A method for configuring group public medical facilities based on a dynamic population data model

Through dynamic population data model and multi-objective optimization algorithm, the problem of unreasonable configuration of public medical facilities in the existing technology is solved, and the prediction and configuration of medical facilities based on dynamic changes in cities is realized, and the reasonable distribution of facilities and resource utilization efficiency are improved.

CN114118512BActive Publication Date: 2024-12-03WUHAN INTERNET OF THINGS TECH CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
CN202111030965.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-09-03
Publication Date
2024-12-03
Estimated Expiration
2041-09-03

AI Technical Summary

Technical Problem

The existing technology cannot reasonably configure and predict medical equipment based on the city's geographical location, migrant population and spatial data, cannot adapt to the evaluation requirements of public medical facilities by the tiered diagnosis and treatment system, and does not consider the characteristics of residents' usage behavior, resulting in the configuration of public medical facilities. unreasonable.

Method used

The group-based public medical facilities configuration method is adopted based on the dynamic population data model, including database units, urban dynamic population estimation units, hierarchical demand balance calculation units and hierarchical facilities intelligent configuration units. Through the improved LSTM model and NSGA-II method, the Urban population forecasting, facility accessibility calculation and configuration modeling realize intelligent configuration of facilities.

Benefits of technology

Through fine urban population calculation and multi-objective optimization configuration model, the long-term configuration plan for public medical facilities is provided, which improves the lag and roughness of facility configuration, ensures that the configuration plan adapts to urban dynamic changes, and improves resource utilization efficiency and facilities reasonable distribution.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114118512B_ABST
    Figure CN114118512B_ABST
Patent Text Reader

Abstract

The present invention provides a method for configuring group public medical facilities based on a dynamic population data model, which relates to the technical field of social resource configuration. The whole system is composed of a database unit, a city dynamic population calculation unit, a hierarchical demand balance calculation unit and a hierarchical facility intelligent configuration unit. The fine calculation of the city dynamic population is combined with the development characteristics of the hierarchical diagnosis and treatment system to carry out long-term configuration plans and simulation optimization of urban public medical facilities. A construction plan is proposed for the configuration of urban dynamic public medical facilities from a time and space perspective, which is convenient for improving the lag and roughness of the configuration of public medical facilities in the current planning. Based on the public medical facilities with dynamic population, an LSTM-based urban agglomeration spatiotemporal population prediction model is proposed, which improves the problem that the original population prediction model ignores time and space dependence, simulates the linkage process of cities in the development process of urban agglomerations, and is convenient for the reasonable configuration of medical facilities in cities.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of social resource allocation, and in particular to a method for configuring group public medical facilities based on a dynamic population data model. Background Art

[0002] Tiered diagnosis and treatment is a powerful tool for responding to major public health events. It is very important to consider long-term dynamic population changes in facility configuration issues. The fundamental issue is how to effectively simulate the dynamic changes in the population during the development of a city.

[0003] According to Chinese patent number "CN111582764A", a modeling method for balanced configuration of similar services at different levels is disclosed. The spatial configuration mode is obtained based on the analysis of the sensitivity of different types of facilities to population size and service scope. The spatial configuration mode includes an indifferent spatial full coverage mode, a layered full coverage mode and a layered complementary full coverage mode. The present invention innovates the principles and modes of balanced configuration of similar public service facilities at different levels, analyzes the sensitivity of different types of facilities to population size and service scope, explores the layered configuration and spatial layout principles of public service facilities, and proposes three spatial configuration modes, namely, an indifferent spatial full coverage mode, a layered full coverage mode and a layered complementary full coverage mode, which are respectively adapted to the characteristics of "one degree for one life" of basic education facilities, the two-level system of "community first diagnosis, two-way referral" of medical services, and the functional compatibility of upper and lower levels of cultural, sports and elderly care facilities, so as to improve resource utilization efficiency.

