A population shrinkage recognition method, system and device based on scale-structure coupling and space-time characteristics, and a storage medium

Abstract

This invention discloses a method, system, device, and storage medium for identifying population shrinkage based on scale-structure coupling and spatiotemporal characteristics, belonging to the field of population data analysis technology. The invention is executed by computer equipment: first, it acquires multi-period regional population size, population structure data, and regional spatial basic data; it constructs a two-dimensional indicator system and completes the standardization of the indicators in the same direction, using the entropy weight method to obtain the weights of each indicator; it calculates the scale and structural shrinkage indices in different dimensions and couples them to diagnose shrinkage types, solving for the comprehensive shrinkage index to complete the shrinkage level classification; it extracts the population shrinkage time trajectory based on multi-period data, and identifies spatial clustering, center of gravity migration, and spatial evolution trajectories by combining spatial adjacency relationships; finally, it outputs the full-dimensional identification results in multiple forms. This invention takes into account both explicit scale shrinkage and implicit structural shrinkage, and can automatically realize the full-process identification of static classification, temporal evolution, and spatial evolution of regional population shrinkage, improving the comprehensiveness and objectivity of population shrinkage identification.

Description

Technical Field

[0001] This invention relates to the fields of population big data analysis and spatial geographic information technology, and in particular to a method, system, device and storage medium for identifying population shrinkage based on scale-structure coupling and spatiotemporal characteristics. Background Technology

[0002] Current mainstream population shrinkage detection technologies generally rely solely on total population growth or decline data to determine whether shrinkage has occurred, resulting in six inherent technical flaws:

[0003] One-sided identification criteria: Relying solely on the shrinking total population fails to identify structurally hidden shrinkage areas where the total population has not decreased significantly, but aging is intensifying and the local population retention rate is declining.

[0004] The contraction type cannot be distinguished: it is impossible to separate the four differentiated regions: scale-driven contraction, structure-driven contraction, compound synchronous contraction, and no obvious contraction.

[0005] Large error in indicator calculation: The original indicator attributes are divided into positive and negative, and the logic of indicator change is not unified. Direct weighted calculation will cause index distortion.

[0006] The weighting is highly subjective: it often relies on human experience to assign weights, resulting in poor repeatability of the identification results and a high degree of human interference.

[0007] Missing temporal evolution analysis: Only static calculation of the contraction level in a single period cannot depict the temporal evolution trajectory of regional population contraction, such as its continuity, aggravation, and phased decline;

[0008] No spatial feature mining: Only outputs a table of regional shrinkage results, and cannot quantify the degree of spatial clustering, the pattern of center of gravity movement, spatial diffusion or isolated new features of shrinkage.

[0009] Based on the aforementioned pain points of existing technologies, this invention proposes a computer-automated full-process population shrinkage identification scheme, which takes the coupling of scale and structure as the core, integrates temporal evolution and spatial geographical features, and systematically solves the aforementioned defects of existing technologies. Summary of the Invention

[0010] In order to overcome the shortcomings of the prior art, the purpose of this invention is to provide a method, system, device and storage medium for population shrinkage identification based on scale-structure coupling and spatiotemporal characteristics.

[0011] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0012] This invention provides a population shrinkage identification method based on scale-structure coupling and spatiotemporal features, executed by a computer device, comprising the following steps:

[0013] S1. Raw data input steps: The computer device imports multi-time series population raw data and spatial basic data of the target research unit; the population raw data is divided into population size index data and population structure index data, and the spatial basic data includes at least the administrative boundary data of the research unit, the unit area data, the geometric center coordinate data of the unit, and the spatial adjacency relationship data between units;

[0014] S2. Indicator System Construction Steps: The computer equipment divides the imported indicators into two major attribute dimensions: the population size dimension, which is used to characterize the population's ability to agglomerate, and the population structure dimension, which is used to characterize changes in the internal composition of the population. Each indicator is then labeled with an attribute type, which is divided into positive and negative indicators. Positive indicators are defined as those with larger values ​​corresponding to a stronger degree of population contraction, while negative indicators are defined as those with smaller values ​​corresponding to a stronger degree of population contraction.

[0015] S3. Standardization Processing Steps for Indicators in the Same Direction: The computer equipment selects matching standardization operation rules based on the attribute type of each indicator label to perform dimensionless and direction-unified processing on all indicators, so that all standardized indicators uniformly follow the principle that the larger the calculated value of the indicator, the stronger the population shrinkage of the corresponding research unit.

[0016] S4. Automatic calculation step of indicator weights: The computer equipment uses the standardized full indicator dataset as the basis for calculation, and adopts the entropy weight algorithm to automatically calculate the objective weight of each indicator based on the degree of data dispersion difference between the indicators and the samples.

[0017] S5. Steps for calculating the dimensional shrinkage index: The computer equipment collects corresponding indicators based on the population size dimension and population structure dimension divided in S2, and combines the indicator weights obtained in S4 with the standardized indicator values ​​generated in S3 to perform independent calculations on each dimension, thereby obtaining the population size shrinkage index and population structure shrinkage index corresponding to each research unit.

[0018] S6. Diagnostic steps for scale-structure coupling type: The computer equipment retrieves the pre-configured population scale contraction threshold and population structure contraction threshold, and combines the numerical combination relationship of the population scale contraction index and the population structure contraction index to classify each research unit into four types of coupled contraction: compound contraction, scale unidirectional contraction, structure unidirectional contraction, and non-obvious contraction.

[0019] S7. Calculation steps for comprehensive shrinkage index and shrinkage level: The computer equipment performs weighted fusion calculation on the population size shrinkage index and the population structure shrinkage index to obtain the comprehensive population shrinkage index; based on the preset multi-level threshold, according to the value range of the comprehensive population shrinkage index, the corresponding population shrinkage intensity level is divided for each research unit;

[0020] S8. Temporal contraction trajectory identification steps: The computer device retrieves the comprehensive population contraction index and the matching contraction intensity level corresponding to multiple consecutive statistical time series, maps the contraction level to ordered codes to construct a single research unit multi-time series coding sequence, calculates the contraction duration parameter, cross-time series level change parameter, and comprehensive index temporal change slope parameter based on the coding sequence, and classifies different types of population contraction time trajectories based on the combination logic of the three types of parameters.

[0021] S9. Spatial contraction characteristics and spatial trajectory identification steps: The computer device introduces the spatial basic data imported in S1, and combines it with the contraction status identifier variables of each research unit under each time series to quantitatively calculate the spatial proportion parameter of the contraction unit, the spatial clustering degree parameter, the centroid coordinate parameter of the whole region contraction, and the centroid cross-time series movement parameter; at the same time, according to the contraction status change relationship between two adjacent time series, the spatial contraction trajectory type corresponding to each research unit is divided.

