Agricultural space function partition planning system

Abstract

The invention relates to the technical field of data processing, in particular to an agricultural space function zoning planning system which comprises a plot division module, a function association module, a matrix arrangement module, a function suitability acquisition module, a function zoning module and an agricultural space planning module. Mapping the agricultural resource data to generate an agricultural functional plot; performing weighted fusion on the internal constraint vector and the external demand vector of the land parcel to obtain a function correlation degree, constructing a dynamic coupling relation matrix, and calculating suitability indexes of various preset agricultural functions according to the function correlation degree; the method comprises the following steps of: initializing a partition agent to form an initial agricultural space function partition scheme by taking maximization of overall suitability of a region and meeting of space connectivity as targets, and iterating by taking space compactness, function homogeneity and adjacent unit coordination as optimization targets to finally generate an agricultural space planning map; according to the invention, the zoning planning efficiency of agricultural space functions can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and particularly relates to an agricultural space function zoning planning system. BACKGROUND

[0002] The existing agricultural space function zoning planning technology has obvious short boards in the data integration and processing link, and cannot effectively realize the standardized fusion of multi-source agricultural resource data. The correlation analysis of internal constraints and external demands of the land lacks scientific quantitative methods. Due to insufficient consideration of data dispersion degree and spatial autocorrelation influence, the weight distribution lacks rationality, resulting in large calculation deviation of function correlation degree, and thus the reliability of agricultural function suitability evaluation result is insufficient, and it is difficult to accurately reflect the adaptation potential of different land to various agricultural functions.

[0003] In the zoning planning and optimization process, the existing technology is difficult to meet the dual requirements of regional overall suitability and spatial connectivity, and the generation of the initial zoning scheme lacks intelligence and systematicness. And the optimization target is single, and the spatial compactness, function internal homogeneity and adjacent unit function coordination are not fully considered, resulting in problems such as scattered layout, mixed function, poor adaptation of adjacent regions in the zoning result, which not only reduces the utilization efficiency of agricultural space resources, but also increases the adjustment cost of the planning scheme, and cannot efficiently support the precise and scientific agricultural space function zoning demand. SUMMARY

[0004] To achieve the above-mentioned purpose, the present application provides an agricultural space function zoning planning system, characterized in that the system comprises a land division module, a function correlation module, a matrix arrangement module, a function suitability acquisition module, a function zoning module and an agricultural space planning module, wherein: The land division module is used for grid division of a target region based on a preset dispersion rule, and mapping agricultural resource data of the target region into a grid to obtain agricultural function land of the target region; The function correlation module is used for weighted fusion of the internal constraint vector and the external demand vector of the agricultural function land to obtain the correlation degree of the corresponding function of the target region; The matrix arrangement module is used for arranging the correlation degree to generate a dynamic coupling relationship matrix of the target region; The function suitability acquisition module is used for generating a function suitability index of each preset agricultural function type of the target region based on the dynamic coupling relationship matrix; The functional zoning module is used to initialize the target area into multiple partition agents based on the functional suitability index set, with the goal of maximizing the overall functional suitability of the area and satisfying spatial connectivity constraints, so as to obtain the initial agricultural spatial functional zoning scheme of the target area. The agricultural space planning module is used to iterate the initial agricultural space functional zoning scheme with the optimization objectives of spatial compactness, internal functional homogeneity and functional coordination of adjacent units, so as to obtain the agricultural space planning map of the target area.

[0005] In a preferred embodiment, when the land parcel division module performs grid division of the target area based on preset discrete rules and maps the agricultural resource data of the target area to the grid to obtain the agricultural functional land parcels of the target area, it is specifically used for:

[0006] The target area is divided into spatial grids based on the boundaries of natural geographical units; The land use status data, soil physicochemical property data, meteorological factor time series data, and agricultural production facility distribution data of the target area are compiled into multi-source agricultural resource data of the target area. Spatial registration and standardization preprocessing are performed on the multi-source agricultural resource data to obtain a standardized spatial dataset of the target region; The standardized spatial dataset is mapped to the spatial grid based on spatial location to obtain agricultural functional plots in the target area.

[0007] In a preferred embodiment, when the functional association module performs a weighted fusion of the internal constraint vector and external demand vector of the agricultural functional plot to obtain the association degree of the corresponding function of the target area, it is specifically used for: The internal constraint indicators and external demand indicators are extracted from the unit attribute dataset of the agricultural functional land plots, and respectively constitute the internal constraint indicator subset and external demand indicator subset of the target area; The internal constraint index subset and the external demand index subset are respectively processed to be dimensionless to obtain the internal constraint vector and the external demand vector of the target region. Based on the data dispersion of the internal constraint vector and the external demand vector, the internal constraint weight vector and the external demand weight vector of the target region are generated. Based on the internal constraint weight vector and the external demand weight vector, the internal constraint vector and the external demand vector are linearly fused to obtain the correlation degree of the function corresponding to the target area.

[0008] In a preferred embodiment, when the functional association module generates the internal constraint weight vector and external demand weight vector of the target region based on the data dispersion of the internal constraint vector and the external demand vector, it is specifically used for: Calculate the degree of variation between the internal constraint vector and the external demand vector for each dimension; Based on the degree of variation of each index in the internal constraint vector, the weight coefficients are assigned in reverse to obtain the internal constraint weight vector of the target region. Based on the degree of variation of each indicator in the external demand vector, weight coefficients are positively assigned to the external demand weight vector of the target region.

[0009] In a preferred embodiment, the formula for calculating the degree of variation is as follows: ; In the formula, The value representing the degree of variation. Let be the standard deviation of the observation sequence of the agricultural functional plots in the same dimension. This is the global average of the observation sequence of the agricultural functional plots in the same dimension. To adjust the preset spatial correction coefficient for the effects of spatial autocorrelation, is the global Moran index of the observed sequence.

[0010] In a preferred embodiment, when the matrix arrangement module generates a dynamic coupling relationship matrix for the target region by arranging the correlation degrees, it is specifically used for: The dimensions of the dynamic coupling relationship matrix are determined based on the number of agricultural functional plots and the types of preset agricultural functions. In the aforementioned dimension, a mapping relationship is established between the spatial identifier of agricultural functional land parcels and the matrix row number, and a mapping relationship is also established between the functional type classification code and the matrix column number; Based on the established mapping relationship, the correlation degree between the agricultural functional plots and the preset agricultural functional types is filled into the intersection of the rows and columns of the dynamic coupling relationship matrix.

[0011] In a preferred embodiment, the formula for calculating the functional suitability index is as follows: ; In the formula, For the first The agricultural functional plot for the first Functional suitability index of preset agricultural function types The first in the dynamic coupling matrix The agricultural functional plot for the first The correlation between the pre-set agricultural function types This is a spatial coordination adjustment coefficient used to adjust the impact of adjacent plots. For the first All spatially adjacent plots of land for agricultural functions are related to the first plot. The average correlation between the pre-defined agricultural functional types, For the first The global average value of the preset agricultural function types, To prevent the denominator from being zero and to adjust the layout balance adjustment coefficient to adjust the balance intensity.