[0004] The above patent documents only focus on the current urban population size and spatial resource allocation, and are unable to predict and reasonably allocate future spatial flows. Existing research is still mainly based on single-level facility evaluation, which cannot adapt to the evaluation requirements of the tiered diagnosis and treatment system for public medical facilities, and most studies do not consider the behavioral characteristics of residents' use of facilities. At the same time, in the absence of a dynamic population data base, it is difficult to evaluate the actual configuration needs of public medical facilities from a long-term perspective, and it is impossible to configure and predict the reasonable distribution of medical equipment based on the city's geographical location, floating population and spatial data, which is not conducive to actual use. Summary of the invention

[0005] Technical issues solved

[0006] In view of the deficiencies of the prior art, the present invention provides a method for configuring group public medical facilities based on a dynamic population data model, which solves the problem of being unable to configure and predict the reasonable distribution of medical equipment based on the city's geographical location, floating population and spatial data.

[0007] Technical Solution

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions: a method for configuring group public medical facilities based on a dynamic population data model, comprising a database unit, a city dynamic population calculation unit, a hierarchical demand balance calculation unit and a hierarchical facility intelligent configuration unit,

[0009] The database unit is used to collect and organize data on the geographical location, population, GDP, medical facilities, etc. in the city, providing a calculation basis for the city dynamic population calculation unit;

[0010] The urban dynamic population calculation unit is based on the data in the database unit and the dependencies between spaces, and calculates the population growth value of each city in the urban agglomeration through an improved LSTM model, providing a calculation basis for the hierarchical demand balance calculation unit;

[0011] The hierarchical demand balance calculation unit calculates the accessibility of hierarchical medical facilities, the balance of facility space and the temporal and spatial accessibility based on the data in the database unit and the data dynamically analyzed by the urban dynamic population calculation unit by improving the Gini coefficient;

[0012] The hierarchical facility intelligent configuration unit models a hierarchical public medical facility configuration model based on the data inside the database unit, the data dynamically analyzed by the urban dynamic population calculation unit, and the data calculated by the hierarchical demand balance calculation unit, solves the model based on the NSGA-II method, and conducts a model feasibility analysis.

[0013] The method for configuring group public medical facilities based on a dynamic population data model, the specific implementation methods of the database unit, the urban dynamic population calculation unit, the hierarchical demand balance calculation unit and the hierarchical facility intelligent configuration unit are as follows:

[0014] Sp1: Database arrangement and collection, the database unit arranges and collects the corresponding contents of the city text database, the city cluster database and the city database;

[0015] Sp2: Total urban dynamic population estimation. The urban dynamic population estimation unit calculates the total population prediction results of each city in the urban agglomeration by adding the data in the database building unit into the improved LSTM model in combination with the spatial dependency relationship;

[0016] Sp3: Fine calculation of urban dynamic population. The urban dynamic population calculation unit forms a multi-agent model based on the total population prediction results of each city in the urban agglomeration, the urban agglomeration database and the city database to make a fine population distribution prediction result;

[0017] Sp4: Hierarchical demand balance calculation, the hierarchical demand balance calculation unit combines the population, medical facilities and urban dynamic population detailed calculation results summarized in the city database to calculate the accessibility of hierarchical medical facilities, and performs spatiotemporal accessibility calculations in turn according to the hierarchical medical facility accessibility, and calculates the spatial balance of facilities by improving the Gini coefficient;

[0018] Sp5: Establishment of a hierarchical configuration model, wherein the hierarchical facility intelligent configuration unit establishes a hierarchical configuration model based on facility spatial balance, spatiotemporal accessibility, and facility spatial requirements;

[0019] Sp6: Model verification and solution, the hierarchical facility intelligent configuration unit verifies the feasibility of the model based on the model of the NSGA-II method based on different data of the hierarchical configuration model;

[0020] Sp7: Iterative sorting of schemes. The hierarchical facility intelligent configuration unit performs reachability superposition iteration on the multi-level facility configuration schemes after model verification and solution, thereby performing urgency sorting to obtain the optimal facility configuration scheme.

[0021] Preferably, the database unit, the urban dynamic population calculation unit, the hierarchical demand balance calculation unit and the hierarchical facility intelligent configuration unit are all electrically connected.

