Grain safety coordinated optimization method in combination with regional coordinated development analysis

Abstract

The invention discloses a grain safety coordinated optimization method in combination with regional coordinated development analysis, which comprises the following steps: acquiring a plurality of different regional coordinated development level evaluation examples, performing category division on each regional coordinated development level evaluation example, and constructing a regional coordinated development level evaluation example data set; screening a grain safety evaluation index and a regional coordination development level evaluation index based on the regional coordination development level evaluation instance data set, and constructing a grain safety evaluation data set and a regional coordination development level evaluation data set; and acquiring each evaluation index parameter of each region of the target region, performing grain safety prediction and region coordination degree evaluation, and formulating a grain reserve allocation scheme for pushing. Therefore, the limitation of traditional index screening is overcome, and scientific decision basis and guidance are provided for regional grain safety.

Description

Technical Field

[0001] The present invention relates to the technical field of food security coordination optimization, and in particular to a food security coordination optimization method combined with regional coordinated development analysis. Background Art

[0002] In the traditional field of food security coordination and optimization, existing technologies often rely on single-dimensional yield forecasting models, employing time series analysis or regression methods to model production factors like climate and soil in isolation. These methods lack quantitative consideration of dynamic correlations such as inter-regional resource flows and industrial chain collaboration. Furthermore, regional coordination evaluation systems generally employ static weight allocation, making it difficult to capture the spatiotemporal evolution of cross-regional factors like infrastructure connectivity and ecological compensation mechanisms. This results in an inaccurate match between coordination analysis results and food distribution needs.

[0003] When developing reserve allocation plans, traditional linear programming methods can handle optimization problems under fixed constraints, but they fail to fully consider the impact of dynamic changes in regional coordination levels on transportation route reliability. Therefore, there is an urgent need to develop a food security coordination optimization method that incorporates regional coordinated development analysis to address the core pain points of existing technologies, such as insufficient forecasting accuracy, significant decision-making lags, and inefficient cross-regional resource allocation. Summary of the Invention

[0004] The present invention overcomes the defects of the prior art and provides a food security coordination optimization method combined with regional coordinated development analysis.

[0005] To achieve the above objectives, the present invention provides a first aspect of a food security coordination optimization method combined with regional coordinated development analysis, comprising: Obtain several different regional coordinated development level evaluation instances, classify the regional coordinated development level evaluation instances into categories, and construct a regional coordinated development level evaluation instance dataset; Based on the regional coordinated development level evaluation example dataset, food security evaluation indicators and regional coordinated development level evaluation indicators are screened respectively, and a food security evaluation dataset and a regional coordinated development level evaluation dataset are constructed.

[0006] In this solution, the acquisition of several different regional coordinated development level evaluation instances, classification of the regional coordinated development level evaluation instances, and construction of a regional coordinated development level evaluation instance dataset specifically includes: Acquire a number of evaluation instances of coordinated development levels of different regions based on big data retrieval, wherein the obtained evaluation instances of coordinated development levels of different regions include relevant text descriptions and evaluation parameters of the evaluation of coordinated development levels of different regions; Extract relevant text descriptions of each evaluation instance from several different regional coordinated development level evaluation instances, import them into the pre-trained BERT model, and use the attention mechanism to obtain the global context embedding of different words in the relevant text descriptions; Build word vectors and keyword vectors based on the relevant text description of each evaluation instance, calculate the semantic relative distance between different word vectors and keyword vectors, and select words with a semantic relative distance less than a preset threshold as local context embeddings; The global context embedding and the local context embedding are concatenated to obtain semantic features. Based on the obtained semantic features, evaluation labels for the corresponding regional coordinated development evaluation instances are generated. The Euclidean distance algorithm is used to calculate the Euclidean distance between the evaluation labels. The calculated Euclidean distance value is compared with a preset Euclidean distance threshold, and regional coordinated development evaluation instances with a value greater than the preset Euclidean distance threshold are defined as the same category, thereby obtaining several evaluation instance categories; The dynamic time warping algorithm is used to align the evaluation parameters of each evaluation instance in the regional coordinated development level evaluation, and outliers are eliminated and missing values are supplemented. After completing data preprocessing, a regional coordinated development level evaluation instance dataset is constructed in combination with the divided evaluation instance categories.

[0007] This solution is characterized in that the method of screening food security evaluation indicators and regional coordinated development level evaluation indicators based on the regional coordinated development level evaluation instance dataset, and constructing a food security evaluation dataset and a regional coordinated development level evaluation dataset specifically includes: Obtaining a regional coordinated development level evaluation instance dataset, extracting evaluation indicators related to food security and corresponding evaluation parameters from the regional coordinated development level evaluation instance dataset, calibrating the selected indicators as first screening indicators, and generating a primary screening indicator dataset; The primary screening indicator dataset is imported as input into the LASSO regression model for preliminary dimensionality reduction, the regularization strength parameter is preset, the L1 regularization constraint is used to impose a sparsity penalty on the regression coefficient, and the primary screening indicators with non-zero regression coefficients are screened to generate a secondary screening indicator dataset; The regularization strength parameter is obtained by dividing the initial screening index data set into several training subsets and validation subsets, constructing a preset logarithmic space using the validation subsets, traversing and calculating the regularization strength parameter in the preset logarithmic space, and selecting the regularization strength parameter with the smallest validation error as the optimal solution; A random forest algorithm is introduced to re-screen the secondary screening indicators, the secondary screening indicator set and the evaluation parameters corresponding to the secondary screening indicators are initialized as the initial input data of the algorithm, and an initial weight is set for each secondary screening indicator; The decision tree is constructed by generating an indicator feature set through the initial input data. A number of sample samples are obtained by probability sampling based on the preset initial weights. The hierarchical structure of the decision tree is constructed through the obtained sample samples and the Gini index is used as the basis for node segmentation. After the segmentation is completed, the random forest is output; After outputting the random forest, extract the out-of-bag samples of each tree, randomly perturb the random forest based on the extracted out-of-bag samples and calculate the error increment. After traversing all trees in the forest, obtain the error increment of the target indicator on all trees and take the average as the global importance score; Based on the global importance score of each indicator, an importance score ranking table is generated. The indicators within the preset range are output through the importance score ranking table as food security evaluation indicators and combined with the corresponding historical evaluation parameters to form a food security evaluation dataset.

