urban grid map.
Firstly, urban raster graphics are acquired by using a Geographic Information System (GIS) technology, and meanwhile, population distribution big data can be acquired by using the GIS technology, namely, actual population data of each grid in the urban raster graphics are acquired, wherein the actual population data comprises the total population number in each grid and the population numbers of different ages in each grid.
Meanwhile, considering that the future population number and population structure in the current city may change, the influence of the change on the public service facility site selection needs to be analyzed, so that the predicted population data of each grid in the urban grid map in different preset future time periods needs to be acquired.
The neural network may be used to predict the population big data in each grid, in this embodiment, ANN artificial neural networks are used to predict the total population number of each future time period and the population numbers of different ages in each grid, and the implementer may select other neural networks to predict, for example, BP neural networks, which will not be described here too much. Meanwhile, in the present embodiment, the preset time length of each future time period is 1 year, the number of future time periods is 10, and the implementer can set according to the specific implementation scenario.
Then, grids are randomly selected from the urban grid map to serve as candidate positions of public service facilities, and in the embodiment, each grid in the urban grid map is regarded as the grid where the candidate facility is located, so that coverage range of each candidate facility can be obtained by using GIS. It should be noted that, in urban and rural planning, the layout and coverage of public facilities are crucial, and the GIS can acquire the coverage of each public facility through spatial data analysis and visualization functions, and the acquisition method is a well-known technology and will not be described in detail here.
And step two, obtaining travel cost evaluation of each candidate facility according to the position distribution between each grid and the grid where the candidate facility is located in the coverage area of each candidate facility and the distribution situation of different age structures in the actual population data of each grid in the coverage area of each candidate facility.
For public service site selection, the main consideration is to enable public service site selection to cover as much population as possible. Considering that the traveling capacities of population at different ages are different to some extent, and also considering the older population with poorer traveling capacity as much as possible, the distribution situation of different age structures in the actual population data needs to be considered when evaluating candidate facilities.
First, different age levels are obtained according to the travel ability of different age population. In this embodiment, the population ages are divided into 5 age levels, which are in turn: the ages of 0-18 are the first age level, 19-50 are the second age level, 50-60 are the third age level, 61-70 are the fourth age level, and 71-100 are the fifth age level. According to population age distribution conditions in different age levels, the second age level has the strongest traveling capacity, and the first age level and the fifth age level have the weakest traveling capacity.
When public service facility site selection planning is carried out, travel costs corresponding to people with different travel capacities are different. Each candidate facility has a certain coverage area correspondingly, the farther the distance between each grid and the grid of the candidate facility is in the coverage area, the higher the travel cost of people in the grids corresponding to the coverage area to the candidate facility is, and the population distribution condition in the coverage area also needs to be considered.
Based on this, in combination with the analysis factors of the aspects, first, the situation of travel costs of each candidate facility is evaluated. And analyzing the position distribution between each grid and the grid of the candidate facility in the coverage area of each candidate facility and the distribution situation of different age structures in the actual population data of each grid in the coverage area of each candidate facility to obtain the travel cost evaluation of each candidate facility.
For any one candidate facility, each grid within the coverage area of the candidate facility is marked as a reference grid. According to the first aspect, population distribution and distance distribution of each reference grid in the coverage range of the candidate facility are analyzed, namely facility construction cost of each reference grid is obtained according to the distance between each reference grid and the grid of the candidate facility and population quantity distribution condition of each age level in actual population data of each reference grid. Specifically, any one reference grid is recorded as a target reference grid, the accumulated sum of the product of the population quantity under each age level in the actual population data of the target reference grid and the travel cost weight preset under the age level is calculated, and the product of the accumulated sum and the distance between the target reference grid and the grid where the candidate facility is located is used as the facility construction cost of the target reference grid.