[0022] Preferably, the text database in the database unit includes papers, policy texts and research reports, etc., and the urban agglomeration database includes population data, GDP data, industrial data and spatial distribution data, etc., and the city database includes basic geographic data, planning and population data, mobile phone signaling data, medical facility data, etc.

[0023] Preferably, the data used by the database unit for fine calculation of the city's dynamic population are basic city data, planning and implementation of spatiotemporal data, and fine grid population data.

[0024] Preferably, the hierarchical demand balance calculation unit performs text analysis based on planning policy texts at all levels to obtain the specifications of the medical facility tiered diagnosis and treatment mechanism, and conducts medical facility usage behavior based on statistical analysis of sample questionnaire surveys, and establishes a work-residence ratio model based on mobile phone signaling and planning data.

[0025] Preferably, the hierarchical demand balance calculation unit calculates the accessibility of hierarchical medical care based on the city database within the database unit, in combination with medical facility usage behavior, medical facility hierarchical diagnosis and treatment mechanism specifications, and work-residence ratio.

[0026] Preferably, when the model verification solution is obtained in the hierarchical facility intelligent configuration unit, multiple Pareto solutions are obtained through multiple calculations and parameter changes under the same objective conditions to check whether the solution set converges.

[0027] Preferably, the improved LSTM model in the urban dynamic population estimation unit is a traditional LSTM model that adds spatial dependency, and the model based on the NSGA-II method in the hierarchical facility intelligent configuration unit is a non-dominated sorting genetic algorithm with an elite strategy, which is a multi-objective optimization algorithm based on a genetic algorithm, and the Pareto solution is the optimal solution obtained based on the NSGA-II method.

[0028] Beneficial Effects

[0029] The present invention provides a method for configuring group public medical facilities based on a dynamic population data model, which has the following beneficial effects:

[0030] 1. The present invention adopts a database unit, a city dynamic population calculation unit, a hierarchical demand balance calculation unit and a hierarchical facility intelligent configuration unit to form the entire system. Through the detailed calculation of the city's dynamic population and combined with the development characteristics of the tiered diagnosis and treatment system, long-term configuration plans and simulation optimization of urban public medical facilities are carried out. With tiered diagnosis and treatment as the major development background, the city is placed in the large environment of the urban agglomeration, and a construction plan is proposed for the dynamic configuration of urban public medical facilities from the perspective of time and space, which is convenient for improving the lag and roughness of the configuration of public medical facilities in the current plan.

[0031] 2. Based on the public medical facilities with dynamic population, the present invention proposes a spatiotemporal population prediction model for urban agglomerations based on LSTM, which improves the problem that the original population prediction model ignores time and space dependence, simulates the linkage process of cities in the development of urban agglomerations, and facilitates the rational allocation of medical facilities in cities.

[0032] 3. The present invention is directed to a method for calculating the accessibility and balance of hierarchical medical facilities. The temporal and spatial dynamic needs of residents obtained through big data analysis are incorporated into the balance calculation process, and a hierarchical multi-objective configuration model is used to calculate the configuration of public medical facilities. At the same time, dynamic population data and balance indicators are used, and the construction urgency of public facilities is ranked through iterative accessibility calculations, so that the facility configuration fits the actual situation of the city. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 It is a system structure diagram of the present invention;

[0034] Figure 2 The algorithm flow chart of the model of the NSGA-II method of the system structure diagram of the present invention. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Specific embodiment one:

[0037] refer to Figure 1 and Figure 2 A method for configuring group public medical facilities based on a dynamic population data model includes a database unit, an urban dynamic population calculation unit, a hierarchical demand balance calculation unit, and a hierarchical facility intelligent configuration unit.

[0038] The database unit is used to collect and organize data on the city's geographical location, population, GDP, medical facilities, etc., providing a basis for the city's dynamic population estimation unit;

[0039] The urban dynamic population calculation unit is based on the data in the database unit and the dependencies between spaces. It calculates the population growth value of each city in the urban agglomeration through the improved LSTM model, providing a calculation basis for the hierarchical demand balance calculation unit.