[0008] In this solution, the method of screening food security evaluation indicators and regional coordinated development level evaluation indicators based on the regional coordinated development level evaluation example dataset, and constructing a food security evaluation dataset and a regional coordinated development level evaluation dataset, further includes: Obtaining a regional coordinated development level evaluation instance dataset, extracting evaluation indicators related to regional coordinated development from the regional coordinated development level evaluation instance dataset, and calibrating them as second screening evaluation indicators; The principal component analysis method is introduced to perform preliminary dimensionality reduction on the selected second screening evaluation index. The second screening evaluation index is used as input data to calculate the covariance matrix. The calculated covariance matrix is subjected to eigenvalue decomposition to obtain eigenvalues and corresponding eigenvectors, and several principal components are obtained. Sorting the principal components based on the eigenvalues of the principal components, selecting the principal components within a preset range as target principal components based on the sorting results, and obtaining a principal component index set; using the principal component index set as input, screening the independent principal component indices using the independent principal component analysis method; The input principal component index set is centralized, and the separation matrix is generated based on the initialization of the processed principal component index set. The orthogonal basis vectors of the principal component direction are used as the initial estimate to iteratively optimize the separation matrix. The final separation matrix is output through continuous iterative optimization analysis until the preset stopping criterion is reached. The independent principal component index is obtained by inverse transformation according to the final separation matrix, which is used as the evaluation index of the regional coordinated development level. The historical evaluation parameters of the corresponding indicators are obtained using the regional coordinated development level evaluation instance data set to form the regional coordinated development level evaluation data set.

[0009] In this plan, the evaluation index parameters of each region in the target area are collected to conduct food security forecasts and regional coordination evaluations, and a food reserve allocation plan is formulated and pushed, specifically including: Obtain a food security evaluation data set, introduce a Markov algorithm, and calculate the state transition probability of historical evaluation parameters corresponding to each food security evaluation indicator in the food security evaluation data set under different time series characteristics through the Markov algorithm; Constructing a food security prediction model based on a generative adversarial network, establishing a training dataset based on a food security evaluation dataset to train the food security prediction model, and introducing the calculated state transition probability into the model training process; When the training data set is input into the food security prediction model, the generator reconstructs the sequence according to the input training data sequence, and introduces the state transition probability in the reconstruction process to correct the reconstructed sequence; The discriminator’s discrimination rule is set based on the calculated state transition probability. The reconstructed sequence generated by the generator is input into the discriminator. If it meets the discrimination rule, the current reconstructed sequence is accepted and output. If it does not meet the discrimination rule, a reconstruction penalty is applied and the next reconstructed sequence is obtained for discrimination. Through repeated iterative learning, a food security prediction model that meets the preset verification standards is obtained. Based on the screened food security indicators, the evaluation index parameters of various regions in the target area are collected in real time and input into the trained food security prediction model to obtain food security prediction information.

[0010] In this plan, the evaluation index parameters of each region in the target area are collected to make food security forecasts and regional coordination evaluations, and a food reserve allocation plan is formulated and pushed. The plan also includes: Acquire a regional coordinated development level evaluation data set, and construct a regional coordinated development level evaluation system based on a regional coordinated development level evaluation indicator set and corresponding evaluation parameters in the regional coordinated development level evaluation data set; Monitor the target area to obtain the real-time parameters corresponding to the evaluation indicators of the coordinated development level of each region. Combined with the constructed regional coordinated development level evaluation system, analyze the regional coordination level of each region in the target area to obtain regional coordination level analysis information; Obtaining food security forecast information, importing the food security forecast information into a pre-trained Bayesian inference network to obtain a transient posterior distribution, and inferring the probability of a food reserve gap in each region within the target area based on the obtained transient posteriori to obtain gap probability inference information; The regional coordination degree analysis information is compared with a preset threshold, and areas within the target area where the regional coordination degree is less than the preset threshold are marked as risk areas, and areas where the regional coordination degree is greater than the preset threshold are marked as safe areas. The gap probability inference information is combined to generate a food reserve risk heat map; Using the regional geographic system, feasible paths within the target area and the geographical locations of risk areas and safe areas are calibrated in the food reserve risk heat map to generate a node topology map, wherein the safe area is calibrated as the starting node and the risk area is the ending node; The ant colony algorithm is introduced to formulate the food reserve allocation plan. The existence of three optimal paths at the end node is set as the node path optimization stop condition. The parameters are initialized in the node topology graph to obtain a virtual ant colony. The virtual ant colony is driven by the preset path selection probability to perform path optimization, and iterative updates are performed until the termination conditions are met to output the optimal food allocation path for each risk area. After a feasibility assessment, a food reserve allocation plan is generated.

[0011] The second aspect of the present invention provides a computer-readable storage medium, characterized in that the computer-readable storage medium includes a food security coordination optimization method program combined with regional coordinated development analysis. When the food security coordination optimization method program suitable for combining regional coordinated development analysis is executed by a processor, the steps of the food security coordination optimization method combined with regional coordinated development analysis as described in any one of the above items are implemented.

[0012] This invention discloses a food security coordination optimization method combined with regional coordinated development analysis. The method comprises the following steps: obtaining a number of different regional coordinated development level evaluation examples, classifying each of these examples into categories, and constructing a regional coordinated development level evaluation example dataset; selecting food security evaluation indicators and regional coordinated development level evaluation indicators based on the regional coordinated development level evaluation example dataset, and constructing a food security evaluation dataset and a regional coordinated development level evaluation dataset; collecting parameters for each evaluation indicator in each region of the target area, performing food security forecasting and regional coordination evaluation, and formulating and distributing a food reserve allocation plan. This method overcomes the limitations of traditional indicator screening and provides a scientific decision-making basis and guidance for regional food security. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions in the embodiments or exemplary embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or exemplary descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained according to these drawings without paying any creative work.

[0014] Figure 1 A flow chart of a food security coordination optimization method combined with regional coordinated development analysis provided by one embodiment of the present invention; Figure 2 A flow chart of a food security evaluation index screening method provided by one embodiment of the present invention; Figure 3 A flow chart of a method for screening regional coordinated development level evaluation indicators provided by one embodiment of the present invention; The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0015] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, in the absence of conflict, the embodiments of the present application and the features therein can be combined with each other.

[0016] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the scope of protection of the present invention is not limited to the specific embodiments disclosed below.