In the second aspect, the final travel cost of the candidate facility is obtained by combining the cost evaluation of all the reference grids in the coverage range of the candidate facility. And obtaining travel cost evaluation of the candidate facilities according to the total number of the actual population data of each reference grid and the facility construction cost. Specifically, the accumulated sum of the ratio of the total number of the actual population data of each reference grid corresponding to the candidate facility to the facility construction cost is taken as the travel cost evaluation of the candidate facility.
In this embodiment, taking any one candidate facility as an example, and taking the kth reference grid in the coverage area of the kth candidate facility as the target reference grid, a calculation formula of travel cost evaluation of the kth candidate facility may be expressed as:
Wherein, Travel cost evaluation indicating the r candidate facility,/>Representing the total number of grids contained within the coverage of the r candidate facility,/>Representing the total population number of actual population data of the kth reference grid in the coverage area of the nth candidate facility,/>Representing the number of population at the nth age level in the actual population data in the kth reference grid in the coverage of the nth candidate facility,/>Representing travel cost weight preset under nth age level,/>Representing the Euclidean distance between the grid where the r candidate facility is located and the target reference grid,/>Indicating the total number of age levels.
The preset travel cost weight and the travel capacity of each age level are in a negative correlation, the travel capacity of the second age level is highest, namely the corresponding travel cost weight value is minimum, and the travel capacities of the first age level and the fifth age level are lowest, namely the corresponding travel cost weight value is maximum. In this embodiment, a travel coefficient is preset for each age level, the travel capability of each age level is represented by the travel coefficient, and the reciprocal of the travel coefficient of each age level is used as the travel cost weight. Specifically, the travel coefficient of the first age level and the fifth age level is set to 1, the travel coefficient of the second age level is set to 5, and the travel coefficient of the third age level and the fourth age level is set to 3.
The travel cost weight reflects the travel cost of different age levels in terms of the behavioral competence of the population,Reflecting the n-th age level weighted travel cost, the more population numbers are contained in the target reference grid, the more the different age levels are rich, the higher the weighted travel cost is, the larger the proportion of aged people in the population structure is, the higher the cost of using public service facilities by the population in the area is, and the greater the cost of using the public service facilities by the population in the area isFor the facility construction cost of the target reference grid, the farther the target reference grid is from the candidate facility, the higher the travel cost of the target reference grid weighted based on the age hierarchy, and the higher the corresponding facility construction cost.
The average travel cost of the whole target reference grid is reflected, the travel cost evaluation of the candidate facilities reflects the personnel travel cost condition of all grids in the coverage area of the candidate facilities, and the population structure factors are considered in the travel cost based on the condition that people with larger age are more difficult to travel in the coverage area of the candidate facilities, so that the influence condition of different population structures on the site selection of the public service facilities is optimized.
And thirdly, obtaining the change trend evaluation of each grid according to the difference between the age structure distribution conditions of the predicted population data of each grid in every two adjacent future time periods and the predicted population data change condition of each grid in every future time period.
The establishment of public service facilities often has sustainable influence on the humanization of cities, when public service facilities are selected and planned, not only the population structure distribution condition of the current time is considered, but also the current site selection is required to be adjusted and optimized by combining future population change data, so that the effect of the public service facilities can be exerted more comprehensively and longer.
And evaluating the site selection effect corresponding to each candidate facility currently according to the future population data change. If the future population count in a region within a city is continuously increasing, this indicates that future demand for public service degrees celsius in that region is increasing, and that the benefits of setting up public service facilities in the vicinity of that region are increasing, the more public service facilities should be set up around that region. Meanwhile, if future population structures in a certain area of a city are more and more aged, it is stated that the traveling capacity of population in the area is gradually reduced, and the public service facilities should be arranged around the area.
Based on the characteristics, variation trend evaluation of each grid is obtained by analyzing the difference between the age structure distribution conditions of the predicted population data of each grid in every two adjacent future time periods and the variation condition chicken heart of the predicted population data of each grid in every future time period.
