Grain safety influence analysis method and system based on regional development level

Abstract

The invention discloses a grain safety influence analysis method and system based on a regional development level, and the method comprises the steps: obtaining related influence factors of the regional development level based on big data retrieval, carrying out the screening of the influence factors and the selection of evaluation indexes, carrying out the weighting through combining with an expert weighting method and an equal-weight method, and constructing a regional development level evaluation model; evaluating the regional development level of the target region by using a regional development level evaluation model, analyzing the relationship between the grain safety of the target region and the regional development level, and judging the influence mechanism of the regional development level on the grain safety degree by using an intermediary utility model; the method comprises the steps of obtaining a plurality of historical regional development examples of different grain safety degrees, constructing a regional grain safety development prediction model, predicting the grain safety development condition of a target region under a current development strategy, judging whether a grain safety risk exists or not, and formulating a regional development optimization strategy, thereby promoting regional coordinated development and guaranteeing grain safety.

Description

Technical Field

[0001] The present invention relates to the technical field of food security impact analysis, and in particular to a food security impact analysis method and system based on regional development level. Background Art

[0002] "Food security is a national priority, and ensuring food security is an eternal issue. However, as my country's natural resource and environmental constraints become increasingly tight, the upgrading of residents' food consumption structure has led to a continuous increase in food demand, and the tight balance between food supply and demand will exist for a long time. Research on food security issues cannot be relaxed in the slightest. At the same time, my country has a vast territory and a large population, and the differences in natural resource endowments in various regions are rare in the world. Coordinating regional development has always been a major issue. At the same time, the relationship between the level of regional coordinated development and food security has received little attention in existing research. How to identify the relationship between the two, as well as their effects and mechanisms of action, so as to better promote regional coordinated development and provide references and suggestions for ensuring national food security is an important issue. Summary of the invention

[0003] The present invention overcomes the defects of the prior art and provides a food security impact analysis method and system based on regional development level, the important purpose of which is to promote regional coordinated development and ensure national food security.

[0004] To achieve the above objectives, the present invention provides a food security impact analysis method based on regional development level in a first aspect, comprising: Based on big data retrieval, relevant influencing factors of regional development level are obtained, influencing factors are screened and evaluation indicators are selected, and weighting is performed by combining expert weighting method and equal weighting method to construct a regional development level evaluation model; The regional development level evaluation model is used to evaluate the regional development level of the target area, the relationship between the food security of the target area and the regional development level is analyzed, and the mediating utility model is used to determine the impact mechanism of the regional development level on the degree of food security; Obtain several historical regional development examples with different levels of food security, build a regional food security development prediction model, predict the food security development status of the target area under the current development strategy, determine whether there is a food security risk and formulate a regional development optimization strategy.

[0005] In this plan, the influencing factors related to regional development level are obtained based on big data retrieval, and the influencing factors are screened and the evaluation indicators are selected, which specifically include: Based on big data retrieval, the influencing factors related to the regional development level are obtained to form an influencing factor data set, and the parallel coordinate method is introduced to map the influencing factor data set to parallel coordinates to obtain an influencing factor coordinate map; Each data axis in the influencing factor coordinate diagram corresponds to a specific dimensional range and influencing factor type, and the influencing factor diagram is subjected to dimensionality reduction processing by principal component analysis to calculate the principal component score corresponding to each influencing factor; The calculated principal component score is compared with a preset threshold, and the influencing factor corresponding to the principal component score greater than the preset threshold is taken as the principal component factor, and the principal component factor is used to perform principal component direction projection to obtain a scatter plot of the influencing factor; A preset selection range is set, and corresponding influencing factors are selected according to the preset selection range in the influencing factor scatter diagram as candidate evaluation indicators to generate a candidate evaluation indicator data set.

[0006] In this plan, the influencing factors screening and evaluation index selection are carried out, and the expert weighting method and the equal weighting method are combined to carry out weighting to construct a regional development level evaluation model, which specifically includes: Obtain a candidate evaluation indicator data set, calculate the Euclidean distance between each evaluation indicator in the candidate evaluation indicator data set, form a distance matrix, convert the distance matrix into an adjacency matrix using a Gaussian kernel function and calculate a vertex matrix; Subtracting the vertex matrix from the adjacency matrix to obtain a Laplace matrix, performing eigendecomposition on the Laplace matrix to obtain eigenvalues ​​and corresponding eigenvectors, presetting a number of cluster centers and selecting a corresponding number of minimum non-zero eigenvalues ​​and eigenvectors, using the selected eigenvectors as new data representations, and constructing an eigenvector space; Introducing a spectral clustering algorithm to perform multiple clustering in the feature vector space, classifying each evaluation indicator in the candidate evaluation indicator data set into categories, and obtaining a number of clustering clusters; Calculate the Pearson correlation coefficient between the evaluation indicators in the clustering clusters to characterize the correlation between the evaluation indicators, and generate a ranking table corresponding to each clustering cluster based on the Pearson correlation coefficient of each evaluation indicator; The evaluation index level is set through the ranking table corresponding to each cluster, and the evaluation indicators of each level under the same cluster are associated according to the level to generate the final evaluation index data set; Based on the final evaluation indicator data set, an importance score of each evaluation indicator is obtained by an expert weighting method, a scoring matrix is ​​constructed, the constructed scoring matrix is ​​normalized, and the expert weight of each evaluation indicator is obtained according to the normalized scoring matrix to obtain first weight information; Perform secondary weight allocation for each evaluation indicator by an equal weight method to obtain second weight information, preset a weighting ratio, and perform comprehensive weight allocation for each evaluation indicator in combination with the first weight information and the second weight information to obtain comprehensive weight allocation information; A regional development level evaluation system is constructed based on the final evaluation indicator data set and the comprehensive weight distribution information, and a regional development level evaluation model is constructed based on the constructed regional development level evaluation system.