[0017] Figure 1 A flow chart of a food security coordination optimization method combined with regional coordinated development analysis provided by one embodiment of the present invention; like Figure 1 As shown, the present invention provides a flow chart of a food security coordination optimization method combined with regional coordinated development analysis, including: S102, obtaining a number of different regional coordinated development level evaluation instances, classifying the regional coordinated development level evaluation instances into categories, and constructing a regional coordinated development level evaluation instance dataset; S104, based on the regional coordinated development level evaluation instance dataset, respectively screening food security evaluation indicators and regional coordinated development level evaluation indicators, and constructing a food security evaluation dataset and a regional coordinated development level evaluation dataset; Furthermore, in a preferred embodiment of the present invention, obtaining a number of different regional coordinated development level evaluation examples, classifying the regional coordinated development level evaluation examples into categories, and constructing a regional coordinated development level evaluation example dataset specifically includes: Acquire a number of evaluation instances of coordinated development levels of different regions based on big data retrieval, wherein the obtained evaluation instances of coordinated development levels of different regions include relevant text descriptions and evaluation parameters of the evaluation of coordinated development levels of different regions; Extract relevant text descriptions of each evaluation instance from several different regional coordinated development level evaluation instances, import them into the pre-trained BERT model, and use the attention mechanism to obtain the global context embedding of different words in the relevant text descriptions; Build word vectors and keyword vectors based on the relevant text description of each evaluation instance, calculate the semantic relative distance between different word vectors and keyword vectors, and select words with a semantic relative distance less than a preset threshold as local context embeddings; The global context embedding and the local context embedding are concatenated to obtain semantic features. Based on the obtained semantic features, evaluation labels for the corresponding regional coordinated development evaluation instances are generated. The Euclidean distance algorithm is used to calculate the Euclidean distance between the evaluation labels. The calculated Euclidean distance value is compared with a preset Euclidean distance threshold, and regional coordinated development evaluation instances with a value greater than the preset Euclidean distance threshold are defined as the same category, thereby obtaining several evaluation instance categories; The dynamic time warping algorithm is used to align the evaluation parameters of each evaluation instance in the regional coordinated development level evaluation, and outliers are eliminated and missing values are supplemented. After completing data preprocessing, a regional coordinated development level evaluation instance dataset is constructed in combination with the divided evaluation instance categories.

[0018] It should be noted that we first integrate multi-source data (such as government work reports, academic literature, and statistical yearbooks) through web crawlers and API interfaces to collect evaluation case data covering different regions and years. Each case contains an unstructured text description (such as "A certain region achieved a balance between grain production and marketing through industrial chain collaboration") and structured evaluation parameters. After preprocessing the text description through sentence segmentation, stop word removal, and stemming, it is input into a pre-trained BERT model (such as bert-base-uncased). A multi-layer bidirectional Transformer encoder extracts a context-sensitive embedding vector for each word. The self-attention mechanism enables the model to capture long-range semantic dependencies. For example, in the sentence "The efficiency of fiscal transfer payments between major grain-producing and major grain-selling areas has significantly improved," the strength of the association between "fiscal transfer payments" and "efficiency" is quantified using attention weights. Subsequently, keywords (such as "industrial chain collaboration" and "ecological compensation") are extracted from the text based on the TF-IDF algorithm to construct keyword vectors. At the same time, word vectors are generated using Word2Vec or GloVe. The semantic distance between the word vector and the keyword vector is calculated through cosine similarity, and words with a similarity higher than the preset threshold are selected as local context embeddings. The global and local embedding vectors are spliced into fused semantic features after dimension alignment, and the input is mapped into evaluation labels (such as "high coordination" and "medium coordination") in the fully connected layer. The similarity between labels is calculated based on the Euclidean distance: if the distance between the label vectors of two instances exceeds the preset threshold, they are judged to be different categories, otherwise they are classified as the same category.

[0019] It should be noted that for structured evaluation parameters, a dynamic time warping (DTW) algorithm was used to align parameter sequences across different regions and time granularities (e.g., aligning quarterly data to an annual scale). Local stretching and compression were used to eliminate phase differences in the time series. Boxplots and KNN interpolation were then combined to remove outliers (e.g., data points exceeding three times the interquartile range) and fill in missing values (e.g., using the mean of the same indicator in adjacent regions). Finally, text-driven semantic category labels were integrated with preprocessed parameter sequences to construct a spatiotemporally aligned, multimodally integrated dataset for evaluating the level of regional coordinated development, providing high-quality input for subsequent indicator screening.

[0020] Furthermore, in a preferred embodiment of this solution, the evaluation index parameters of each region in the target area are collected to perform food security forecasts and regional coordination evaluations, and a food reserve allocation plan is formulated and pushed, specifically including: Obtain a food security evaluation data set, introduce a Markov algorithm, and calculate the state transition probability of historical evaluation parameters corresponding to each food security evaluation indicator in the food security evaluation data set under different time series characteristics through the Markov algorithm; Constructing a food security prediction model based on a generative adversarial network, establishing a training dataset based on a food security evaluation dataset to train the food security prediction model, and introducing the calculated state transition probability into the model training process; When the training data set is input into the food security prediction model, the generator reconstructs the sequence according to the input training data sequence, and introduces the state transition probability in the reconstruction process to correct the reconstructed sequence; The discriminator’s discrimination rule is set based on the calculated state transition probability. The reconstructed sequence generated by the generator is input into the discriminator. If it meets the discrimination rule, the current reconstructed sequence is accepted and output. If it does not meet the discrimination rule, a reconstruction penalty is applied and the next reconstructed sequence is obtained for discrimination. Through repeated iterative learning, a food security prediction model that meets the preset verification standards is obtained. Based on the screened food security indicators, the evaluation index parameters of various regions in the target area are collected in real time and input into the trained food security prediction model to obtain food security prediction information.

[0021] It should be noted that the first step is to obtain a food security evaluation data set, covering core indicators such as agricultural production conditions, resource and environmental carrying capacity, and market circulation efficiency. The Markov algorithm focuses on exploring the evolution of evaluation parameters in the time dimension, and quantifies the dynamic change patterns of each indicator at different time slices by constructing a state transition probability matrix. Specifically, the time series observations of each evaluation indicator are discretized into a finite state space, and the state transition probability between adjacent time steps is calculated using the maximum likelihood estimation method to form a random process model that reflects the inherent evolution mechanism of food security. This probability matrix not only characterizes the time series dependence characteristics of a single indicator, but also reveals the co-evolutionary relationship between multiple indicators through joint transition probability analysis. For example, the conditional transition probability between declining soil fertility and improved irrigation efficiency may affect the stability of food production capacity.

[0022] Subsequently, a food security prediction model was constructed based on a generative adversarial network, and state transition probabilities were deeply integrated into the training process. The input layer of the generator receives a standardized time-series training data sequence, and its hidden layer captures long-term dependency features through gated recurrent units. The Markov state transition matrix is introduced as a priori constraint during the sequence reconstruction stage. Specifically, in the calculation of the reconstruction value at each time step, a weighted correction is made based on the probability distribution of the previous state to ensure that the generated sequence conforms to both the data distribution characteristics and the statistical laws of state transitions. The discriminator uses a convolutional neural network to extract the local time series features of the sequence. Its discrimination rule sets a threshold condition based on the steady-state distribution theory of Markov chains: for the reconstructed sequence output by the generator, the cumulative probability value of its state transition path is calculated and compared with the state transition expectation obtained from historical statistics. If the path probability is lower than a preset confidence interval, a reconstruction penalty mechanism is triggered, forcing the generator to adjust its parameters and regenerate a sequence that better conforms to the Markov characteristics.