[0022] S10, Result Multi-format Output Step: The computer device summarizes and couples the classification results, various contraction indices, contraction level data, time-series trajectory parameters, and spatial feature parameters, and completes the storage and output of the recognition results through at least one format among data tables, spatial vector layers, thematic visualization maps, and statistical documents.

[0023] Furthermore, in S1, the population size indicators should at least include the total population at the end of the year, the natural population growth rate, and the population density; the population structure indicators should at least include the urbanization rate, the aging rate, and the local population retention rate; among them, the aging rate is the ratio of the total population aged 65 and above in the unit to the total population of the unit, and the local population retention rate is the ratio of the local resident population to the unit's resident population.

[0024] Furthermore, in S3, the standardization process adopts the range normalization method, and after processing, the value range of all indicators is uniformly constrained to a fixed range; if the value of a single indicator does not fluctuate in the whole sample, the computer equipment will set all standardized values ​​of the indicator to the preset value.

[0025] Furthermore, the coupling classification judgment rule in S6 is as follows: if both the population size shrinkage index and the population structure shrinkage index exceed the corresponding threshold at the same time, it is a compound shrinkage type; if only the population size shrinkage index exceeds the limit, it is a unidirectional shrinkage type; if only the population structure shrinkage index exceeds the limit, it is a unidirectional shrinkage type; if neither index reaches the corresponding threshold, it is a non-obvious shrinkage type. The size shrinkage threshold and the structure shrinkage threshold are determined by any algorithm of the sample quantile method, the mean method, and the natural breakpoint method.

[0026] Furthermore, the comprehensive population shrinkage index in S7 is obtained by multiplying the size shrinkage index and the structural shrinkage index by their respective dimension weights and then summing them up. The sum of the two dimension weights is fixed at 1. The dimension weights are determined by equal assignment or objective weighting. The shrinkage intensity level is divided into five levels: no shrinkage, mild shrinkage, moderate shrinkage, severe shrinkage, and extremely severe shrinkage.

[0027] Furthermore, the population contraction time trajectory types in S8 include non-contraction trajectory, recent contraction trajectory, phased contraction trajectory, continuously aggravated contraction trajectory, continuously stable contraction trajectory, and continuously slowing contraction trajectory.

[0028] Furthermore, the spatial contraction trajectory in S9 includes continuous contraction type, newly occurring contraction type, contraction relief type, and continuous non-contraction type; the newly occurring contraction type is further divided into spatial expansion type contraction and isolated sudden type contraction; the spatial adjacency determination of the research unit includes two determination methods: shared edge adjacency and pre-set distance threshold adjacency.

[0029] This invention also provides a population shrinkage identification system based on scale-structure coupling and spatiotemporal features, comprising:

[0030] Data acquisition module: used to import multi-time series population raw data and spatial basic data of the target research unit into the computer device; the population raw data is divided into population size index data and population structure index data, and the spatial basic data includes at least the administrative boundary data of the research unit, the area data of the unit, the geometric center coordinate data of the unit, and the spatial adjacency relationship data between the units;

[0031] The indicator construction module is used by the computer device to divide the imported indicators into two major attribute dimensions: the population size dimension, which represents the ability of the total population to gather, and the population structure dimension, which represents the changes in the internal composition of the population. Each indicator is labeled with an attribute type, which is divided into positive indicators and negative indicators. Positive indicators are defined as those with larger values, corresponding to a stronger degree of population contraction, while negative indicators are defined as those with smaller values, corresponding to a stronger degree of population contraction.

[0032] Standardization processing module: The computer device selects matching standardization operation rules based on the attribute type of each indicator to perform dimensionless and directional unification processing on all indicators, so that all standardized indicators uniformly follow the principle that the larger the calculated value of the indicator, the stronger the population shrinkage of the corresponding research unit.

[0033] Weight calculation module: The computer device uses the standardized full dataset of indicators as the basis for calculation, and adopts the entropy weight algorithm to automatically solve for the objective weight corresponding to each indicator based on the degree of data dispersion difference between the indicators and the samples.

[0034] Index calculation module: The computer device collects corresponding indicators based on the population size dimension and population structure dimension divided by S2, combines the indicator weights obtained by S4 and the standardized indicator values ​​generated by S3, and performs independent calculations on each dimension to obtain the population size shrinkage index and population structure shrinkage index corresponding to each research unit.

[0035] Coupled Diagnosis Module: Used by the computer device to retrieve pre-configured population size shrinkage threshold and population structure shrinkage threshold, and combine the numerical combination relationship of population size shrinkage index and population structure shrinkage index to classify each research unit into four types of coupled shrinkage: compound shrinkage, unidirectional size shrinkage, unidirectional structure shrinkage, and non-obvious shrinkage.

[0036] The level identification module is used by the computer device to perform weighted fusion calculations on the population size shrinkage index and the population structure shrinkage index to obtain a comprehensive population shrinkage index; based on preset multi-level thresholds, it divides each research unit into corresponding population shrinkage intensity levels according to the value range of the comprehensive population shrinkage index.

[0037] The time-series trajectory recognition module is used by the computer device to retrieve the comprehensive population shrinkage index and the matching shrinkage intensity level corresponding to multiple consecutive statistical time series, map the shrinkage level to an ordered code to construct a single research unit multi-time series coding sequence, and calculate the shrinkage duration parameter, cross-time series level change parameter, and comprehensive index time series change slope parameter based on the coding sequence. Based on the combination logic of the three types of parameters, different types of population shrinkage time trajectories are divided.

[0038] Spatial feature recognition module: used to import the spatial basic data imported by S1 into the computer device, and combine the shrinkage state identifier variables of each research unit under each time series to quantify and calculate the spatial proportion parameter of the shrinkage unit, the spatial contiguous clustering parameter, the whole region shrinkage center of gravity coordinate parameter, and the center of gravity cross-time series movement parameter; at the same time, according to the shrinkage state change relationship between two adjacent time series, the spatial shrinkage trajectory type corresponding to each research unit is classified.

[0039] The results output module is used by the computer device to summarize the coupling classification results, various contraction indices, contraction level data, time-series trajectory parameters, and spatial feature parameters, and to store and output the recognition results through at least one format among data tables, spatial vector layers, thematic visualization maps, and statistical documents.

[0040] The present invention also provides an electronic device, including a memory and a processor, the memory being used to store a computer program, and the processor being used to implement the method described in any of the preceding claims when the computer program is executed.