[0007] In this plan, the regional development level evaluation model is used to evaluate the regional development level of the target area, analyze the relationship between the food security of the target area and the regional development level, and use the mediating utility model to determine the impact mechanism of the regional development level on the degree of food security, which specifically includes: Acquire regional development monitoring information of the target area within a unit time based on big data retrieval, perform data preprocessing on the regional development monitoring information, and obtain preprocessing result information; Acquire a regional development level evaluation model, input the preprocessing result information into the regional development level evaluation model, evaluate the regional development level of the target area per unit time, and obtain regional development level assessment information; Preset food security assessment indicators and assign weights, build a food security assessment system, use the regional development monitoring information to extract food development data per unit time in the target area, conduct regional food security assessment, and obtain food security assessment information; Based on the regional development level assessment information and the food security assessment information, a multi-source linear regression equation is used to analyze the direct impact of the regional coordinated development level of the target area on food security, thereby obtaining first analysis information; Define mediating variables based on regional development level assessment indicators, and construct a regression path equation between regional coordinated development level and food security level, taking regional coordinated development level as the independent variable and food security level as the dependent variable; Based on the regional development level assessment information, food security assessment information and the first analysis information, the mediating effect model is used to analyze the impact mechanism of the regional development level of the target area on the degree of food security, and the impact mechanism analysis information is obtained.

[0008] In this scheme, the acquisition of several historical regional development examples with different food security levels and the construction of a regional food security development prediction model specifically include: Based on data retrieval, several historical regional development examples with different food security levels are obtained, and features of the historical regional development examples are extracted to extract food security features and regional development strategy features corresponding to each historical regional development example to obtain first feature information; Preset time period, constructing a time series feature sequence of each historical regional development instance according to the first feature information in units of the preset time period; Obtaining impact mechanism analysis information, constructing an impact path between regional development strategy and food security level based on the impact mechanism analysis information, and constructing a feature profile of each historical regional development instance in combination with the temporal feature sequence of each historical regional development instance; The characteristic portrait of each historical regional development instance is a representation of the degree of food security when the corresponding historical development instance is developed in the region, and the cosine similarity between the characteristic portraits of each historical regional development instance is calculated using a cosine measurement algorithm; According to the calculated cosine similarity, a connection path between the characteristic portraits of each historical regional development instance is established and the corresponding similarity is used as an auxiliary feature of the connection path to construct a first database; Using a stacked autoencoder to perform feature encoding and reconstruction on the feature portraits and contact paths stored in the first database, and using the corresponding cosine similarity as a weight to weight the importance, thereby obtaining encoding and reconstruction features; The encoded reconstruction features are imported into the BiGRU network for learning and a regional food security development prediction model is constructed. The temporal dependency of the reconstructed feature sequence is captured through the BiGRU network, and the regional food security development prediction results are output using the fully connected layer.

[0009] In this plan, the food security development status of the target area under the current development strategy is predicted, whether there is a food security risk and the regional development optimization strategy is formulated, including: Acquire regional development monitoring information, generate a regional development feature sequence of the target region at the current moment according to the regional development monitoring information, input it into a regional food security development prediction model for analysis, and obtain regional food security development prediction information; Generate a regional food security development forecast sequence with a preset time period as an interval according to the regional food security development forecast information, and extract the forecast characteristics of the food security development degree within each sequence interval; The predicted characteristics of the food security development degree of each sequence interval extracted are compared with the preset risk threshold, and the sequence area less than the preset threshold is defined as the risk sequence interval. The time node of the occurrence of food security risk is determined through the risk sequence interval to obtain food security risk analysis information; If the target area has food security risks in the future period under the current regional development strategy, then the regional development strategy optimization analysis is performed based on the food security risk analysis information; Obtain regional development level assessment information and food security assessment information, and build a regional development representation portrait of the target area based on the regional development feature sequence of the target area at the current moment; Matching and analyzing the regional development representation portrait of the target area with the characteristic portraits of each regional development instance stored in the first database, obtaining matching instances, performing food security evaluation on each matching instance, and screening matching instances that meet preset standards; Calculate the difference between the time point when the food security risk occurs and the current time according to the food security risk analysis information, use it as the optimization time limit, extract the regional development time characteristics of the selected matching instances and sort them; Through the optimization time limit, several matching instances that are shorter than the optimization time limit are selected and the corresponding regional development strategy features are extracted to conduct a feasibility analysis, and a regional development optimization strategy is generated and pushed according to the feasibility analysis results.

[0010] A second aspect of the present invention provides a food security impact analysis system based on regional development level, the system comprising: a memory, a processor, the memory containing a food security impact analysis method program based on regional development level, the food security impact analysis method program based on regional development level when executed by the processor implements the following steps: Based on big data retrieval, relevant influencing factors of regional development level are obtained, influencing factors are screened and evaluation indicators are selected, and weighting is performed by combining expert weighting method and equal weighting method to construct a regional development level evaluation model; The regional development level evaluation model is used to evaluate the regional development level of the target area, the relationship between the food security of the target area and the regional development level is analyzed, and the mediating utility model is used to determine the impact mechanism of the regional development level on the degree of food security; Obtain several historical regional development examples with different levels of food security, build a regional food security development prediction model, predict the food security development status of the target area under the current development strategy, determine whether there is a food security risk and formulate a regional development optimization strategy.