[0023] It is worth mentioning that the model training adopts an adversarial alternating optimization strategy. The generator improves the prediction accuracy by minimizing the joint loss function of reconstruction error and state transition deviation, while the discriminator dynamically adjusts the discrimination threshold to balance the authenticity and diversity of the generated sequence. During the iterative process, as the state transition probability matrix is continuously updated, the system gradually learns the nonlinear evolution law of food security indicators under the influence of complex factors. When the model reaches the preset performance indicators through cross-validation, the deployment phase collects dynamic monitoring data of the target area in real time, and inputs it into the model after feature processing with the same source as the training data. Based on the current observation sequence and state transition law, the generator predicts the evolution trajectory of indicators in the future time window. After probability verification by the discriminator, it outputs food security prediction results with confidence assessment, providing a quantitative basis for decision support.

[0024] Furthermore, in a preferred embodiment of this solution, the collection of evaluation index parameters of various regions in the target area, the food security forecast and regional coordination evaluation, and the formulation and delivery of a food reserve allocation plan also include: Acquire a regional coordinated development level evaluation data set, and construct a regional coordinated development level evaluation system based on a regional coordinated development level evaluation indicator set and corresponding evaluation parameters in the regional coordinated development level evaluation data set; Monitor the target area to obtain the real-time parameters corresponding to the evaluation indicators of the coordinated development level of each region. Combined with the constructed regional coordinated development level evaluation system, analyze the regional coordination level of each region in the target area to obtain regional coordination level analysis information; Obtaining food security forecast information, importing the food security forecast information into a pre-trained Bayesian inference network to obtain a transient posterior distribution, and inferring the probability of a food reserve gap in each region within the target area based on the obtained transient posteriori to obtain gap probability inference information; The regional coordination degree analysis information is compared with a preset threshold, and areas within the target area where the regional coordination degree is less than the preset threshold are marked as risk areas, and areas where the regional coordination degree is greater than the preset threshold are marked as safe areas. The gap probability inference information is combined to generate a food reserve risk heat map; Using the regional geographic system, feasible paths within the target area and the geographical locations of risk areas and safe areas are calibrated in the food reserve risk heat map to generate a node topology map, wherein the safe area is calibrated as the starting node and the risk area is the ending node; The ant colony algorithm is introduced to formulate the food reserve allocation plan. The existence of three optimal paths at the end node is set as the node path optimization stop condition. The parameters are initialized in the node topology graph to obtain a virtual ant colony. The virtual ant colony is driven by the preset path selection probability to perform path optimization, and iterative updates are performed until the termination conditions are met to output the optimal food allocation path for each risk area. After a feasibility assessment, a food reserve allocation plan is generated.

[0025] It should be noted that the method first obtains a regional coordinated development level evaluation dataset. A regional coordinated development level evaluation system is constructed based on the set of regional coordinated development level evaluation indicators and corresponding evaluation parameters in the dataset. Real-time parameters corresponding to each regional coordinated development level evaluation indicator are obtained. Combined with the constructed regional coordinated development level evaluation system, the degree of regional coordination within the target region is analyzed, resulting in regional coordination analysis information. Subsequently, food security forecast information is obtained and fed into a pre-trained Bayesian inference network to obtain a transient posterior distribution. Based on the obtained transient posterior, the probability of a food reserve gap in each region within the target region is inferred, resulting in inferred gap probability information. The pre-trained Bayesian network uses food production capacity volatility and consumption demand growth rate as parent nodes, and reserve storage turnover rate and cross-border transportation capacity as child nodes, forming a multi-layer network structure containing a conditional probability table. Once the real-time forecast data is input, the Markov Chain Monte Carlo (MCMC) sampling method is used to rapidly update the posterior distribution, and confidence intervals for the reserve gap probability are derived using KL divergence calculations. Regional coordination analysis information is compared with a preset threshold. Areas within the target region with a coordination level below the threshold are designated as risk areas, while areas with a coordination level above the threshold are designated as safe areas. This is combined with gap probability inference information to generate a food reserve risk heat map. Discrete risk points are spatially smoothed using kernel density estimation, and a gradient risk visualization layer is constructed using HSV color space mapping. A regional geographic system is used to map feasible paths within the target region and the geographic locations of risk and safe areas within the food reserve risk heat map to generate a node topology map, with designated safe areas as starting nodes and risk areas as ending nodes. This node topology map utilizes a multi-layered graph structure. In addition to the basic road network data, three special edge types are defined: emergency corridors (weighted based on historical disaster relief route data), potential alternative routes (based on accessibility analysis considering terrain undulation and bridge load capacity), and virtual connectors (for cross-regional coordination paths that transcend administrative boundaries).

[0026] Furthermore, an ant colony algorithm was introduced to develop food reserve allocation plans. A coordination attenuation factor was incorporated into the movement decisions of individual ants to modify path weights, thereby favoring transportation routes in areas with high coordination. After each iteration, non-inferior solutions were screened through Pareto front analysis. Termination conditions were triggered when each risk region obtained three candidate paths that met multiple objective constraints (minimum transportation cost, maximum path reliability, and optimal regional coordination impact). During the feasibility evaluation process, if a starting node is connected to more than a preset number of ending nodes, the feasibility of the plan is determined based on the predicted food reserves at the target starting node. The corresponding allocation volume is then calculated based on the target starting node's predicted food reserves. If not, the corresponding ending nodes are removed and the optimization process is re-optimized to obtain the final food reserve allocation plan.

[0027] Figure 2 A flow chart of a food security evaluation index screening method provided by one embodiment of the present invention; like Figure 2 As shown, the present invention provides a flow chart of a food security evaluation index screening method, comprising: S202, obtaining a regional coordinated development level evaluation instance dataset, extracting evaluation indicators and corresponding evaluation parameters related to food security from the regional coordinated development level evaluation instance dataset, calibrating the selected indicators as first screening indicators, and generating a primary screening indicator dataset; S204, importing the primary screening indicator dataset as input into the LASSO regression model for preliminary dimensionality reduction, presetting the regularization strength parameter, applying a sparsity penalty to the regression coefficient using the L1 regularization constraint, and screening the primary screening indicators with non-zero regression coefficients to generate a secondary screening indicator dataset; S206, wherein the regularization strength parameter is obtained by dividing the primary screening index dataset into a plurality of training subsets and validation subsets, constructing a preset logarithmic space using the validation subsets, traversing and calculating the regularization strength parameter in the preset logarithmic space, and selecting the regularization strength parameter with the smallest validation error as the optimal solution; S208, introducing a random forest algorithm to re-screen the secondary screening indicators, initializing the secondary screening indicator set and the evaluation parameters corresponding to the secondary screening indicators as initial input data of the algorithm and setting initial weights for each secondary screening indicator; S210, generating an indicator feature set based on the initial input data to construct a decision tree, performing probability sampling based on preset initial weights to obtain a number of sample samples, constructing a hierarchical structure of the decision tree based on the obtained sample samples, and using the Gini index as a basis for node segmentation. After the segmentation is completed, a random forest is output; S212, after outputting the random forest, extracting out-of-bag samples of each tree, performing random perturbations on the random forest based on the extracted out-of-bag samples and calculating the error increment, traversing all trees in the forest to obtain the error increments of the target indicator on all trees and taking the average as the global importance score; S214, generating an importance score ranking table based on the global importance score of each indicator, outputting indicators within a preset range through the importance score ranking table as food security evaluation indicators and combining them with corresponding historical evaluation parameters to form a food security evaluation data set.