[0041] The present invention also provides a readable storage medium storing a computer program that, when executed by a processor, implements the method described in any of the preceding claims.

[0042] Compared with the prior art, the technical solution disclosed in this invention has the following beneficial effects:

[0043] 1. Based on the technical features of S2 dual-dimensional indicator division and S5 multi-dimensional index calculation, this invention solves the shortcomings of existing technologies that rely solely on total population and cannot identify structural hidden contraction. This invention splits the indicators into two dimensions: population size and population structure, and calculates the size contraction index and structural contraction index independently for each. In addition to identifying the explicit size contraction caused by the decline in total population and population density, it can also identify structural contraction caused by a stable total population but rising aging and declining local population retention capacity. This breaks through the limitations of the traditional single total quantity assessment dimension and improves the coverage of population contraction identification.

[0044] 2. Based on the characteristics of S6 scale-structure coupling diagnostic technology, it solves the shortcomings of existing technologies that cannot distinguish between different types of contraction caused by different factors. Through the dual threshold coupling judgment rule of scale index and structure index, it automatically distinguishes four types of regions: compound contraction, scale contraction, structural contraction, and non-obvious contraction, clarifies the source of contraction, makes up for the shortcomings of traditional schemes that cannot finely classify the causes of contraction, and provides a classification basis for the formulation of differentiated regional policies.

[0045] 3. Based on the S3 index's unidirectional standardization technology, the shortcomings of existing technical indicators, such as mixed positive and negative attributes and systematic bias in index calculation, are addressed by standardizing the positive and negative indicators, unifying the change logic of all indicators, realizing that the larger the standardized value, the stronger the contraction, eliminating the weighted calculation error caused by the inconsistent change direction of different indicators, and ensuring the accuracy of various contraction index calculations.

[0046] 4. Based on the objective weighting technology of S4 entropy weight, it solves the defects of existing technologies such as manual subjective weighting, poor stability of recognition results and low repeatability. It automatically calculates the index weight based on the dispersion of index data, abandons human experience-based value assignment, and the weight generation relies on the objective laws of the original data. Multiple calculations from the same data source can obtain consistent results, effectively reducing the randomness of results caused by human intervention and improving the objectivity and reusability of recognition conclusions.

[0047] 5. Based on the characteristics of S8 multi-temporal trajectory recognition technology, this technology overcomes the shortcomings of existing technologies that only provide static single-period analysis and cannot depict the temporal evolution of population shrinkage. By constructing a time-series coding sequence of shrinkage level using continuous data over many years, and combining the duration, level change amplitude, and change slope to classify multiple time trajectories, it can quantitatively determine whether regional population shrinkage is new, phased, continuously aggravated, or continuously slowing down, thus upgrading from static cross-sectional identification to dynamic evolution analysis.

[0048] 6. Based on the S9 and combined with spatial adjacency data, the technology of spatial feature recognition is used to solve the defects of existing technologies that lack spatial dimension analysis and cannot quantify the characteristics of shrinkage spatial evolution. It integrates regional spatial adjacency, geographic coordinates, and area data to quantify the shrinkage ratio, spatial contiguous clustering degree, shrinkage center displacement, and spatial state transition type. It can accurately identify spatial patterns such as isolated outbreaks or contiguous expansion of shrinkage and supplement the spatial evolution analysis capabilities that are lacking in traditional solutions.

[0049] 7. Relying on the complete set of technical features of S1~S10 full-process computer automation processing + S10 multi-format result output, it solves the defects of traditional manual calculation, such as large workload and single output format. The entire chain from raw data entry, indicator calculation, type identification to spatiotemporal analysis is automatically executed by computer, saving a lot of manual calculation and processing costs; the results support export in multiple formats such as tables, spatial layers, and thematic maps, adapting to the data use needs of multiple scenarios such as land planning and grassroots governance. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1 A schematic diagram of the population shrinkage identification method based on scale-structure coupling and spatiotemporal features provided in an embodiment of the present invention;

[0052] Figure 2 This is a structural diagram of a regional population shrinkage identification system provided in an embodiment of the present invention. Detailed Implementation

[0053] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0054] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0055] like Figures 1-2As shown, this embodiment of the invention provides a population shrinkage identification method based on scale-structure coupling and spatiotemporal features. The execution subject of this method is a computer device, which can be a server, personal computer, workstation, cloud computing platform or terminal device with data processing capabilities.

[0056] Explanation of English abbreviations: PS stands for Population Shrinkage Index; PS scale Population shrinkage index; PS structure is the population structure shrinkage index; Traj is the time trajectory of population shrinkage; SpatialTraj is the spatial shrinkage trajectory.

[0057] S1 can be summarized as: obtaining regional population data.

[0058] Computer equipment acquires regional population data for a target area over multiple periods. This population data includes population size data and population structure data. Population size data includes, but is not limited to, year-end total population, natural growth rate, and population density; population structure data includes, but is not limited to, urbanization rate, aging rate, and local population retention rate. The spatial data includes regional administrative boundary data, regional area data, regional geometric center point coordinates data, and regional spatial adjacency data. The multiple periods can be consecutive years, census years, or preset statistical periods.

[0059] In one implementation, the target region can be a province, a regional economic unit, a major grain-producing area, an urban cluster, a regional set, or other preset administrative regions; the analysis unit can be a county, a county-level city, a municipal district, or other regional-level administrative units. If multiple periods are compared, the computer equipment organizes the population data for each period according to the same regional unit set.

[0060] S2 can be summarized as: constructing a population size-structural indicator system.

[0061] Computer equipment divides population shrinkage indicators into population size and population structure. Population size is used to characterize the total population base, natural population growth capacity, and degree of spatial population agglomeration in a region; population structure is used to characterize the degree of population aging, urbanization absorption capacity, and local population retention capacity in a region.

[0062] population size Total population at the end of the year Reflecting the basic population size of the region negative indicators The smaller the value, the stronger the contraction. population size Natural growth rate Reflects the relationship between life and death and the natural reproductive capacity of the population. negative indicators The smaller the value, the stronger the contraction. population size population density Reflects the degree of population concentration per unit area negative indicators The smaller the value, the stronger the contraction. population structure urbanization rate Reflecting regional population absorption and changes in urban-rural structure negative indicators The smaller the value, the stronger the contraction. population structure aging rate Reflects the proportion of the population aged 65 and above in the total population Positive indicators The higher the value, the stronger the contraction. population structure Local population retention rate Reflects the ability of the local population to remain in the region negative indicators The smaller the value, the stronger the contraction.