[0012] In a preferred embodiment, when the functional zoning module executes the initial division of the target region into multiple partition agents based on the set of functional suitability indices, with the goal of maximizing the overall functional suitability of the region and satisfying spatial connectivity constraints, to obtain the initial agricultural spatial functional zoning scheme for the target region, it is specifically used for: Define the partitioned intelligent agent; Based on the principles of spatial proximity and functional similarity, all agricultural functional plots within the target area are aggregated to initially form multiple candidate partition agents, and an initial dominant agricultural function type identifier is assigned to each candidate partition agent. Establish negotiation rules among the candidate partition agents; Based on the negotiation rules, the ownership of boundary plots of the partitioned smart agents is exchanged among them. When the negotiation process reaches the preset convergence condition, the negotiation is terminated, and the initial agricultural spatial function zoning scheme is generated based on the spatial range of all partition agents and the corresponding dominant agricultural function type identifier at this time.

[0013] In a preferred embodiment, when the agricultural spatial planning module iterates through the initial agricultural spatial functional zoning scheme with the optimization objectives of spatial compactness, functional homogeneity, and functional coordination of adjacent units to obtain the agricultural spatial planning map of the target area, it is specifically used for: Using the initial agricultural spatial functional zoning scheme as the starting point for iteration, a set of candidate schemes for the target area is generated through simulation of crossover and variation. Based on three optimization objectives—spatial compactness, functional homogeneity, and functional coordination of neighboring units—the fitness of each candidate partitioning scheme in the candidate scheme set is evaluated to obtain the fitness evaluation results of the candidate partitioning scheme. Based on the fitness evaluation results, a candidate partitioning scheme with high fitness is selected from the candidate scheme set as the parent scheme; When the preset optimization termination condition is met, the candidate partitioning scheme with the highest fitness at this time is determined as the agricultural spatial planning map of the target area.

[0014] In a preferred embodiment, when the agricultural spatial planning module performs fitness evaluation on each candidate partitioning scheme in the candidate scheme set based on three optimization objectives—spatial compactness, functional homogeneity, and functional coordination of neighboring units—and obtains the fitness evaluation results of the candidate partitioning schemes, it is specifically used for: The overall compactness evaluation value of the candidate partitioning scheme is obtained by summing the compactness indices of the geometry of all independent partitions in the candidate partitioning scheme. The internal homogeneity evaluation value of the candidate partitioning scheme is obtained by summing the consistency ratios between the dominant functional type of all independent partitions and the designated dominant agricultural functional type of each independent partition in the candidate partitioning scheme. Identify all spatially adjacent pairs of agricultural functional plots belonging to different independent zones in the candidate zoning scheme, analyze the proportion of compatible plot pairs in the agricultural functional plot pairs based on the dynamic coupling relationship matrix, and obtain the overall neighboring unit functional coordination evaluation value of the candidate zoning scheme; The overall compactness evaluation value, the internal homogeneity evaluation value, and the overall neighboring unit functional coordination evaluation value are weighted and fused to obtain the fitness evaluation result of the candidate partitioning scheme.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention integrates multi-source agricultural resource data and performs standardized preprocessing. It generates a weight vector by combining the data dispersion and spatial autocorrelation effects, and then weights and fuses internal constraints and external demand vectors. Finally, it calculates the suitability index through a dynamic coupling relationship matrix and scientific formulas, which comprehensively and accurately reflects the adaptation potential of land parcels and agricultural functions, providing reliable data support for zoning planning.

[0016] 2. This invention is multi-objective oriented. The initial zoning takes into account the overall suitability of the region and spatial connectivity. Iterative optimization focuses on spatial compactness, functional homogeneity and neighbor coordination. The optimal solution is selected through agent negotiation and fitness evaluation to avoid problems such as scattered layout and mixed functions. This not only improves the efficiency of agricultural spatial resource utilization, but also significantly shortens the planning cycle, and achieves scientific and precise zoning. Attached Figure Description

[0017] Figure 1 This is a system architecture diagram of an agricultural spatial functional zoning planning system provided in an embodiment of the present invention;

[0018] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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 belong to some, but not all, embodiments of the present invention. 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.

[0020] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “said” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms, and “multiple” generally includes at least two unless the context clearly indicates otherwise.

[0021] Depending on the context, the word "if" or "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0022] Furthermore, the timing of the steps in the following method embodiments is merely an example and not a strict limitation.

[0023] In practice, the server-side equipment deployed in an agricultural spatial functional zoning planning system may consist of one or more devices. This agricultural spatial functional zoning planning system can be implemented as: a business instance, a virtual machine, or hardware devices. For example, it can be implemented as a business instance deployed on one or more devices in a cloud node. Simply put, it can be understood as software deployed on a cloud node, providing an agricultural spatial functional zoning planning system to various user terminals. Alternatively, it can be implemented as a virtual machine deployed on one or more devices in a cloud node, with application software installed to manage various user terminals. Or, it can also be implemented as a server composed of numerous identical or different types of hardware devices, with one or more hardware devices configured to provide an agricultural spatial functional zoning planning system to various user terminals.

[0024] In terms of implementation, the agricultural spatial functional zoning planning system and the user terminal are mutually compatible. That is, if the agricultural spatial functional zoning planning system is implemented as an application installed on a cloud service platform, then the user terminal is implemented as a client that establishes a communication connection with the application; or if the agricultural spatial functional zoning planning system is implemented as a website, then the user terminal is implemented as a webpage; or if the agricultural spatial functional zoning planning system is implemented as a cloud service platform, then the user terminal is implemented as a mini-program in an instant messaging application.

[0025] like Figure 1 The figure shown is a system architecture diagram of an agricultural spatial functional zoning planning system provided by an embodiment of the present invention.

[0026] The agricultural spatial functional zoning planning system 100 described in this invention can be set up in a cloud server. In terms of implementation, it can be used as one or more service devices, or as an application installed in the cloud (e.g., a mobile service operator's server, server cluster, etc.), or it can be developed as a website. Depending on the functions implemented, the agricultural spatial functional zoning planning system 100 may include a plot division module 101, a functional association module 102, a matrix arrangement module 103, a functional suitability acquisition module 104, a functional zoning module 105, and an agricultural spatial planning module 106. The modules described in this invention can also be called units, referring to a series of computer program segments that can be executed by an electronic device's processor and perform a fixed function, stored in the electronic device's memory.

[0027] In this embodiment of the invention, in an agricultural spatial functional zoning planning system, each of the above-mentioned modules can be implemented independently and can call other modules. Here, "calling" can be understood as one module connecting to multiple modules of another type and providing corresponding services to those connected modules. In the agricultural spatial functional zoning planning system provided by this embodiment of the invention, without modifying the program code, the applicable scope of an agricultural spatial functional zoning planning system architecture can be adjusted by adding modules and directly calling them, achieving cluster-based horizontal expansion to quickly and flexibly expand the agricultural spatial functional zoning planning system. In practical applications, the above-mentioned modules can be set in the same device or different devices, or they can be set in virtual devices, such as service instances in a cloud server.