Firstly, evaluating future population change conditions of each grid in a city, namely marking any grid as a selected grid, calculating the difference between each future time period of the selected grid and the total number of people in the predicted population data of the adjacent previous future time period, and obtaining the global prediction difference of each future time period of the selected grid; the difference between the population count ratio of each age level in the predicted population data of each future time period of the selected grid and the adjacent previous future time period is calculated to obtain the local predicted difference of each age level in each future time period of the selected grid.
It should be noted that, when calculating the corresponding global prediction difference and the local prediction difference of the first future time period, the data difference between the previous time period adjacent to the first future time period is calculated, that is, the time period is the same as the time length of the future time period, and it is understood that the previous time period adjacent to the first future time period is the current time period.
In this embodiment, the s-th grid in the urban raster image is taken as the selected grid, and the global prediction difference of the t future time period of the selected grid can be expressed asWherein/>Total number of demographics in predicted population data representing the t future time period of the selected grid,/>Total number of demographics in the predicted population data representing the t-1 future time period of the selected grid. The local prediction difference for the nth age level within the nth future time period of the selected grid may be expressed as/>Wherein/>Representing the number of populations at the nth age level in the predicted population data for the nth future time period of the selected grid,/>Representing the population quantity of the nth age level in the predicted population data for the t-1 future time period of the selected grid. The local prediction difference reflects the population count change of each age level in two adjacent years, and the global prediction difference reflects the population count change in the future each year compared to the last year.
Then, the fluctuation trend of the change condition of the mouth of each grid in each future time period is analyzed. Obtaining a first characteristic coefficient according to the distribution condition and the fluctuation condition of the global prediction difference of each future time period of the selected grid; calculating the average value of the global prediction differences of all future time periods of the selected grid to obtain a first coefficient, calculating the product of the variance and the range of the global prediction differences of all future time periods of the selected grid to obtain a second coefficient, and obtaining a first characteristic coefficient according to the first coefficient and the second coefficient, wherein the first coefficient and the first characteristic coefficient are in positive correlation, and the second coefficient and the first characteristic coefficient are in negative correlation.
In this embodiment, taking the s-th grid in the urban raster image as the selected grid, the calculation formula of the first characteristic coefficient of the selected grid may be expressed as:
Wherein, Representing the first characteristic coefficient of the selected grid, s representing the s-th grid in the urban grid map,/>, andMean value representing global prediction difference of the s-th grid in all future time periods,/>Representing the very poor global prediction difference of the s-th grid over all future time periods,/>Representing the variance of the global prediction difference of the s-th grid over all future time periods, norm () is a linear normalization function.
The first coefficient reflects the variation trend of the population total number in the area where the selected grid is located, and the larger the value of the first coefficient is, the faster the future population growth in the selected grid is, and the more public service facilities are required to be arranged in the area where the selected grid is located.And reflecting the fluctuation condition of the total number of population in the area where the selected grid is positioned for the second coefficient, wherein the larger the value is, the more unstable the future population change trend of the area where the selected grid is positioned is, and further the more unreliable the population change trend is, namely, the fluctuation condition of the total number of population is taken as a punishment item. The first characteristic factor reflects how well the public service facility is set in the selected grid in terms of the trend of the population total number.
Further, travel cost analysis is performed in combination with future population change trends of each age level. Obtaining a second characteristic coefficient according to the local prediction difference of each future time period of the selected grid at each age level and the preset travel cost weight; calculating the accumulated sum of the products of the local prediction difference of each future time period of the selected grid at each age level and the travel cost weight of the corresponding age level to obtain travel change evaluation of each future time period of the selected grid; taking the mean value of travel change evaluation of all future time periods of the selected grid as a second characteristic coefficient.