[0063] The aging rate can be expressed as:

[0064] AR i = POP65 i / TP i

[0065] In the formula, AR iPOP65 represents the aging rate of the i-th region unit. i TP represents the number of people aged 65 and above in the i-th regional unit. i This represents the total population of the i-th regional unit.

[0066] The local population retention rate can be expressed as:

[0067] LRR i = LocalRes i / RP i

[0068] In the formula, LRR i LocalRes represents the local population retention rate of the i-th regional unit. i RP represents the number of local registered permanent residents or the local population determined according to a preset metric in the i-th regional unit. i This represents the resident population of the i-th regional unit. If the local registered resident population is unavailable in the original data, it can be replaced by the matching relationship between the registered population and the resident population or by local population indicators available in statistical data.

[0069] S3 can be summarized as: performing consistency and standardization of indicator directions.

[0070] Computer equipment performs directional consistency processing on various population shrinkage indicators, ensuring that the standardized indicator values ​​all satisfy the principle that "the larger the value, the stronger the population shrinkage." Let X... ij X' represents the original value of the i-th regional unit on the j-th index. ij This represents the standardized index value.

[0071] For positive indicators where larger values ​​signify a stronger degree of population contraction, the following standardized formula is used:

[0072] For negative indicators where smaller values ​​represent a stronger degree of population contraction, the following standardized formula is used:

[0073]

[0074] In the formula, max(X) j ) and min(X j ) represent the maximum and minimum values ​​of the j-th indicator within the preset sample range, respectively. For single-period identification, the preset sample range is all regional units within that period; for multi-period comparison, the preset sample range can be a unified sample range consisting of all periods to be compared and all regional units. After the above processing, all indicators are converted to the same direction, i.e., X'. ijThe larger the value, the stronger the corresponding regional unit's performance in terms of population shrinkage. After processing with formula (1) or formula (2), X' ij The value of is between 0 and 1, and the larger the value, the stronger the population contraction. When max(X) j )=min(X j If the value is zero, it indicates that the indicator does not differ in the sample. The computer device can set the standardized value of the indicator to 0, or remove the indicator from the weight calculation.

[0075] S4 can be summarized as: using the entropy weight method to determine the index weights.

[0076] The computer equipment uses the entropy weighting method to determine the weights of each indicator based on standardized indicator values. The entropy weighting method can determine the weights according to the degree of difference between indicators in different regional units, reducing the bias caused by completely subjective weighting.

[0077] First, calculate the weight of the i-th regional unit on the j-th indicator:

[0078]

[0079] In the formula, p ij This represents the weight of the i-th regional unit in the j-th index, where ε is a very small positive number used to avoid X' ij Logarithmic calculations are invalid when the value is 0.

[0080] Then calculate the information entropy of the j-th indicator:

[0081]

[0082] In the formula, e j Let represent the information entropy of the j-th indicator, and n represent the number of regional units. The smaller the information entropy, the more significant the differences between regions for that indicator, and the greater the amount of information it provides.

[0083] Further calculate the difference coefficient of the j-th indicator:

[0084]

[0085] Finally, calculate the weight of the j-th indicator:

[0086]

[0087] In the formula, w j d represents the weight of the j-th indicator. j This represents the difference coefficient of the j-th indicator.

[0088] S5 can be summarized as: calculating the population size contraction index and the population structure contraction index separately.

[0089] To reflect the coupled diagnostic relationship between population size and population structure, the computer equipment does not directly combine all indicators into a single composite index, but instead calculates the population size contraction index and the population structure contraction index separately.

[0090] Let the set of indicators for the population size dimension be:

[0091] S = {Total population at year-end, natural growth rate, population density}

[0092] Let the set of population structure dimension indicators be:

[0093] R = {Urbanization rate, Aging rate, Local population retention rate}

[0094] The population shrinkage index is expressed as:

[0095]

[0096] In the formula, PS scale i S represents the population shrinkage index of the i-th regional unit; S represents the set of population size dimension indicators, including year-end total population, natural growth rate, and population density; w S j X' represents the weight of the j-th indicator in the population size dimension; ij This represents the standardized value of the i-th regional unit on the j-th index. PS scale i The larger the value, the greater the degree of population shrinkage in that region.

[0097] The population structure shrinkage index is expressed as:

[0098]

[0099] In the formula, PS structure i R represents the population structure shrinkage index of the i-th regional unit; R represents the set of population structure dimension indicators, including urbanization rate, aging rate, and local population retention rate; w R k X' represents the weight of the k-th indicator in the demographic dimension; ik This represents the standardized value of the i-th regional unit on the k-th index. PS structure i The larger the value, the stronger the degree of population contraction in that region.

[0100] In one implementation, the weights within the population size dimension and the population structure dimension are calculated using the entropy weight method. In another implementation, the weights of all indicators can be calculated using the entropy weight method, and then the population size shrinkage index and the population structure shrinkage index can be obtained by summing them up.

[0101] S6 can be summarized as: conducting population size-structure coupling diagnostics.

[0102] Computer equipment performs coupled diagnosis of regional population shrinkage based on the combined relationship between the population size shrinkage index and the population structure shrinkage index. Let T... s T represents the threshold for population shrinkage. r If the threshold for population structure contraction is given, then the diagnostic rule for population size-structure coupling is:

[0103] Type i = {complex contraction type, PS} scale i ≥T s And PS structure i ≥T r ;

[0104] Shrinking size, PS scale i ≥T s And PS structure i < T r ;

[0105] Structural contraction type, PS scale i < T s And PS structure i ≥T r ;

[0106] Non-obvious shrinkage type, PS scale i < T s And PS structure i < T r .}

[0107] In the formula, Type i This indicates the population contraction coupled diagnosis type for the i-th regional unit. A compound contraction type indicates that both population size and population structure contractions are significant simultaneously; a size contraction type indicates a more pronounced decline in total population, population density, or natural growth capacity; a structural contraction type indicates that while the total population may not have declined significantly, structural problems such as aging and declining local population retention capacity are prominent; and a non-significant contraction type indicates that neither the population size nor population structure dimensions have reached the preset contraction threshold.

[0108] T s and T rThe value of T can be determined based on the sample distribution of the study area, quantile method, natural breakpoint method, mean method, or preset empirical threshold. In a preferred embodiment, T s and T r Take the median, mean, or 60th percentile of the corresponding index in all regional units, respectively.

[0109] S7 can be summarized as: calculating the comprehensive population shrinkage index and identifying the level of population shrinkage.