[0028] The following describes, with reference to specific embodiments, each component of an agricultural spatial functional zoning planning system and its specific workflow: The land parcel division module 101 is used to divide the target area into grids based on preset discrete rules, and map the agricultural resource data of the target area into the grids to obtain the agricultural functional land parcels of the target area. In this embodiment of the invention, when the land parcel division module performs grid division of the target area based on preset discrete rules and maps the agricultural resource data of the target area into the grid to obtain the agricultural functional land parcels of the target area, it is specifically used for: The target area is divided into spatial grids based on the boundaries of natural geographical units; The land use status data, soil physicochemical property data, meteorological factor time series data, and agricultural production facility distribution data of the target area are compiled into multi-source agricultural resource data of the target area. Spatial registration and standardization preprocessing are performed on the multi-source agricultural resource data to obtain a standardized spatial dataset of the target region; The standardized spatial dataset is mapped to the spatial grid based on spatial location to obtain agricultural functional plots in the target area.

[0029] The boundaries of natural geographical units in the target area are determined, including the boundaries of various natural geographical elements such as mountain ranges, riverbanks, and topographical boundaries. These boundaries are used as the basis for spatial grid division. According to the distribution and extension characteristics of the boundaries, the target area is divided into multiple continuous and non-overlapping spatial regions. Each spatial region forms an independent spatial grid. All the spatial grids formed by the division together constitute the spatial grid of the target area based on the boundaries of natural geographical units.

[0030] Data on the current land use status within the target area is collected. This data represents the current land use types and distribution status within the target area. Data on the physical and chemical properties of the soil within the target area is also collected. This data covers relevant physical and chemical indicators such as soil pH, organic matter content, and soil texture. Time-series data on meteorological factors within the target area is collected. This data includes information on meteorological elements such as temperature, precipitation, sunshine, and humidity at different time points. Data on the distribution of agricultural production facilities within the target area is also collected. This data records the spatial locations of facilities such as farmland irrigation facilities, agricultural greenhouses, and agricultural machinery storage sites. The above four types of data are categorized and integrated according to the spatial scope of the target area, and finally compiled into multi-source agricultural resource data for the target area.

[0031] A unified geographic coordinate system for the target area is selected as the benchmark for spatial registration. The spatial reference systems of all types of data in the multi-source agricultural resource data are adjusted to this benchmark coordinate system. By comparing the spatial location information of various types of data, the land use status data, soil physicochemical property data, meteorological factor time series data, and agricultural production facility distribution data from different sources are accurately aligned in spatial location. Subsequently, standardization preprocessing is carried out to unify the dimensions and expression forms of various types of data, standardize the classification standards of land use status data, unify the index descriptions of soil physicochemical property data, standardize the time recording format of meteorological factor time series data, and standardize the facility type classification of agricultural production facility distribution data. After the above spatial registration and standardization preprocessing operations, the standardized spatial dataset of the target area is finally obtained.

[0032] Extract the spatial location information corresponding to each data item in the standardized spatial dataset, clarify the spatial distribution range of various data in the target area, match this spatial location information with the spatial range of the previously divided spatial grids one by one, and associate all the land use status data, soil physicochemical property data, meteorological factor time series data, and agricultural production facility distribution data in the standardized spatial dataset that fall within a certain spatial grid range with that spatial grid, so that each spatial grid has corresponding agricultural resource attribute data support. Each spatial grid that has completed data association is a basic unit with specific agricultural functional attributes. After integrating all the spatial grids that have completed data mapping, the agricultural functional plots of the target area are finally obtained.

[0033] The beneficial effects are that spatial grids are divided based on the boundaries of natural geographical units, so that the grid division results fit the natural geographical characteristics of the target area. By collecting multi-source agricultural resource data, the comprehensive collection of relevant information on land use, soil physicochemical properties, meteorological factors, and agricultural production facilities in the target area is achieved. After spatial registration and standardization preprocessing, the spatial consistency and data format uniformity of multi-source data are ensured, eliminating spatial deviations and format differences between data. The standardized spatial dataset is mapped to the spatial grid to form agricultural functional plots, so that each plot has corresponding agricultural resource attributes, providing accurate and standardized basic support for subsequent agricultural resource management and planning work in the target area.

[0034] The functional association module 102 is used to perform weighted fusion of the internal constraint vector and external demand vector of the agricultural functional plot to obtain the association degree of the corresponding function of the target area. In this embodiment of the invention, when the functional association module performs a weighted fusion of the internal constraint vector and the external demand vector of the agricultural functional plot to obtain the association degree of the corresponding function of the target area, it is specifically used for: The internal constraint indicators and external demand indicators are extracted from the unit attribute dataset of the agricultural functional land plots, and respectively constitute the internal constraint indicator subset and external demand indicator subset of the target area; The internal constraint index subset and the external demand index subset are respectively processed to be dimensionless to obtain the internal constraint vector and the external demand vector of the target region. Based on the data dispersion of the internal constraint vector and the external demand vector, the internal constraint weight vector and the external demand weight vector of the target region are generated. Based on the internal constraint weight vector and the external demand weight vector, the internal constraint vector and the external demand vector are linearly fused to obtain the correlation degree of the function corresponding to the target area.

[0035] When the functional association module generates the internal constraint weight vector and external demand weight vector of the target region based on the data dispersion of the internal constraint vector and external demand vector, it is specifically used for: Calculate the degree of variation between the internal constraint vector and the external demand vector for each dimension; Based on the degree of variation of each index in the internal constraint vector, the weight coefficients are assigned in reverse to obtain the internal constraint weight vector of the target region. Based on the degree of variation of each indicator in the external demand vector, weight coefficients are positively assigned to the external demand weight vector of the target region.

[0036] The formula for calculating the degree of variation is as follows: ; In the formula, The value representing the degree of variation. Let be the standard deviation of the observation sequence of the agricultural functional plots in the same dimension. This is the global average of the observation sequence of the agricultural functional plots in the same dimension. To adjust the preset spatial correction coefficient for the effects of spatial autocorrelation, is the global Moran index of the observed sequence.

[0037] The observed values ​​of all agricultural functional plots under the same dimension are statistically analyzed. These observed values ​​are arranged into a sequence in order, and the deviation of each observed value in the sequence from the global mean of the sequence is calculated to obtain the standard deviation of the observed value sequence.

[0038] The observations of all agricultural functional plots under the same dimension are statistically analyzed, and these observations are summed to obtain a total. The total is then divided by the number of agricultural functional plots to obtain the global average value of this observation series.

[0039] Based on the spatial distribution characteristics of agricultural functional plots in the target area and the degree of influence of spatial autocorrelation, and in combination with the needs of actual research or application, a value is pre-set to adjust the influence of spatial autocorrelation. This value is the preset spatial correction coefficient.

