Cultivated land quality evaluation method and system based on adaptive weight

Abstract

The invention discloses a cultivated land quality evaluation method and system based on adaptive weight, and the method comprises the steps: obtaining target cultivated land data of a cultivated land to be evaluated; inputting the target cultivated land data into the optimized cultivated land quality evaluation component for quality evaluation to obtain a cultivated land quality evaluation result of the cultivated land to be evaluated; the optimized cultivated land quality evaluation component is obtained by the following steps: acquiring a cultivated land training data set; inputting the cultivated land training data set into a tree model for model training to obtain a trained tree model and a decision tree output by the trained tree model; according to the cultivated land training data set, performing rule weight extraction on all decision trees to obtain a target weight parameter; and optimizing and updating the cultivated land quality evaluation component according to the target weight parameter to obtain an optimized cultivated land quality evaluation component. According to the method, the interpretability and accuracy of quality evaluation of the cultivated land can be improved. The invention relates to the technical field of soil quality evaluation.

Description

Technical Field

[0001] The present invention relates to the technical field of soil quality evaluation, and in particular to a method and system for evaluating cultivated land quality based on adaptive weights. Background Art

[0002] With the rapid development of modern agriculture, arable land quality has become a key factor affecting agricultural production efficiency and sustainability. In order to fully understand and grasp the quality of arable land and scientifically guide agricultural production, arable land quality evaluation has become one of the key issues of concern to relevant personnel.

[0003] At present, relevant technologies are usually based on weight assignment methods, such as expert scoring method and hierarchical analysis method, to assign weights to various cultivated land elements and evaluate the quality of cultivated land based on each assigned weight. This method relies heavily on the subjective judgment of experts and is difficult to fully reflect the actual situation of cultivated land in different regions and different types. The interpretability and accuracy of cultivated land quality evaluation are unsatisfactory.

[0004] Therefore, the problems existing in related technologies still need to be solved and optimized urgently. Summary of the Invention

[0005] The purpose of the present invention is to solve one of the technical problems existing in the related art to at least a certain extent.

[0006] To this end, an object of an embodiment of the present invention is to provide a method and system for evaluating cultivated land quality based on adaptive weights, wherein the method can improve the interpretability and accuracy of cultivated land quality evaluation.

[0007] In order to achieve the above technical objectives, the technical solutions adopted in the embodiments of the present application include:

[0008] In a first aspect, an embodiment of the present application provides a method for evaluating farmland quality based on adaptive weights, comprising:

[0009] Obtain target cultivated land data for cultivated land to be evaluated;

[0010] Inputting the target cultivated land data into the optimized cultivated land quality evaluation component for quality evaluation to obtain the cultivated land quality evaluation result of the cultivated land to be evaluated;

[0011] The optimized farmland quality evaluation component is obtained by optimizing the following steps:

[0012] Acquire a cultivated land training data set, wherein the cultivated land training data set includes a plurality of cultivated land data groups, each cultivated land data group including cultivated land element data and cultivated land quality quantitative data;

[0013] Inputting the cultivated land training data set into a tree model for model training to obtain a trained tree model and a plurality of decision trees output by the trained tree model, wherein the decision tree is a tree-like representation set of a plurality of decision rules, and the decision rules are used to indicate a nonlinear relationship between the cultivated land element data and the cultivated land quality quantification data;

[0014] According to the cultivated land training data set, rule weight extraction is performed on all the decision trees to obtain a plurality of target weight parameters, wherein the target weight parameters are adaptive weight parameters of original linear features, and the original linear features are feature features of the cultivated land feature data or rule features of the decision rules;

[0015] According to all the target weight parameters, the original weight parameters in the cultivated land quality evaluation component are optimized and updated to obtain the optimized cultivated land quality evaluation component.

[0016] In addition, the method according to the above embodiment of the present application may also have the following additional technical features:

[0017] Furthermore, in one embodiment of the present application, rule weights are extracted from all the decision trees based on the cultivated land training dataset to obtain several target weight parameters, including:

[0018] Obtaining element features of each of the cultivated land element data;

[0019] Inputting the cultivated land training data set and all the decision trees into a rule model to extract rule features, and obtaining rule features output by the rule model;

[0020] All the element features and the rule features are subjected to weighted linear analysis processing to obtain a plurality of target weight parameters.