[0110] Based on the completed population size-structure coupling diagnosis, the computer equipment further calculates a comprehensive population shrinkage index, which is used to uniformly rank and classify the degree of regional population shrinkage. The comprehensive population shrinkage index is expressed as:

[0111] PS i = α PS scale i + β PS structure i

[0112] α + β = 1

[0113] In the formula, PS i Let α represent the comprehensive population shrinkage index of the i-th regional unit; α represents the dimensional weight of the population size shrinkage index; and β represents the dimensional weight of the population structure shrinkage index. In one implementation, α and β can be set to 0.5 and 0.5 respectively to reflect the equal importance of the population size dimension and the population structure dimension; in another implementation, α and β can be determined using the entropy weighting method, expert weighting method, analytic hierarchy process, or preset weighting method. PS i The larger the value, the stronger the degree of population shrinkage in the region.

[0114] Computer equipment based on the comprehensive population shrinkage index PS i Based on preset threshold levels, the degree of regional population shrinkage is classified into different levels. The formula for population shrinkage level identification is:

[0115] Level i = {non-shrinking, PS i < L0;

[0116] Mild contraction, L0 ≤ PS i < L1;

[0117] Moderate contraction, L1 ≤ PS i < L2;

[0118] Severe contraction, L2 ≤ PS i < L3;

[0119] Extremely severe shrinkage, PS i≥ L3.}

[0120] In the formula, Level i L1 represents the population shrinkage level of the i-th regional unit; L0, L1, L2, and L3 represent the threshold values ​​for level classification. These threshold values ​​can be determined based on the population shrinkage index distribution of the study area, preset empirical thresholds, quantile methods, or natural breakpoint methods. In one implementation, L0, L1, L2, and L3 can be set to 0, 0.06, 0.12, and 0.18, respectively.

[0121] S8 can be summarized as: Identifying population shrinkage trajectories.

[0122] After obtaining the composite population shrinkage index for multiple adjacent periods, the computer equipment identifies the population shrinkage trajectory based on the relationship between the population shrinkage status and intensity changes of the same regional unit in the two consecutive periods. This step is used to identify whether the population shrinkage has a continuous, phased, recent occurrence, or slowing trend.

[0123] Suppose the target region contains q periods to be identified, and the time series is represented as T={t1,t2,...,t...} q The i-th region unit at time t r The composite population shrinkage index for the period is expressed as PS. i,tr The corresponding population shrinkage level is represented as Level. i,tr The computer equipment converts the population shrinkage levels into ordered level codes:

[0124] G i,tr = {0, no contraction; 1, mild contraction; 2, moderate contraction; 3, severe contraction; 4, extreme contraction.}

[0125] In the formula, G i,tr This indicates that the i-th region unit is in the t-th region. r The population contraction level is coded for the period. The higher the code value, the stronger the population contraction.

[0126] The population contraction trajectory vector is represented as:

[0127] Traj i = (G i,t1 G i,t2 , ..., G i,tq )

[0128] In the formula, Traj i This represents the population contraction trajectory of the i-th regional unit over multiple periods. This trajectory can be represented as a hierarchical sequence, such as "0→1→2" indicating a gradual evolution from non-contraction to moderate contraction, and "2→2→3" indicating continuous contraction with increasing severity.

[0129] To determine whether regional population shrinkage persists over multiple periods, computer equipment constructs shrinkage state variables:

[0130] H i,tr = I(G i,tr ≥ 1)

[0131] In the formula, H i,tr This indicates that the i-th region unit is in the t-th region. r Whether the period is in a contraction state; I(·) is an indicator function, which takes the value 1 if the condition is true, and 0 otherwise.

[0132] The duration of population contraction is expressed as:

[0133]

[0134] In the formula, D i D represents the period in which the i-th regional unit is identified as experiencing population contraction within the q-th period. i The larger the value, the stronger the persistence of population decline in the region.

[0135] The magnitude of the population contraction level change is expressed as follows:

[0136] ΔG i = G i,tq - G i,t1

[0137] In the formula, ΔG i ΔG represents the change in the level of population contraction between the latest period and the initial period for the i-th regional unit. i >0 indicates a more severe degree of population contraction, ΔG i =0 indicates that the population contraction level is relatively stable, ΔG i <0 indicates a slowdown in the rate of population contraction.

[0138] Changes in rank between adjacent periods:

[0139] To further determine whether the population contraction trajectory is continuously worsening or continuously slowing down, the grade change between adjacent periods can be calculated:

[0140] ΔG i,r = G i,tr - G i,tr-1

[0141] In the formula, ΔG i,r ΔG represents the change in the level of population contraction in the i-th regional unit between two adjacent periods. i,r >0 indicates that the degree of population contraction worsens in adjacent periods, ΔG i,r =0 indicates that the level of population contraction is relatively stable in adjacent periods, ΔG i,r<0 indicates that the rate of population contraction slows down in adjacent periods.

[0142] In one implementation, the computer device can also calculate the slope of the population shrinkage trend based on the comprehensive population shrinkage index:

[0143]

[0144] In the formula, Trend i Let represent the slope of the trend of the comprehensive population shrinkage index of the i-th regional unit over time, and t represent the average value for each period. i This represents the average of the composite population shrinkage index over multiple periods for the i-th regional unit. i >0 indicates an overall increase in the degree of population contraction. (Trend) i <0 indicates that the overall degree of population contraction has weakened.

[0145] Based on the duration of population contraction, the magnitude of grade changes, and the slope of the trend, computer equipment identifies the types of population contraction trajectories.

[0146] TrajType i = {non-contracting trajectory, D} i = 0; Recent contraction trajectory, H i,tq = 1 and D i < q; Phased contraction trajectory, 0 < D i < q and H i,tq = 0; The contraction trajectory is continuously aggravated, D i = q and ΔG i > 0; Continuously stable contraction trajectory, D i = q and ΔG i = 0; Continuously slowing down the contraction trajectory, D i = q and ΔG i < 0.}

[0147] In the formula, TrajType i This represents the population contraction trajectory type of the i-th regional unit. Using this trajectory identification rule, computer equipment can further reveal the evolution of regional population contraction based on the identification of single-period population contraction levels. The above trajectory types can also be combined into continuous contraction, phased contraction, recent contraction, and non-contraction types according to research needs.

[0148] Furthermore, let the i-th region unit be at the t-th... r The population size-structural coupling diagnostic type for the period is CType. (i,t_r ) Then the population size-structure coupling diagnostic trajectory is represented as:

[0149]

[0150] In the formula, CTraj i This represents the sequence of population-size-structure coupling diagnostic types for the i-th regional unit across multiple periods. (via Traj) i With CTraj i The combined output of the computer equipment enables it to simultaneously identify the evolutionary trajectory of population shrinkage intensity and the changing process of the dominant mechanism of population shrinkage.