[0040] The observation sequence of all agricultural functional plots under the same dimension is statistically analyzed. The spatial unit corresponding to each agricultural functional plot is identified, the adjacency relationship between each spatial unit is determined, the deviation of the observation of each plot from the global average of the observations of all plots is calculated, and the sum of the products of the deviations of each plot and its neighboring plots is calculated. This sum of products is divided by the sum of the squares of the deviations of all plots to obtain the global Moran index of this observation sequence.

[0041] This formula is used to calculate the degree of variation of the observation value sequence under the same dimension of agricultural functional plots. It takes into account the spatial autocorrelation effect of the observation values ​​on the basis of considering the numerical dispersion of the observation value sequence itself. This makes the obtained degree of variation measure reflect both the differences of the observation values ​​at the numerical level and the role of the correlation of the spatial distribution of the observation values ​​in the degree of difference.

[0042] When the standard deviation of an observation series increases, the numerical deviation of the observations increases, and the measure of variability increases accordingly. When the global mean of an observation series increases, if the standard deviation remains constant, the relative deviation of the observations decreases, and the measure of variability decreases accordingly.

[0043] As the absolute value of the global Moran's index increases, the spatial autocorrelation of the observations improves. Combined with the moderating effect of the preset spatial correction coefficient, the variability measure increases with the increase of the absolute value of the global Moran's index. When the preset spatial correction coefficient increases, the weight of spatial autocorrelation on variability increases. If the absolute value of the global Moran's index remains unchanged, the variability measure will increase accordingly.

[0044] This study analyzes the entire dataset of unit attributes for agricultural functional land parcels. This dataset includes inherent attribute data such as soil fertility, topography, water resource carrying capacity, and climate adaptability, as well as externally relevant data such as agricultural product market demand, policy guidance, industrial development planning, and ecological protection requirements. The study identifies indicators that characterize the inherent attributes of the land parcels and exert a rigid constraint on their agricultural functions. The numerical value of these indicators directly determines the upper limit of the agricultural functions of the land parcels. All these indicators are extracted and categorized according to their attributes to form a subset of internal constraint indicators for the target area. Simultaneously, the study identifies indicators that characterize the specific needs and explicit requirements of the external environment for the agricultural functions of the land parcels. The content of these indicators directly guides the positioning direction of the agricultural functions of the land parcels. All these indicators are extracted and categorized according to demand type to form a subset of external demand indicators for the target area.

[0045] For each indicator within the subset of internal constraint indicators, which have different dimensions and numerical expressions, making direct comparative analysis impossible, a unified numerical conversion method is adopted based on the indicator's attribute characteristics. The original value of each indicator is converted by comparing it with the maximum and minimum values ​​of that indicator across all agricultural functional plots within the target area, mapping the original values ​​to a unified relative numerical range. This eliminates dimensional differences between different indicators, converting all original values ​​into relative values ​​that can be directly compared and analyzed. All converted internal constraint indicators are then integrated in their original order to form the internal constraint vector for the target area. Similarly, for each indicator within the subset of external demand indicators, the same numerical conversion method is used, converting the indicators by comparing them with the maximum and minimum values ​​within the target area. This eliminates dimensional differences between different indicators, converting all original values ​​into relative values ​​that can be directly compared and analyzed. All converted external demand indicators are then integrated in their original order to form the external demand vector for the target area.

[0046] For the indicators of each dimension contained in the internal constraint vector, the specific values ​​of each indicator in all agricultural functional plots in the target area are statistically analyzed. The distribution of the values ​​of each indicator is analyzed, and the degree of deviation of the values ​​of each indicator between different plots is analyzed. The more dispersed the value distribution, the higher the degree of variation of the indicator. Based on the analysis results, the degree of variation measure corresponding to each indicator is determined. For the indicators of each dimension contained in the external demand vector, the same analysis method is used to statistically analyze the specific values ​​of each indicator in all agricultural functional plots in the target area, the distribution of the values ​​of each indicator is analyzed, and the degree of deviation of the values ​​of each indicator between different plots is analyzed, thereby determining the degree of variation measure of each indicator.

[0047] Referring to the variability measure values ​​of each dimension indicator in the internal constraint vector, and following the reverse allocation principle that the larger the variability measure value, the smaller the corresponding weight coefficient, the larger the variability measure value indicates. Indicators with large variability measure values ​​indicate large differences between different agricultural functional plots and weak stability of their impact on the overall internal constraints, thus they are assigned smaller weight coefficients. Indicators with small variability measure values ​​indicate small differences between different agricultural functional plots and strong stability of their impact on the overall internal constraints, thus they are assigned larger weight coefficients. Following this principle, corresponding weight coefficients are assigned to each dimension indicator of the internal constraint vector one by one. All assigned weight coefficients are integrated in the order of the indicators to form the internal constraint weight vector of the target area.

[0048] Referring to the variability measures of each dimension of the external demand vector, and following the positive allocation principle that the larger the variability measure, the larger the weight coefficient, the greater the variability measure. Indicators with large variability measures indicate large differences between different agricultural functional plots and are key indicators for distinguishing differences in external demand for plots. Therefore, they are assigned larger weight coefficients. Indicators with small variability measures indicate small differences between different agricultural functional plots and are less effective in distinguishing differences in external demand for plots. Therefore, they are assigned smaller weight coefficients. Following this principle, corresponding weight coefficients are assigned to each dimension of the external demand vector. All assigned weight coefficients are integrated in the order of indicators to form the external demand weight vector of the target area.

[0049] The values ​​of each dimension indicator in the internal constraint vector are matched one-to-one with the corresponding weight coefficients in the internal constraint weight vector, so that each dimension indicator value is assigned a corresponding weight percentage. Similarly, the values ​​of each dimension indicator in the external demand vector are matched one-to-one with the corresponding weight coefficients in the external demand weight vector, so that each dimension indicator value is also assigned a corresponding weight percentage. The two sets of weighted indicator values ​​are then linearly superimposed. The superimposed result can comprehensively reflect the combined influence of internal constraints and external demand on agricultural functional plots, and finally obtain the correlation degree of the target area's corresponding function.

[0050] The beneficial effects are as follows: by extracting internal constraint indicators and external demand indicators from the attribute dataset of agricultural functional land parcels and forming indicator subsets respectively, the inherent constraints of the land parcels and the external guiding demands are clearly distinguished. After dimensionless processing, internal constraint vectors and external demand vectors are obtained, eliminating the dimensional differences between different indicators and enabling comparable analysis of various indicators. By calculating the degree of variation of each dimension vector, an objective basis is provided for weight allocation. Based on the degree of variation, the internal constraint weight coefficients are allocated in reverse to highlight the basic constraint role of stable internal indicators on land parcel functions. The external demand weight coefficients are allocated in forward to strengthen the guiding role of highly distinguishable external indicators on land parcel functions. Finally, the correlation degree of the corresponding functions of the target area is obtained through linear fusion, comprehensively reflecting the synergistic influence of internal constraints and external demands, and providing reliable data support for the accurate positioning and scientific planning of agricultural functional land parcels.