[0028] It should be noted that during the indicator screening process for the regional coordinated development level evaluation dataset, evaluation indicators directly or indirectly related to food security (such as "grain reserve coverage rate," "grain logistics timeliness," and "arable land non-agriculturalization rate") were first extracted from the dataset and calibrated as a preliminary screening indicator set. These indicators were then associated with corresponding historical evaluation parameters (such as the annual value of reserve coverage rate and the monthly average of logistics timeliness), forming a preliminary screening dataset containing multidimensional indicators and spatiotemporal parameters. Subsequently, this dataset was input into the LASSO regression model for preliminary dimensionality reduction. By setting the regularization intensity parameter to control the sparsity of the model, a coordinate descent algorithm was used to solve the linear regression problem with L1 regularization constraints, compressing some regression coefficients to zero. This allowed the selection of non-zero coefficient indicators that significantly impacted the target variables of regional coordination (such as the "rural-urban income gap reduction rate").

[0029] To further optimize indicator importance, a random forest algorithm was introduced. This algorithm takes the secondary screening indicator set and its parameters as input and constructs a decision tree ensemble model. Each tree generates a training subset through bootstrap sampling, and the optimal split point is selected at the node splitting point, minimizing the Gini index. After model training, feature importance is calculated based on out-of-bag (OOB) samples. The values of the target indicator (e.g., "cultivated land quality") in the OOB samples of each tree are randomly perturbed (e.g., permutation or noise injection). The predictions are then re-calculated and the mean squared error increment is calculated. The mean squared error increment across all trees is then averaged as the global importance score. For example, the error increment for "grain reserve coverage" is 0.15 (high importance), while the error increment for "agricultural science and technology investment intensity" is only 0.03 (low importance). Finally, an indicator importance ranking table is generated. Core indicators, such as reserve coverage, logistics timeliness, cultivated land quality, total grain output, grain yield per unit area, and grain sown area, are selected based on preset thresholds (e.g., importance > 0.1). These indicators, combined with their historical parameters, are used to construct a food security assessment dataset. By quantitatively characterizing food production and circulation capacity, accurate and representative food evaluation indicators can be screened.

[0030] Figure 3 A flow chart of a method for screening regional coordinated development level evaluation indicators provided by one embodiment of the present invention; like Figure 3 As shown, the present invention provides a flow chart of a method for screening regional coordinated development level evaluation indicators, including: S302, obtaining a regional coordinated development level evaluation instance dataset, extracting evaluation indicators related to regional coordinated development from the regional coordinated development level evaluation instance dataset, and marking them as second screening evaluation indicators; S304, introducing a principal component analysis method to perform preliminary dimensionality reduction on the selected second screening evaluation index, using the second screening evaluation index as input data to calculate a covariance matrix, performing eigenvalue decomposition on the calculated covariance matrix to obtain eigenvalues and corresponding eigenvectors, and obtaining a number of principal components; S306, sorting the principal components based on the eigenvalues of the principal components, selecting the principal components within a preset range as target principal components based on the sorting results, and obtaining a principal component index set; using the principal component index set as input, performing independent principal component index screening using independent principal component analysis; S308, performing centralization processing on the input principal component index set, initializing and generating a separation matrix based on the processed principal component index set, and performing iterative optimization of the separation matrix using the orthogonal basis vectors of the principal component direction as initial estimates; S310, output the final separation matrix through continuous iterative optimization analysis until the preset stopping criterion is reached, perform inverse transformation on the final separation matrix to obtain independent principal component indicators as regional coordinated development level evaluation indicators, and use the regional coordinated development level evaluation instance data set to obtain historical evaluation parameters of corresponding indicators to form a regional coordinated development level evaluation data set.

[0031] It should be noted that the first step in the evaluation of regional coordinated development was to extract specific indicators from the example dataset, encompassing economic, social, environmental, and infrastructure dimensions. These indicators included the annual growth rate of regional gross domestic product (GDP), the added value of industrial enterprises above designated size, the per capita disposable income of urban residents, the ratio of per capita disposable income of rural residents, the annual average PM2.5 concentration reduction rate, the annual growth rate of railway freight volume, the night light index (NTL), and 5G base station coverage. These indicators were then calibrated as the second screening evaluation indicator set. Principal component analysis (PCA) was used to perform preliminary dimensionality reduction on the indicators: the covariance matrix was calculated for the standardized data, followed by eigenvalue decomposition of the covariance matrix to extract eigenvalues and eigenvectors. After sorting by eigenvalue, the top k principal components with a cumulative variance contribution of ≥85% were selected. For example, the eigenvalue of the first principal component is 8.2, which is composed of high-load indicators such as GDP growth rate, industrial added value, and night light index, reflecting economic activity; the eigenvalue of the second principal component is 5.1, which is dominated by the PM2.5 concentration decline rate and the intensity of ecological protection and development, and represents the level of environmental governance; the eigenvalue of the third principal component is 3.3, which is composed of the rural residents' income ratio and 5G base station coverage rate, reflecting the digital development of urban and rural areas.

[0032] Subsequently, the scores of the first three principal components were input into independent component analysis (ICA). The data was first centered (mean zero), and the separating matrix was initialized with random orthogonal basis vectors. The FastICA algorithm was used to maximize non-Gaussianity. The separating matrix was iteratively optimized until convergence, ultimately yielding statistically independent components. For example, the independent component "Economy-Energy Synergy" was driven by a nonlinear combination of "GDP Growth Rate" and "Nighttime Light Index." An inverse transformation was used to map the independent components back to the original indicator space. Specific indicators with absolute loadings > 0.6 were selected, ultimately retaining core indicators such as regional GDP growth rate, industrial added value above designated size, nighttime light index, and railway freight volume. Redundant indicators (e.g., "General Public Budget Revenue" was filtered out due to its strong correlation with GDP) were removed. A dataset for evaluating the level of regional coordinated development was constructed by combining historical parameters. This two-stage screening process, using PCA to extract common trends and ICA to analyze independent drivers, not only preserves the economic explanatory power of key indicators (e.g., the nighttime light index intuitively reflects the intensity of economic activity) but also highlights the independent influences of environmental and urban-rural dimensions, providing a high-information quantitative basis for the level of regional coordinated development.