[0040] The hierarchical demand balance calculation unit is based on the data in the database unit and the data of the dynamic analysis of the urban dynamic population calculation unit. It calculates the accessibility of hierarchical medical facilities, the balance of facility space and the spatial and temporal accessibility by improving the Gini coefficient.

[0041] The hierarchical facility intelligent configuration unit builds a hierarchical public medical facility configuration model based on the data inside the database unit, the data dynamically analyzed by the urban dynamic population calculation unit, and the data calculated by the hierarchical demand balance calculation unit, solves the model based on the NSGA-II method, and conducts a model feasibility analysis.

[0042] The database unit, the urban dynamic population estimation unit, the hierarchical demand balance estimation unit and the hierarchical facility intelligent configuration unit are electrically connected. The text database in the database unit includes papers, policy texts and research reports, and the urban agglomeration database includes population data, GDP data, industrial data and spatial distribution data, and the urban database includes basic geographic data, planning and population data, mobile phone signaling data, medical facility data, etc. The dynamic population estimation of the city is divided into two aspects. One is the prediction of the total population of the city in the urban agglomeration, and the other is the prediction of the population distribution in the city. For the prediction of the total population of the city, the LSTM model is used to calculate the population growth value of each city in the urban agglomeration. The traditional LSTM achieves the retention and transmission of information in time by adding forget gates, input gates and output gates in the block, which solves the defect of gradient diffusion of the RNN model and is very suitable for solving the prediction problem of time series. However, although the algorithm considers the long-term dependency in time, it does not consider the spatial dependency between things. When predicting the population of each city that is interrelated in the urban agglomeration, it is necessary to consider their spatial synergy. The spatial dependency is added to the traditional LSTM model to calculate the corresponding dynamic population data. Specific embodiment 2:

[0044] refer to Figure 1 and Figure 2 , the specific implementation methods of the group public medical facilities configuration method based on the dynamic population data model, the database unit, the urban dynamic population calculation unit, the hierarchical demand balance calculation unit and the hierarchical facility intelligent configuration unit are as follows:

[0045] Sp1: Database organization and collection. The database unit organizes and collects the corresponding contents of the city's text database, the city cluster database, and the city database;

[0046] Sp2: Total urban dynamic population estimation: The urban dynamic population estimation unit adds the data in the database building unit into the improved LSTM model based on the spatial dependency relationship to calculate the total population prediction results of each city in the urban agglomeration;

[0047] Sp3: Detailed estimation of urban dynamic population. The urban dynamic population estimation unit forms a multi-agent model based on the total population prediction results of each city in the urban agglomeration, the urban agglomeration database and the city database to make a detailed population distribution prediction result.

[0048] Sp4: Hierarchical demand balance calculation. The hierarchical demand balance calculation unit combines the population, medical facilities and urban dynamic population detailed calculation results summarized in the city database to calculate the accessibility of hierarchical medical facilities. It calculates the spatiotemporal accessibility in turn according to the accessibility of hierarchical medical facilities, and calculates the spatial balance of facilities by improving the Gini coefficient.

[0049] Sp5: Establishment of hierarchical configuration model. The hierarchical facility intelligent configuration unit establishes a hierarchical configuration model based on the spatial balance of facilities, spatiotemporal accessibility, and spatial requirements of facilities;

[0050] Sp6: Model verification and solution, the hierarchical facility intelligent configuration unit verifies the feasibility of the model by introducing different data of the hierarchical configuration model into the NSGA-II method;

[0051] Sp7: Iterative sorting of schemes. The hierarchical facility intelligent configuration unit performs reachability superposition iteration on the multi-level facility configuration schemes after model verification and solution, and then sorts them by urgency to obtain the optimal facility configuration scheme.

[0052] The data used by the database unit in the fine calculation of the dynamic population of the city are the basic data of the city, the spatiotemporal data of the planning implementation, and the fine grid population data. The multi-agent model is used to model the distribution of the city's future population. This study takes Shenzhen as an example for calculation and analysis, and uses the community grid as the basic analysis unit (cell). The initial population distribution is based on the data provided by the Urban Rental Grid Office. The data records in detail the people living in each house in the corresponding city, their occupations, ages, and other information. Each person in the data is used as an initial agent in the model. For the income attributes of the agents, according to the information obtained in the questionnaire, they are counted and randomly assigned to agents that meet the age level in units of communities. The agents decide whether to move to the new cell according to the migration rules. At the same time, the status of each cell is calculated, and the new agents are added to the agent set according to the agent addition rules. The number of new agents is determined according to the above urban agglomeration population forecast results.