[0051] The matrix arrangement module 103 is used to arrange the correlation degrees to generate a dynamic coupling relationship matrix of the target region. In this embodiment of the invention, when the matrix arrangement module generates the dynamic coupling relationship matrix of the target region by arranging the correlation degrees, it is specifically used for: The dimensions of the dynamic coupling relationship matrix are determined based on the number of agricultural functional plots and the types of preset agricultural functions. In the aforementioned dimension, a mapping relationship is established between the spatial identifier of agricultural functional land parcels and the matrix row number, and a mapping relationship is also established between the functional type classification code and the matrix column number; Based on the established mapping relationship, the correlation degree between the agricultural functional plots and the preset agricultural functional types is filled into the intersection of the rows and columns of the dynamic coupling relationship matrix.

[0052] One by one, the agricultural functional plots within the target area are counted to obtain the total number of all agricultural functional plots. The total number of types included in the pre-defined agricultural functional types is determined, and the number of these types is counted. The number of rows in the dynamic coupling relationship matrix is ​​set to the total number of agricultural functional plots, and the number of columns in the matrix is ​​set to the number of types of the pre-defined agricultural functional types. This determines the dimension of the dynamic coupling relationship matrix.

[0053] Each agricultural functional plot is assigned a unique spatial identifier, which directly associates with the specific spatial range information of the plot. Following the predetermined row order of the dynamic coupling matrix, the spatial identifier of each agricultural functional plot is mapped one-to-one to the corresponding row number, ensuring that each row number uniquely corresponds to the spatial identifier of an agricultural functional plot, thus establishing the mapping relationship between the spatial identifier of the agricultural functional plot and the matrix row number. Simultaneously, each preset agricultural function type is assigned a unique classification code, which directly corresponds to the specific function type content. Following the predetermined column order of the dynamic coupling matrix, the classification code of each function type is mapped one-to-one to the corresponding column number, ensuring that each column number uniquely corresponds to the classification code of a function type, thus establishing the mapping relationship between the function type classification code and the matrix column number.

[0054] For a specific agricultural functional plot, based on the established mapping relationship, find the row number of the dynamic coupling relationship matrix corresponding to the spatial identifier of the plot, then find the column number of the matrix corresponding to the classification code of a certain preset agricultural functional type of the plot, determine the intersection of the row and column numbers in the matrix, extract the correlation degree between the agricultural functional plot and this preset agricultural functional type, and fill this correlation degree into the intersection position determined above in the dynamic coupling relationship matrix. Following the same operation method, process the correlation degree between each agricultural functional plot and each preset agricultural functional type in turn, and fill all the correlation degrees into the corresponding intersection positions in the matrix to complete the filling of the dynamic coupling relationship matrix.

[0055] The beneficial effect is that the dimensions of the dynamic coupling relationship matrix are determined based on the number of agricultural functional plots and the types of preset agricultural functions, so that the matrix can accurately adapt to the plot size and functional type requirements of the target area. By establishing the mapping relationship between the spatial identifier of agricultural functional plots and the matrix row number, and the functional type classification code and the matrix column number, each plot and functional type can correspond to a unique position in the matrix, avoiding information confusion and misalignment. The correlation between agricultural functional plots and preset agricultural functional types is filled into the intersection of the rows and columns of the matrix, so that the relationship between each plot and each functional type is clearly and intuitively presented in the matrix, providing a clear and structured basis for the matching, optimization and planning of subsequent agricultural functions.

[0056] The functional suitability acquisition module 104 is used to generate a functional suitability index for each preset agricultural function type in the target area based on the dynamic coupling relationship matrix; In this embodiment of the invention, the formula for calculating the functional suitability index is as follows: ; In the formula, For the first The agricultural functional plot for the first Functional suitability index of preset agricultural function types The first in the dynamic coupling matrix The agricultural functional plot for the first The correlation between the pre-set agricultural function types This is a spatial coordination adjustment coefficient used to adjust the impact of adjacent plots. For the first All spatially adjacent plots of land for agricultural functions are related to the first plot. The average correlation between the pre-defined agricultural functional types, For the first The global average value of the preset agricultural function types, To prevent the denominator from being zero and to adjust the layout balance adjustment coefficient to adjust the balance intensity.

[0057] From the dynamic coupling matrix, locate the first... The row and number corresponding to each agricultural functional plot The value corresponding to the intersection of the columns corresponding to the preset agricultural function types is the correlation degree.

[0058] Based on the spatial distribution characteristics of agricultural functional plots in the target area, the degree of functional correlation between adjacent plots, and the actual application requirements for adjusting the impact of adjacent plots, a fixed value is pre-set. This value is the spatial coordination adjustment coefficient used to adjust the impact of adjacent plots.

[0059] Determine the first All spatially adjacent plots of land belonging to a given agricultural functional plot are extracted from the dynamic coupling relationship matrix, corresponding to the plots of the first plot. The correlation degree of each of the preset agricultural function types is calculated by summing the correlation values ​​and dividing the sum by the number of adjacent plots. The result is the first (or second) correlation degree. All adjacent plots of land to the first agricultural functional plot are related to the first The average value of the correlation between the preset agricultural function types.

[0060] All agricultural functional plots within the statistical target area correspond to the first The correlation degree of each preset agricultural function type is calculated, and the values ​​of these correlation degrees are added together to obtain a sum. This sum is then divided by the total number of agricultural function plots to obtain the result of the first correlation degree calculation. The global average value of the preset agricultural function types.

[0061] Based on the distribution requirements of agricultural functional types and the numerical range of correlation in the target area, and in combination with the need to prevent the denominator from being zero in actual calculations, a fixed value is preset. This value is the layout balance adjustment coefficient to prevent the denominator from being zero and to adjust the balance intensity.

[0062] This formula is used to calculate the first... The agricultural functional plot for the first The functional suitability index for a pre-defined agricultural function type is based on the correlation between the plot itself and the function type. It incorporates the average influence of the correlation between adjacent plots to reflect the spatial synergy effect. At the same time, it combines the global average value of the function type and the layout balance adjustment coefficient for balance processing. This makes the functional suitability index reflect the degree of adaptation between the plot itself and the function type, take into account the spatial synergy relationship between adjacent plots, and balance the distribution of the function type in the global scope.

[0063] As the correlation coefficient increases, the functional suitability index also increases. When the average correlation coefficient between adjacent plots increases, the functional suitability index increases under the influence of the spatial coordination adjustment coefficient. When the spatial coordination adjustment coefficient increases, the weight of the average correlation coefficient between adjacent plots on the result increases; if the average correlation coefficient between adjacent plots remains unchanged, the functional suitability index will still increase.

[0064] When the global average value increases, if the correlation remains constant, the denominator in the formula will increase, and the functional suitability index will decrease accordingly. When the layout balance adjustment coefficient increases, the denominator in the formula will increase, and if the correlation and the global average remain constant, the functional suitability index will decrease accordingly.