[0011] The present invention discloses a method and system for analyzing the impact of food security based on regional development level, including: obtaining influencing factors related to regional development level based on big data retrieval, screening influencing factors and selecting evaluation indicators, and weighting in combination with expert weighting method and equal weighting method to construct a regional development level evaluation model; using the regional development level evaluation model to evaluate the regional development level of a target area, analyzing the relationship between the food security of the target area and the regional development level, and using an intermediary utility model to judge the impact mechanism of the regional development level on the degree of food security; obtaining a number of historical regional development examples with different degrees of food security, constructing a regional food security development prediction model, predicting the food security development status of the target area under the current development strategy, judging whether there is a food security risk and formulating a regional development optimization strategy, so as to promote regional coordinated development and ensure food security. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments or exemplary embodiments of the present invention, the drawings required for use in the embodiments or exemplary descriptions will be briefly introduced below. 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 the drawings without paying creative work.

[0013] Figure 1 A flow chart of a food security impact analysis method based on regional development level provided by one embodiment of the present invention; Figure 2 A flow chart of a regional food security analysis method provided by one embodiment of the present invention; Figure 3 A block diagram of a food security impact analysis system based on regional development level provided by an embodiment of the present invention; The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0014] In order to more clearly understand the above-mentioned purpose, 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 the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0015] 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 protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0016] Figure 1 A flow chart of a food security impact analysis method based on regional development level provided by one embodiment of the present invention; like Figure 1 As shown, the present invention provides a flow chart of a food security impact analysis method based on regional development level, including: S102, based on big data retrieval, obtain the influencing factors related to the regional development level, screen the influencing factors and select the evaluation indicators, and combine the expert weighting method and the equal weighting method to assign weights and build a regional development level evaluation model; S104, using the regional development level evaluation model to evaluate the regional development level of the target area, analyzing the relationship between food security and regional development level in the target area, and using the mediating utility model to determine the impact mechanism of regional development level on food security; S106, obtain several historical regional development examples with different levels of food security, construct a regional food security development prediction model, predict the food security development status of the target region under the current development strategy, determine whether there is a food security risk and formulate a regional development optimization strategy.

[0017] It should be noted that the present invention provides a method and system for analyzing the impact of regional development level on food security. First, the influencing factors related to the regional development level are extracted from a large amount of regional related data based on a big data retrieval method. Next, the weights are allocated by two weighting methods, the expert weighting method and the equal weighting method, so as to ensure that each indicator has a reasonable influence in the evaluation process, and then a regional development level evaluation model is constructed. After the development level of the target area is evaluated by the model, the relationship between the regional development level and food security is further analyzed. The study is conducted through the mediating utility model to explore how the regional development level affects food security, thereby revealing the potential mechanism affecting food security. Subsequently, several historical regional development examples with different food security levels are obtained to establish a regional food security development prediction model. The prediction model is used to evaluate the food security development trend of the target area under the current development strategy, and further determine whether there is a food security risk. If the risk exists, an optimization strategy will be proposed based on the analysis results, aiming to improve the food security level and avoid potential food security crises by adjusting the regional development policy or development strategy. By understanding the impact mechanism of the regional development level on food security, decision support is provided for the formulation of future regional development and food security policies.

[0018] Furthermore, in a preferred embodiment of the present invention, the acquisition of influencing factors related to regional development level based on big data retrieval, screening of influencing factors and selection of evaluation indicators specifically include: Based on big data retrieval, the influencing factors related to the regional development level are obtained to form an influencing factor data set, and the parallel coordinate method is introduced to map the influencing factor data set to parallel coordinates to obtain an influencing factor coordinate map; Each data axis in the influencing factor coordinate diagram corresponds to a specific dimensional range and influencing factor type, and the influencing factor diagram is subjected to dimensionality reduction processing by principal component analysis to calculate the principal component score corresponding to each influencing factor; The calculated principal component score is compared with a preset threshold, and the influencing factor corresponding to the principal component score greater than the preset threshold is taken as the principal component factor, and the principal component factor is used to perform principal component direction projection to obtain a scatter plot of the influencing factor; A preset selection range is set, and corresponding influencing factors are selected according to the preset selection range in the influencing factor scatter diagram as candidate evaluation indicators to generate a candidate evaluation indicator data set.

[0019] It should be noted that, firstly, through big data retrieval, the influencing factor data set related to the regional development level is collected and constructed. The parallel coordinate method is used to map these influencing factor data into the parallel coordinate system to obtain the coordinate diagram of the influencing factors. Each coordinate axis represents an influencing factor, and each data axis corresponds to a specific dimensional range and influencing factor type, thus forming a multi-dimensional influencing factor diagram. Next, in order to reduce the dimension of the data and improve the efficiency of analysis, the principal component analysis (PCA) method is used to reduce the dimension of the influencing factor coordinate diagram. Through principal component analysis, the principal component score corresponding to each influencing factor is calculated, and these scores represent the contribution and correlation of different influencing factors in the entire data set. The calculated principal component score is compared with the preset threshold. If the score is greater than the preset threshold, it is considered that the influencing factor has a greater impact on the regional development level, and then the influencing factors corresponding to these principal component scores are regarded as the main influencing factors. On this basis, these main influencing factors are used to project the principal component direction, so as to obtain a scatter plot reflecting the relationship between the influencing factors. The scatter plot shows the distribution of each influencing factor in the principal component space, which helps to further understand the relationship between different influencing factors. Next, according to the preset selection range, qualified influencing factors are selected from the scatter plot as candidate evaluation indicators, and then a candidate evaluation indicator data set is constructed to provide basic data for the subsequent regional development level evaluation. The key influencing factors are effectively extracted, and the data structure is simplified through dimensionality reduction and visualization to help determine the most representative evaluation indicators.