In this embodiment, taking the s-th grid in the urban grid map as an example for illustration, the calculation formula of the second characteristic coefficient of the selected grid may be expressed as:
Wherein, A second characteristic coefficient representing the selected grid, s representing the s-th grid in the urban grid map,/>, andRepresenting the total number of future time periods,/>Representing local prediction differences of the nth age level within the nth future time period of the selected grid,/>Representing travel cost weight preset under nth age level,/>Representing the total number of age levels, norm () is a linear normalization function.
The future population quantity change condition under the corresponding age level in the selected grid is weighted by using the travel cost weights of different age levels,Reflects the influence of population structural changes on the whole traveling capacity of the future t year and the previous year of the area where the selected grid is located under the nth age level,/>And the travel change evaluation of the selected grid in the t future time period reflects the change condition of population travel capacity in the selected grid.
The change trend of the traveling capacity of the future time period in the area where the selected grid is located is represented, the smaller the value is, the more serious the aging condition in the population structure is, and further, the future traveling capacity in the area where the selected grid is located is gradually reduced, and public service facilities are needed to be set. The second characteristic factor reflects how well the public service facility is located within the corresponding grid in terms of the trend of the change in the population structured number within each grid.
Finally, the rating structure of the final population variation trend of each grid is obtained by combining the evaluation results of the two aspects. And obtaining the change trend evaluation of the selected grid according to the first characteristic coefficient and the second characteristic coefficient, wherein the first characteristic coefficient and the change trend evaluation are in positive correlation, and the second characteristic coefficient and the change trend evaluation are in negative correlation.
In this embodiment, the ratio of the first characteristic coefficient to the second characteristic coefficient of the selected grid is used as the change trend evaluation of the selected grid. The larger the value of the first characteristic coefficient is, the larger the change trend of the future population total number of the selected grid is, which means that the larger the future population growth trend of the selected grid is, the larger the value of the corresponding change trend evaluation is. The smaller the value of the second characteristic coefficient, the smaller the trip capability of future population in the selected grid is, the larger the value of corresponding change trend evaluation is required to be in the regional facilities and public service facilities. The change trend evaluation shows that the future change condition of the area where the selected grid is located on the public service facility is compared with the current travel cost, and the larger the value is, the higher the future travel cost of the selected grid becomes, and the larger the demand on the public service facility is.
The future population change trend of the area where each grid is located is quantified through the change trend evaluation, and the future population change condition is considered in public service facility site selection, so that the last obtained site selection can exert the effect of the city more comprehensively and in a long term.
And step four, determining a heuristic function and a pheromone updating mode in an ant colony algorithm according to travel cost evaluation of each candidate facility, change trend evaluation of grids of each candidate facility and grids in a coverage area, and acquiring the optimal site proposal of the public service facility by using the ant colony algorithm.
The method comprises the steps of obtaining an optimal addressing scheme of public service facilities by utilizing an ant colony algorithm, and firstly, building a mapping relation between a solving problem and a human public ant colony, namely, converting the addressing problem of the public service facilities into a multi-objective space optimization problem of a vector diagram, wherein the vector diagram is N rows, and N is the addressing quantity of the public service facilities.
When the ant colony algorithm is applied to the public service facility site selection problem, each ant represents a site selection candidate scheme, and the number of ants is set. Meanwhile, the updating modes of the heuristic function and the pheromone need to be determined, the average person travel cost, the future population change trend and the future population travel cost change condition in the coverage range of the candidate facilities can be combined, the preference degree of each candidate facility serving as a public service facility is evaluated, and the evaluation result is used as the heuristic function, so that the operation process of the ant colony algorithm can be converged more quickly.
Based on the above, for any one candidate facility, the heuristic function value of the candidate facility is obtained according to the travel cost evaluation of the candidate facility and the change trend evaluation of each grid in the coverage area of the candidate facility. Specifically, calculating the product of the average value of the change trend evaluations of all grids in the coverage area of the candidate facility and the travel cost evaluation of the candidate facility to obtain the heuristic function value of the candidate facility.
