Population life expectancy estimation method and device, computer equipment and storage medium

Abstract

The invention relates to the field of population life prediction, in particular to a population life expectancy estimation method and device, computer equipment and a storage medium, population age distribution raster data prediction is performed based on population association raster data and a pre-constructed nonlinear regression mapping model, and matching is performed in combination with a model life table. The population life expectancy raster data is obtained, the necessary requirement for the number of dead people in a traditional method is overcome, the spatial distribution characteristics of the population life expectancy are represented, and the accuracy of population life expectancy estimation of the target area is improved.

Description

Technical Field

[0001] This invention relates to the field of life expectancy prediction, and in particular to a method, apparatus, computer device, and storage medium for estimating life expectancy. Background Technology

[0002] Life expectancy refers to the average number of years a person born in the same period is expected to live, assuming that the mortality rate in each age group remains constant. It comprehensively reflects healthcare, public health, quality of life, and social development, and is one of the three composite indicators of the United Nations Human Development Index, as well as an internationally recognized indicator for evaluating the health level of residents.

[0003] Life expectancy is typically calculated using the Jiang Qinglang Simplified Life Table, which requires current population and mortality figures broken down by age group and sex. Currently, publicly available census data mainly involves current population figures broken down by age group and sex, while mortality figures broken down by age group and sex are difficult to obtain. This makes it difficult to estimate the spatial distribution characteristics of life expectancy. Summary of the Invention

[0004] Based on this, the purpose of the present invention is to provide a method, apparatus, computer device, and storage medium for estimating life expectancy. The method predicts the age distribution of the population based on population-related raster data and a pre-constructed nonlinear regression mapping model, and matches it with the model's life table to obtain the life expectancy at birth raster data. This overcomes the requirement of selecting the number of deaths in traditional methods to characterize the spatial distribution characteristics of life expectancy and improves the accuracy of life expectancy estimation in the target area.

[0005] In a first aspect, embodiments of this application provide a method for estimating life expectancy, comprising the following steps: Obtain population-related raster data for the target area, wherein the population-related raster data includes population-related parameters of several types for several rasters; The population-related raster data is input into a pre-built nonlinear regression mapping model to obtain population age distribution raster data, wherein the population age distribution raster data includes the population age distribution data of each raster; the nonlinear regression mapping model is a model constructed with various types of population-related parameters as explanatory variables and the population number of several age groups of each gender in the population age distribution data as dependent variables. The population age distribution raster data is resampled several times to obtain several resampled population age distribution raster data; the population age distribution raster data is matched with a preset model life table to obtain several resampled population life expectancy raster data, wherein the population life expectancy raster data includes the life expectancy of each gender in each raster. Quality control indicators are calculated based on the population life expectancy raster data from several resampling iterations to obtain the quality control indicators for each gender in each raster. Effective raster identification is performed based on the quality control indicators for each gender of each raster, and effective raster label data for each gender is obtained. By matching the population age distribution raster data, the effective raster label data for each gender, and the model life table, the life expectancy at birth raster data for each gender is obtained, which serves as the life expectancy estimate for the target area.

[0006] Secondly, embodiments of this application provide a life expectancy estimation device, comprising: The data acquisition module is used to obtain population-related raster data of the target area, wherein the population-related raster data includes population-related parameters of several types for several rasters; The model prediction module is used to input the population association raster data into a pre-built nonlinear regression mapping model to obtain population age distribution raster data, wherein the population age distribution raster data includes the population age distribution data of each raster; the nonlinear regression mapping model is a model constructed with various types of population association parameters as explanatory variables and the population number of several age groups of each gender in the population age distribution data as dependent variables. The life expectancy prediction module is used to perform several resampling operations on the population age distribution raster data to obtain several resampled population age distribution raster data; and to match the several resampled population age distribution raster data with a preset model life table to obtain several resampled population life expectancy raster data, wherein the population life expectancy raster data includes the life expectancy at birth for each gender in each raster. The indicator calculation module is used to calculate quality control indicators based on the population life expectancy raster data from several resamplings, and to obtain the quality control indicators for each gender in each raster. The effective grid identification module is used to identify effective grids according to the quality control indicators of each gender for each grid, and obtain effective grid label data for each gender. The life expectancy estimation module is used to match the population age distribution raster data, the effective raster label data for each gender, and the model life table to obtain the life expectancy at birth raster data for each gender, which serves as the life expectancy estimation result for the target area.