[0020] Furthermore, in a preferred embodiment of the present invention, the screening of influencing factors and the selection of evaluation indicators are performed, and weighting is performed in combination with the expert weighting method and the equal weighting method to construct a regional development level evaluation model, which specifically includes: Obtain a candidate evaluation indicator data set, calculate the Euclidean distance between each evaluation indicator in the candidate evaluation indicator data set, form a distance matrix, convert the distance matrix into an adjacency matrix using a Gaussian kernel function and calculate a vertex matrix; Subtracting the vertex matrix from the adjacency matrix to obtain a Laplace matrix, performing eigendecomposition on the Laplace matrix to obtain eigenvalues ​​and corresponding eigenvectors, presetting a number of cluster centers and selecting a corresponding number of minimum non-zero eigenvalues ​​and eigenvectors, using the selected eigenvectors as new data representations, and constructing an eigenvector space; Introducing a spectral clustering algorithm to perform multiple clustering in the feature vector space, classifying each evaluation indicator in the candidate evaluation indicator data set into categories, and obtaining a number of clustering clusters; Calculate the Pearson correlation coefficient between the evaluation indicators in the clustering clusters to characterize the correlation between the evaluation indicators, and generate a ranking table corresponding to each clustering cluster based on the Pearson correlation coefficient of each evaluation indicator; The evaluation index level is set through the ranking table corresponding to each cluster, and the evaluation indicators of each level under the same cluster are associated according to the level to generate the final evaluation index data set; Based on the final evaluation indicator data set, an importance score of each evaluation indicator is obtained by an expert weighting method, a scoring matrix is ​​constructed, the constructed scoring matrix is ​​normalized, and the expert weight of each evaluation indicator is obtained according to the normalized scoring matrix to obtain first weight information; Perform secondary weight allocation for each evaluation indicator by an equal weight method to obtain second weight information, preset a weighting ratio, and perform comprehensive weight allocation for each evaluation indicator in combination with the first weight information and the second weight information to obtain comprehensive weight allocation information; A regional development level evaluation system is constructed based on the final evaluation indicator data set and the comprehensive weight distribution information, and a regional development level evaluation model is constructed based on the constructed regional development level evaluation system.

[0021] It should be noted that, first, the candidate evaluation indicator data set is obtained, the Euclidean distance between each evaluation indicator is calculated, thereby forming a distance matrix, the distance matrix is ​​converted into an adjacency matrix by a Gaussian kernel function, and then the vertex matrix is ​​calculated. The Laplace matrix is ​​obtained by subtracting the adjacency matrix from the vertex matrix, and the eigendecomposition of the Laplace matrix can extract the eigenvalue and the corresponding eigenvector. According to the preset number of cluster centers, the minimum non-zero eigenvalue and eigenvector corresponding to the number are selected as a new data representation to construct an eigenvector space. After obtaining the eigenvector space, the spectral clustering algorithm is used to cluster the data multiple times, and the evaluation indicators in the candidate evaluation indicator data set are divided into several cluster clusters. In order to better understand the relationship between the evaluation indicators in each cluster, the Pearson correlation coefficient between the evaluation indicators in the cluster cluster is calculated to characterize the degree of correlation between the evaluation indicators. Based on these Pearson correlation coefficients, the various clusters are sorted, and a sorting table corresponding to each cluster cluster is generated. The evaluation indicators in each cluster are set to a level through the sorting table, and the evaluation indicators under the same cluster are associated according to these levels, thereby generating the final evaluation indicator data set. Next, based on the final evaluation indicator data set, an importance score is assigned to each evaluation indicator through the expert weighting method, and then a scoring matrix is ​​constructed. After the scoring matrix is ​​normalized, the expert weight of each evaluation indicator can be obtained according to the normalized scoring matrix to obtain the weight information of the first stage. Then, the equal weight method is used to perform secondary weight distribution on each evaluation indicator to obtain the weight information of the second stage. Through the preset weighting ratio, the expert weight of the first stage is combined with the equal weight of the second stage to obtain the comprehensive weight distribution information of each evaluation indicator. Finally, based on these comprehensive weight distribution information and the evaluation indicator data set, a regional development level evaluation system is constructed, and based on this evaluation system, a regional development level evaluation model is established. Through scientific weight distribution and cluster analysis methods, the regional development level can be accurately evaluated and analyzed, providing effective support for regional development decision-making.

[0022] Further, in a preferred embodiment of the present invention, the regional development level of the target area is evaluated by using the regional development level evaluation model, the relationship between the food security of the target area and the regional development level is analyzed, and the mechanism of the influence of the regional development level on the degree of food security is determined by using the intermediary utility model, which specifically includes: Acquire regional development monitoring information of the target area within a unit time based on big data retrieval, perform data preprocessing on the regional development monitoring information, and obtain preprocessing result information; Acquire a regional development level evaluation model, input the preprocessing result information into the regional development level evaluation model, evaluate the regional development level of the target area per unit time, and obtain regional development level assessment information; Preset food security assessment indicators and assign weights, build a food security assessment system, use the regional development monitoring information to extract food development data per unit time in the target area, conduct regional food security assessment, and obtain food security assessment information; Based on the regional development level assessment information and the food security assessment information, a multi-source linear regression equation is used to analyze the direct impact of the regional coordinated development level of the target area on food security, thereby obtaining first analysis information; Define mediating variables based on regional development level assessment indicators, and construct a regression path equation between regional coordinated development level and food security level, taking regional coordinated development level as the independent variable and food security level as the dependent variable; Based on the regional development level assessment information, food security assessment information and the first analysis information, the mediating effect model is used to analyze the impact mechanism of the regional development level of the target area on the degree of food security, and the impact mechanism analysis information is obtained.