[0033] Furthermore, in a preferred embodiment of the present invention, the association rules between food security evaluation indicators and regional coordinated development level evaluation indicators are analyzed, and a cross-dimensional association rule library is constructed, specifically including: Obtaining a food security evaluation dataset and a regional coordinated development level evaluation dataset, and discretizing historical evaluation parameters associated with food security evaluation indicators stored in the food security evaluation dataset into a number of food security states; Discretizing historical evaluation parameters associated with the regional coordinated development level evaluation indicators stored in the regional coordinated development level evaluation data set into a plurality of regional coordination states, and constructing a state combination transaction set by combining the discretized food security state and the regional coordination state; The state combination transaction set is used as input to perform cross-dimensional frequent item set mining using the Apriori algorithm, and the occurrence frequency of all single indicator states in the state combination transaction set is scanned and counted as the support of the corresponding indicator state; Select the indicator state greater than the preset minimum support to construct the initial frequent itemset, generate candidate frequent itemsets based on the initial frequent itemset, introduce time continuity constraints to optimize the candidate frequent itemset, eliminate candidates that do not meet the time continuity constraints, and output the final frequent itemset through repeated iterative mining and optimization; The final frequent item set is converted into a rule-instance matrix, each rule corresponds to a Boolean feature, and sparse principal component analysis is used to reduce the dimension of each rule-instance matrix to extract the principal component score representing the rule coordination pattern; Taking the principal component score as the input layer feature and the regional coordination status as the output layer feature, the radial basis function hidden layer is used to fit the nonlinear relationship between the rule cluster and the coordination level, and finally an asymmetric association rule data set is output. The final frequent item set is combined to construct a cross-dimensional association rule library.

[0034] It should be noted that first, the historical data of the two major evaluation systems of food security and regional coordinated development need to be integrated, and the continuous parameters in the food security evaluation data set (such as food reserve coverage rate, arable land quality index, etc.) need to be discretized and graded, and converted into three-level status labels of "high, medium, and low" according to industry standards or quantile division methods. At the same time, the evaluation parameters in the regional coordination data set (such as economic synergy index, ecological compensation compliance rate, etc.) are discretized into "excellent, good, and poor" levels according to policy target thresholds or historical distributions, forming a state combination transaction set containing spatiotemporal labels (year, regional code), and each transaction corresponds to a discrete state combination of each indicator under a specific spatiotemporal unit.

[0035] Subsequently, based on the state-combined transaction set, the Apriori algorithm was used to mine cross-dimensional frequent itemsets. In the first round, the transaction set was scanned and the support of a single indicator state was calculated (e.g., "high arable land quality" has an occurrence frequency of 18%). Initial frequent itemsets exceeding a preset minimum support were screened. Subsequently, candidate frequent itemsets were generated through layer-by-layer concatenation. A temporal continuity constraint was imposed, requiring the candidate itemsets to appear stably in at least three consecutive time windows. Cross-dimensional frequent itemsets were then output (e.g., "moderate reserve coverage - good emergency coordination" has a support of 0.18). The frequent itemsets were converted into a rule-instance matrix, where rows represent regional instances, columns correspond to rules, and elements are Boolean values (1 if a rule is satisfied, 0 otherwise). Sparse principal component analysis (SPCA) was used to reduce the dimensionality of the high-dimensional matrix and extract principal components with cumulative variance contributions ≥80%. Each principal component represents a class of rule-based coordination patterns. The principal component scores are input into a generalized regression neural network (GRNN), and radial basis function hidden layers are used to fit the nonlinear relationship between rule cluster strength and regional coordination status. This outputs asymmetric rules and their strengths (e.g., "When the production-distribution synergy cluster strength is greater than 0.7, the probability of achieving excellent coordination is 83%"). Ultimately, a cross-dimensional association rule library with spatiotemporal annotations is constructed, forming a closed loop from data discretization to nonlinear association modeling.

[0036] Furthermore, in a preferred embodiment of the present invention, a comprehensive evaluation model for regional coordination status is constructed through a cross-dimensional association rule base, specifically including: Obtain a cross-dimensional association rule library, define the food security indicator status as a first node and the regional coordination status as a second node, and establish a directed edge description according to a number of rules stored in the cross-dimensional association rule library to connect the first node and the second node to construct a food security status-regional coordination status topological structure diagram; Obtaining an adjacency matrix through the food security status-regional coordination status topological structure graph, constructing a comprehensive evaluation model of regional coordination status using a graph neural network, and training the model using the obtained adjacency matrix; When the output comprehensive evaluation results meet the preset standards, the trained regional coordination status comprehensive evaluation model is output.

[0037] It should be noted that all association rules for "food security indicator_status X → regional coordination indicator_status Y" were first extracted from the cross-dimensional association rule library. Each food security indicator status (e.g., "reserve coverage rate is fair") was defined as a first-class node in the topological graph, while the regional coordination indicator status (e.g., "emergency coordination is good") and its corresponding coordination score (e.g., 0.72) were defined as second-class nodes. Directed edge weights were constructed based on rule confidence. For example, the rule "high arable land quality → excellent ecological compensation" with a confidence of 0.82 and a causal strength of 0.75 would be transformed into a directed edge from the high arable land quality node to the excellent ecological compensation node. The edge weight was calculated jointly by the rule support and confidence. The adjacency matrix was generated by integrating the association rule weights between all nodes. If there is no direct rule connection between two nodes, the weight is zero, resulting in a sparse weighted adjacency matrix. For complex association rules (e.g., multi-indicator combination rules), virtual nodes were introduced to represent composite states, and temporal effects were addressed using edge weight decay factors. The final topological structure graph contains a dynamic adjacency matrix, the matrix elements are filled by the weighted values of the directed edges between nodes, and the weights between nodes that are not directly connected are set to 0.

[0038] Subsequently, a graph neural network was used to construct a comprehensive evaluation model for regional coordination status based on the adjacency matrix and node features (such as the historical frequency of food security status and the time-series mean of regional coordination scores). The input layer receives node feature vectors and aggregates information about neighboring nodes through multi-layer graph convolution operations. The hidden layer captures complex interactions using the nonlinear ReLU activation function, and the output layer maps the model to a comprehensive regional coordination score. During training, the true historical coordination scores serve as supervisory signals. A mean squared error (MSE) loss function combined with L1 regularization is used to prevent overfitting, and network parameters are optimized through backpropagation. During the model verification phase, the preset standards include the mean absolute error between the predicted score of the test set and the actual value, the causal strength retention rate of the key rule path (>85%), etc. When the model output meets the threshold, the trained GNN model and the topological structure visualization map are output to achieve end-to-end mapping from a single indicator state to a comprehensive score. For example, if the "cultivated land quality_high" state node is input, the model can output the score improvement prediction value along the path of "cultivated land quality_high→ecological compensation_excellent→regional coordination total score", providing an explainable path deduction for policy intervention and providing differentiated regulatory strategy guidance for different regions.