[0053] The hierarchical demand balance calculation unit performs text analysis based on the planning policy texts at all levels to obtain the specifications of the medical facility hierarchical diagnosis and treatment mechanism, and conducts statistical analysis on the use of medical facilities based on the sample questionnaire survey, and establishes a work-residence ratio model based on mobile phone signaling and planning data. The hierarchical demand balance calculation unit calculates the accessibility of hierarchical medical care based on the city database inside the database unit, combined with the medical facility use behavior, the medical facility hierarchical diagnosis and treatment mechanism specifications, and the work-residence ratio. The use of certain public medical facilities by urban residents is often spatiotemporal and is affected by the changes in the flow of people in time and space. Therefore, based on land use and the law of population flow in the city, the use of public facilities should be simulated in detail. Since the use of medical facilities is not only related to the resident population, but also to the population working in the area, the balance of urban public medical facilities is calculated by the accessibility of each urban unit to the medical facilities. The accessibility of the first-level hospital and the overall accessibility are calculated. When the model is verified and solved in the hierarchical facility intelligent configuration unit, under the same target conditions, multiple Pareto solutions are obtained through multiple calculations and parameter changes to test whether the solution set converges. The improved LSTM model in the urban dynamic population estimation unit adds spatial dependence to the traditional LSTM model. The model based on the NSGA-II method in the hierarchical facility intelligent configuration unit is a non-dominated sorting genetic algorithm with an elite strategy. It is a multi-objective optimization algorithm based on the genetic algorithm, and the Pareto solution is the optimal solution obtained based on the NSGA-II method. The optimal solution is sought using the hill climbing algorithm and the simulated annealing algorithm, and its results are compared and analyzed with this result. Combined with the experience of urban planners, the rationality of the results is qualitatively analyzed. The results obtained through multi-objective optimization It cannot provide planners with practical implementation suggestions. Therefore, the optimal construction order of medical facilities is obtained through the urgency ranking based on accessibility. Therefore, based on the calculation results of future population demand, through the combination of multi-objective public facility configuration model and accessibility model, not only can the facility configuration plan be obtained, but also the spatiotemporal sequence of its construction can be set. The concept of "urban dynamic population demand" is introduced into the public facility configuration theory, and the city is considered in the urban agglomeration. The configuration of public facilities is considered from a forward-looking perspective to avoid the problem that the existing plan cannot meet the needs of rapid urban development. At the same time, the balance and configuration plan of medical facilities are considered from the perspective of hierarchical coordination, which enriches the theoretical system of "tiered diagnosis and treatment" and provides a theoretical basis for the progress of the medical system. On the other hand, from the perspective of fairness, the construction ranking suggestions of public facility configuration are proposed, so as to provide a practical implementation plan. Based on the public medical facilities of dynamic population, a spatiotemporal population prediction model of urban agglomeration based on LSTM is proposed, which improves the problem that the original population prediction model ignores time and space dependence, simulates the linkage process of cities in the development of urban agglomerations, and facilitates the reasonable configuration of medical facilities in cities.

[0054] Specific embodiment three: reference Figure 2 , Figure 2 In order to find multiple Pareto solutions based on the NSGA-II method, spatial dependency is added to the traditional LSTM model, and its input calculation formula is modified as follows:

[0055] X ti =W i I t

[0056] Where X ti is the input of the ith city in year t, W i =diag(W i1 ,W i2 …,W in ) is the distance weight between the ith city and other cities in the urban agglomeration. The distance weight is calculated using the Gauss kernel function. t =(I1,I2…,I n ) is the characteristic value of each city, including: last year's total population, GDP growth rate, proportion of secondary industry, proportion of tertiary industry, proportion of real estate investment, natural population growth rate, and the difference between GDP growth rate and national average growth rate.