[0023] It should be noted that, firstly, the regional development monitoring information of the target area per unit time is obtained through big data retrieval. These monitoring information include economic, social, environmental and other data. After data preprocessing, the cleaned and standardized preprocessing result information is obtained to ensure the accuracy and consistency of the data. Next, the existing regional development level evaluation model is used to input the preprocessed data into the model to evaluate the regional development level. The model can calculate the regional development level of the target area per unit time and generate regional development level evaluation information. Subsequently, the food security evaluation indicators are preset, and these indicators are weighted to construct a food security evaluation system. By analyzing the regional development monitoring information, the food development data of the target area per unit time are extracted, and these data are used to evaluate the regional food security, obtain the food security evaluation information, and quantify the food security status of the target area. Based on the regional development level evaluation information and the food security evaluation information, the multi-source linear regression equation is used to analyze the direct impact of the regional coordinated development level of the target area on food security. Through regression analysis, the first analytical information of the regional development level on food security is obtained, revealing how the regional coordinated development level directly affects food security. Furthermore, mediating variables are defined based on the regional development level assessment indicators, and a regression path equation is constructed, with the regional coordinated development level as the independent variable and the degree of food security as the dependent variable. Combining the regional development level assessment information, food security assessment information and the first analysis information, the mediating effect model is used to deeply analyze the mechanism of how the regional development level affects food security through the mediating variables. This analysis result can reveal the complex impact path between the regional coordinated development level and food security, and obtain detailed impact mechanism analysis information, which is helpful to formulate more effective regional development and food security policies.

[0024] It should be noted that the mediating variables can be land mobility rate, labor resource mobility rate, etc. When using the mediating effect model to analyze the complex impact path between the level of regional coordinated development and food security, we first analyze the impact of the regional development level on the mediating variables, and then analyze the joint impact of the mediating variables and the level of regional coordinated development on food security.

[0025] Furthermore, in a preferred embodiment of the present invention, the step of obtaining several historical regional development examples with different food security levels and constructing a regional food security development prediction model specifically includes: Based on data retrieval, several historical regional development examples with different food security levels are obtained, and features of the historical regional development examples are extracted to extract food security features and regional development strategy features corresponding to each historical regional development example to obtain first feature information; Preset time period, constructing a time series feature sequence of each historical regional development instance according to the first feature information in units of the preset time period; Obtaining impact mechanism analysis information, constructing an impact path between regional development strategy and food security level based on the impact mechanism analysis information, and constructing a feature profile of each historical regional development instance in combination with the temporal feature sequence of each historical regional development instance; The characteristic portrait of each historical regional development instance is a representation of the degree of food security when the corresponding historical development instance is developed in the region, and the cosine similarity between the characteristic portraits of each historical regional development instance is calculated using a cosine measurement algorithm; According to the calculated cosine similarity, a connection path between the characteristic portraits of each historical regional development instance is established and the corresponding similarity is used as an auxiliary feature of the connection path to construct a first database; Using a stacked autoencoder to perform feature encoding and reconstruction on the feature portraits and contact paths stored in the first database, and using the corresponding cosine similarity as a weight to weight the importance, thereby obtaining encoding and reconstruction features; The encoded reconstruction features are imported into the BiGRU network for learning and a regional food security development prediction model is constructed. The temporal dependency of the reconstructed feature sequence is captured through the BiGRU network, and the regional food security development prediction results are output using the fully connected layer.

[0026] It should be noted that after analyzing the regional development level of the target area based on the corresponding food security level, its development status in the future time period can be further analyzed on this basis. First, historical regional development examples with different food security levels are obtained through data retrieval. The characteristics of these historical examples are extracted through the feature extraction process, and the features related to food security and the features related to regional development strategies are extracted to obtain the first feature information. Next, according to the preset time period, the time series feature sequences of each historical regional development instance are constructed based on the first feature information. Using these time series feature sequences, combined with the influence mechanism analysis information, the influence path between regional development strategy and food security is constructed, and on this basis, a feature portrait is generated for each historical regional development instance. The feature portrait is a general description of the historical regional development instance. By calculating the cosine similarity between these feature portraits, the similarity between different historical regional development instances can be quantified. The cosine similarity measures the similarity between different feature portraits. The calculation result is to establish a connection path between each pair of historical instances, and the similarity of these connection paths is used as an additional feature to form the first database. Then, the stacked autoencoder is used to feature encode and reconstruct the feature portraits and connection paths in the first database. In the encoding process, cosine similarity is introduced as a weight to weight the relative importance of each feature. This effectively extracts features that are important for food security prediction from the original data. Finally, the encoded and reconstructed features are imported into the Bidirectional Gated Recurrent Unit (BiGRU) network for learning. The BiGRU network can process time series data and capture the time dependency in the feature sequence, thereby predicting the future development of regional food security. Establishing an accurate regional food security development prediction model provides a scientific basis for future regional development decisions.