[0065] The functional zoning module 105 is used to initialize the target area into multiple partition agents based on the functional suitability index set, with the goal of maximizing the overall functional suitability of the area and satisfying spatial connectivity constraints, so as to obtain the initial agricultural spatial functional zoning scheme of the target area. In this embodiment of the invention, when the functional zoning module executes the initial division of the target region into multiple partition agents based on the functional suitability index set, with the goal of maximizing the overall functional suitability of the region and satisfying spatial connectivity constraints, to obtain the initial agricultural spatial functional zoning scheme for the target region, it is specifically used for: Define the partitioned intelligent agent; Based on the principles of spatial proximity and functional similarity, all agricultural functional plots within the target area are aggregated to initially form multiple candidate partition agents, and an initial dominant agricultural function type identifier is assigned to each candidate partition agent. Establish negotiation rules among the candidate partition agents; Based on the negotiation rules, the ownership of boundary plots of the partitioned smart agents is exchanged among them. When the negotiation process reaches the preset convergence condition, the negotiation is terminated, and the initial agricultural spatial function zoning scheme is generated based on the spatial range of all partition agents and the corresponding dominant agricultural function type identifier at this time.

[0066] The core connotation and constituent elements of a zonal intelligent agent are clearly defined. A zonal intelligent agent is a spatial decision-making unit with the ability to autonomously negotiate the ownership of boundary plots. Its core constituent elements include spatial range attributes, functional suitability index attributes, dominant agricultural function type identification attributes, and association attributes with neighboring zonal intelligent agents. Among them, the spatial range attribute is used to define the set of agricultural function plots covered by the intelligent agent, the functional suitability index attribute is used to characterize the adaptability of the intelligent agent to various preset agricultural function types, the dominant agricultural function type identification attribute is used to clarify the core functional positioning of the intelligent agent, and the association attribute is used to record the adjacent relationship between the intelligent agent and other surrounding zonal intelligent agents, thereby completing the definition of a zonal intelligent agent.

[0067] Based on the principles of spatial proximity and functional similarity, the aggregation operation of agricultural functional plots is carried out. The principle of spatial proximity requires that the agricultural functional plots participating in the aggregation are spatially adjacent to each other without any spatially separated areas. The principle of functional similarity requires that the agricultural functional plots participating in the aggregation have similar matching degrees to the functional suitability indices of various preset agricultural functional types. First, groups of agricultural functional plots that are spatially adjacent to each other within the target area are screened out. Then, the similarity of the functional suitability indices of each plot within the group is compared. Agricultural functional plot groups that simultaneously meet both principles are integrated. Each integrated plot group forms an independent candidate partition agent. Subsequently, the sum of the functional suitability indices of all agricultural functional plots in each candidate partition agent for various preset agricultural functional types is calculated. The preset agricultural functional type with the highest sum of indices is determined as the core adaptability function of the candidate partition agent, and the initial dominant agricultural functional type identifier of this functional type is assigned to the corresponding candidate partition agent.

[0068] To address the exchange of ownership of boundary plots between candidate partition agents, a complete and clear set of negotiation rules is established. These rules consist of three core parts: triggering conditions, exchange basis, and judgment criteria. The triggering condition is a dispute between two adjacent candidate partition agents regarding the ownership of agricultural functional plots at their common boundary. The exchange basis is the functional suitability index of the boundary plot relative to the dominant agricultural functional types of the two adjacent candidate partition agents. The judgment criterion is that after the boundary plot is assigned to a candidate partition agent, the sum of the overall functional suitability indices of that agent and its neighboring agents increases compared to before the exchange. This clear rule system guides subsequent ownership exchange operations.

[0069] Guided by the established negotiation rules, the boundary plot ownership exchange operation between regional agents is carried out. Two adjacent candidate regional agents first jointly identify all boundary plots at the intersection of their spatial ranges. Then, they calculate the functional suitability index of each boundary plot for its dominant agricultural function type. Based on the judgment criteria in the negotiation rules, they compare the changes in the total functional suitability index after the boundary plot is assigned to two different candidate regional agents to determine the optimal regional affiliation of the boundary plot. The ownership of the boundary plot is then assigned to the optimal regional affiliation, and the spatial range attributes of the two candidate regional agents are updated simultaneously. The above boundary plot identification index calculation and ownership determination operation are repeated until the ownership exchange of all boundary plots in the current round is completed.

[0070] The system continuously monitors the process of exchanging ownership of boundary plots between regional agents. When the exchange process reaches a preset convergence condition, the negotiation behavior between all regional agents is immediately terminated. The preset convergence condition is that after multiple rounds of boundary plot ownership exchange operations, the sum of the overall functional suitability index of all regional agents in the target area no longer increases, or the number of rounds of boundary plot ownership exchange reaches a preset upper limit threshold. After terminating the negotiation, the system sorts out the final spatial range of each regional agent and the corresponding dominant agricultural function type identifier. This information is integrated and arranged according to the spatial geographical distribution of the target area to finally generate the initial agricultural spatial function zoning scheme for the target area.

[0071] The beneficial effects are as follows: by defining the core components and functional attributes of the zoning agents, a standardized decision-making unit is provided for the functional zoning of agricultural space. Based on the principles of spatial proximity and functional similarity, agricultural functional plots are aggregated to form candidate zoning agents and initial dominant agricultural function type identifiers are assigned, ensuring that candidate agents have both spatial continuity and functional consistency. Negotiation rules are established between candidate zoning agents, providing clear operational basis and judgment criteria for the exchange of boundary plot ownership. Based on the negotiation rules, the exchange of boundary plot ownership between zoning agents is carried out, optimizing the spatial range and functional adaptability of each agent. When the negotiation reaches the convergence condition, it terminates and generates an initial agricultural spatial functional zoning scheme, so that the scheme fully takes into account the rationality of spatial layout and the adaptability of functional types, providing a scientific and feasible initial basis for the subsequent refined planning and management of agricultural space.

[0072] The agricultural space planning module 106 is used to iterate the initial agricultural space functional zoning scheme with the optimization objectives of spatial compactness, internal functional homogeneity and functional coordination of adjacent units, so as to obtain the agricultural space planning map of the target area.

[0073] In this embodiment of the invention, when the agricultural spatial planning module iterates the initial agricultural spatial functional zoning scheme with the optimization objectives of spatial compactness, functional homogeneity, and functional coordination of adjacent units to obtain the agricultural spatial planning map of the target area, it is specifically used for: Using the initial agricultural spatial functional zoning scheme as the starting point for iteration, a set of candidate schemes for the target area is generated through simulation of crossover and variation. Based on three optimization objectives—spatial compactness, functional homogeneity, and functional coordination of neighboring units—the fitness of each candidate partitioning scheme in the candidate scheme set is evaluated to obtain the fitness evaluation results of the candidate partitioning scheme. Based on the fitness evaluation results, a candidate partitioning scheme with high fitness is selected from the candidate scheme set as the parent scheme; When the preset optimization termination condition is met, the candidate partitioning scheme with the highest fitness at this time is determined as the agricultural spatial planning map of the target area.