[0057] i t =σ(M i X t +V i h t-1 +B i )

[0058] f t =σ(M f X t +V f h t-1 +B f )

[0059] o t =σ(M o X t +V o h t-1 +B o )

[0060] m t =tanh(M m X t +V m h t-1 +B m )

[0061] c t =i t *m t +f t *ct-1

[0062] h t =o t *tanh(c t )

[0063] Among them, X t is the input value at time t, σ(·) is the sigmoid function, tanh(·) is the hyperbolic function, i t ,f t , and o t are the control structures of the input gate, forget gate and output gate at time tt, c t is the memory cell state, h t is the hidden output at time t (the population growth value of that year), M and V are weight parameters, and B is a biased parameter. When using the model results to calculate the urban population inflow in future years, the GDP growth rate and industrial situation of the city can be adjusted according to the development of the urban agglomeration, thereby calculating the total population for each year in the next ten years.

[0064] The basic idea of ​​the traditional NSGA-II algorithm is that, first, an initial population of size N is randomly generated, and after non-dominated sorting, the first generation of offspring population is obtained through the three basic operations of genetic algorithm selection, crossover, and mutation; secondly, starting from the second generation, the parent population and the offspring population are merged to perform fast non-dominated sorting, and the crowding degree of individuals in each non-dominated layer is calculated at the same time, and suitable individuals are selected according to the non-dominated relationship and the crowding degree of the individuals to form a new parent population; finally, a new offspring population is generated through the basic operations of the genetic algorithm: and so on, until the conditions for the end of the program are met. The method used in this system is the non-dominated sorting genetic algorithm with elite strategy (NSGA-II), which is an improved genetic algorithm. The core is to coordinate various objective functions and find the optimal solution of the function when all objective functions are met as much as possible.

[0065] The optimal solution for multi-objective optimization problems is very different from that for single-objective optimization problems. When there is only one objective function, people look for the best solution, which is better than all other solutions. It is usually the global maximum or minimum, that is, the global optimal solution. When there are multiple objectives, it is difficult to find a solution that makes all objective functions optimal at the same time because there are conflicts between the objectives and they cannot be compared. In other words, a solution may be the best for a certain objective function, but not the best for other objective functions, or even the worst. Therefore, for multi-objective optimization problems, there is usually a solution set, and these solutions cannot be compared in terms of all objective functions. Its characteristics are: it is impossible to improve any objective function without weakening at least one other objective function. This solution is called a non-dominated solution or a Pareto optimal solution. The algorithm flow of the improved NSGA-II is as follows: Figure 2 As shown in the figure, in the modeling process, firstly, a random two-dimensional chromosome is generated in combination with the initial data, and each buildable point corresponds to a gene point, thereby forming the second-generation chromosome; secondly, the NSGA-II operator is used to iterate, and the number of iterations is set to finally generate the Pareto solution.