[0021] Furthermore, in one embodiment of the present application, the inputting of the cultivated land training dataset and all the decision trees into the rule model to extract rule features, and obtaining the rule features output by the rule model, includes:

[0022] Extracting the root and leaf node paths of the decision tree through the rule model to obtain a plurality of decision paths;

[0023] Performing rule characterization processing on all the decision paths to obtain candidate rules corresponding to each decision path;

[0024] According to all the candidate rules, relationship encoding is performed on each cultivated land data group in the cultivated land training data set to obtain the rule features.

[0025] Furthermore, in one embodiment of the present application, the weighted linear analysis processing is performed on all the element features and the rule features to obtain several target weight parameters, including:

[0026] Constructing a feature matrix according to all the element features and the rule features;

[0027] Constructing a sparse linear regression model based on the quantified farmland quality data and the characteristic matrix;

[0028] Extracting non-zero coefficients in the sparse linear regression model to obtain a plurality of intermediate weight parameters;

[0029] Importance optimization processing is performed on all the intermediate weight parameters to obtain a plurality of target weight parameters, each of which corresponds to one intermediate weight parameter.

[0030] Furthermore, in one embodiment of the present application, the importance optimization process is performed on all the intermediate weight parameters to obtain several target weight parameters, including:

[0031] Performing importance measurement on all the intermediate weight parameters to obtain an importance measurement value of each intermediate weight parameter;

[0032] Performing normalized measurement on all original weight parameters in the cultivated land quality evaluation component to obtain a normalized measurement value of each original weight parameter;

[0033] The intermediate weight parameter is weight-optimized according to the normalized metric value and the importance metric value to obtain the target weight parameter.

[0034] Furthermore, in one embodiment of the present application, performing weight optimization on the intermediate weight parameter according to the normalized metric value and the importance metric value to obtain the target weight parameter includes:

[0035] updating the importance metric value according to the normalized metric value to obtain a target metric value of the intermediate weight parameter;

[0036] According to the target metric value, the intermediate weight parameter is metrically optimized to obtain the target weight parameter.

[0037] Furthermore, in one embodiment of the present application, the target cultivated land data is input into an optimized cultivated land quality evaluation component for quality evaluation to obtain the cultivated land quality evaluation result of the cultivated land to be evaluated, including:

[0038] Obtain the table of arable land quality grading system;

[0039] Inputting the target cultivated land data into the optimized cultivated land quality evaluation component to calculate the quality score, thereby obtaining the cultivated land quality score of the cultivated land to be evaluated;

[0040] According to the arable land quality grade system table, the arable land quality scores are graded and evaluated to obtain the arable land quality evaluation results.

[0041] In a second aspect, an embodiment of the present application provides a farmland quality evaluation system based on adaptive weights, comprising:

[0042] The first processing unit is used to obtain target cultivated land data of the cultivated land to be evaluated;

[0043] The second processing unit is used to input the target cultivated land data into the optimized cultivated land quality evaluation component for quality evaluation, and obtain the cultivated land quality evaluation result of the cultivated land to be evaluated;

[0044] The optimized farmland quality evaluation component is obtained by optimizing the following steps:

[0045] Acquire a cultivated land training data set, wherein the cultivated land training data set includes a plurality of cultivated land data groups, each cultivated land data group including cultivated land element data and cultivated land quality quantitative data;

[0046] Inputting the cultivated land training data set into a tree model for model training to obtain a trained tree model and a plurality of decision trees output by the trained tree model, wherein the decision tree is a tree-like representation set of a plurality of decision rules, and the decision rules are used to indicate a nonlinear relationship between the cultivated land element data and the cultivated land quality quantification data;

[0047] According to the cultivated land training data set, rule weight extraction is performed on all the decision trees to obtain a plurality of target weight parameters, wherein the target weight parameters are adaptive weight parameters of original linear features, and the original linear features are feature features of the cultivated land feature data or rule features of the decision rules;

[0048] According to all the target weight parameters, the original weight parameters in the cultivated land quality evaluation component are optimized and updated to obtain the optimized cultivated land quality evaluation component.

[0049] In a third aspect, an embodiment of the present application further provides an electronic device, including:

[0050] at least one processor;

[0051] at least one memory for storing at least one program;

[0052] When the at least one program is executed by the at least one processor, the at least one processor implements the above method.

[0053] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores a program executable by a processor, and the program executable by the processor is used to implement the above method when executed by the processor.