[0039] Furthermore, the present invention provides a method for food security coordination optimization combined with regional coordinated development analysis, further comprising: Based on the food security evaluation indicators, the food security-related data of the target area are obtained. The regional coordinated development-related data of the target area are obtained through the regional coordinated development level evaluation indicators, and are imported into the regional coordinated status comprehensive evaluation model for analysis as input; By inputting food security-related data into the model, a food security assessment is conducted on the target area to obtain a food security assessment result, and a food security assessment portrait of the target area is generated in combination with the food security-related data; Using cosine similarity as the basis for rule matching, cross-dimensional association rule matching is performed in the preset search space according to the food security evaluation portrait of the target area, and several matching cross-dimensional association rules are obtained; By matching cross-dimensional association rules, historical evaluation data of the regional coordinated development level of each cross-dimensional association rule is obtained, and the difference is calculated with the regional coordinated development related data of the target area to obtain the difference; The calculated difference is compared with the preset evaluation rules, and the evaluation results of the regional coordinated development level of the target area are output according to the judgment results. Combined with the food security evaluation results, comprehensive evaluation information of the regional coordination status is generated.

[0040] It should be noted that the comprehensive evaluation process for regional coordination status first collects historical and real-time data for the target region based on selected food security indicators (such as "grain reserve coverage rate," "arable land quality index," and "cold chain logistics timeliness"). (For example, in 2023, a region's reserve coverage rate was 75%, its arable land quality index was 0.82, and its average cold chain logistics timeliness was 24 hours.) Simultaneously, data corresponding to regional coordinated development indicators (such as "GDP growth rate," "nighttime light index," and "PM2.5 concentration reduction rate") are extracted (for example, GDP growth of 6.2%, an 8% year-over-year increase in the nighttime light index, and a 5% decrease in PM2.5 concentration). These two sets of data are then fed into a pre-trained comprehensive evaluation model for regional coordination status. The model calculates a food security score for the target region using the food security data and generates a multidimensional profile. Subsequently, cosine similarity matching is performed on the profile feature vectors within a cross-dimensional association rule library. Each rule in the rule library maps a combination of food security statuses to regional coordination statuses. Rules with similarity exceeding a threshold are selected as valid matching rules. The difference between historical regional coordination data associated with matching rules (e.g., the average GDP growth rate for the region corresponding to Rule A is 6.5%) and the current data for the target region (e.g., an actual GDP growth rate of 6.2%) is calculated. The degree of deviation from the coordination level is determined using pre-set evaluation rules (e.g., an absolute difference of <0.5% is considered satisfactory). If the difference exceeds a threshold, a flag is issued (e.g., "GDP growth rate does not meet association rule expectations"). Finally, the food security score, coordination deviation analysis, and rule matching conclusions are integrated to generate a comprehensive evaluation report (e.g., a "good" coordination rating indicates a need to improve GDP growth). This report highlights regional shortcomings, provides a quantitative basis for dynamic optimization, and offers guidance for coordinated regional development.

[0041] The present invention further provides a computer-readable storage medium, characterized in that the computer-readable storage medium includes a food security coordination optimization method program combined with regional coordinated development analysis. When the food security coordination optimization method program suitable for combining regional coordinated development analysis is executed by a processor, the steps of the food security coordination optimization method combined with regional coordinated development analysis as described in any one of the above items are implemented.

[0042] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0043] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed across multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0044] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0045] Those skilled in the art will appreciate that all or part of the steps of the above-mentioned method embodiments may be implemented by hardware associated with program instructions, and the aforementioned program may be stored in a computer-readable storage medium. When the program is executed, the program executes the steps of the above-mentioned method embodiments. The aforementioned storage medium includes various media that can store program codes, such as mobile storage devices, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0046] Alternatively, if the integrated units described above are implemented as software modules and sold or used as standalone products, they can also be stored on a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present invention, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product, stored on a storage medium, includes instructions for enabling a computer device (such as a personal computer, server, or network device) to execute all or part of the methods described in various embodiments of the present invention. The aforementioned storage media include various media capable of storing program code, such as removable storage devices, ROM, RAM, magnetic disks, or optical disks.

[0047] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A food security coordination optimization method combined with regional coordinated development analysis, characterized by: include: Obtain several different regional coordinated development level evaluation instances, classify the regional coordinated development level evaluation instances into categories, and construct a regional coordinated development level evaluation instance dataset; Based on the regional coordinated development level evaluation example dataset, food security evaluation indicators and regional coordinated development level evaluation indicators are respectively selected, and a food security evaluation dataset and a regional coordinated development level evaluation dataset are constructed; Based on the screened food security indicators and regional coordinated development level evaluation indicators, the evaluation indicator parameters of each region in the target area are collected to conduct food security forecasts and regional coordination evaluations, and a food reserve allocation plan is formulated and pushed.

2. A food security coordination optimization method combined with regional coordinated development analysis according to claim 1, characterized in that: The step of obtaining a number of different regional coordinated development level evaluation instances, classifying the regional coordinated development level evaluation instances into categories, and constructing a regional coordinated development level evaluation instance dataset specifically includes: Acquire a number of evaluation instances of coordinated development levels of different regions based on big data retrieval, wherein the obtained evaluation instances of coordinated development levels of different regions include relevant text descriptions and evaluation parameters of the evaluation of coordinated development levels of different regions; Extract relevant text descriptions of each evaluation instance from several different regional coordinated development level evaluation instances, import them into the pre-trained BERT model, and use the attention mechanism to obtain the global context embedding of different words in the relevant text descriptions; Build word vectors and keyword vectors based on the relevant text description of each evaluation instance, calculate the semantic relative distance between different word vectors and keyword vectors, and select words with a semantic relative distance less than a preset threshold as local context embeddings; The global context embedding and the local context embedding are concatenated to obtain semantic features. Based on the obtained semantic features, evaluation labels for the corresponding regional coordinated development evaluation instances are generated. The Euclidean distance algorithm is used to calculate the Euclidean distance between the evaluation labels. The calculated Euclidean distance value is compared with a preset Euclidean distance threshold, and regional coordinated development evaluation instances with a value greater than the preset Euclidean distance threshold are defined as the same category, thereby obtaining several evaluation instance categories; The dynamic time warping algorithm is used to align the evaluation parameters of each evaluation instance in the regional coordinated development level evaluation, and outliers are eliminated and missing values are supplemented. After completing data preprocessing, a regional coordinated development level evaluation instance dataset is constructed in combination with the divided evaluation instance categories.