[0066] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprising a reference structure" do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0067] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for configuring group public medical facilities based on a dynamic population data model, including a database unit, an urban dynamic population calculation unit, a hierarchical demand balance calculation unit, and a hierarchical facility intelligent configuration unit. Features: The database unit is used to collect and organize data on the geographical location, population, GDP, and medical facilities in the city, providing a basis for the city dynamic population calculation unit; The urban dynamic population calculation unit is based on the data in the database unit and the dependencies between spaces, and calculates the population growth value of each city in the urban agglomeration through an improved LSTM model, providing a calculation basis for the hierarchical demand balance calculation unit; The hierarchical demand balance calculation unit calculates the accessibility of hierarchical medical facilities, the balance of facility space and the temporal and spatial accessibility based on the data in the database unit and the data dynamically analyzed by the urban dynamic population calculation unit by improving the Gini coefficient; The hierarchical facility intelligent configuration unit models the hierarchical public medical facility configuration model based on the data in the database unit, the data dynamically analyzed by the urban dynamic population calculation unit, and the data calculated by the hierarchical demand balance calculation unit, solves the model based on the NSGA-II method, and performs a model feasibility analysis; The specific implementation methods of the database unit, the urban dynamic population calculation unit, the hierarchical demand balance calculation unit and the hierarchical facility intelligent configuration unit are as follows: Sp1: Database arrangement and collection, the database unit arranges and collects the corresponding contents of the city text database, the city cluster database and the city database; Sp2: Total urban dynamic population estimation. The urban dynamic population estimation unit calculates the total population prediction results of each city in the urban agglomeration by adding the data in the database building unit into the improved LSTM model in combination with the spatial dependency relationship; Sp3: Fine calculation of urban dynamic population. The urban dynamic population calculation unit forms a multi-agent model based on the total population prediction results of each city in the urban agglomeration, the urban agglomeration database and the city database to make a fine population distribution prediction result; Sp4: Hierarchical demand balance calculation, the hierarchical demand balance calculation unit combines the population, medical facilities and urban dynamic population detailed calculation results summarized in the city database to calculate the accessibility of hierarchical medical facilities, and performs spatiotemporal accessibility calculations in turn according to the hierarchical medical facility accessibility, and calculates the spatial balance of facilities by improving the Gini coefficient; Sp5: Establishment of a hierarchical configuration model, wherein the hierarchical facility intelligent configuration unit establishes a hierarchical configuration model based on facility spatial balance, spatiotemporal accessibility, and facility spatial requirements; Sp6: Model verification and solution, the hierarchical facility intelligent configuration unit verifies the feasibility of the model based on the model of the NSGA-II method based on different data of the hierarchical configuration model; Sp7: Iterative sorting of schemes. The hierarchical facility intelligent configuration unit performs reachability superposition iteration on the multi-level facility configuration schemes after model verification and solution, thereby performing urgency sorting to obtain the optimal facility configuration scheme.

2. The method for configuring group public medical facilities based on a dynamic population data model according to claim 1, Features: The database unit, the urban dynamic population calculation unit, the hierarchical demand balance calculation unit and the hierarchical facility intelligent configuration unit are all electrically connected.

3. According to the method for configuring group public medical facilities based on a dynamic population data model as described in claim 1: the text database in the database unit includes papers, policy texts and research reports, and the urban agglomeration database includes population data, GDP data, industrial data and spatial distribution data, and the city database includes basic geographic data, planning and population data, mobile phone signaling data, and medical facility data.

4. The method for configuring group public medical facilities based on a dynamic population data model according to claim 1, Features: The data used by the database unit for fine calculation of the city's dynamic population are basic urban data, planning and spatial-temporal data, and fine grid population data.

5. The method for configuring group public medical facilities based on a dynamic population data model according to claim 1, Features: The hierarchical demand balance calculation unit performs text analysis based on the planning policy texts at all levels to obtain the specifications of the medical facility hierarchical diagnosis and treatment mechanism, and conducts medical facility usage behavior based on statistical analysis of sample questionnaires, and establishes a work-residence ratio model based on mobile phone signaling and planning data.

6. The method for configuring group public medical facilities based on a dynamic population data model according to claim 5, Features: The hierarchical demand balance calculation unit calculates the hierarchical medical accessibility based on the city database within the database unit, combined with the medical facility usage behavior, the medical facility hierarchical diagnosis and treatment mechanism specifications, and the work-residence ratio.

7. The method for configuring group public medical facilities based on a dynamic population data model according to claim 1, Features: When the model verification solution is solved in the hierarchical facility intelligent configuration unit, multiple Pareto solutions are obtained through multiple calculations and parameter changes under the same target conditions to check whether the solution set converges.

8. The method for configuring group public medical facilities based on a dynamic population data model according to claim 1, Features: The improved LSTM model in the urban dynamic population estimation unit adds spatial dependency to the traditional LSTM model. The model based on the NSGA-II method in the hierarchical facility intelligent configuration unit is a non-dominated sorting genetic algorithm with an elite strategy, which is a multi-objective optimization algorithm based on a genetic algorithm, and the Pareto solution is the optimal solution obtained based on the NSGA-II method.

Citation Information

Patent Citations

  • Modeling method for balanced configuration of similar services of different hierarchies

    CN111582764A