[0007] Thirdly, embodiments of this application provide a computer device including a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the life expectancy estimation method as described in the first aspect.

[0008] Fourthly, embodiments of this application provide a storage medium storing a computer program that, when executed by a processor, implements the steps of the life expectancy estimation method as described in the first aspect.

[0009] In this application embodiment, a method, apparatus, computer device, and storage medium for estimating life expectancy are provided. The method predicts the age distribution of the population based on population-related raster data and a pre-built nonlinear regression mapping model, and matches it with the model's life table to obtain the life expectancy at birth raster data. This overcomes the requirement of selecting the number of deaths in traditional methods to characterize the spatial distribution characteristics of life expectancy and improves the accuracy of life expectancy estimation in the target area.

[0010] To better understand and implement this invention, the following detailed description is provided in conjunction with the accompanying drawings. Attached Figure Description

[0011] Figure 1 A flowchart illustrating a life expectancy estimation method provided in one embodiment of this application; Figure 2 A schematic diagram of step S2 in the flow of a life expectancy estimation method provided in one embodiment of this application; Figure 3 A schematic diagram of step S3 in the flowchart of a life expectancy estimation method provided in one embodiment of this application; Figure 4 A schematic diagram of step S4 in the life expectancy estimation method provided in one embodiment of this application; Figure 5 A schematic diagram of step S4 in the flow of a life expectancy estimation method provided in another embodiment of this application; Figure 6 A schematic diagram of step S5 in the flow chart of a life expectancy estimation method provided in one embodiment of this application; Figure 7 A schematic diagram of step S6 in the life expectancy estimation method provided in one embodiment of this application; Figure 8 A schematic diagram of the life expectancy estimation device provided in one embodiment of this application; Figure 9 This is a schematic diagram of the structure of a computer device provided in one embodiment of this application. Detailed Implementation

[0012] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0013] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0014] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0015] Please see Figure 1 , Figure 1 The following is a flowchart illustrating a life expectancy estimation method provided in one embodiment of this application. The method includes the following steps: S1: Obtain population-related raster data for the target area.

[0016] The execution entity of the life expectancy estimation method is the estimation device (hereinafter referred to as the estimation device). In an optional embodiment, the estimation device may be a computer device, a server, or a server cluster composed of multiple computer devices.

[0017] In this embodiment, the estimation device can obtain population-related raster data of the target area, wherein the population-related raster data includes several types of population-related parameters for several raster cells. Specifically, the population-related parameters include GDP data of the primary industry, GDP data of the secondary industry, GDP data of the tertiary industry, DEM, slope, aspect, nighttime light, red light, near-infrared, and thermal infrared raster data.

[0018] S2: Input the population-related raster data into a pre-built nonlinear regression mapping model to obtain population age distribution raster data.

[0019] The nonlinear regression mapping model adopts the CatBoost model, which is a model constructed with various types of population-related parameters as explanatory variables and the population number of several age groups of each gender in the population age distribution data as the dependent variable.

[0020] In this embodiment, the estimation device inputs the population-related raster data into a pre-built nonlinear regression mapping model to obtain population age distribution raster data, wherein the population age distribution raster data includes the population age distribution data of each raster.

[0021] Please see Figure 2 , Figure 2 A schematic diagram of step S2 in the life expectancy estimation method provided in one embodiment of this application, including steps S21 to S23, is shown below: S21: The population counts of all grids of the same gender and the same age group in the population age distribution raster data are summed to obtain the predicted population counts of each gender and each age group.

[0022] In this embodiment, the estimation device sums up the population counts of all grids of the same age group for the same gender in the population age distribution grid data to obtain the predicted population counts for each age group for each gender.

[0023] S22: Obtain the population statistics for each age group of each gender; divide the population statistics for the same age group of the same gender by the population projection to obtain the scaling factor for each age group of each gender.

[0024] In this embodiment, the estimation device obtains the population statistics for each age group of each gender; the estimation device divides the population statistics for the same age group of the same gender by the predicted population number to obtain the scaling factor for each age group of each gender.