[0151] S9 can be summarized as: identifying the spatial characteristics and spatial trajectory of population contraction.

[0152] After obtaining the regional population shrinkage level, comprehensive population shrinkage index, and population shrinkage time trajectory, the computer equipment further combines the regional administrative boundaries, regional area, regional geometric center point, and regional spatial adjacency relationships to identify the spatial characteristics and spatial shrinkage trajectory of population shrinkage in the target region. This step is used to determine whether the population shrinkage spatially manifests as clustering, contiguous expansion, isolated occurrence, continuous shrinkage, or spatial slowdown.

[0153] Suppose the target region has n regional units, the spatial adjacency matrix of the regions is represented as:

[0154]

[0155] Where, q ij This represents the spatial adjacency relationship between the i-th region unit and the j-th region unit. q ij The rules for determining the value are as follows:

[0156] Where, when region unit i and region unit j are spatially adjacent, q ij =1; when the two are not adjacent, q ij =0; and q ij =0.

[0157] The spatial adjacency can be adjacent along a common edge, adjacent along a common point, or adjacent within a preset distance threshold.

[0158] According to the i-th region unit at time t r Population contraction level code G i,tr Construct spatial state variables for population shrinkage:

[0159]

[0160] In the formula, H i,tr This indicates that the i-th region unit is in the t-th region. r Whether the period is in a state of population contraction; I(·) is an indicator function, which takes the value 1 if the condition is true, and 0 otherwise. Hi,tr =1 indicates that the region is experiencing population decline, H i,tr =0 indicates that the population is not in a state of shrinkage.

[0161] t r The number of areas experiencing population decline, the proportion of areas experiencing population decline, and the proportion of areas experiencing population decline are expressed as follows:

[0162]

[0163]

[0164]

[0165] In the formula, N shrink tr Indicates the t-th r The number of regions experiencing population decline during the period; R shrink tr Indicates the proportion of regions experiencing population decline out of the total population; AR shrink tr This indicates the proportion of the target area to the region experiencing population shrinkage; A i This represents the area of ​​the i-th region unit.

[0166] t r The average population contraction intensity of the contraction zone is expressed as:

[0167]

[0168] In the formula, N shrink tr bar represents the t-th r Average population shrinkage index in shrinking regions; PS i,tr This indicates that the i-th region unit is in the t-th region. r The overall population shrinkage index for the period. If there are no areas experiencing population shrinkage during that period, the computer will set this value to 0 or a blank value.

[0169] To determine whether population shrinkage areas are spatially contiguous, computer equipment calculates the shrinkage adjacency ratio based on a spatial adjacency matrix:

[0170]

[0171] In the formula, CA tr Indicates the t-th r The degree of spatial clustering during the period of population contraction. CA tr The larger the value, the more likely the population shrinking area is to be adjacent to other shrinking areas, and the stronger the spatial contiguousness; CA trThe smaller the value, the more scattered or isolated the population shrinkage areas tend to be.

[0172] Let the coordinates of the geometric center point of the i-th region be (x... i ,y i ), then the t-th r The center of gravity of population contraction during the period is represented as:

[0173]

[0174]

[0175] In the formula, (X c tr Y c tr ) represents the t-th r The coordinates of the centroid of population contraction during a given period. The distance the centroid of population contraction shifts between adjacent periods is expressed as:

[0176]

[0177] In the formula, L (tr-1,tr) This indicates that the center of gravity of population contraction shifted from t r-1 Period moved to t r The distance over a period of time is used to characterize whether the spatial center of gravity of population shrinkage has shifted.

[0178] Computer equipment identifies the spatial shrinkage trajectory of a region based on changes in the spatial state of population shrinkage within the same regional unit in adjacent periods. The i-th regional unit in two adjacent periods t... r-1 To t r The spatial state transition is represented as:

[0179]

[0180] Based on the state transition results, the spatial contraction trajectory of the region is divided into:

[0181] The spatial contraction trajectory includes: a continuous contraction type, i.e., H... i,tr-1 =1 and H i,tr =1; New contraction type occurs, i.e., H i,tr-1 =0 and H i,tr =1; contraction-relieving type, i.e., H i,tr-1 =1 and H i,tr =0; persistent non-contractile type, i.e., H i,tr-1 =0 and H i,tr =0.

[0182] Furthermore, for newly occurring contraction regions, if they are adjacent to existing contraction regions from the previous period, they are identified as spatially expanding contractions; if they are not adjacent to existing contraction regions from the previous period, they are identified as isolated contractions.

[0183]

[0184]

[0185] In the formula, NE i,tr =1 indicates that the i-th region unit is in the t-th region. r The period belongs to the spatially extended type of new contraction; NI i,tr =1 indicates that the i-th region unit is in the t-th region. r This period belongs to the isolated, newly emerging type of population contraction. Based on the above rules, computer equipment can further reveal the spatial scope, spatial clustering, spatial center of gravity shift, and spatial state transition processes of population contraction, building upon time trajectory recognition.

[0186] S10 can be summarized as: Output recognition results

[0187] The computer equipment outputs regional population shrinkage identification results. The output results include, but are not limited to: a population size shrinkage index table, a population structure shrinkage index table, a comprehensive population shrinkage index table, a population size-structure coupling diagnostic type table, a population shrinkage level table, a population shrinkage time trajectory table, a population shrinkage spatial characteristic statistics table, a spatial shrinkage trajectory type table, a population shrinkage level distribution map, a population shrinkage time trajectory zoning map, a spatial contiguous clustering map, a shrinkage center of gravity movement map, a spatial shrinkage trajectory map, and a population shrinkage statistical report.

[0188] The output results can be saved and displayed in the form of spreadsheets, database tables, vector spatial data, raster layers, thematic maps, visualization interfaces, or report files.

[0189] Following the same approach, this invention also provides a regional population shrinkage identification system based on population size-structure coupling diagnosis. This system can be deployed on servers, personal computers, workstations, cloud computing platforms, or terminal devices. The system includes the following modules:

[0190] Data acquisition module Output raw regional population data to the indicator construction module Obtain data such as year-end total population, natural growth rate, population density, urbanization rate, aging rate, and local population retention rate. Indicator building module Receive data from the data acquisition module and output indicators for population size and population structure dimensions. The indicators are divided into population size and population structure dimensions, and positive or negative attributes are marked. Standardized processing module Receive data from the indicator construction module and output standardized indicator values ​​with consistent direction. The indicators are processed using positive or negative standardized formulas to unify them so that the larger the value, the stronger the population contraction. Weight Calculation Module Receive standardized indicator values ​​and output indicator weights. The entropy weight method is used to calculate the index proportion, information entropy, difference coefficient and index weight. Index Calculation Module <![CDATA[Receive standardized values and weights, output PS scale , PS structure and PS]]> Calculate the population size shrinkage index, population structure shrinkage index, and comprehensive population shrinkage index separately. Coupled diagnostic module <![CDATA[Receive PS scale , PS structure , output coupling diagnosis type]]> Based on two-dimensional threshold rules, composite contraction, scale contraction, structural contraction, and non-obvious contraction types are identified. Level recognition module Receive the comprehensive PS index and output the population shrinkage level. The levels of contraction—non-contraction, mild, moderate, severe, and very severe—are identified based on threshold rules. Trajectory recognition module Receives multiple periods of PS index, grade, and coupled diagnostic type, and outputs population contraction trajectory. Identify persistently worsening contractions, recent contractions, phased contractions, persistently slowing contractions, and non-contraction trajectories based on rank sequence, duration, and trend slope. Spatial Feature Recognition Module Receives region boundaries, spatial adjacency matrix, population shrinkage level, comprehensive population shrinkage index, and temporal trajectory results; outputs spatial shrinkage characteristics and spatial shrinkage trajectory type. Calculate the proportion of population shrinkage areas, the proportion of shrinkage area, the average shrinkage intensity, the degree of spatial clustering, and the distance of shrinkage center of gravity shift, and identify the continuous shrinkage type, the newly occurring shrinkage type, the shrinkage mitigation type, the continuous non-shrinkage type, the spatial expansion type, and the isolated occurrence type. Result Output Module Receive results by type and level, and output tables, layers, and reports. Output population shrinkage index table, coupled diagnostic type map, grade distribution map and statistical report.

[0191] The modules described above can be connected via data bus, program interface, database interface, or function call. The data acquisition module provides raw population data and spatial foundation data; the indicator construction module and standardization processing module form an indicator matrix with a unified direction; the weight calculation module generates indicator weights; the index calculation module generates various population shrinkage indices; the coupled diagnosis module and level identification module form single-period identification results; the trajectory identification module forms a regional population shrinkage time trajectory based on multi-period identification results; the spatial feature identification module identifies spatial shrinkage characteristics and spatial state transition types based on regional boundaries, spatial adjacency relationships, and multi-period shrinkage states; and the result output module is responsible for result storage, visualization, and report generation.

[0192] The present invention can also be embodied as an electronic device, including a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein the processor executes the computer program to implement the above-mentioned regional population shrinkage identification method.

[0193] Embodiments of the present invention may also be embodied as a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0194] The basic principles of the present invention have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in the present invention are merely examples and not limitations, and should not be considered as essential features of each embodiment of the present invention. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the present invention to the necessity of employing the aforementioned specific details.

[0195] The block diagrams of devices, apparatuses, devices, and systems involved in this invention are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0196] It should also be noted that in the apparatus, device, and method of the present invention, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions of the present invention.

[0197] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the invention. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the invention. Therefore, the invention is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.

[0198] It should be understood that the qualifying terms "first", "second", "third", "fourth", "fifth" and "sixth" used in the description of the embodiments of the present invention are only used to more clearly illustrate the technical solutions and are not intended to limit the scope of protection of the present invention.

[0199] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of the invention to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein.

Claims

1. A population shrinkage identification method based on scale-structure coupling and spatiotemporal features, characterized in that, Performed by a computer device, including the following steps: S1. Raw data input steps: The computer device imports multi-time series population raw data and spatial basic data of the target research unit; the population raw data is divided into population size index data and population structure index data, and the spatial basic data includes at least the administrative boundary data of the research unit, the unit area data, the geometric center coordinate data of the unit, and the spatial adjacency relationship data between units; S2. Indicator System Construction Steps: The computer equipment divides the imported indicators into two major attribute dimensions: the population size dimension, which is used to characterize the population's ability to agglomerate, and the population structure dimension, which is used to characterize changes in the internal composition of the population. Each indicator is then labeled with an attribute type, which is divided into positive and negative indicators. Positive indicators are defined as those with larger values ​​corresponding to a stronger degree of population contraction, while negative indicators are defined as those with smaller values ​​corresponding to a stronger degree of population contraction. S3. Standardization Processing Steps for Indicators in the Same Direction: The computer equipment selects matching standardization operation rules based on the attribute type of each indicator label to perform dimensionless and direction-unified processing on all indicators, so that all standardized indicators uniformly follow the principle that the larger the calculated value of the indicator, the stronger the population shrinkage of the corresponding research unit. S4. Automatic calculation step of indicator weights: The computer equipment uses the standardized full indicator dataset as the basis for calculation, and adopts the entropy weight algorithm to automatically calculate the objective weight of each indicator based on the degree of data dispersion difference between the indicators and the samples. S5. Steps for calculating the dimensional shrinkage index: The computer equipment collects corresponding indicators based on the population size dimension and population structure dimension divided in S2, and combines the indicator weights obtained in S4 with the standardized indicator values ​​generated in S3 to perform independent calculations on each dimension, thereby obtaining the population size shrinkage index and population structure shrinkage index corresponding to each research unit. S6. Diagnostic steps for scale-structure coupling type: The computer equipment retrieves the pre-configured population scale contraction threshold and population structure contraction threshold, and combines the numerical combination relationship of the population scale contraction index and the population structure contraction index to classify each research unit into four types of coupled contraction: compound contraction, scale unidirectional contraction, structure unidirectional contraction, and non-obvious contraction. S7. Calculation steps for comprehensive shrinkage index and shrinkage level: The computer equipment performs weighted fusion calculation on the population size shrinkage index and the population structure shrinkage index to obtain the comprehensive population shrinkage index; based on the preset multi-level threshold, according to the value range of the comprehensive population shrinkage index, the corresponding population shrinkage intensity level is divided for each research unit; S8. Temporal contraction trajectory identification steps: The computer device retrieves the comprehensive population contraction index and the matching contraction intensity level corresponding to multiple consecutive statistical time series, maps the contraction level to ordered codes to construct a single research unit multi-time series coding sequence, calculates the contraction duration parameter, cross-time series level change parameter, and comprehensive index temporal change slope parameter based on the coding sequence, and classifies different types of population contraction time trajectories based on the combination logic of the three types of parameters. S9. Spatial contraction characteristics and spatial trajectory identification steps: The computer device introduces the spatial basic data imported in S1, and combines it with the contraction status identifier variables of each research unit under each time series to quantitatively calculate the spatial proportion parameter of the contraction unit, the spatial clustering degree parameter, the centroid coordinate parameter of the whole region contraction, and the centroid cross-time series movement parameter; at the same time, according to the contraction status change relationship between two adjacent time series, the spatial contraction trajectory type corresponding to each research unit is divided. S10, Result Multi-format Output Step: The computer device summarizes and couples the classification results, various contraction indices, contraction level data, time-series trajectory parameters, and spatial feature parameters, and completes the storage and output of the recognition results through at least one format among data tables, spatial vector layers, thematic visualization maps, and statistical documents.

2. The method according to claim 1, characterized in that: In S1, the population size indicators should include at least the total population at the end of the year, the natural population growth rate, and the population density; the population structure indicators should include at least the urbanization rate, the aging rate, and the local population retention rate; among them, the aging rate is the ratio of the total population aged 65 and above in the unit to the total population of the unit, and the local population retention rate is the ratio of the local resident population to the unit's resident population.

3. The method according to claim 1, characterized in that: In S3, the standardization process uses range normalization, and after processing, the value range of all indicators is uniformly constrained to a fixed range. If the value of a single indicator does not fluctuate in the whole sample, the computer equipment will set all standardized values ​​of the indicator to the preset value.

4. The method according to claim 1, characterized in that: The coupling classification judgment rule in S6 is as follows: if both the population size shrinkage index and the population structure shrinkage index exceed the corresponding threshold, it is a compound shrinkage type; if only the population size shrinkage index exceeds the limit, it is a unidirectional shrinkage type; if only the population structure shrinkage index exceeds the limit, it is a unidirectional shrinkage type; if neither index reaches the corresponding threshold, it is a non-obvious shrinkage type. The size shrinkage threshold and the structure shrinkage threshold are determined by any algorithm of the sample quantile method, the mean method, or the natural breakpoint method.

5. The method according to claim 1, characterized in that: The comprehensive population shrinkage index in S7 is obtained by multiplying the size shrinkage index and the structural shrinkage index by their respective dimension weights and then summing them. The sum of the two dimension weights is fixed at 1. The dimension weights are determined by equal assignment or objective weighting. The shrinkage intensity level is divided into five levels: no shrinkage, mild shrinkage, moderate shrinkage, severe shrinkage, and extremely severe shrinkage.

6. The method according to claim 1, characterized in that: The population contraction time trajectory types in S8 include non-contraction trajectory, recent contraction trajectory, phased contraction trajectory, continuously aggravated contraction trajectory, continuously stable contraction trajectory, and continuously slowing contraction trajectory.

7. The method according to claim 1, characterized in that: The spatial contraction trajectory in S9 includes continuous contraction type, newly occurring contraction type, contraction relief type, and continuous non-contraction type; the newly occurring contraction type is further divided into spatial expansion type contraction and isolated sudden type contraction; the spatial adjacency determination of the research unit includes two determination methods: shared edge adjacency and pre-set distance threshold adjacency.

8. A population shrinkage identification system based on scale-structure coupling and spatiotemporal features, characterized in that, include: Data acquisition module: used to import multi-time series population raw data and spatial basic data of the target research unit into the computer device; the population raw data is divided into population size index data and population structure index data, and the spatial basic data includes at least the administrative boundary data of the research unit, the area data of the unit, the geometric center coordinate data of the unit, and the spatial adjacency relationship data between the units; The indicator construction module is used by the computer device to divide the imported indicators into two major attribute dimensions: the population size dimension, which represents the ability of the total population to gather, and the population structure dimension, which represents the changes in the internal composition of the population. Each indicator is labeled with an attribute type, which is divided into positive indicators and negative indicators. Positive indicators are defined as those with larger values, corresponding to a stronger degree of population contraction, while negative indicators are defined as those with smaller values, corresponding to a stronger degree of population contraction. Standardization processing module: The computer device selects matching standardization operation rules based on the attribute type of each indicator to perform dimensionless and directional unification processing on all indicators, so that all standardized indicators uniformly follow the principle that the larger the calculated value of the indicator, the stronger the population shrinkage of the corresponding research unit. Weight calculation module: The computer device uses the standardized full dataset of indicators as the basis for calculation, and adopts the entropy weight algorithm to automatically solve for the objective weight corresponding to each indicator based on the degree of data dispersion difference between the indicators and the samples. Index calculation module: The computer device collects corresponding indicators based on the population size dimension and population structure dimension divided by S2, combines the indicator weights obtained by S4 and the standardized indicator values ​​generated by S3, and performs independent calculations on each dimension to obtain the population size shrinkage index and population structure shrinkage index corresponding to each research unit. Coupled Diagnosis Module: Used by the computer device to retrieve pre-configured population size shrinkage threshold and population structure shrinkage threshold, and combine the numerical combination relationship of population size shrinkage index and population structure shrinkage index to classify each research unit into four types of coupled shrinkage: compound shrinkage, unidirectional size shrinkage, unidirectional structure shrinkage, and non-obvious shrinkage. The level identification module is used by the computer device to perform weighted fusion calculations on the population size shrinkage index and the population structure shrinkage index to obtain a comprehensive population shrinkage index; based on preset multi-level thresholds, it divides each research unit into corresponding population shrinkage intensity levels according to the value range of the comprehensive population shrinkage index. The time-series trajectory recognition module is used by the computer device to retrieve the comprehensive population shrinkage index and the matching shrinkage intensity level corresponding to multiple consecutive statistical time series, map the shrinkage level to an ordered code to construct a single research unit multi-time series coding sequence, and calculate the shrinkage duration parameter, cross-time series level change parameter, and comprehensive index time series change slope parameter based on the coding sequence. Based on the combination logic of the three types of parameters, different types of population shrinkage time trajectories are divided. Spatial feature recognition module: used to import the spatial basic data imported by S1 into the computer device, and combine the shrinkage status identifier variables of each research unit under each time series to quantitatively calculate the spatial proportion parameter of the shrinkage unit, the spatial contiguous aggregation parameter, the centroid coordinate parameter of the shrinkage of the whole region, and the centroid cross-time series movement parameter. Simultaneously, based on the relationship between the contraction state changes between two adjacent time series, the spatial contraction trajectory types corresponding to each research unit are classified; The results output module is used by the computer device to summarize the coupling classification results, various contraction indices, contraction level data, time-series trajectory parameters, and spatial feature parameters, and to store and output the recognition results through at least one format among data tables, spatial vector layers, thematic visualization maps, and statistical documents.

9. An electronic device, characterized in that: The system includes a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to execute the computer program to implement the method according to any one of claims 1 to 7.

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

Images