[0054] The advantages and benefits of this application will be partially given in the following description, and partially become apparent from the following description, or learned through practice of this application:

[0055] The embodiment of the present application discloses a method and system for evaluating cultivated land quality based on adaptive weights, wherein the method obtains target cultivated land data of cultivated land to be evaluated; inputs the target cultivated land data into an optimized cultivated land quality evaluation component for quality evaluation, and obtains the cultivated land quality evaluation result of the cultivated land to be evaluated; wherein the optimized cultivated land quality evaluation component is optimized by the following steps: obtaining a cultivated land training data set, wherein the cultivated land training data set includes several cultivated land data groups, each cultivated land data group includes cultivated land element data and cultivated land quality quantitative data; inputs the cultivated land training data set into a tree model for model training, and obtains a trained tree model, and the training A good tree model outputs several decision trees, each of which is a tree-like representation of a set of decision rules, each of which is used to indicate the nonlinear relationship between the cultivated land element data and the cultivated land quality quantification data. Based on the cultivated land training data set, rule weights are extracted from all the decision trees to obtain several target weight parameters, each of which is an adaptive weight parameter of the original linear feature, the original linear feature being the feature feature of the cultivated land element data or the rule feature of the decision rule. Based on all the target weight parameters, the original weight parameters in the cultivated land quality evaluation component are optimized and updated to obtain the optimized cultivated land quality evaluation component. This method extracts the weight parameters corresponding to each decision rule in the decision tree through a rule model, wherein the decision rule records the nonlinear relationship between the cultivated land element data and the cultivated land quality quantification data. The extracted target weight parameters can indicate the contribution of the corresponding cultivated land element to the cultivated land quality. The original weight parameters in the cultivated land quality evaluation component are then optimized and updated based on the adaptive target weight parameters, which is conducive to improving the interpretability and accuracy of cultivated land quality evaluation and can more fully reflect the actual conditions of different regions and types. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following introduction is made to the drawings of the embodiments of the present application or the related technical solutions in the prior art. It should be understood that the drawings introduced below are only for the convenience of clearly expressing some embodiments of the technical solutions of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without any creative work.

[0057] Figure 1 A flowchart of a method for evaluating farmland quality based on adaptive weights provided in an embodiment of the present application;

[0058] Figure 2 An optimization flow chart of a cultivated land quality evaluation component provided in an embodiment of the present application;

[0059] Figure 3 A schematic diagram of a framework of a farmland quality evaluation system based on adaptive weights provided in an embodiment of the present application;

[0060] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0061] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application and are not to be construed as limiting the present application. For the step numbers in the following embodiments, they are provided only for the convenience of explanation and are not intended to limit the order of the steps. The order of execution of the steps in the embodiments can be adaptively adjusted according to the understanding of those skilled in the art.

[0062] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0063] Currently, relevant technologies typically use weighted assignment methods, such as expert scoring and the analytic hierarchy process, to assign weights to various cultivated land elements and evaluate cultivated land quality based on these weights. This approach relies heavily on subjective expert judgment, making it difficult to fully reflect the actual conditions of cultivated land in different regions and types. Consequently, the interpretability and accuracy of cultivated land quality evaluations are unsatisfactory. Furthermore, the assigned weights determined by this approach are often fixed, making it difficult to adapt to the complex nonlinear relationship between cultivated land quality and cultivated land elements. Furthermore, they cannot fully reflect the dynamic changes of different cultivated land elements across different regions and cultivation projects. Consequently, these methods are inflexible, have limited applicability, and suffer from poor accuracy.

[0064] Some related technologies assess farmland quality by building machine learning models and using them to directly predict the quality category of farmland data. However, due to the black box effect of machine learning models, the farmland quality evaluation results obtained using this approach are not easily interpretable. To ensure high prediction accuracy, machine learning models require a large amount of training data, which is costly and time-consuming.

[0065] It should be noted that the above-mentioned related technologies are only used to assist in understanding the technical solutions of this application and do not mean that they belong to the disclosed prior art.

[0066] In view of this, an embodiment of the present invention provides a method and system for evaluating cultivated land quality based on adaptive weights, wherein the method extracts weight parameters corresponding to each decision rule of a decision tree through a rule model, and the decision rule records the nonlinear relationship between cultivated land element data and cultivated land quality quantitative data. The extracted target weight parameters can indicate the contribution of the corresponding cultivated land element to the cultivated land quality, and then the original weight parameters in the cultivated land quality evaluation component are optimized and updated based on the target weight parameters, which is conducive to improving the interpretability and accuracy of cultivated land quality evaluation, can more fully reflect the actual conditions of different regions and types, has higher flexibility and a wider range of applications.

[0067] In addition, this method learns the nonlinear relationship between cultivated land elements and cultivated land quality through a tree model and outputs decision rules, and then extracts the weight parameters corresponding to each interpretable decision rule of the decision tree through a rule model. It can determine the contribution of each cultivated land element to cultivated land quality in a data-driven manner, which can not only reduce the training cost and the required training data, but also help to improve the interpretability and objectivity of subsequent cultivated land quality evaluation.