[0025] S23: Based on the population number of each gender and age group in each grid of the population age distribution raster data, the scaling factor of each gender and age group, and the preset constraint scaling algorithm, obtain the processed population age distribution raster data.

[0026] The constraint scaling algorithm is as follows:

[0027] In the formula, For the processed first i Gender of each grid s The Population size in each age group For the first i Gender of each grid s The Population size in each age group For gender s The Scaling factor for each age group These are numerical operation functions.

[0028] In this embodiment, the estimation device obtains the processed population age distribution raster data based on the population number of each gender and age group in each raster of the population age distribution raster data, the scaling factor of each gender and age group, and a preset constraint scaling algorithm, so that the predicted total population is consistent with the total statistical population.

[0029] S3: Perform several resampling operations on the population age distribution raster data to obtain several resampled population age distribution raster data; match the several resampled population age distribution raster data with the preset model life table to obtain several resampled population life expectancy raster data.

[0030] Due to sampling errors and model errors, in this embodiment, the estimation device performs several resampling operations based on the population age distribution raster data to obtain several resampled population age distribution raster data.

[0031] The estimation device matches several resampled population age distribution raster data with a preset model life table to obtain several resampled population life expectancy raster data, wherein the population life expectancy raster data includes life expectancy for each gender in each raster, so as to improve the accuracy of life expectancy prediction.

[0032] Specifically, the model life table adopts the United Nations General Model Life Table (UN_General). For a given range of life expectancies at birth... e The model's life table provides information for each age group. Standardized survival population ratio vector , This characterizes life expectancy at birth under the assumptions of a stable population and no migration. e The standard age structure of the population at that time For the resampled population life expectancy raster data, please refer to Figure 3 , Figure 3 A schematic diagram of step S3 in the life expectancy estimation method provided in one embodiment of this application, including steps S31 to S33, is shown below: S31: Based on the population age distribution raster data and the preset population proportion vector calculation algorithm, obtain the population proportion vector of each age group for each gender in each raster.

[0033] The algorithm for calculating the population proportion vector is as follows:

[0034] In the formula, For the first i Gender of each grid s The Population proportion vector for each age group For the first i Gender of each grid s The Population size in each age group For the first i Gender of each grid s The total population.

[0035] In this embodiment, the estimation device obtains the population proportion vectors of each gender and each age group for each grid based on the population age distribution grid data and a preset population proportion vector calculation algorithm.

[0036] S32: Based on the population proportion vectors of each gender and age group in each grid, the population proportion vectors of each age group in the model life table under each life expectancy at birth, and the preset squared error calculation algorithm, obtain the squared error sum of each gender in each grid under each life expectancy at birth.

[0037] The algorithm for calculating the sum of squared errors is as follows:

[0038] In the formula, For the first i A grid in life expectancy at birth e The gender below s The sum of squared errors, Number of age groups To life expectancy at birth The next Population proportion vector for each age group.

[0039] In this embodiment, the estimation device obtains the sum of squared errors for each gender under each life expectancy based on the population proportion vectors for each age group of each gender in each grid, the population proportion vectors for each age group under each life expectancy in the model life table, and a preset sum of squared errors calculation algorithm, in order to quantify the difference between the observed age structure and the model expected structure.

[0040] S33: Based on the sum of squared errors of each grid cell for each sex and age group under each life expectancy, determine the life expectancy for each sex and age group with the smallest sum of squared errors, and obtain the life expectancy for each grid cell for each sex and age group.

[0041] In this embodiment, the estimation device determines the life expectancy at birth for each age group of each sex with the smallest sum of squared errors for each grid under each life expectancy, based on the sum of squared errors for each grid at each age group of each sex, and obtains the life expectancy at birth for each age group of each grid at each sex.

[0042] S4: Calculate quality control indicators based on the population life expectancy raster data from several resampling iterations, and obtain the quality control indicators for each gender in each raster.

[0043] In this embodiment, the estimation device calculates quality control indicators based on several resampled population life expectancy at birth raster data to obtain quality control indicators for each gender in each raster.