In this embodiment, taking the r candidate facility as an example, the calculation formula of the heuristic function value of the r candidate facility may be expressed as:
Wherein, Heuristic function value representing the r candidate facility,/>Travel cost evaluation indicating the r candidate facility,/>Representing the total number of grids contained within the coverage of the r candidate facility,/>And (5) representing the change trend evaluation of the kth grid in the coverage range of the (r) candidate facility.
The heuristic function value of the candidate facility reflects the travel cost of people in the region after the future population change trend and the future population travel cost change trend are combined, and the demand level of the region where the candidate facility is located for public service facilities is represented.
The average travel cost of people of the whole coverage area of the r candidate facility is reflected, the larger the value is, the more the population structure in the coverage area is aged, the larger the corresponding heuristic function value is, and the larger the demand degree of the candidate facility for finally setting public service facilities is indicated. /(I)The change condition of future average travel cost in the coverage area of the candidate facility is reflected, and the larger the value is, the larger the demand degree of public service facilities arranged in the area where the candidate facility is located in the future is, and the larger the corresponding heuristic function value is.
Firstly, a greedy algorithm is used in a vector diagram to obtain a global optimal stroke of a first iteration process; for the subsequent iteration process, the optimal journey acquired in each iteration process is recorded as the global optimal journey of the current iteration process; meanwhile, ants running through the optimal travel are marked as elites, so that the opportunity that the optimal schemes corresponding to the ants are selected in the subsequent iteration process is increased; the iteration stop condition is set to 30 iterations.
In this embodiment, the update mode of the pheromone specifically includes:
Wherein, For the updated pheromone concentration from path i to j,/>Is the pheromone concentration from path i to j at time t,/>Is the volatile factor of pheromone,/>For the current iteration number,/>Evaluation of the trend of variation of the kth grid in the coverage of the (r) th candidate facility between paths i to j,/>Representing the total number of grids contained within the coverage of the r-th candidate facility between paths i to j,/>Representing the trend evaluation of the s-th grid in the urban grid map,/>Representing the total number of grids contained in the urban raster image.
Representing additional increments of elite ant travel on paths i through j, the greater the extent to which the grid within the coverage of a candidate facility between paths i through j will change in future population travel capacity, the greater the demand for public service facilities between paths i through j, and thus the greater the likelihood that paths i through j will be the optimal trip. Meanwhile, the more the iteration number is, the less the corresponding additional information is, and the more the optimal path is determined.
When the heuristic function is constructed, the average travel cost of people in the grid where each candidate facility is located, the future population change trend and the future population travel cost change condition are considered. When the updating mode of the pheromone is determined, the change condition of the grid in the coverage area of the candidate facilities on each path in the future population travelling capacity is considered, and the future population change condition is used as an additional pheromone to optimize the updating mode of the pheromone, so that the proportion of future population data change is increased in the process of selecting the optimal path. According to the determined heuristic function and pheromone updating mode, the ant colony algorithm can be used for determining the optimal site scheme of the public service facilities, the obtained optimization result can be more in line with the future population development trend, and the public service facilities have more profound functions.
It should be noted that, the method of determining the optimal location scheme of the facility by using the ant colony algorithm is a well-known technique, and will not be described here too much.
The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the application and are intended to be included within the scope of the application.