[0027] Furthermore, in a preferred embodiment of the present invention, the food security development status of the target area under the current development strategy is predicted, and whether there is a food security risk and a regional development optimization strategy is formulated, specifically including: Acquire regional development monitoring information, generate a regional development feature sequence of the target region at the current moment according to the regional development monitoring information, input it into a regional food security development prediction model for analysis, and obtain regional food security development prediction information; Generate a regional food security development forecast sequence with a preset time period as an interval according to the regional food security development forecast information, and extract the forecast characteristics of the food security development degree within each sequence interval; The predicted characteristics of the food security development degree of each sequence interval extracted are compared with the preset risk threshold, and the sequence area less than the preset threshold is defined as the risk sequence interval. The time node of the occurrence of food security risk is determined through the risk sequence interval to obtain food security risk analysis information; If the target area has food security risks in the future period under the current regional development strategy, then the regional development strategy optimization analysis is performed based on the food security risk analysis information; Obtain regional development level assessment information and food security assessment information, and build a regional development representation portrait of the target area based on the regional development feature sequence of the target area at the current moment; Matching and analyzing the regional development representation portrait of the target area with the characteristic portraits of each regional development instance stored in the first database, obtaining matching instances, performing food security evaluation on each matching instance, and screening matching instances that meet preset standards; Calculate the difference between the time point when the food security risk occurs and the current time according to the food security risk analysis information, use it as the optimization time limit, extract the regional development time characteristics of the selected matching instances and sort them; Through the optimization time limit, several matching instances that are shorter than the optimization time limit are selected and the corresponding regional development strategy features are extracted to conduct a feasibility analysis, and a regional development optimization strategy is generated and pushed according to the feasibility analysis results.

[0028] It should be noted that, first, the current regional development monitoring information of the target area is obtained, and the regional development feature sequence of the target area at the current moment is generated. It is input into the regional food security development prediction model to obtain the prediction information of regional food security development. Then, a regional food security development prediction sequence with a preset time period as an interval is generated according to the prediction information, and the prediction characteristics of the degree of food security development are extracted from each time interval. It is compared with the preset risk threshold, and the area less than the threshold is judged as the risk sequence interval. By identifying the risk interval, the time node at which the food security risk occurs can be determined, thereby generating food security risk analysis information. If food security risks are found in the future time period of the target area, the regional development strategy optimization analysis is performed according to the food security risk analysis information. The regional development level assessment information and the food security assessment information are obtained, and the regional development characterization portrait of the target area is constructed in combination with the regional development feature sequence of the target area at the current moment. The portrait provides a comprehensive description of the regional development status and food security status of the target area. Then, the regional development characterization portrait of the target area is matched and analyzed with the feature portraits of each regional development instance stored in the first database, and the relevant historical instances are found through matching. According to the food security risk analysis information, the difference between the time node when the food security risk occurs and the current moment is calculated, which is defined as the optimization time limit. Then, the regional development time characteristics of the screened matching instances are extracted and sorted. Through the optimization time limit, several matching instances that are less than the optimization time limit are selected, and their regional development strategy characteristics are extracted for feasibility analysis. It is analyzed whether the regional development strategies adopted in these historical instances are applicable to the current target area. If applicable, the corresponding regional development optimization strategy is generated, and finally the optimization strategy is pushed to the decision maker.

[0029] Figure 2 A flow chart of a regional food security analysis method provided by one embodiment of the present invention; like Figure 2 As shown, the present invention provides a flow chart of a regional food security analysis method, comprising: S202, obtaining regional development monitoring information, generating a regional development feature sequence of the target region at the current moment according to the regional development monitoring information, inputting the sequence into a regional food security development prediction model for analysis, and obtaining regional food security development prediction information; S204, generating a regional food security development forecast sequence with a preset time period as an interval according to the regional food security development forecast information, and extracting the food security development degree forecast characteristics within each sequence interval; S206, judging the predicted characteristics of the food security development degree of each sequence interval extracted from the preset risk threshold, defining the sequence area less than the preset threshold as the risk sequence interval, determining the time node of the occurrence of food security risk through the risk sequence interval, and obtaining food security risk analysis information; S208, if the target region has a food security risk in the future time period under the current regional development strategy, construct a regional development representation portrait of the target region, and perform matching analysis with the feature portraits of each regional development instance stored in the first database to obtain a matching instance; S210, conduct food security evaluation on each matching instance, screen the matching instances, calculate the difference between the time node when the food security risk occurs and the current time, use it as the optimization time limit, and generate a regional development optimization strategy for push.

[0030] Furthermore, in a food security impact analysis method based on regional development level provided by the present invention, the following steps are also included: Acquire regional development monitoring information of the target area, form a regional development monitoring time series based on the regional development monitoring information, evaluate the regional development level of the target area, and obtain first evaluation information; Associating the first evaluation information with the regional development monitoring time series, analyzing the score values ​​of each regional development evaluation index of the target area in different time periods, and obtaining second analysis information; Preset an abnormal risk threshold, judge the second analysis information with the abnormal risk threshold, select a regional development assessment index less than the abnormal risk threshold, and obtain third analysis information; Introducing a Markov algorithm, extracting corresponding regional development monitoring data based on the third analysis information, initializing the transfer state, and calculating the transfer probability of the next state, and generating a state transfer prediction result of the corresponding evaluation index; Analyze the state transition prediction results, calculate the deviation between the state transition prediction results and the current moment, and determine whether the corresponding regional development indicators are in a deteriorating trend based on the deviation value; If it is a deteriorating trend, it means that the regional development direction of the corresponding regional development indicator is in a risky direction, and a risk warning is generated for management and control prompts.

[0031] It should be noted that in the process of regional development, various practical measures are implemented through various regional development decisions, thereby carrying out various developments and improvements in the target areas. However, some strategies have a negative impact on local development after implementation. At this time, it is necessary to analyze whether the continued implementation of the corresponding regional development strategy will bring greater losses and impacts, so as to avoid development mistakes and losses in a timely manner.

[0032] Figure 3A food security impact analysis system 3 based on regional development level is provided in one embodiment of the present invention. The system comprises: a memory 31 and a processor 32. The memory 31 contains a food security impact analysis method program based on regional development level. When the food security impact analysis method program based on regional development level is executed by the processor 32, the following steps are implemented: Based on big data retrieval, relevant influencing factors of regional development level are obtained, influencing factors are screened and evaluation indicators are selected, and weighting is performed by combining expert weighting method and equal weighting method to construct a regional development level evaluation model; The regional development level evaluation model is used to evaluate the regional development level of the target area, the relationship between the food security of the target area and the regional development level is analyzed, and the mediating utility model is used to determine the impact mechanism of the regional development level on the degree of food security; Obtain several historical regional development examples with different levels of food security, build a regional food security development prediction model, predict the food security development status of the target area under the current development strategy, determine whether there is a food security risk and formulate a regional development optimization strategy.

[0033] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, 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.

[0034] 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 on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0035] 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.

[0036] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0037] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0038] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A food security impact analysis method based on regional development level, characterized in that: include: Based on big data retrieval, relevant influencing factors of regional development level are obtained, influencing factors are screened and evaluation indicators are selected, and weighting is performed by combining expert weighting method and equal weighting method to construct a regional development level evaluation model; The regional development level evaluation model is used to evaluate the regional development level of the target area, the relationship between the food security of the target area and the regional development level is analyzed, and the mediating utility model is used to determine the impact mechanism of the regional development level on the degree of food security; Obtain several historical regional development examples with different levels of food security, build a regional food security development prediction model, predict the food security development status of the target area under the current development strategy, determine whether there is a food security risk and formulate a regional development optimization strategy.

2. The food security impact analysis method based on regional development level according to claim 1 is characterized in that: The above-mentioned acquisition of influencing factors related to regional development level based on big data retrieval, screening of influencing factors and selection of evaluation indicators specifically include: Based on big data retrieval, the influencing factors related to the regional development level are obtained to form an influencing factor data set, and the parallel coordinate method is introduced to map the influencing factor data set to parallel coordinates to obtain an influencing factor coordinate map; Each data axis in the influencing factor coordinate diagram corresponds to a specific dimensional range and influencing factor type, and the influencing factor diagram is subjected to dimensionality reduction processing by principal component analysis to calculate the principal component score corresponding to each influencing factor; The calculated principal component score is compared with a preset threshold, and the influencing factor corresponding to the principal component score greater than the preset threshold is taken as the principal component factor, and the principal component factor is used to perform principal component direction projection to obtain a scatter plot of the influencing factor; A preset selection range is set, and corresponding influencing factors are selected according to the preset selection range in the influencing factor scatter diagram as candidate evaluation indicators to generate a candidate evaluation indicator data set.

3. The method for analyzing food security impact based on regional development level according to claim 1 is characterized in that: The above mentioned screening of influencing factors and selection of evaluation indicators, combined with the expert weighting method and the equal weighting method for weighting, builds a regional development level evaluation model, which specifically includes: Obtain a candidate evaluation indicator data set, calculate the Euclidean distance between each evaluation indicator in the candidate evaluation indicator data set, form a distance matrix, convert the distance matrix into an adjacency matrix using a Gaussian kernel function and calculate a vertex matrix; Subtracting the vertex matrix from the adjacency matrix to obtain a Laplace matrix, performing eigendecomposition on the Laplace matrix to obtain eigenvalues ​​and corresponding eigenvectors, presetting a number of cluster centers and selecting a corresponding number of minimum non-zero eigenvalues ​​and eigenvectors, using the selected eigenvectors as new data representations, and constructing an eigenvector space; Introducing a spectral clustering algorithm to perform multiple clustering in the feature vector space, classifying each evaluation indicator in the candidate evaluation indicator data set into categories, and obtaining a number of clustering clusters; Calculate the Pearson correlation coefficient between the evaluation indicators in the clustering clusters to characterize the correlation between the evaluation indicators, and generate a ranking table corresponding to each clustering cluster based on the Pearson correlation coefficient of each evaluation indicator; The evaluation index level is set through the ranking table corresponding to each cluster, and the evaluation indicators of each level under the same cluster are associated according to the level to generate the final evaluation index data set; Based on the final evaluation indicator data set, an importance score of each evaluation indicator is obtained by an expert weighting method, a scoring matrix is ​​constructed, the constructed scoring matrix is ​​normalized, and the expert weight of each evaluation indicator is obtained according to the normalized scoring matrix to obtain first weight information; Perform secondary weight distribution for each evaluation indicator by an equal weight method to obtain second weight information, preset a weighting ratio, and perform comprehensive weight distribution for each evaluation indicator in combination with the first weight information and the second weight information to obtain comprehensive weight distribution information; A regional development level evaluation system is constructed based on the final evaluation indicator data set and the comprehensive weight allocation information, and a regional development level evaluation model is constructed based on the constructed regional development level evaluation system.