[0044] Specifically, the quality control indicators include standard error; please refer to [link / reference]. Figure 4 , Figure 4 A schematic diagram of step S4 in the life expectancy estimation method provided in one embodiment of this application, including steps S401 to S402, is shown below: S401: Based on the life expectancy at birth for each gender in each grid of the population life expectancy at birth raster data from several resampled periods, and a preset mean calculation algorithm, obtain the average life expectancy at birth for each gender in each grid.

[0045] The mean calculation algorithm is as follows:

[0046] In the formula, For the first i Gender of each grid s Life expectancy at birth B This represents the number of resamples. For the first b Second resampled raster data of life expectancy at birth i Gender of each grid s Life expectancy at birth.

[0047] In this embodiment, the estimation device obtains the average life expectancy at birth for each gender in each grid based on the life expectancy at birth for each gender in the population life expectancy at birth grid data from several resampled population life expectancy at birth grids and a preset mean calculation algorithm.

[0048] S402: Based on the life expectancy at birth, average life expectancy at birth, and a preset standard error calculation algorithm for each gender in each grid of the population life expectancy at birth raster data from several resampled data, obtain the standard error for each gender in each grid.

[0049] The algorithm for calculating the sum of squared errors is as follows:

[0050] In the formula, For the first i Gender of each grid s The standard error.

[0051] In this embodiment, the estimation device obtains the standard error for each gender in each grid based on the life expectancy at birth, mean life expectancy at birth, and a preset standard error calculation algorithm for each grid in several resampled population life expectancy at birth raster data. The standard error measures the dispersion of the resampled estimate, i.e., the sampling standard error of the original mean life expectancy at birth. The larger the value, the higher the uncertainty in estimating life expectancy based on the age structure of that cell.

[0052] The quality control indicators also include the confidence interval width; please refer to [link / reference needed]. Figure 5 , Figure 5 A schematic diagram of step S4 in the life expectancy estimation method provided in another embodiment of this application, including steps S411 to S412, is shown below: S411: Sort the life expectancy of the same sex in the same grid in the population life expectancy raster data that has been resampled several times, and obtain the sorted life expectancy data of each sex in each grid.

[0053] In this embodiment, the estimation device sorts the life expectancy at birth for the same sex in the same grid from several resampled population life expectancy at birth grid data to obtain sorted life expectancy at birth for each sex in each grid.

[0054] S412: Construct confidence intervals based on the life expectancy at birth sorted data for each gender in each grid, and obtain the confidence intervals for each gender in each grid; calculate the confidence width based on the confidence intervals for each gender in each grid, and obtain the confidence interval width for each gender in each grid.

[0055] In this embodiment, the estimation device constructs confidence intervals for each gender based on the life expectancy ranking data for each grid, thereby obtaining confidence intervals for each gender in each grid. Specifically, the estimation device uses the 2.5 percentile and 97.5 percentile of the life expectancy ranking data as the lower limits of the confidence intervals to construct confidence intervals for each gender in each grid.

[0056] The estimation device calculates the confidence width based on the confidence intervals for each gender in each grid, and obtains the confidence interval width for each gender in each grid. Specifically, the estimation device subtracts the upper limit and lower limit of the confidence interval for the same gender in the same grid to obtain the confidence interval width for each gender in each grid.

[0057] S5: Based on the quality control indicators of each gender in each grid, perform effective grid identification to obtain effective grid label data for each gender; In this embodiment, the estimation device performs effective grid identification based on the quality control indicators of each gender for each grid, and obtains effective grid label data for each gender.

[0058] Please see Figure 6 , Figure 6 A schematic diagram of step S5 in the life expectancy estimation method provided in one embodiment of this application, including steps S51 to S52, is shown below: S51: Calculate the standard error threshold by performing 95th percentile calculations based on the standard errors of each gender in each grid.

[0059] In this embodiment, the estimation device calculates the standard error threshold by performing 95th percentile calculations based on the standard error of each gender in each grid.

[0060] S52: Based on the standard error, confidence interval width, standard error threshold, and preset confidence interval width threshold for each gender of each grid, if the standard error is less than the standard error threshold and the confidence interval width is less than the confidence interval width threshold, the grid is used as a valid grid for the corresponding gender, and valid grid label data for each gender is constructed.

[0061] In this embodiment, the estimation device uses the standard error, confidence interval width, standard error threshold, and preset confidence interval width threshold for each gender of each grid. If the standard error is less than the standard error threshold and the confidence interval width is less than the confidence interval width threshold, the grid is considered as a valid grid for the corresponding gender, and valid grid label data for each gender is constructed.

[0062] S6: Match the population age distribution raster data, the effective raster label data for each gender, and the model life table to obtain the life expectancy raster data for each gender, which serves as the life expectancy estimation result for the target area.

[0063] In this embodiment, the estimation device matches the population age distribution raster data, valid raster label data for each gender, and the model life table to obtain life expectancy at birth raster data for each gender, which serves as the life expectancy estimation result for the target area. By predicting population age distribution raster data based on population-related raster data and a pre-built nonlinear regression mapping model, and then matching it with the model life table to obtain life expectancy at birth raster data, this method overcomes the traditional requirement of selecting the number of deaths to characterize the spatial distribution characteristics of life expectancy, thus improving the accuracy of life expectancy estimation for the target area.

[0064] Please see Figure 7 , Figure 7 A schematic diagram of step S5 in the life expectancy estimation method provided in one embodiment of this application, including steps S61 to S64, is shown below: S61: Based on the population age distribution raster data and the effective raster label data for each gender, determine the population number of each age group in each effective raster for each gender; calculate the population ratio based on the population number of each age group in each effective raster for each gender, and obtain the population ratio vector of each age group in each effective raster for each gender.

[0065] In this embodiment, the estimation device determines the population size of each age group in each valid grid for each gender based on the population age distribution grid data and the valid grid label data for each gender.

[0066] The estimation device calculates the population ratio based on the population size of each age group in each effective grid for each gender, and obtains the population ratio vector of each age group in each effective grid for each gender. For specific implementation, please refer to step S31, which will not be repeated here.

[0067] S62: Based on the population proportion vector of each effective grid for each gender and the life table of the model, calculate the sum of squared errors and life expectancy at birth to obtain the sum of squared errors of each effective grid for each gender under each life expectancy and the life expectancy at birth of each effective grid for each gender under each age.

[0068] In this embodiment, the estimation device calculates the sum of squared errors and life expectancy at birth based on the population proportion vectors of each age group for each effective grid of each gender and the model life table, thereby obtaining the sum of squared errors for each effective grid of each gender under each life expectancy at each age group, and the life expectancy at birth for each effective grid of each gender. Specific embodiments can be found in steps S32 and S33, and will not be repeated here.

[0069] S63: Determine the minimum squared error of each valid grid cell for each gender, and calculate the 95th percentile based on the minimum squared error of each valid grid cell for the same gender to obtain the squared error threshold.

[0070] In this embodiment, the estimation device determines the minimum squared error of each effective grid for each gender, and calculates the 95th percentile based on the minimum squared error of each effective grid for the same gender to obtain the squared error threshold.

[0071] S64: Based on the sum of the least squares errors of each effective grid for each gender and the threshold of the sum of squares errors, if the sum of the least squares errors is greater than the threshold of the sum of squares errors, the effective grids are reduced. Based on the life expectancy at birth for each age group of each effective grid for each gender after the reduction, population life expectancy at birth grid data is constructed to obtain population life expectancy at birth grid data for each gender.

[0072] In this embodiment, the estimation device calculates the minimum squared error of each effective grid for each gender and the threshold value of the sum of squared errors. If the minimum squared error is greater than the threshold value of the sum of squared errors, the effective grid is reduced. Based on the life expectancy at birth for each age group of each effective grid for each gender after the reduction, population life expectancy at birth grid data is constructed to obtain population life expectancy at birth grid data for each gender.

[0073] Please refer to Figure 8 , Figure 8 This is a schematic diagram of a life expectancy estimation device provided in one embodiment of this application. The device can be implemented entirely or partially through software, hardware, or a combination of both. The device 8 includes: The data acquisition module 81 is used to obtain population-related raster data of the target area, wherein the population-related raster data includes population-related parameters of several types of several rasters; The model prediction module 82 is used to input the population association raster data into a pre-built nonlinear regression mapping model to obtain population age distribution raster data, wherein the population age distribution raster data includes the population age distribution data of each raster; the nonlinear regression mapping model is a model constructed with various types of population association parameters as explanatory variables and the population number of several age groups of each gender in the population age distribution data as dependent variables. The life expectancy prediction module 83 is used to perform several resampling operations on the population age distribution raster data to obtain several resampled population age distribution raster data; and to match the several resampled population age distribution raster data with a preset model life table to obtain several resampled population life expectancy raster data, wherein the population life expectancy raster data includes the life expectancy at birth for each gender in each raster. The indicator calculation module 84 is used to calculate quality control indicators based on the population life expectancy raster data from several resamplings, and to obtain the quality control indicators for each gender in each raster. The effective grid identification module 85 is used to identify effective grids according to the quality control indicators of each gender of each grid, and obtain effective grid label data for each gender. The life expectancy estimation module 86 is used to match the population age distribution raster data, the effective raster label data of each gender, and the model life table to obtain the life expectancy at birth raster data of each gender, as the life expectancy estimation result of the target area.

[0074] In this embodiment, a data acquisition module obtains population-related raster data of a target area, wherein the population-related raster data includes several types of population-related parameters for several raster cells; a model prediction module inputs the population-related raster data into a pre-constructed nonlinear regression mapping model to obtain population age distribution raster data, wherein the population age distribution raster data includes population age distribution data for each raster cell; the nonlinear regression mapping model is constructed using various types of population-related parameters as explanatory variables and the population number of several age groups for each gender in the population age distribution data as the dependent variable; a life expectancy prediction module performs several resampling operations on the population age distribution raster data to obtain several resampled population age distribution raster data; based on the several resampled population age distribution... The process involves matching raster data with a pre-defined model life table to obtain several resampled raster data sets of life expectancy at birth, including life expectancy at birth for each gender in each raster. A quality control index is calculated based on the resampled raster data using an index calculation module, yielding quality control indices for each gender in each raster. A valid raster identification module identifies valid raster labels for each gender based on the quality control indices for each raster, obtaining valid raster label data for each gender. Finally, a life expectancy estimation module matches the population age distribution raster data, the valid raster label data for each gender, and the model life table to obtain the life expectancy at birth raster data for each gender, serving as the life expectancy estimation result for the target area. This method, based on population-related raster data and a pre-constructed nonlinear regression mapping model, predicts population age distribution raster data and matches it with the model life table to obtain life expectancy at birth raster data. This overcomes the traditional method's requirement to select the number of deaths to characterize the spatial distribution of life expectancy, improving the accuracy of life expectancy estimation for the target area.

[0075] Please refer to Figure 9 , Figure 9 This is a schematic diagram of the structure of a computer device provided in one embodiment of this application. The computer device 9 includes: a processor 91, a memory 92, and a computer program 93 stored in the memory 92 and executable on the processor 91; the computer device can store multiple instructions, which are adapted to be loaded and executed by the processor 91. Figures 1 to 7 The method steps of the illustrated embodiment can be found in the following documentation for detailed execution. Figures 1 to 7 The specific details of the illustrated embodiments will not be elaborated here.

[0076] The processor 91 may include one or more processing cores. The processor 91 connects to various parts of the server using various interfaces and lines, and executes various functions and processes data of the life expectancy estimation device 8 by running or executing instructions, programs, code sets, or instruction sets stored in the memory 92, and by calling data stored in the memory 92. Optionally, the processor 91 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 91 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required to be displayed on the touch screen; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 91 and may be implemented as a separate chip.

[0077] The memory 92 may include random access memory (RAM) or read-only memory. Optionally, the memory 92 may include a non-transitory computer-readable storage medium. The memory 92 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 92 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch instructions), instructions for implementing the various method embodiments described above, etc.; the data storage area may store data involved in the various method embodiments described above, etc. Optionally, the memory 92 may also be at least one storage device located remotely from the aforementioned processor 91.

[0078] This application also provides a storage medium that can store multiple instructions. These instructions are applicable to being loaded and executed by a processor using the method steps described in Embodiments 1 to 4 above. For details of the execution process, please refer to the specific descriptions of Embodiments 1 to 4, which will not be repeated here.

[0079] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0080] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0081] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the algorithm. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0082] In the embodiments provided by this invention, it should be understood that the disclosed apparatus / terminal devices and methods can be implemented in other ways. For example, the apparatus / terminal device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0083] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0084] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0085] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms.

[0086] This invention is not limited to the above-described embodiments. If any modifications or variations to this invention do not depart from the spirit and scope of this invention, and if such modifications and variations fall within the scope of the claims and equivalent technologies of this invention, then this invention also intends to include such modifications and variations.

Claims

1. A method for estimating life expectancy, characterized in that, Includes the following steps: Obtain population-related raster data for the target area, wherein the population-related raster data includes population-related parameters of several types for several rasters; The population-related raster data is input into a pre-built nonlinear regression mapping model to obtain population age distribution raster data, wherein the population age distribution raster data includes the population age distribution data of each raster; the nonlinear regression mapping model is a model constructed with various types of population-related parameters as explanatory variables and the population number of several age groups of each gender in the population age distribution data as dependent variables. The population age distribution raster data is resampled several times to obtain several resampled population age distribution raster data; the population age distribution raster data is matched with a preset model life table to obtain several resampled population life expectancy raster data, wherein the population life expectancy raster data includes the life expectancy of each gender in each raster. Quality control indicators are calculated based on the population life expectancy raster data from several resampling iterations to obtain the quality control indicators for each gender in each raster. Effective raster identification is performed based on the quality control indicators for each gender of each raster, and effective raster label data for each gender is obtained. By matching the population age distribution raster data, the effective raster label data for each gender, and the model life table, the life expectancy at birth raster data for each gender is obtained, which serves as the life expectancy estimate for the target area.

2. The life expectancy estimation method according to claim 1, characterized in that, The step of inputting the population-related raster data into a pre-built nonlinear regression mapping model to obtain population age distribution raster data further includes the following steps: The population counts of all grids of the same sex and the same age group in the population age distribution raster data are summed to obtain the predicted population counts of each sex and each age group. Obtain demographic data for each gender and age group; Divide the population statistics for the same age group of the same sex by the population projection to obtain the scaling factor for each age group of each sex. Based on the population size of each gender and age group in each grid of the population age distribution raster data, the scaling factor of each gender and age group, and a preset constraint scaling algorithm, the processed population age distribution raster data is obtained, wherein the constraint scaling algorithm is: In the formula, For the processed first i Gender of each grid s The Population size in each age group For the first i Gender of each grid s The Population size in each age group For gender s The Scaling factor for each age group These are numerical operation functions.

3. The life expectancy estimation method according to claim 2, characterized in that, The step of matching resampled population age distribution raster data with a pre-set model life table to obtain resampled life expectancy raster data includes the following steps: Based on the population age distribution raster data and a preset population proportion vector calculation algorithm, the population proportion vectors for each gender and age group in each raster are obtained. The population proportion vector calculation algorithm is as follows: In the formula, For the first i Gender of each grid s The Population proportion vector for each age group For the first i Gender of each grid s The Population size in each age group For the first i Gender of each grid s The total population; Based on the population proportion vectors of each gender and age group in each grid, the population proportion vectors of each age group in the model life table under each life expectancy at birth, and a preset sum of squared errors calculation algorithm, the sum of squared errors for each gender in each grid under each life expectancy at birth is obtained, wherein the sum of squared errors calculation algorithm is as follows: In the formula, For the first i A grid in life expectancy at birth e The gender below s The sum of squared errors, Number of age groups To life expectancy at birth The next Population proportion vector for each age group; Based on the sum of squared errors of each grid cell for each sex and age group under each life expectancy, determine the life expectancy for each sex and age group with the smallest sum of squared errors, and obtain the life expectancy for each grid cell for each sex and age group.

4. The life expectancy estimation method according to claim 3, characterized in that: The quality control indicators include standard error; The step of calculating quality control indicators based on several resampled raster data of life expectancy at birth to obtain quality control indicators for each gender in each raster includes the following steps: Based on the life expectancy at birth for each sex in each grid of the population life expectancy at birth raster data from several resampling iterations, and a preset mean calculation algorithm, the average life expectancy at birth for each sex in each grid is obtained. The mean calculation algorithm is as follows: In the formula, For the first i Gender of each grid s Life expectancy at birth B This represents the number of resamples. For the first b Second resampled raster data of life expectancy at birth i Gender of each grid s Life expectancy at birth; Based on the life expectancy at birth, mean life expectancy at birth, and a pre-defined standard error calculation algorithm for each sex in each grid of the population life expectancy at birth raster data from several resampling iterations, the standard error for each sex in each grid is obtained. The algorithm for calculating the sum of squared errors is as follows: In the formula, For the first i Gender of each grid s The standard error.

5. The life expectancy estimation method according to claim 4, characterized in that: The quality control indicators include the confidence interval width; The step of calculating quality control indicators based on several resampled raster data of life expectancy at birth to obtain quality control indicators for each gender in each raster includes the following steps: The life expectancy at birth for the same sex in the same grid cell is sorted based on the life expectancy at birth raster data from several resampled population data, to obtain the sorted life expectancy at birth for each sex in each grid cell. Confidence intervals are constructed based on the life expectancy at birth sorted by gender for each grid, to obtain the confidence intervals for each gender in each grid; confidence widths are calculated based on the confidence intervals for each gender in each grid, to obtain the confidence interval widths for each gender in each grid.

6. The life expectancy estimation method according to claim 5, characterized in that, The process of identifying effective raster labels for each gender based on quality control indicators for each raster includes the following steps: The standard error threshold is obtained by calculating the 95th percentile based on the standard error of each gender in each grid. Based on the standard error, confidence interval width, standard error threshold, and preset confidence interval width threshold for each gender of each grid, if the standard error is less than the standard error threshold and the confidence interval width is less than the confidence interval width threshold, the grid is considered a valid grid for the corresponding gender, and valid grid label data for each gender is constructed.

7. The life expectancy estimation method according to claim 5, characterized in that, The step of matching the population age distribution raster data, the effective raster label data for each gender, and the model life table to obtain the life expectancy at birth raster data for each gender includes the following steps: Based on the population age distribution raster data and the effective raster label data for each gender, determine the population number of each age group in each effective raster for each gender; calculate the population ratio based on the population number of each age group in each effective raster for each gender, and obtain the population ratio vector of each age group in each effective raster for each gender. Based on the population proportion vector of each effective grid for each gender and the life table of the model, the sum of squared errors and life expectancy at birth are calculated to obtain the sum of squared errors of each effective grid for each gender under each life expectancy at each gender, and the life expectancy at birth of each effective grid for each gender in each age group. Determine the minimum squared error of each valid grid cell for each gender, and calculate the 95th quantile based on the minimum squared error of each valid grid cell for the same gender to obtain the squared error threshold. Based on the sum of least squares errors of each effective grid for each gender and the threshold of the sum of squares errors, if the sum of least squares errors is greater than the threshold of the sum of squares errors, the effective grids are reduced. Based on the life expectancy at birth for each age group of each effective grid for each gender after the reduction, population life expectancy at birth grid data is constructed to obtain population life expectancy at birth grid data for each gender.

8. A life expectancy estimation device, characterized in that, include: The data acquisition module is used to obtain population-related raster data of the target area, wherein the population-related raster data includes population-related parameters of several types for several rasters; The model prediction module is used to input the population association raster data into a pre-built nonlinear regression mapping model to obtain population age distribution raster data, wherein the population age distribution raster data includes the population age distribution data of each raster; the nonlinear regression mapping model is a model constructed with various types of population association parameters as explanatory variables and the population number of several age groups of each gender in the population age distribution data as dependent variables. The life expectancy prediction module is used to perform several resampling operations on the population age distribution raster data to obtain several resampled population age distribution raster data; and to match the several resampled population age distribution raster data with a preset model life table to obtain several resampled population life expectancy raster data, wherein the population life expectancy raster data includes the life expectancy at birth for each gender in each raster. The indicator calculation module is used to calculate quality control indicators based on the population life expectancy raster data from several resamplings, and to obtain the quality control indicators for each gender in each raster. The effective grid identification module is used to identify effective grids according to the quality control indicators of each gender for each grid, and obtain effective grid label data for each gender. The life expectancy estimation module is used to match the population age distribution raster data, the effective raster label data for each gender, and the model life table to obtain the life expectancy at birth raster data for each gender, which serves as the life expectancy estimation result for the target area.

9. A computer device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the life expectancy estimation method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a computer program that, when executed by a processor, implements the steps of the life expectancy estimation method as described in any one of claims 1 to 7.

Images