[0068] Reference Figure 1 In an embodiment of the present application, a method for evaluating farmland quality based on adaptive weights includes:

[0069] Step 110: Obtain target farmland data of the farmland to be evaluated;

[0070] Step 120: input the target cultivated land data into the optimized cultivated land quality evaluation component for quality evaluation, and obtain the cultivated land quality evaluation result of the cultivated land to be evaluated;

[0071] In the embodiment of the present application, the cultivated land to be evaluated can be a paddy field, irrigated land, or dry land to be evaluated, and the target cultivated land data can be a data set of various cultivated land elements to be evaluated, which specifically includes stable cultivated land elements and variable cultivated land elements. Among them, stable cultivated land elements include terrain slope, surface rock outcrop, depth of barrier layer from the surface, and degree of salinization; variable cultivated land elements include field slope, groundwater level, effective soil layer thickness, profile configuration, irrigation guarantee rate, drainage conditions, surface soil texture, organic matter content, and soil pH. The cultivated land quality evaluation component can be a workflow execution tool built based on ModelBuilder technology, which records several weight parameters.

[0072] It can be understood that after obtaining the target cultivated land data of the cultivated land to be evaluated, the target cultivated land data can be input into the optimized cultivated land quality evaluation component, and the target cultivated land data can be calculated based on the various weight parameters in the optimized cultivated land quality evaluation component. There are many specific calculation methods, such as weighted average calculation method, weighted summation calculation method, etc. The examples in this application are only for illustration and do not limit this application, so as to obtain the cultivated land quality evaluation results of the cultivated land to be evaluated.

[0073] In some embodiments, the inputting of the target cultivated land data into an optimized cultivated land quality evaluation component for quality evaluation to obtain the cultivated land quality evaluation result of the cultivated land to be evaluated includes:

[0074] Obtain the table of arable land quality grading system;

[0075] Inputting the target cultivated land data into the optimized cultivated land quality evaluation component to calculate the quality score, thereby obtaining the cultivated land quality score of the cultivated land to be evaluated;

[0076] According to the arable land quality grade system table, the arable land quality scores are graded and evaluated to obtain the arable land quality evaluation results.

[0077] In this embodiment of the present application, the target cultivated land data can be input into the optimized cultivated land quality evaluation component for score calculation to obtain the cultivated land quality score of the cultivated land to be evaluated. The cultivated land quality score can specifically include at least one of the cultivated land crop quality score, the cultivated land natural quality score, the cultivated land utilization quality score, and the cultivated land economic quality score. For example, the equivalent expression of the cultivated land quality score can be:

[0078]

[0079] Among them, C Lij is the crop quality score of the cultivated land, which is specifically the natural quality score of the cultivated land when the i-th cultivated land to be evaluated is planted with the j-th designated crop; m is the total number of weight parameters; w k is the kth weight parameter in the optimized farmland quality evaluation component; w k is the total number of weight parameters in the optimized farmland quality evaluation component; f ijk When the jth designated crop is planted on the i-th evaluated cultivated land, the index score of the cultivated land element corresponding to the k-th weight parameter; R i is the natural quality score of the ith cultivated land to be evaluated; N is the total number of designated crops; a tj is the production potential index of the jth designated crop; β j is the yield ratio coefficient of the jth designated crop; Y i is the cultivated land utilization quality score of the i-th cultivated land to be evaluated; R ij K is the natural quality score of the arable land when the jth designated crop is planted on the i-th arable land to be evaluated; Lj is the land use coefficient of the jth specified crop; G i is the economic quality score of the ith cultivated land to be evaluated; K Cj is the land economic coefficient of the jth specified crop.

[0080] It is understandable that the production potential index a tj , β j Yield ratio coefficient, K Lj Land utilization coefficient, land economic coefficient K Cj etc. are known parameters, which can be determined by consulting existing data, or by assigning parameters using the calculate field tool in the ArcGIS Toolbox toolbox when using the Modelbuilder modeling tool to model the cultivated land to be evaluated. There are many specific implementation methods, which will not be repeated in this application.

[0081] It should be noted that after determining the arable land quality score of the arable land to be evaluated, the corresponding arable land quality grade in the arable land quality grade system table can be queried based on the arable land quality score. The arable land quality grade can specifically be at least one of the arable land natural quality grade, arable land utilization quality grade, arable land economic quality grade, etc., so as to obtain the arable land quality evaluation result of the arable land to be evaluated.