Claims (7)
1. A method for institutional service site selection planning based on demographic data, the method comprising the steps of:
Acquiring actual population data of each grid, predicted population data in preset different future time periods, each candidate facility and coverage range of the candidate facility in the urban grid map;
Obtaining travel cost evaluation of each candidate facility according to the position distribution between each grid and the grid where the candidate facility is located in the coverage area of each candidate facility and the distribution situation of different age structures in the actual population data of each grid in the coverage area of each candidate facility;
Obtaining the change trend evaluation of each grid according to the difference between the age structure distribution conditions of the predicted population data of each grid in every two adjacent future time periods and the predicted population data change condition of each grid in every future time period;
Determining heuristic functions and pheromone updating modes in an ant colony algorithm according to travel cost evaluation of each candidate facility, change trend evaluation of grids of each candidate facility and grids in a coverage area, and acquiring the optimal site proposal of the public service facility by using the ant colony algorithm;
the method for obtaining the change trend evaluation of each grid according to the difference between the age structure distribution conditions of the predicted population data of each grid in every two adjacent future time periods and the predicted population data change conditions of each grid in every future time period comprises the following specific steps:
Marking any grid as a selected grid, calculating the difference between each future time period of the selected grid and the total number of people in the predicted population data of the adjacent previous future time period, and obtaining the global predicted difference of each future time period of the selected grid; calculating the difference between the population number ratio of each age level in the predicted population data of each future time period of the selected grid and the adjacent previous future time period to obtain the local predicted difference of each age level in each future time period of the selected grid;
obtaining a first characteristic coefficient according to the distribution condition and the fluctuation condition of the global prediction difference of each future time period of the selected grid; obtaining a second characteristic coefficient according to the local prediction difference of each future time period of the selected grid at each age level and the preset travel cost weight;
Obtaining a change trend evaluation of the selected grid according to the first characteristic coefficient and the second characteristic coefficient, wherein the first characteristic coefficient and the change trend evaluation are in a positive correlation relationship, and the second characteristic coefficient and the change trend evaluation are in a negative correlation relationship;
the method for obtaining the first characteristic coefficient according to the distribution condition and the fluctuation condition of the global prediction difference of each future time period of the selected grid specifically comprises the following steps:
Calculating the average value of the global prediction differences of all future time periods of the selected grid to obtain a first coefficient, calculating the product of the variance and the range of the global prediction differences of all future time periods of the selected grid to obtain a second coefficient, and obtaining a first characteristic coefficient according to the first coefficient and the second coefficient, wherein the first coefficient and the first characteristic coefficient are in positive correlation, and the second coefficient and the first characteristic coefficient are in negative correlation;
The obtaining a second characteristic coefficient according to the local prediction difference of each future time period of the selected grid at each age level and the preset travel cost weight specifically includes:
calculating the accumulated sum of the products of the local prediction difference of each future time period of the selected grid at each age level and the travel cost weight of the corresponding age level to obtain travel change evaluation of each future time period of the selected grid; taking the mean value of travel change evaluation of all future time periods of the selected grid as a second characteristic coefficient.
2. The method for planning public service facility location based on demographic data according to claim 1, wherein the step of obtaining the travel cost evaluation of each candidate facility according to the location distribution between each grid and the grid where the candidate facility is located in the coverage area of each candidate facility and the distribution of different age structures in the actual demographic data of each grid in the coverage area of each candidate facility specifically comprises the following steps:
acquiring different age levels according to the traveling capacities of different age population, and marking each grid in the coverage range of any candidate facility as a reference grid for any candidate facility;
obtaining the facility construction cost of each reference grid according to the distance between each reference grid and the grid of the candidate facility and population quantity distribution condition of each age level in the actual population data of each reference grid;
And obtaining travel cost evaluation of the candidate facilities according to the total number of the actual population data of each reference grid and the facility construction cost.
3. The method for planning public service facility site selection based on demographic data according to claim 2, wherein the obtaining the facility construction cost of each reference grid according to the distance between each reference grid and the grid where the candidate facility is located and population quantity distribution condition under each age level in the actual demographic data of each reference grid specifically comprises:
And marking any one reference grid as a target reference grid, calculating the accumulated sum of the product of the population quantity under each age level and the travel cost weight preset under the age level in the actual population data of the target reference grid, and taking the product of the accumulated sum and the distance between the target reference grid and the grid of the candidate facility as the facility construction cost of the target reference grid.