3. The method for food security coordination optimization combined with regional coordinated development analysis according to claim 1 is characterized in that: The step of selecting food security evaluation indicators and regional coordinated development level evaluation indicators based on the regional coordinated development level evaluation example dataset, and constructing a food security evaluation dataset and a regional coordinated development level evaluation dataset, specifically includes: Obtaining a regional coordinated development level evaluation instance dataset, extracting evaluation indicators related to food security and corresponding evaluation parameters from the regional coordinated development level evaluation instance dataset, calibrating the selected indicators as first screening indicators, and generating a primary screening indicator dataset; The primary screening indicator dataset is imported as input into the LASSO regression model for preliminary dimensionality reduction, the regularization strength parameter is preset, the L1 regularization constraint is used to impose a sparsity penalty on the regression coefficient, and the primary screening indicators with non-zero regression coefficients are screened to generate a secondary screening indicator dataset; The regularization strength parameter is obtained by dividing the initial screening index data set into several training subsets and validation subsets, constructing a preset logarithmic space using the validation subsets, traversing and calculating the regularization strength parameter in the preset logarithmic space, and selecting the regularization strength parameter with the smallest validation error as the optimal solution; A random forest algorithm is introduced to re-screen the secondary screening indicators, the secondary screening indicator set and the evaluation parameters corresponding to the secondary screening indicators are initialized as the initial input data of the algorithm, and an initial weight is set for each secondary screening indicator; The decision tree is constructed by generating an indicator feature set through the initial input data. A number of sample samples are obtained by probability sampling based on the preset initial weights. The hierarchical structure of the decision tree is constructed through the obtained sample samples and the Gini index is used as the basis for node segmentation. After the segmentation is completed, the random forest is output; After outputting the random forest, extract the out-of-bag samples of each tree, randomly perturb the random forest based on the extracted out-of-bag samples and calculate the error increment. After traversing all trees in the forest, obtain the error increment of the target indicator on all trees and take the average as the global importance score; Based on the global importance score of each indicator, an importance score ranking table is generated. The indicators within the preset range are output through the importance score ranking table as food security evaluation indicators and combined with the corresponding historical evaluation parameters to form a food security evaluation dataset.

4. The method for food security coordination optimization combined with regional coordinated development analysis according to claim 1 is characterized in that: The method of screening food security evaluation indicators and regional coordinated development level evaluation indicators based on the regional coordinated development level evaluation example dataset, and constructing a food security evaluation dataset and a regional coordinated development level evaluation dataset, further includes: Obtaining a regional coordinated development level evaluation instance dataset, extracting evaluation indicators related to regional coordinated development from the regional coordinated development level evaluation instance dataset, and calibrating them as second screening evaluation indicators; The principal component analysis method is introduced to perform preliminary dimensionality reduction on the selected second screening evaluation index. The second screening evaluation index is used as input data to calculate the covariance matrix. The calculated covariance matrix is subjected to eigenvalue decomposition to obtain eigenvalues and corresponding eigenvectors, and several principal components are obtained. Sorting the principal components based on the eigenvalues of the principal components, selecting the principal components within a preset range as target principal components based on the sorting results, and obtaining a principal component index set; using the principal component index set as input, screening the independent principal component indices using the independent principal component analysis method; The input principal component index set is centralized, and the separation matrix is generated based on the initialization of the processed principal component index set. The orthogonal basis vectors of the principal component direction are used as the initial estimate to iteratively optimize the separation matrix. The final separation matrix is output through continuous iterative optimization analysis until the preset stopping criterion is reached. The independent principal component index is obtained by inverse transformation according to the final separation matrix, which is used as the evaluation index of the regional coordinated development level. The historical evaluation parameters of the corresponding indicators are obtained using the regional coordinated development level evaluation instance data set to form the regional coordinated development level evaluation data set.

5. The method for food security coordination optimization combined with regional coordinated development analysis according to claim 1 is characterized in that: The aforementioned collection of evaluation index parameters for each region in the target area, the conduct of food security forecasts and regional coordination evaluations, and the formulation and delivery of food reserve allocation plans specifically include: Obtain a food security evaluation data set, introduce a Markov algorithm, and calculate the state transition probability of historical evaluation parameters corresponding to each food security evaluation indicator in the food security evaluation data set under different time series characteristics through the Markov algorithm; Constructing a food security prediction model based on a generative adversarial network, establishing a training dataset based on a food security evaluation dataset to train the food security prediction model, and introducing the calculated state transition probability into the model training process; When the training data set is input into the food security prediction model, the generator reconstructs the sequence according to the input training data sequence, and introduces the state transition probability in the reconstruction process to correct the reconstructed sequence; The discriminator’s discrimination rule is set based on the calculated state transition probability. The reconstructed sequence generated by the generator is input into the discriminator. If it meets the discrimination rule, the current reconstructed sequence is accepted and output. If it does not meet the discrimination rule, a reconstruction penalty is applied and the next reconstructed sequence is obtained for discrimination. Through repeated iterative learning, a food security prediction model that meets the preset verification standards is obtained. Based on the screened food security indicators, the evaluation index parameters of various regions in the target area are collected in real time and input into the trained food security prediction model to obtain food security prediction information.

6. The method for food security coordination optimization combined with regional coordinated development analysis according to claim 1 is characterized in that: The aforementioned collection of evaluation index parameters of various regions in the target area, conducting food security forecasts and regional coordination evaluations, and formulating and delivering food reserve allocation plans also includes: Acquire a regional coordinated development level evaluation data set, and construct a regional coordinated development level evaluation system based on a regional coordinated development level evaluation indicator set and corresponding evaluation parameters in the regional coordinated development level evaluation data set; Monitor the target area to obtain the real-time parameters corresponding to the evaluation indicators of the coordinated development level of each region. Combined with the constructed regional coordinated development level evaluation system, analyze the regional coordination level of each region in the target area to obtain regional coordination level analysis information; Obtaining food security forecast information, importing the food security forecast information into a pre-trained Bayesian inference network to obtain a transient posterior distribution, and inferring the probability of a food reserve gap in each region within the target area based on the obtained transient posteriori to obtain gap probability inference information; The regional coordination degree analysis information is compared with a preset threshold, and areas within the target area where the regional coordination degree is less than the preset threshold are marked as risk areas, and areas where the regional coordination degree is greater than the preset threshold are marked as safe areas. The gap probability inference information is combined to generate a food reserve risk heat map; Using the regional geographic system, feasible paths within the target area and the geographical locations of risk areas and safe areas are calibrated in the food reserve risk heat map to generate a node topology map, wherein the safe area is calibrated as the starting node and the risk area is the ending node; The ant colony algorithm is introduced to formulate the food reserve allocation plan. The existence of three optimal paths at the end node is set as the node path optimization stop condition. The parameters are initialized in the node topology graph to obtain a virtual ant colony. The virtual ant colony is driven by the preset path selection probability to perform path optimization, and iterative updates are performed until the termination conditions are met to output the optimal food allocation path for each risk area. After a feasibility assessment, a food reserve allocation plan is generated.

7. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a food security coordination optimization method program combined with regional coordinated development analysis. When the food security coordination optimization method program suitable for combining regional coordinated development analysis is executed by a processor, the steps of the food security coordination optimization method combined with regional coordinated development analysis as described in any one of claims 1 to 6 are implemented.

Images