[0082] Reference Figure 2 The optimized cultivated land quality evaluation component is obtained by optimizing the following steps:

[0083] Step 130: Acquire a cultivated land training data set, wherein the cultivated land training data set includes a plurality of cultivated land data groups, each cultivated land data group including cultivated land element data and cultivated land quality quantitative data;

[0084] In an embodiment of the present application, the cultivated land training dataset includes several cultivated land data groups, each of which corresponds to a cultivated land unit for training. Specifically, for a certain cultivated land data group, its cultivated land element data can be a data set of each cultivated land element of the corresponding cultivated land unit. The specific cultivated land elements are similar to the cultivated land elements of the aforementioned target cultivated land data and can be derived by simple analogy. The cultivated land quality quantitative data can be the cultivated land quality score of the corresponding cultivated land unit, which is similar to the cultivated land quality score of the cultivated land to be evaluated. This application will not repeat it here.

[0085] Step 140: inputting the cultivated land training data set into a tree model for model training to obtain a trained tree model and a plurality of decision trees output by the trained tree model, wherein the decision tree is a tree-like representation set of a plurality of decision rules, and the decision rules are used to indicate a nonlinear relationship between the cultivated land element data and the cultivated land quality quantification data;

[0086] In the embodiment of the present application, the tree model can be a random forest model, a gradient boosted tree (XGBoost) model, or other models. Specifically, the cultivated land training dataset can be input into the random forest model and the gradient boosted tree model for training, respectively. The nonlinear relationship between cultivated land element data and cultivated land quality quantitative data can be learned by the model, thereby obtaining a trained random forest model and a gradient boosted tree model. Then, the model with the highest prediction accuracy is selected as the trained tree model, and several decision trees output by the trained tree model are obtained.

[0087] Step 150: extracting rule weights from all the decision trees based on the cultivated land training data set to obtain a plurality of target weight parameters, where the target weight parameters are adaptive weight parameters of original linear features, and the original linear features are feature features of the cultivated land feature data or rule features of the decision rules;

[0088] In an embodiment of the present application, based on the cultivated land training data set, the nonlinear relationships recorded by all decision trees can be encoded into a set of original linear features that are easy to process by the linear model, and then the target weight parameters are determined based on the original linear features.

[0089] In some embodiments, the rule weights of all the decision trees are extracted based on the cultivated land training dataset to obtain several target weight parameters, including:

[0090] Obtaining element features of each of the cultivated land element data;

[0091] In an embodiment of the present application, each cultivated land element data in the cultivated land training data set can be preprocessed and then characterized to obtain the element features of each cultivated land element data. There are many specific characterization methods, which will not be repeated in this application.

[0092] Inputting the cultivated land training data set and all the decision trees into a rule model to extract rule features, and obtaining rule features output by the rule model;

[0093] Furthermore, the farmland training data set and all the decision trees are input into a rule model to extract rule features, and the rule features output by the rule model are obtained, including:

[0094] Extracting the root and leaf node paths of the decision tree through the rule model to obtain a plurality of decision paths;

[0095] Performing rule characterization processing on all the decision paths to obtain candidate rules corresponding to each decision path;

[0096] According to all the candidate rules, relationship encoding is performed on each cultivated land data group in the cultivated land training data set to obtain the rule features.

[0097] In an embodiment of the present application, the rule model can be a RuleFit model. Specifically, for any decision tree, the rule model can be used to extract all paths from the root node to each leaf node of the decision tree, which are recorded as decision paths. Each decision path is used to represent a decision rule recorded by the decision tree. The decision rule specifically includes several features, feature thresholds, and logical conditions, for example, "decision rule R1: IF effective soil layer thickness > 100 cm AND organic matter content > 20 g / kg."

[0098] It can be understood that the rule characterization process can be to characterize the decision rules corresponding to each decision path to obtain candidate rules corresponding to each macro-volume path; for any candidate rule, the relationship encoding can be to calculate the rule feature value between each cultivated land data set and the candidate rule, and then, based on the candidate rule, encode each rule feature value separately to obtain several rule features corresponding to the candidate rule. Each rule feature records the candidate rule and the corresponding rule feature value. The remaining candidate rules can be derived similarly. Specifically, if a cultivated land data set meets all the conditions in the candidate rule, the rule feature value between the cultivated land array and the candidate rule is 1; otherwise, it is 0.

[0099] All the element features and the rule features are subjected to weighted linear analysis processing to obtain a plurality of target weight parameters.