4. The method for analyzing food security impact based on regional development level according to claim 1 is characterized in that: The regional development level evaluation model is used to evaluate the regional development level of the target area, analyze the relationship between the food security of the target area and the regional development level, and use the intermediary utility model to determine the impact mechanism of the regional development level on the degree of food security, which specifically includes: Acquire regional development monitoring information of the target area within a unit time based on big data retrieval, perform data preprocessing on the regional development monitoring information, and obtain preprocessing result information; Acquire a regional development level evaluation model, input the preprocessing result information into the regional development level evaluation model, evaluate the regional development level of the target area per unit time, and obtain regional development level assessment information; Preset food security assessment indicators and assign weights, build a food security assessment system, use the regional development monitoring information to extract food development data per unit time in the target area, conduct regional food security assessment, and obtain food security assessment information; Based on the regional development level assessment information and the food security assessment information, a multi-source linear regression equation is used to analyze the direct impact of the regional coordinated development level of the target area on food security, thereby obtaining first analysis information; Define mediating variables based on regional development level assessment indicators, and construct a regression path equation between regional coordinated development level and food security level, taking regional coordinated development level as the independent variable and food security level as the dependent variable; Based on the regional development level assessment information, food security assessment information and the first analysis information, the mediating effect model is used to analyze the impact mechanism of the regional development level of the target area on the degree of food security, and the impact mechanism analysis information is obtained.

5. The method for analyzing food security impact based on regional development level according to claim 1 is characterized in that: The step of obtaining several historical regional development examples with different food security levels and constructing a regional food security development prediction model specifically includes: Based on data retrieval, several historical regional development examples with different food security levels are obtained, and features of the historical regional development examples are extracted to extract food security features and regional development strategy features corresponding to each historical regional development example to obtain first feature information; Preset time period, constructing a time series feature sequence of each historical regional development instance according to the first feature information in units of the preset time period; Obtaining impact mechanism analysis information, constructing an impact path between regional development strategy and food security level based on the impact mechanism analysis information, and constructing a feature profile of each historical regional development instance in combination with the temporal feature sequence of each historical regional development instance; The characteristic portrait of each historical regional development instance is a representation of the degree of food security when the corresponding historical development instance is developed in the region, and the cosine similarity between the characteristic portraits of each historical regional development instance is calculated using a cosine measurement algorithm; According to the calculated cosine similarity, a connection path between the characteristic portraits of each historical regional development instance is established and the corresponding similarity is used as an auxiliary feature of the connection path to construct a first database; Using a stacked autoencoder to perform feature encoding and reconstruction on the feature portraits and contact paths stored in the first database, and using the corresponding cosine similarity as a weight to weight the importance, thereby obtaining encoding and reconstruction features; The encoded reconstruction features are imported into the BiGRU network for learning and a regional food security development prediction model is constructed. The temporal dependency of the reconstructed feature sequence is captured through the BiGRU network, and the regional food security development prediction results are output using the fully connected layer.

6. The method for analyzing food security impact based on regional development level according to claim 1 is characterized in that: The aforementioned prediction of the food security development status of the target area under the current development strategy, determining whether there is a food security risk and formulating a regional development optimization strategy specifically includes: Acquire regional development monitoring information, generate a regional development feature sequence of the target region at the current moment according to the regional development monitoring information, input it into a regional food security development prediction model for analysis, and obtain regional food security development prediction information; Generate a regional food security development forecast sequence with a preset time period as an interval according to the regional food security development forecast information, and extract the forecast characteristics of the food security development degree within each sequence interval; The predicted characteristics of the food security development degree of each sequence interval extracted are compared with the preset risk threshold, and the sequence area less than the preset threshold is defined as the risk sequence interval. The time node of the occurrence of food security risk is determined through the risk sequence interval to obtain food security risk analysis information; If the target area has food security risks in the future period under the current regional development strategy, then the regional development strategy optimization analysis is performed based on the food security risk analysis information; Obtain regional development level assessment information and food security assessment information, and build a regional development representation portrait of the target area based on the regional development feature sequence of the target area at the current moment; Matching and analyzing the regional development representation portrait of the target area with the characteristic portraits of each regional development instance stored in the first database, obtaining matching instances, performing food security evaluation on each matching instance, and screening matching instances that meet preset standards; Calculate the difference between the time point when the food security risk occurs and the current time according to the food security risk analysis information, use it as the optimization time limit, extract the regional development time characteristics of the selected matching instances and sort them; Through the optimization time limit, several matching instances that are shorter than the optimization time limit are selected and the corresponding regional development strategy features are extracted to conduct a feasibility analysis, and a regional development optimization strategy is generated and pushed according to the feasibility analysis results.

7. A food security impact analysis system based on regional development level, characterized in that: The system comprises: a memory and a processor, wherein the memory contains a food security impact analysis method program based on regional development level, and when the food security impact analysis method program based on regional development level is executed by the processor, the following steps are implemented: Based on big data retrieval, relevant influencing factors of regional development level are obtained, influencing factors are screened and evaluation indicators are selected, and weighting is performed by combining expert weighting method and equal weighting method to construct a regional development level evaluation model; The regional development level evaluation model is used to evaluate the regional development level of the target area, the relationship between the food security of the target area and the regional development level is analyzed, and the mediating utility model is used to determine the impact mechanism of the regional development level on the degree of food security; Obtain several historical regional development examples with different levels of food security, build a regional food security development prediction model, predict the food security development status of the target area under the current development strategy, determine whether there is a food security risk and formulate a regional development optimization strategy.

Images