[0074] When the agricultural spatial planning module performs fitness evaluation on each candidate partitioning scheme in the candidate scheme set based on three optimization objectives—spatial compactness, functional homogeneity, and functional coordination of neighboring units—and obtains the fitness evaluation results of the candidate partitioning scheme, it is specifically used for: The overall compactness evaluation value of the candidate partitioning scheme is obtained by summing the compactness indices of the geometry of all independent partitions in the candidate partitioning scheme. The internal homogeneity evaluation value of the candidate partitioning scheme is obtained by summing the consistency ratios between the dominant functional type of all independent partitions and the designated dominant agricultural functional type of each independent partition in the candidate partitioning scheme. Identify all spatially adjacent pairs of agricultural functional plots belonging to different independent zones in the candidate zoning scheme, analyze the proportion of compatible plot pairs in the agricultural functional plot pairs based on the dynamic coupling relationship matrix, and obtain the overall neighboring unit functional coordination evaluation value of the candidate zoning scheme; The overall compactness evaluation value, the internal homogeneity evaluation value, and the overall neighboring unit functional coordination evaluation value are weighted and fused to obtain the fitness evaluation result of the candidate partitioning scheme.

[0075] Taking the initial agricultural spatial functional zoning scheme as the starting point of the iteration, the boundary areas of two different independent zones in the scheme are selected, and some boundary agricultural functional plots of these two zones are interchanged. This operation is called simulated crossover. Then, a small number of agricultural functional plots in an independent zone in the scheme are selected, and the zone to which these plots belong is adjusted to other adjacent independent zones. This operation is called simulated mutation. The above simulated crossover and simulated mutation operations are repeated multiple times. Each time an operation is completed, a new zoning scheme is formed. All the new zoning schemes generated in this way are integrated to obtain the candidate scheme set of the target area.

[0076] For each independent partition in the candidate partitioning scheme, the characteristics of its geometric shape are analyzed. The compactness index is determined by comparing the relationship between the area and the perimeter of the partition. The higher the ratio of area to perimeter, the higher the compactness index of the partition. After calculating the compactness index of all independent partitions, the values ​​of these indices are summed to obtain the overall compactness evaluation value of the candidate partitioning scheme.

[0077] Identify the designated dominant agricultural function type for each independent partition in the candidate partitioning scheme, count the number of agricultural function plots within the independent partition whose dominant function type is consistent with the designated dominant agricultural function type, divide this number by the total number of agricultural function plots included in the independent partition to obtain the consistency ratio of the independent partition, and sum the consistency ratios of all independent partitions to obtain the internal homogeneity evaluation value of the candidate partitioning scheme.

[0078] One by one, agricultural functional plots in the candidate zoning schemes are examined to identify all spatially adjacent agricultural functional plot combinations that belong to different independent zones. Each such combination is a pair of spatially adjacent agricultural functional plots belonging to different independent zones. The correlation degree of the dominant functional types of the two plots in the plot pair is extracted from the dynamic coupling relationship matrix. If the matching state of the correlation degree of the two plots meets the preset functional compatibility standard, the plot pair is determined to be a compatible plot pair. The number of compatible plot pairs in all such plot pairs is counted. This number is divided by the total number of spatially adjacent plot pairs in different zones to obtain the overall neighboring unit functional coordination evaluation value of the candidate zoning scheme.

[0079] Based on the emphasis placed on different dimensions in agricultural spatial planning, fixed weights are assigned to the overall compactness evaluation value, the internal homogeneity evaluation value, and the overall neighboring unit functional coordination evaluation value, respectively. Each evaluation value is multiplied by its corresponding weight, and the results of the three operations are added together. The sum is the fitness evaluation result of the candidate zoning scheme.

[0080] The fitness evaluation results of all candidate partitioning schemes in the candidate scheme set are arranged in descending order of value. The candidate partitioning schemes with high fitness at the top of the ranking are selected and these schemes are determined as the parent schemes used in subsequent iterations.

[0081] The fitness evaluation results are continuously tracked during the iteration process. When the fitness evaluation result of the candidate partition scheme with the highest fitness no longer improves after multiple consecutive iterations, or when the number of iterations reaches the preset upper limit, it is determined that the preset optimization termination condition is met. At this time, the candidate partition scheme with the highest fitness evaluation result is selected from all current candidate partition schemes and determined as the agricultural spatial planning map of the target area.

[0082] The beneficial effects are as follows: using the initial agricultural spatial functional zoning scheme as the starting point for iteration, a candidate scheme set is generated through simulated crossover and variation, enriching the range of options for agricultural spatial zoning schemes. By calculating the overall compactness evaluation value, internal homogeneity evaluation value, and overall functional coordination evaluation value of neighboring units, the rationality of candidate schemes is comprehensively evaluated from dimensions such as spatial morphology, functional matching, and neighborly coordination. Weighted fusion of each evaluation value yields the fitness evaluation result, achieving comprehensive consideration of multi-dimensional indicators and avoiding the one-sidedness of a single dimension. Selecting candidate schemes with high fitness as the parent scheme provides a high-quality foundation for subsequent iterative optimization, ensuring the rationality of the optimization direction. Based on the preset optimization termination conditions, the scheme with the highest fitness is determined as the agricultural spatial planning map, avoiding ineffective iterations and ensuring that the final scheme takes into account spatial compactness, internal functional homogeneity, and functional coordination of neighboring units, thus improving the scientificity and adaptability of agricultural spatial planning.

[0083] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0084] This application embodiment can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0085] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. An agricultural spatial functional zoning planning system, characterized in that, The system includes a land parcel division module, a functional association module, a matrix arrangement module, a functional suitability acquisition module, a functional zoning module, and an agricultural spatial planning module, wherein: The land parcel division module is used to divide the target area into grids based on preset discrete rules, and to map the agricultural resource data of the target area into the grids to obtain the agricultural functional land parcels of the target area. The functional association module is used to weight and fuse the internal constraint vector and external demand vector of the agricultural functional plot to obtain the association degree of the corresponding function of the target area; The matrix arrangement module is used to arrange the correlation degrees to generate a dynamic coupling relationship matrix of the target region; The functional suitability acquisition module is used to generate a functional suitability index for each preset agricultural function type in the target area based on the dynamic coupling relationship matrix. The functional zoning module is used to initialize the target area into multiple partition agents based on the functional suitability index set, with the goal of maximizing the overall functional suitability of the area and satisfying spatial connectivity constraints, so as to obtain the initial agricultural spatial functional zoning scheme of the target area. The agricultural space planning module is used to iterate the initial agricultural space functional zoning scheme with the optimization objectives of spatial compactness, internal functional homogeneity and functional coordination of adjacent units, so as to obtain the agricultural space planning map of the target area.