[0100] Furthermore, the weighted linear analysis is performed on all the element features and the rule features to obtain several target weight parameters, including:

[0101] Constructing a feature matrix according to all the element features and the rule features;

[0102] Constructing a sparse linear regression model based on the quantified farmland quality data and the characteristic matrix;

[0103] Extracting non-zero coefficients in the sparse linear regression model to obtain a plurality of intermediate weight parameters;

[0104] In an embodiment of the present application, after obtaining all element features and rule features, all element features and rule features can be merged to form an extended feature matrix, the matrix columns of which contain element features and rule features, and the matrix rows of which correspond to each cultivated land data group.

[0105] It is understandable that a sparse linear regression model can be constructed by fitting the quantitative data of cultivated land quality as the target variable and the feature matrix as the input prediction variable. The sparse linear regression model can be specifically obtained based on Lasso (Least Absolute Shrinkage and Selection Operator) regression. After the sparse linear regression model is constructed, several non-zero coefficients can be extracted from the model parameters of the sparse linear regression model, and each non-zero coefficient is recorded as an intermediate weight parameter. Each intermediate weight parameter corresponds to an original linear feature selected by the sparse linear regression model. The intermediate weight parameter is used to indicate the importance of the corresponding original linear feature.

[0106] Importance optimization processing is performed on all the intermediate weight parameters to obtain a plurality of target weight parameters, each of which corresponds to one intermediate weight parameter.

[0107] Furthermore, the importance optimization process is performed on all the intermediate weight parameters to obtain several target weight parameters, including:

[0108] Performing importance measurement on all the intermediate weight parameters to obtain an importance measurement value of each intermediate weight parameter;

[0109] Performing normalized measurement on all original weight parameters in the cultivated land quality evaluation component to obtain a normalized measurement value of each original weight parameter;

[0110] In an embodiment of the present application, the importance measurement can first obtain the absolute value of each intermediate weight parameter, and then normalize the absolute values ​​of all intermediate weight parameters, such as Min-Max normalization, to obtain the importance measurement value corresponding to each intermediate weight parameter, and the importance measurement value is used to characterize the relative importance of the corresponding intermediate weight parameter among all intermediate weight parameters.

[0111] It can be understood that the normalized measurement can first obtain all the weight parameters used in the cultivated land quality evaluation component, record them as original weight parameters, and then normalize all the original weight parameters to obtain the normalized measurement value of each original weight parameter, and the sum of all normalized measurement values ​​is 1.

[0112] The intermediate weight parameter is weight-optimized according to the normalized metric value and the importance metric value to obtain the target weight parameter.

[0113] Furthermore, the weight optimization of the intermediate weight parameter according to the normalized metric value and the importance metric value to obtain the target weight parameter includes:

[0114] updating the importance metric value according to the normalized metric value to obtain a target metric value of the intermediate weight parameter;

[0115] According to the target metric value, the intermediate weight parameter is metrically optimized to obtain the target weight parameter.

[0116] In an embodiment of the present application, for any intermediate weight parameter, a first implementation method is to update the importance metric value based on the normalized metric value. For example, the normalized metric value and the importance metric value can be calculated in a weighted average manner. The weights used in the specific calculation process can be set according to actual conditions to obtain a target metric value of the intermediate weight parameter; then, the intermediate weight parameter is metrically optimized using the target metric value, for example, the target metric value and the intermediate weight parameter are multiplied to obtain the target weight parameter.

[0117] Alternatively, in the second embodiment, after the target metric value is determined, the metric optimization of the intermediate weight parameter may be to replace the intermediate weight parameter with the target metric value, and determine the target metric value as the target weight parameter.

[0118] Step 160: Optimize and update the original weight parameters in the cultivated land quality evaluation component according to all the target weight parameters to obtain the optimized cultivated land quality evaluation component.

[0119] In an embodiment of the present application, for any target weight parameter, the original weight parameter corresponding to the target weight parameter can be first determined, and the target weight parameter and the corresponding original weight parameter are used for the same cultivated land element; then, the target weight parameter is used to replace the corresponding original weight parameter in the cultivated land quality evaluation component, and the same applies to the remaining target weight parameters, thereby completing the optimization and update of the original weight parameters in the cultivated land quality evaluation component to obtain an optimized cultivated land quality evaluation component.

[0120] A farmland quality evaluation system based on adaptive weights proposed according to an embodiment of the present application is described in detail below with reference to the accompanying drawings.