4. The method for planning public service facility site selection based on demographic data according to claim 2, wherein the obtaining the travel cost evaluation of the candidate facilities according to the total number of the actual demographic data of each reference grid and the facility construction cost specifically comprises:
And taking the accumulated sum of the ratio of the total number of the actual population data of each reference grid corresponding to the candidate facility to the facility construction cost as the travel cost evaluation of the candidate facility.
5. The method for planning public service facility site selection based on demographic data according to claim 1, wherein the determining the heuristic function and the pheromone updating mode in the ant colony algorithm according to travel cost evaluation of each candidate facility, change trend evaluation of grids of each candidate facility and grids in a coverage area specifically comprises:
For any one candidate facility, obtaining a heuristic function value of the candidate facility according to travel cost evaluation of the candidate facility and change trend evaluation of each grid in the coverage range of the candidate facility;
and determining a pheromone updating mode according to the ratio situation of the change trend evaluation of all grids belonging to the grids in the coverage area of the candidate facility on the ant driving path.
6. The method for planning public service facility site selection based on demographic data according to claim 5, wherein the obtaining the heuristic function value of the candidate facility according to the travel cost evaluation of the candidate facility and the change trend evaluation of each grid in the coverage area of the candidate facility specifically comprises:
And calculating the product of the average value of the change trend evaluations of all grids in the coverage area of the candidate facility and the travel cost evaluation of the candidate facility to obtain the heuristic function value of the candidate facility.
7. The method for planning public service facility location based on demographic data as in claim 5, wherein the pheromone updating mode specifically comprises:
Wherein, For the updated pheromone concentration from path i to j,/>Is the pheromone concentration from path i to j at time t,/>Is the volatile factor of pheromone,/>For the current iteration number,/>Evaluation of the trend of variation of the kth grid in the coverage of the (r) th candidate facility between paths i to j,/>Representing the total number of grids contained within the coverage of the r-th candidate facility between paths i to j,/>Representing the trend evaluation of the s-th grid in the urban grid map,/>Representing the total number of grids contained in the urban grid image,/>Representing additional increments of elite ant travel on paths i through j.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410122857.4A CN117649063B (en) | 2024-01-30 | 2024-01-30 | Public service facility site selection planning method based on demographic big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410122857.4A CN117649063B (en) | 2024-01-30 | 2024-01-30 | Public service facility site selection planning method based on demographic big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117649063A CN117649063A (en) | 2024-03-05 |
| CN117649063B true CN117649063B (en) | 2024-05-07 |
Family
ID=90043754
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410122857.4A Active CN117649063B (en) | 2024-01-30 | 2024-01-30 | Public service facility site selection planning method based on demographic big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117649063B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111523698A (en) * | 2020-03-20 | 2020-08-11 | 全球能源互联网集团有限公司 | Ant colony site selection method and device for macroscopically site selection of clean energy base |
| KR102225813B1 (en) * | 2019-12-26 | 2021-03-11 | 한국국토정보공사 | Welfare facility demand forecast management device and method |
| CN114897228A (en) * | 2022-04-26 | 2022-08-12 | 南通大学 | Public facility layout inspection method based on population distribution and road network |
| CN115345373A (en) * | 2022-08-22 | 2022-11-15 | 福州大学 | Accessibility prediction method for old people in public service facilities |
| CN115630978A (en) * | 2022-12-23 | 2023-01-20 | 广州市交通规划研究院有限公司 | Multi-traffic facility site selection method based on population employment distribution |