2. The agricultural spatial functional zoning planning system as described in claim 1, characterized in that, When the land parcel division module performs grid division of the target area based on preset discrete rules and maps the agricultural resource data of the target area into the grid to obtain the agricultural functional land parcels of the target area, it is specifically used for: The target area is divided into spatial grids based on the boundaries of natural geographical units; The land use status data, soil physicochemical property data, meteorological factor time series data, and agricultural production facility distribution data of the target area are compiled into multi-source agricultural resource data of the target area. Spatial registration and standardization preprocessing are performed on the multi-source agricultural resource data to obtain a standardized spatial dataset of the target region; The standardized spatial dataset is mapped to the spatial grid based on spatial location to obtain agricultural functional plots in the target area.

3. The agricultural spatial functional zoning planning system as described in claim 1, characterized in that, When the functional association module performs a weighted fusion of the internal constraint vector and external demand vector of the agricultural functional plot to obtain the association degree of the corresponding function of the target area, it is specifically used for: The internal constraint indicators and external demand indicators are extracted from the unit attribute dataset of the agricultural functional land plots, and respectively constitute the internal constraint indicator subset and external demand indicator subset of the target area; The internal constraint index subset and the external demand index subset are respectively processed to be dimensionless to obtain the internal constraint vector and the external demand vector of the target region. Based on the data dispersion of the internal constraint vector and the external demand vector, the internal constraint weight vector and the external demand weight vector of the target region are generated. Based on the internal constraint weight vector and the external demand weight vector, the internal constraint vector and the external demand vector are linearly fused to obtain the correlation degree of the function corresponding to the target area.

4. An agricultural spatial functional zoning planning system as described in claim 3, characterized in that, When the functional association module generates the internal constraint weight vector and external demand weight vector of the target region based on the data dispersion of the internal constraint vector and external demand vector, it is specifically used for: Calculate the degree of variation between the internal constraint vector and the external demand vector for each dimension; Based on the degree of variation of each index in the internal constraint vector, the weight coefficients are assigned in reverse to obtain the internal constraint weight vector of the target region. Based on the degree of variation of each indicator in the external demand vector, weight coefficients are positively assigned to the external demand weight vector of the target region.

5. An agricultural spatial functional zoning planning system as described in claim 4, characterized in that, The formula for calculating the degree of variation is as follows: ； In the formula, The value representing the degree of variation. Let be the standard deviation of the observation sequence of the agricultural functional plots in the same dimension. This is the global average of the observation sequence of the agricultural functional plots in the same dimension. To adjust the preset spatial correction coefficient for the effects of spatial autocorrelation, is the global Moran index of the observed sequence.

6. An agricultural spatial functional zoning planning system as described in claim 5, characterized in that, When the matrix arrangement module generates the dynamic coupling relationship matrix of the target region by arranging the correlation degrees, it is specifically used for: The dimensions of the dynamic coupling relationship matrix are determined based on the number of agricultural functional plots and the types of preset agricultural functions. In the aforementioned dimension, a mapping relationship is established between the spatial identifier of agricultural functional land parcels and the matrix row number, and a mapping relationship is also established between the functional type classification code and the matrix column number; Based on the established mapping relationship, the correlation degree between the agricultural functional plots and the preset agricultural functional types is filled into the intersection of the rows and columns of the dynamic coupling relationship matrix.

7. An agricultural spatial functional zoning planning system as described in claim 6, characterized in that, The formula for calculating the functional suitability index is as follows: ； In the formula, For the first The agricultural functional plot for the first Functional suitability index of preset agricultural function types The first in the dynamic coupling matrix The agricultural functional plot for the first The correlation between the pre-set agricultural function types This is a spatial coordination adjustment coefficient used to adjust the impact of adjacent plots. For the first All spatially adjacent plots of land for agricultural functions are related to the first plot. The average correlation between the pre-defined agricultural functional types, For the first The global average value of the preset agricultural function types, To prevent the denominator from being zero and to adjust the layout balance adjustment coefficient to adjust the balance intensity.

8. An agricultural spatial functional zoning planning system as described in claim 1, characterized in that, When the functional zoning module executes an initial agricultural spatial functional zoning scheme for the target region by initially dividing the target region into multiple partition agents based on the functional suitability index set, with the goal of maximizing the overall functional suitability of the region and satisfying spatial connectivity constraints, it is specifically used for: Define the partitioned intelligent agent; Based on the principles of spatial proximity and functional similarity, all agricultural functional plots within the target area are aggregated to initially form multiple candidate partition agents, and an initial dominant agricultural function type identifier is assigned to each candidate partition agent. Establish negotiation rules among the candidate partition agents; Based on the negotiation rules, the ownership of boundary plots of the partitioned smart agents is exchanged among them. When the negotiation process reaches the preset convergence condition, the negotiation is terminated, and the initial agricultural spatial function zoning scheme is generated based on the spatial range of all partition agents and the corresponding dominant agricultural function type identifier at this time.

9. An agricultural spatial functional zoning planning system as described in claim 1, characterized in that, When the agricultural spatial planning module iterates through the initial agricultural spatial functional zoning scheme to obtain the agricultural spatial planning map of the target area, with the optimization objectives of spatial compactness, internal functional homogeneity, and functional coordination of adjacent units, it is specifically used for: Using the initial agricultural spatial functional zoning scheme as the starting point for iteration, a set of candidate schemes for the target area is generated through simulation of crossover and variation. Based on three optimization objectives—spatial compactness, functional homogeneity, and functional coordination of neighboring units—the fitness of each candidate partitioning scheme in the candidate scheme set is evaluated to obtain the fitness evaluation results of the candidate partitioning scheme. Based on the fitness evaluation results, a candidate partitioning scheme with high fitness is selected from the candidate scheme set as the parent scheme; When the preset optimization termination condition is met, the candidate partitioning scheme with the highest fitness at this time is determined as the agricultural spatial planning map of the target area.

10. An agricultural spatial functional zoning planning system as described in claim 9, characterized in that, When the agricultural spatial planning module performs fitness evaluation on each candidate partitioning scheme in the candidate scheme set based on three optimization objectives—spatial compactness, functional homogeneity, and functional coordination of neighboring units—and obtains the fitness evaluation results of the candidate partitioning scheme, it is specifically used for: The overall compactness evaluation value of the candidate partitioning scheme is obtained by summing the compactness indices of the geometry of all independent partitions in the candidate partitioning scheme. The internal homogeneity evaluation value of the candidate partitioning scheme is obtained by summing the consistency ratios between the dominant functional type of all independent partitions and the designated dominant agricultural functional type of each independent partition in the candidate partitioning scheme. Identify all spatially adjacent pairs of agricultural functional plots belonging to different independent zones in the candidate zoning scheme, analyze the proportion of compatible plot pairs in the agricultural functional plot pairs based on the dynamic coupling relationship matrix, and obtain the overall neighboring unit functional coordination evaluation value of the candidate zoning scheme; The overall compactness evaluation value, the internal homogeneity evaluation value, and the overall neighboring unit functional coordination evaluation value are weighted and fused to obtain the fitness evaluation result of the candidate partitioning scheme.

Images