[0121] Reference Figure 3 In the embodiment of the present application, a farmland quality evaluation system based on adaptive weights is proposed, comprising:

[0122] The first processing unit 101 is used to obtain target farmland data of the farmland to be evaluated;

[0123] The second processing unit 102 is used to input the target cultivated land data into the optimized cultivated land quality evaluation component for quality evaluation, and obtain the cultivated land quality evaluation result of the cultivated land to be evaluated;

[0124] The optimized farmland quality evaluation component is obtained by optimizing the following steps:

[0125] Acquire a cultivated land training data set, wherein the cultivated land training data set includes a plurality of cultivated land data groups, each cultivated land data group including cultivated land element data and cultivated land quality quantitative data;

[0126] Inputting the cultivated land training data set into a tree model for model training to obtain a trained tree model and a plurality of decision trees output by the trained tree model, wherein the decision tree is a tree-like representation set of a plurality of decision rules, and the decision rules are used to indicate a nonlinear relationship between the cultivated land element data and the cultivated land quality quantification data;

[0127] According to the cultivated land training data set, rule weight extraction is performed on all the decision trees to obtain a plurality of target weight parameters, wherein the target weight parameters are adaptive weight parameters of original linear features, and the original linear features are feature features of the cultivated land feature data or rule features of the decision rules;

[0128] According to all the target weight parameters, the original weight parameters in the cultivated land quality evaluation component are optimized and updated to obtain the optimized cultivated land quality evaluation component.

[0129] It can be understood that the contents of the above method embodiments are all applicable to the present system embodiments, the functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0130] Reference Figure 4 , an embodiment of the present application further provides an electronic device, including:

[0131] at least one processor 201;

[0132] At least one memory 202, configured to store at least one program;

[0133] When the at least one program is executed by the at least one processor 201 , the at least one processor 201 implements the above method embodiment.

[0134] Similarly, it can be understood that the contents of the above method embodiments are applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0135] An embodiment of the present application further provides a computer-readable storage medium, in which a program executable by the processor 201 is stored. The program executable by the processor 201 is used to implement the above-mentioned method embodiment when executed by the processor 201.

[0136] Similarly, the contents of the above method embodiments are applicable to the computer-readable storage medium embodiments. The functions specifically implemented by the computer-readable storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0137] In some optional embodiments, the functions / operations mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the functions / operations involved, the two boxes shown in succession may actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiments presented and described in the flow chart of the present application are provided in an exemplary manner for the purpose of providing a more comprehensive understanding of the technology. The disclosed method is not limited to the operations and logic flows presented herein. Optional embodiments are contemplated in which the order of the various operations is changed and the sub-operations described as a part of a larger operation are performed independently.

[0138] In addition, although the present application is described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in separate physical devices or software modules. It is also understood that a detailed discussion of the actual implementation of each module is not necessary for understanding the present application. More specifically, given the properties, functions, and internal relationships of the various functional modules in the devices disclosed herein, the actual implementation of the module will be understood within the routine skills of an engineer. Therefore, a person skilled in the art can implement the present application as set forth in the claims using ordinary techniques without undue experimentation. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present application, which is determined by the full scope of the appended claims and their equivalents.

[0139] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the embodiment method of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0140] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0141] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0142] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0143] In the above description of this specification, reference to the terms "one embodiment / example," "another embodiment / example," or "certain embodiments / examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples.

[0144] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and intent of the present application, and that the scope of the present application is defined by the claims and their equivalents.

[0145] The above is a specific description of the preferred implementation of the present application, but the present application is not limited to the embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the present application, and these equivalent modifications or substitutions are all included in the scope defined by the claims of the present application.

Claims

1. A method for evaluating cultivated land quality based on adaptive weights, characterized in that: include: Obtain target cultivated land data for cultivated land to be evaluated; Inputting the target cultivated land data into the optimized cultivated land quality evaluation component for quality evaluation to obtain the cultivated land quality evaluation result of the cultivated land to be evaluated; The optimized farmland quality evaluation component is obtained by optimizing the following steps: Acquire a cultivated land training data set, wherein the cultivated land training data set includes a plurality of cultivated land data groups, each cultivated land data group including cultivated land element data and cultivated land quality quantitative data; Inputting the cultivated land training data set into a tree model for model training to obtain a trained tree model and a plurality of decision trees output by the trained tree model, wherein the decision tree is a tree-like representation set of a plurality of decision rules, and the decision rules are used to indicate a nonlinear relationship between the cultivated land element data and the cultivated land quality quantification data; According to the cultivated land training data set, rule weight extraction is performed on all the decision trees to obtain a plurality of target weight parameters, wherein the target weight parameters are adaptive weight parameters of original linear features, and the original linear features are feature features of the cultivated land feature data or rule features of the decision rules; According to all the target weight parameters, the original weight parameters in the cultivated land quality evaluation component are optimized and updated to obtain the optimized cultivated land quality evaluation component.

2. The method according to claim 1, characterized in that According to the cultivated land training data set, rule weights are extracted for all the decision trees to obtain several target weight parameters, including: Obtaining element features of each of the cultivated land element data; Inputting the cultivated land training data set and all the decision trees into a rule model to extract rule features, and obtaining rule features output by the rule model; All the element features and the rule features are subjected to weighted linear analysis processing to obtain a plurality of target weight parameters.

3. The method according to claim 2, characterized in that The step of inputting the cultivated land training data set and all the decision trees into a rule model to extract rule features and obtain the rule features output by the rule model includes: Extracting the root and leaf node paths of the decision tree through the rule model to obtain a plurality of decision paths; Performing rule characterization processing on all the decision paths to obtain candidate rules corresponding to each decision path; According to all the candidate rules, relationship encoding is performed on each cultivated land data group in the cultivated land training data set to obtain the rule features.

4. The method according to claim 2, characterized in that The weighted linear analysis process is performed on all the element features and the rule features to obtain a plurality of target weight parameters, including: Constructing a feature matrix according to all the element features and the rule features; Constructing a sparse linear regression model based on the quantified farmland quality data and the characteristic matrix; Extracting non-zero coefficients in the sparse linear regression model to obtain a plurality of intermediate weight parameters; Importance optimization processing is performed on all the intermediate weight parameters to obtain a plurality of target weight parameters, each of which corresponds to one intermediate weight parameter.

5. The method according to claim 4, characterized in that The importance optimization process is performed on all the intermediate weight parameters to obtain a plurality of target weight parameters, including: Performing importance measurement on all the intermediate weight parameters to obtain an importance measurement value of each intermediate weight parameter; Performing normalized measurement on all original weight parameters in the cultivated land quality evaluation component to obtain a normalized measurement value of each original weight parameter; The intermediate weight parameter is weight-optimized according to the normalized metric value and the importance metric value to obtain the target weight parameter.

6. The method according to claim 5, characterized in that The step of performing weight optimization on the intermediate weight parameter according to the normalized metric value and the importance metric value to obtain the target weight parameter includes: updating the importance metric value according to the normalized metric value to obtain a target metric value of the intermediate weight parameter; According to the target metric value, the intermediate weight parameter is metrically optimized to obtain the target weight parameter.

7. The method according to claim 1, characterized in that The target cultivated land data is input into the optimized cultivated land quality evaluation component for quality evaluation to obtain the cultivated land quality evaluation result of the cultivated land to be evaluated, including: Obtain the table of arable land quality grading system; Inputting the target cultivated land data into the optimized cultivated land quality evaluation component to calculate the quality score, thereby obtaining the cultivated land quality score of the cultivated land to be evaluated; According to the arable land quality grade system table, the arable land quality scores are graded and evaluated to obtain the arable land quality evaluation results.

8. A farmland quality evaluation system based on adaptive weights, characterized in that: include: The first processing unit is used to obtain target cultivated land data of the cultivated land to be evaluated; The second processing unit is used to input the target cultivated land data into the optimized cultivated land quality evaluation component for quality evaluation, and obtain the cultivated land quality evaluation result of the cultivated land to be evaluated; The optimized farmland quality evaluation component is obtained by optimizing the following steps: Acquire a cultivated land training data set, wherein the cultivated land training data set includes a plurality of cultivated land data groups, each cultivated land data group including cultivated land element data and cultivated land quality quantitative data; Inputting the cultivated land training data set into a tree model for model training to obtain a trained tree model and a plurality of decision trees output by the trained tree model, wherein the decision tree is a tree-like representation set of a plurality of decision rules, and the decision rules are used to indicate a nonlinear relationship between the cultivated land element data and the cultivated land quality quantification data; According to the cultivated land training data set, rule weight extraction is performed on all the decision trees to obtain a plurality of target weight parameters, wherein the target weight parameters are adaptive weight parameters of original linear features, and the original linear features are feature features of the cultivated land feature data or rule features of the decision rules; According to all the target weight parameters, the original weight parameters in the cultivated land quality evaluation component are optimized and updated to obtain the optimized cultivated land quality evaluation component.

9. An electronic device, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a program executable by a processor, characterized in that: The program executable by the processor is used to implement the method according to any one of claims 1 to 7 when executed by the processor.

Images