| CN115965171A (en) * | 2023-03-10 | 2023-04-14 | 吉奥时空信息技术股份有限公司 | Micro-park site selection method based on ant colony optimization algorithm |
| CN116485011A (en) * | 2023-03-27 | 2023-07-25 | 广州大学 | Rural public facility optimization method and device based on multi-scenario population prediction |
-
2024
- 2024-01-30 CN CN202410122857.4A patent/CN117649063B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102225813B1 (en) * | 2019-12-26 | 2021-03-11 | 한국국토정보공사 | Welfare facility demand forecast management device and method |
| CN111523698A (en) * | 2020-03-20 | 2020-08-11 | 全球能源互联网集团有限公司 | Ant colony site selection method and device for macroscopically site selection of clean energy base |
| CN114897228A (en) * | 2022-04-26 | 2022-08-12 | 南通大学 | Public facility layout inspection method based on population distribution and road network |
| CN115345373A (en) * | 2022-08-22 | 2022-11-15 | 福州大学 | Accessibility prediction method for old people in public service facilities |
| CN115630978A (en) * | 2022-12-23 | 2023-01-20 | 广州市交通规划研究院有限公司 | Multi-traffic facility site selection method based on population employment distribution |
| CN115965171A (en) * | 2023-03-10 | 2023-04-14 | 吉奥时空信息技术股份有限公司 | Micro-park site selection method based on ant colony optimization algorithm |
| CN116485011A (en) * | 2023-03-27 | 2023-07-25 | 广州大学 | Rural public facility optimization method and device based on multi-scenario population prediction |
Non-Patent Citations (3)
| Title |
|---|
| 基于GIS的合肥市包河区养老设施选址适宜性评价;李璐;;居业;20160220(02);第26-27页，第29页 * |
| 基于蚁群算法的应急避难场所选址研究;王亚慧;《中国优秀硕士论文全文数据库 工程科技Ⅰ辑》;20220601;第1-81页 * |
| 考虑人口结构变化的城市客运机动车辆发展规模研究;孙山;李文权;;交通运输工程与信息学报;20070615(02);第89-94、102页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117649063A (en) | 2024-03-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108564790B (en) | Urban short-term traffic flow prediction method based on traffic flow space-time similarity | |
| CN110390349A (en) | Bus passenger flow volume based on XGBoost model predicts modeling method | |
| CN111915083B (en) | Wind power prediction method and prediction system based on time layered combination | |
| CN112785029B (en) | Charging station power consumption prediction method based on deep clustering model | |
| CN104751249A (en) | Space load prediction method | |
| CN108717642B (en) | City mall site selection method based on GIS | |
| CN108834079A (en) | A kind of load balance optimization method based on mobility prediction in heterogeneous network | |
| CN114511143A (en) | Urban rail transit network generation method based on grouping division | |
| CN114580762A (en) | Hydrological forecast error correction method based on XGboost | |
| CN116796904A (en) | Method, system, electronic equipment and medium for predicting new line passenger flow of rail transit | |
| CN113743659B (en) | Urban layout prediction method based on component method and Markov cellular automaton and application | |
| CN115345373A (en) | Accessibility prediction method for old people in public service facilities | |
| CN117649063B (en) | Public service facility site selection planning method based on demographic big data | |
| CN112954624B (en) | Hybrid land use form estimation method based on mobile phone signaling big data | |
| Rahman et al. | ANALYSIS OF MODE CHOICE BEHAVIOR AND VALUE OF TIME IN DHAKA CITY, BANGLADESH. | |
| KR102387284B1 (en) | Apparatus and method for forecasting heatwave Impact considering severity of health impacts and socio-economic vulnerability | |
| CN113537596A (en) | Short-time passenger flow prediction method for new line station of urban rail transit | |
| CN116680586A (en) | Urban resident activity space access mode analysis method based on access probability | |
| CN111144628A (en) | Distributed energy supply type cooling, heating and power load prediction model system and method | |
| CN116070738A (en) | Urban mobile charging pile migration method and system based on track prediction | |
| CN113254554B (en) | Urban block heat island modeling method and system based on map capturing and cluster learning | |
| Kim et al. | Congestion and scheduling preferences of car commuters in California: estimates using big data | |
| CN114254250A (en) | Network taxi appointment travel demand prediction method considering space-time non-stationarity | |
| CN112784423A (en) | Urban area feature analysis method based on complex network | |
| CN111062536A (en) | Central air conditioner load prediction system and method based on 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |