Method for evaluating application effect of sustained and controlled release pesticide
By constructing a large database of controlled-release pesticides using the Ochii a coefficient measurement method, particle swarm optimization algorithm, and graph neural network, the problem of pesticide resistance in controlled-release pesticides was solved, and the application plan was dynamically adjusted to improve the control effect of pesticides.
Patent Information
- Application Number
- CN202411267882.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-11
- Publication Date
- 2024-11-29
AI Technical Summary
After a certain number of uses, controlled-release pesticides can cause plants to develop resistance, leading to a decrease in their effectiveness in controlling diseases and pests, and resulting in economic losses for growers.
The membership degree of the initial application effect was re-evaluated using the Ochii a coefficient metric and particle swarm optimization algorithm. By combining fuzzy clustering algorithm and graph neural network, a large database of controlled-release pesticides was constructed to recommend the optimal application scheme.
By dynamically adjusting the application plan of controlled-release pesticides, the application effect in the target area can be improved, resistance can be reduced, and pesticide utilization can be optimized.
Smart Images

Figure CN119048181A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of pesticide application, and in particular to a method for evaluating the application effect of a sustained-release pesticide. Background Art
[0002] Pesticide controlled-release formulations have become the most promising formulation in pesticide formulation research because of their advantages of improving the utilization rate of active substances, reducing the application amount, increasing the stability of active substances, and extending the duration of effectiveness. Pesticide controlled-release formulations use modern scientific methods and natural or synthetic materials as the base material to achieve a purposeful release of the active ingredients of pesticides according to predetermined goals. However, after a certain number of times of using controlled-release pesticides, plants will develop a certain degree of resistance, resulting in a decrease in the effectiveness of controlled-release pesticides in preventing and controlling diseases and pests, causing economic losses to growers. Summary of the invention
[0003] The invention overcomes the shortcomings of the prior art and provides a method for evaluating the application effect of a slow-release pesticide.
[0004] To achieve the above object, the technical solution adopted by the present invention is:
[0005] The first aspect of the present invention provides a method for evaluating the application effect of a sustained-release pesticide, comprising the following steps:
[0006] Obtaining real-time disease data and pest data of each slow-release pesticide in each application area, and obtaining the initial application effect membership of each application area according to the real-time disease data and pest data;
[0007] Introducing an Ochia coefficient measurement method and a particle swarm algorithm, and re-evaluating the initial application effect membership according to the Ochia coefficient measurement method and the particle swarm algorithm to obtain an evaluated application effect membership;
[0008] According to the evaluated application effect membership, the application area where the abnormal application membership is located is obtained, and a large database of slow-release pesticides is constructed;
[0009] Based on the application area where the abnormal application membership is located and the large database of controlled-release pesticides, an optimal controlled-release pesticide application plan is recommended, and the controlled-release pesticides are applied according to the optimal controlled-release pesticide application plan.
[0010] Furthermore, in this method, real-time disease data and pest data of each slow-release pesticide in each application area are obtained, and the initial application effect membership of each application area is obtained according to the real-time disease data and pest data, specifically:
[0011] Obtain disease and pest data of the target area within a preset time, and obtain real-time disease and pest data of each controlled-release pesticide in each application area;
[0012] Calculate the killing ratio of diseases and pests in each application area within the preset time according to the disease data and pest data of the target area within the preset time and the real-time disease data and pest data of each slow-release pesticide in each application area;
[0013] Introducing a fuzzy clustering algorithm, initializing the number of cluster centers in the fuzzy clustering algorithm, and constructing sample data based on the killing ratio of diseases and pests in each application area within the preset time;
[0014] The sample data is initialized and clustered based on the number of cluster centers in the fuzzy clustering algorithm, and the cluster centers corresponding to the sample data are obtained. Based on the cluster centers, the initial application effect membership corresponding to each sample data is obtained and used as the initial application effect membership of each application area.
[0015] Furthermore, in this method, the Ochia coefficient measurement method and the particle swarm algorithm are introduced, and the initial application effect membership is re-evaluated according to the Ochia coefficient measurement method and the particle swarm algorithm to obtain the evaluated application effect membership, specifically:
[0016] Introducing the Ochi a coefficient measurement method and the particle swarm algorithm, setting the number of iterations based on the particle swarm algorithm, obtaining the clusters corresponding to each initial application effect membership, and calculating the Ochi a coefficients between the clusters corresponding to the initial application effect membership;
[0017] Setting an Ochi a coefficient threshold, and determining whether the Ochi a coefficient is greater than the Ochi a coefficient threshold;
[0018] When the Ochi a coefficient is greater than the Ochi a coefficient threshold, all clusters are output, and the application effect membership corresponding to each cluster is obtained and output as the evaluated application effect membership;
[0019] When the Ochi a coefficient is not greater than the Ochi a coefficient threshold, iteration is performed based on the number of iterations, and the number of cluster centers is adjusted until the Ochi a coefficient is greater than the Ochi a coefficient threshold. Then, iteration is stopped, and the application effect membership corresponding to each cluster is obtained, and output as the evaluated application effect membership.
[0020] Furthermore, in the present method, obtaining the application area where the abnormal application membership is located according to the evaluated application effect membership specifically includes:
[0021] Preset a membership evaluation index, and determine whether the membership of the application effect after the evaluation is greater than the membership evaluation index;
[0022] When the membership of the application effect after evaluation is greater than the membership evaluation index, the application area corresponding to the current membership of the application effect after evaluation is used as the release area of the abnormal membership;
[0023] When the membership of the application effect after evaluation is not greater than the membership evaluation index, the application area corresponding to the current membership of the application effect after evaluation is used as the release area of the normal membership;
[0024] The application area where the abnormal application membership is located is obtained, and the application area where the abnormal application membership is located is output.
[0025] Furthermore, in this method, a large database of slow-release pesticides is constructed, specifically:
[0026] Obtain the chemical composition data information of each controlled-release pesticide, and build a large database of controlled-release pesticides, introduce a graph neural network, use the chemical composition data information as the first node of the graph neural network, and use the type of controlled-release pesticide as the second node;
[0027] Constructing a directed edge description relationship, connecting the first node and the second node based on the directed edge description relationship, constructing a topological structure graph, and acquiring a related adjacency matrix based on the topological structure graph;
[0028] The related adjacency matrix is input into the storage space in the slow-release pesticide database for storage, and a query address is configured for each storage space.
[0029] Furthermore, in this method, based on the application area where the abnormal application membership is located and the large database of controlled-release pesticides, the optimal controlled-release pesticide application scheme is recommended, and the controlled-release pesticide application is performed according to the optimal controlled-release pesticide application scheme, specifically:
[0030] Acquire chemical composition data corresponding to the controlled-release pesticide in the application area where the abnormal application membership is located, and input the chemical composition data corresponding to the controlled-release pesticide in the application area where the abnormal application membership is located into the controlled-release pesticide database;
[0031] Calculate the Pearson correlation coefficient between the chemical composition data of each type of controlled-release pesticide in the controlled-release pesticide database and the chemical composition data corresponding to the controlled-release pesticide in the application area where the abnormal application membership is located;
[0032] Presetting a Pearson correlation coefficient threshold, determining whether the Pearson correlation coefficient is not greater than the Pearson correlation coefficient threshold, and selecting a controlled-release pesticide type corresponding to a controlled-release pesticide type not greater than the Pearson correlation coefficient threshold as a candidate controlled-release pesticide application scheme;
[0033] The sustained-release pesticide application scheme candidate with the largest Pearson correlation coefficient is selected as the optimal sustained-release pesticide application scheme, and the sustained-release pesticide application is performed according to the optimal sustained-release pesticide application scheme.
[0034] A second aspect of the present invention provides a system for evaluating the application effect of a controlled-release pesticide. The system includes a memory and a processor. The memory includes a program for evaluating the application effect of a controlled-release pesticide. When the program for evaluating the application effect of a controlled-release pesticide is executed by the processor, the following steps are implemented:
[0035] Obtaining real-time disease data and pest data of each slow-release pesticide in each application area, and obtaining the initial application effect membership of each application area according to the real-time disease data and pest data;
[0036] Introducing an Ochia coefficient measurement method and a particle swarm algorithm, and re-evaluating the initial application effect membership according to the Ochia coefficient measurement method and the particle swarm algorithm to obtain an evaluated application effect membership;
[0037] According to the evaluated application effect membership, the application area where the abnormal application membership is located is obtained, and a large database of slow-release pesticides is constructed;
[0038] Based on the application area where the abnormal application membership is located and the large database of controlled-release pesticides, an optimal controlled-release pesticide application plan is recommended, and the controlled-release pesticides are applied according to the optimal controlled-release pesticide application plan.
[0039] The third aspect of the present invention provides a computer-readable storage medium, which includes a program for evaluating the application effect of a sustained-release pesticide. When the program for evaluating the application effect of a sustained-release pesticide is executed by a processor, the steps of any one of the methods for evaluating the application effect of a sustained-release pesticide are implemented.
[0040] The present invention solves the defects existing in the background technology and has the following beneficial effects:
[0041] The present invention obtains the real-time disease data and pest data of each controlled-release pesticide in each application area, obtains the initial application effect membership of each application area according to the real-time disease data and pest data, and then introduces the Ochia coefficient measurement method and the particle swarm algorithm, and re-evaluates the initial application effect membership according to the Ochia coefficient measurement method and the particle swarm algorithm, obtains the evaluated application effect membership, thereby obtaining the application area where the abnormal application membership is located according to the evaluated application effect membership, and constructs a controlled-release pesticide database, and finally recommends the optimal controlled-release pesticide application scheme based on the application area where the abnormal application membership is located and the controlled-release pesticide database, and applies it according to the optimal controlled-release pesticide application scheme. The present invention evaluates the real-time disease data and pest data of each controlled-release pesticide in each application area, thereby obtaining the application effect data in the target area, thereby dynamically adjusting the controlled-release pesticide application scheme in the target area according to the application effect, and improving the application effect of the controlled-release pesticide in the target area. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, drawings of other embodiments can be obtained based on these drawings without paying creative work.
[0043] Figure 1 The overall flow chart of the method for evaluating the application effect of slow-release pesticides is shown;
[0044] Figure 2 A partial flow chart of a method for evaluating the application effect of a slow-release pesticide is shown;
[0045] Figure 3 The system block diagram of the application effect evaluation system of the slow-release pesticide is shown. DETAILED DESCRIPTION
[0046] 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.
[0047] 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.
[0048] like Figure 1 As shown, the first aspect of the present invention provides a method for evaluating the application effect of a sustained-release pesticide, comprising the following steps:
[0049] S102: Obtaining real-time disease data and pest data of each slow-release pesticide in each application area, and obtaining the initial application effect membership of each application area according to the real-time disease data and pest data;
[0050] S104: introducing the Ochia coefficient measurement method and the particle swarm algorithm, and re-evaluating the initial application effect membership according to the Ochia coefficient measurement method and the particle swarm algorithm to obtain the evaluated application effect membership;
[0051] S106: Obtaining the application area where the abnormal application membership is located according to the evaluated application effect membership, and constructing a large database of slow-release pesticides;
[0052] S108: Based on the application area where the abnormal application membership is located and the large database of controlled-release pesticides, the optimal controlled-release pesticide application plan is recommended, and the controlled-release pesticides are applied according to the optimal controlled-release pesticide application plan.
[0053] It should be noted that the present invention obtains application effect data in the target area by evaluating the real-time disease data and pest and disease data of each slow-release pesticide in each application area, and then dynamically adjusts the application plan of the slow-release pesticide in the target area according to the application effect, thereby improving the application effect of the slow-release pesticide in the target area.
[0054] like Figure 2 As shown, further, in this method, the real-time disease data and pest data of each slow-release pesticide in each application area are obtained, and the initial application effect membership of each application area is obtained according to the real-time disease data and pest data, specifically:
[0055] S202: Obtain disease data and pest data of the target area within a preset time, and obtain real-time disease data and pest data of each slow-release pesticide in each application area;
[0056] S204: Calculate the killing ratio of diseases and pests in each application area within the preset time according to the disease data and pest data of the target area within the preset time and the real-time disease data and pest data of each slow-release pesticide in each application area;
[0057] S206: introducing a fuzzy clustering algorithm, initializing the number of cluster centers in the fuzzy clustering algorithm, and constructing sample data based on the killing ratio of diseases and pests in each application area within a preset time;
[0058] S208: Initialize clustering of sample data based on the number of cluster centers in the fuzzy clustering algorithm, obtain the cluster center corresponding to the sample data, obtain the initial application effect membership corresponding to each sample data based on the cluster center, and use it as the initial application effect membership of each application area.
[0059] It should be noted that fuzzy clustering algorithms include k-means clustering algorithm, FCM clustering algorithm, etc., among which the application effect membership includes high application effect, medium application effect, low application effect, etc. For example, the killing ratio is 90%-100% for high application effect. This method can be used to quickly process massive data. Among them, disease data include the number of diseased plants within a unit area, the number of diseased plants within a preset area, etc., and pest data include the number of diseased and insect-infested plants within a unit area, the number of diseased and insect-infested plants within a preset area, etc.
[0060] Furthermore, in this method, the Och IIa coefficient measurement method and the particle swarm algorithm are introduced, and the initial application effect membership is re-evaluated according to the Och IIa coefficient measurement method and the particle swarm algorithm to obtain the evaluated application effect membership, which is specifically:
[0061] The Ochia coefficient measurement method and particle swarm algorithm are introduced. The number of iterations is set based on the particle swarm algorithm to obtain the clusters corresponding to each initial application effect membership, and the Ochia coefficients between the clusters corresponding to the initial application effect membership are calculated.
[0062] Set the Och ii a coefficient threshold to determine whether the Och iia coefficient is greater than the Och iia coefficient threshold;
[0063] When the Ochi a coefficient is greater than the Ochi a coefficient threshold, all clusters are output, and the application effect membership corresponding to each cluster is obtained and output as the evaluated application effect membership;
[0064] When the Ochi a coefficient is not greater than the Ochi a coefficient threshold, iteration is performed based on the number of iterations, and the number of cluster centers is adjusted until the Ochi a coefficient is greater than the Ochi a coefficient threshold. The iteration is stopped, and the application effect membership corresponding to each cluster is obtained and output as the evaluated application effect membership.
[0065] It should be noted that, since the fuzzy clustering algorithm is prone to local optimal solution when the number of cluster centers is not suitable during clustering, when the Ochi a coefficient is not greater than the Ochi a coefficient threshold, it indicates that a local optimal solution has occurred. The accuracy of data classification can be improved by integrating the Ochi a coefficient measurement method and the particle swarm algorithm.
[0066] Furthermore, in this method, obtaining the application area where the abnormal application membership is located according to the evaluated application effect membership specifically includes:
[0067] Preset the membership evaluation index, and judge whether the membership of the application effect after evaluation is greater than the membership evaluation index;
[0068] When the membership of the application effect after evaluation is greater than the membership evaluation index, the application area corresponding to the current application effect membership after evaluation is used as the release area of the abnormal membership;
[0069] When the membership of the application effect after evaluation is not greater than the membership evaluation index, the application area corresponding to the current membership of the application effect after evaluation is used as the release area of the normal membership;
[0070] Obtain the release area where the abnormal application membership is located, and output the release area where the abnormal application membership is located.
[0071] Furthermore, in this method, a large database of slow-release pesticides is constructed, specifically:
[0072] Obtain the chemical composition data information of each controlled-release pesticide, build a large database of controlled-release pesticides, introduce graph neural network, use the chemical composition data information as the first node of the graph neural network, and use the type of controlled-release pesticide as the second node;
[0073] Constructing a directed edge description relationship, connecting the first node and the second node based on the directed edge description relationship, constructing a topological structure graph, and obtaining a related adjacency matrix based on the topological structure graph;
[0074] The related adjacency matrix is input into the storage space in the slow-release pesticide database for storage, and a query address is configured for each storage space.
[0075] Furthermore, in this method, the optimal application scheme of controlled-release pesticides is recommended based on the application area where the abnormal application membership is located and the controlled-release pesticide database, and the controlled-release pesticides are applied according to the optimal application scheme, specifically:
[0076] Acquire chemical composition data corresponding to the controlled-release pesticide in the application area where the abnormal application membership is located, and input the chemical composition data corresponding to the controlled-release pesticide in the application area where the abnormal application membership is located into a large database of controlled-release pesticides;
[0077] Calculate the Pearson correlation coefficient between the chemical composition data of each type of controlled-release pesticide in the controlled-release pesticide database and the chemical composition data corresponding to the controlled-release pesticide in the application area where the abnormal application membership is located;
[0078] Presetting a Pearson correlation coefficient threshold, determining whether the Pearson correlation coefficient is not greater than the Pearson correlation coefficient threshold, and selecting a controlled-release pesticide type corresponding to a controlled-release pesticide type not greater than the Pearson correlation coefficient threshold as a candidate controlled-release pesticide application scheme;
[0079] The controlled-release pesticide application scheme with the largest Pearson correlation coefficient is selected as the optimal controlled-release pesticide application scheme, and the controlled-release pesticide application is performed according to the optimal controlled-release pesticide application scheme.
[0080] It should be noted that when the membership of the application effect after evaluation is greater than the membership evaluation index, the current application area indicates that resistance has occurred. The sustained-release pesticide application scheme with the largest Pearson correlation coefficient is selected as the optimal sustained-release pesticide application scheme to improve the application effect of sustained-release pesticides in the target area.
[0081] In addition, the method may further comprise the following steps:
[0082] Obtaining the sustained-release pesticide application effect data of the optimal sustained-release pesticide application scheme under each meteorological characteristic environment through big data, and constructing a sustained-release pesticide application effect prediction model based on a deep neural network, and constructing a feature matrix based on the sustained-release pesticide application effect data of the optimal sustained-release pesticide application scheme under each meteorological characteristic environment;
[0083] Inputting the feature matrix into the slow-release pesticide application effect prediction model for training, and when the loss function of the slow-release pesticide application effect prediction model converges to a preset value, outputting the slow-release pesticide application effect prediction model;
[0084] Acquire meteorological characteristic data of the target area within a preset time, and input the meteorological characteristic data of the target area within the preset time into the slow-release pesticide application effect prediction model for prediction, and acquire the slow-release pesticide application effect data under the meteorological characteristic data of the target area within the current preset time;
[0085] When the slow-release pesticide application effect data is lower than the preset slow-release pesticide application effect evaluation index, the optimal slow-release pesticide application plan is readjusted until the slow-release pesticide application effect data is not lower than the preset slow-release pesticide application effect evaluation index, and the optimal slow-release pesticide application plan is output.
[0086] It should be noted that due to the differences in the chemical composition of the application scheme of slow-release pesticides, the application effects of slow-release pesticides under various meteorological characteristic environments (such as temperature, humidity, etc.) will be inconsistent. This method can further optimize the optimal application scheme of slow-release pesticides, thereby improving the rationality of the recommendation of slow-release pesticides.
[0087] like Figure 3As shown, the second aspect of the present invention provides a system 4 for evaluating the application effect of a controlled-release pesticide. The system 4 includes a memory 41 and a processor 42. The memory 41 includes a program for evaluating the application effect of a controlled-release pesticide. When the program for evaluating the application effect of a controlled-release pesticide is executed by the processor 42, the following steps are implemented:
[0088] Obtain the real-time disease data and pest data of each slow-release pesticide in each application area, and obtain the initial application effect membership of each application area based on the real-time disease data and pest data;
[0089] The Ochia coefficient measurement method and the particle swarm algorithm are introduced, and the initial application effect membership is re-evaluated according to the Ochia coefficient measurement method and the particle swarm algorithm to obtain the evaluated application effect membership;
[0090] According to the evaluated application effect membership, the application area with abnormal application membership is obtained, and a large database of slow-release pesticides is constructed;
[0091] Based on the application area where the abnormal application membership is located and the large database of slow-release pesticides, the optimal slow-release pesticide application plan is recommended, and the slow-release pesticides are applied according to the optimal application plan.
[0092] Furthermore, in this system, the real-time disease data and pest data of each slow-release pesticide in each application area are obtained, and the initial application effect membership of each application area is obtained based on the real-time disease data and pest data, specifically:
[0093] Obtain disease and pest data of the target area within a preset time, and obtain real-time disease and pest data of each controlled-release pesticide in each application area;
[0094] Calculate the killing ratio of diseases and pests in each application area within the preset time according to the disease data and pest data of the target area within the preset time and the real-time disease data and pest data of each slow-release pesticide in each application area;
[0095] Introducing a fuzzy clustering algorithm, initializing the number of cluster centers in the fuzzy clustering algorithm, and constructing sample data based on the proportion of diseases and pests killed in each application area within a preset time;
[0096] The sample data is initialized and clustered based on the number of cluster centers in the fuzzy clustering algorithm to obtain the cluster center corresponding to the sample data. The initial application effect membership corresponding to each sample data is obtained based on the cluster center and used as the initial application effect membership of each application area.
[0097] It should be noted that fuzzy clustering algorithms include k-means clustering algorithm, FCM clustering algorithm, etc., among which the application effect membership includes high application effect, medium application effect, low application effect, etc. For example, the killing ratio is 90%-100% for high application effect. This method can be used to quickly process massive data. Among them, disease data include the number of diseased plants within a unit area, the number of diseased plants within a preset area, etc., and pest data include the number of diseased and insect-infested plants within a unit area, the number of diseased and insect-infested plants within a preset area, etc.
[0098] Furthermore, in this system, the Ochia coefficient measurement method and the particle swarm algorithm are introduced, and the initial application effect membership is re-evaluated according to the Ochia coefficient measurement method and the particle swarm algorithm to obtain the evaluated application effect membership, which is specifically:
[0099] The Ochi a coefficient measurement method and particle swarm algorithm are introduced. The number of iterations is set based on the particle swarm algorithm to obtain the clusters corresponding to each initial application effect membership, and the Ochi a coefficients between the clusters corresponding to the initial application effect membership are calculated.
[0100] Set an Och ii a coefficient threshold, and determine whether the Och ii a coefficient is greater than the Och ii a coefficient threshold;
[0101] When the Ochi a coefficient is greater than the Ochi a coefficient threshold, all clusters are output, and the application effect membership corresponding to each cluster is obtained and output as the evaluated application effect membership;
[0102] When the Ochi a coefficient is not greater than the Ochi a coefficient threshold, iteration is performed based on the number of iterations, and the number of cluster centers is adjusted until the Ochi a coefficient is greater than the Ochi a coefficient threshold. The iteration is stopped, and the application effect membership corresponding to each cluster is obtained and output as the evaluated application effect membership.
[0103] It should be noted that, since the fuzzy clustering algorithm is prone to local optimal solution when the number of cluster centers is not suitable during clustering, when the Ochi a coefficient is not greater than the Ochi a coefficient threshold, it indicates that a local optimal solution has occurred. The accuracy of data classification can be improved by integrating the Ochi a coefficient measurement method and the particle swarm algorithm.
[0104] Furthermore, in this system, the application area where the abnormal application membership is located is obtained according to the evaluated application effect membership, specifically including:
[0105] Preset the membership evaluation index, and judge whether the membership of the application effect after evaluation is greater than the membership evaluation index;
[0106] When the membership of the application effect after evaluation is greater than the membership evaluation index, the application area corresponding to the current application effect membership after evaluation is used as the release area of the abnormal membership;
[0107] When the membership of the application effect after evaluation is not greater than the membership evaluation index, the application area corresponding to the current membership of the application effect after evaluation is used as the release area of the normal membership;
[0108] Obtain the release area where the abnormal application membership is located, and output the release area where the abnormal application membership is located.
[0109] Furthermore, in this system, a large database of slow-release pesticides is constructed, specifically:
[0110] Obtain the chemical composition data information of each controlled-release pesticide, build a large database of controlled-release pesticides, introduce graph neural network, use the chemical composition data information as the first node of the graph neural network, and use the type of controlled-release pesticide as the second node;
[0111] Constructing a directed edge description relationship, connecting the first node and the second node based on the directed edge description relationship, constructing a topological structure graph, and obtaining a related adjacency matrix based on the topological structure graph;
[0112] The related adjacency matrix is input into the storage space in the slow-release pesticide database for storage, and a query address is configured for each storage space.
[0113] Furthermore, in this system, the optimal controlled-release pesticide application scheme is recommended based on the application area where the abnormal application membership is located and the controlled-release pesticide database, and the controlled-release pesticide application is carried out according to the optimal controlled-release pesticide application scheme, specifically:
[0114] Acquire chemical composition data corresponding to the controlled-release pesticide in the application area where the abnormal application membership is located, and input the chemical composition data corresponding to the controlled-release pesticide in the application area where the abnormal application membership is located into a large database of controlled-release pesticides;
[0115] Calculate the Pearson correlation coefficient between the chemical composition data of each type of controlled-release pesticide in the controlled-release pesticide database and the chemical composition data corresponding to the controlled-release pesticide in the application area where the abnormal application membership is located;
[0116] Presetting a Pearson correlation coefficient threshold, determining whether the Pearson correlation coefficient is not greater than the Pearson correlation coefficient threshold, and selecting a controlled-release pesticide type corresponding to a controlled-release pesticide type not greater than the Pearson correlation coefficient threshold as a candidate controlled-release pesticide application scheme;
[0117] The controlled-release pesticide application scheme with the largest Pearson correlation coefficient is selected as the optimal controlled-release pesticide application scheme, and the controlled-release pesticide application is performed according to the optimal controlled-release pesticide application scheme.
[0118] It should be noted that when the membership of the application effect after evaluation is greater than the membership evaluation index, the current application area indicates that resistance has occurred. The sustained-release pesticide application scheme with the largest Pearson correlation coefficient is selected as the optimal sustained-release pesticide application scheme to improve the application effect of sustained-release pesticides in the target area.
[0119] The third aspect of the present invention provides a computer-readable storage medium, which includes a program for evaluating the application effect of a sustained-release pesticide. When the program for evaluating the application effect of a sustained-release pesticide is executed by a processor, any step of the method for evaluating the application effect of a sustained-release pesticide is implemented.
[0120] 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.
[0121] 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.
[0122] 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.
[0123] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiments 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 embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks or optical disks, and other media that can store program codes.
[0124] 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, a server, or a network device, etc.) to execute all or part of the methods of 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.
[0125] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field 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 method for evaluating the application effect of a slow-release pesticide, It is characterized in that The following steps are involved: Obtaining real-time disease data and pest data of each slow-release pesticide in each application area, and obtaining the initial application effect membership of each application area according to the real-time disease data and pest data; Introducing an Ochiia coefficient measurement method and a particle swarm algorithm, and re-evaluating the initial application effect membership according to the Ochiia coefficient measurement method and the particle swarm algorithm to obtain the evaluated application effect membership; According to the evaluated application effect membership, the application area where the abnormal application membership is located is obtained, and a large database of slow-release pesticides is constructed; Based on the application area where the abnormal application membership is located and the large database of controlled-release pesticides, an optimal controlled-release pesticide application plan is recommended, and the controlled-release pesticides are applied according to the optimal controlled-release pesticide application plan.
2. A method for evaluating the application effect of a sustained-release pesticide according to claim 1, It is characterized in that Obtain the real-time disease data and pest data of each slow-release pesticide in each application area, and obtain the initial application effect membership of each application area based on the real-time disease data and pest data, specifically: Obtain disease and pest data of the target area within a preset time, and obtain real-time disease and pest data of each controlled-release pesticide in each application area; Calculate the killing ratio of diseases and pests in each application area within the preset time according to the disease data and pest data of the target area within the preset time and the real-time disease data and pest data of each slow-release pesticide in each application area; Introducing a fuzzy clustering algorithm, initializing the number of cluster centers in the fuzzy clustering algorithm, and constructing sample data based on the killing ratio of diseases and pests in each application area within the preset time; The sample data is initialized and clustered based on the number of cluster centers in the fuzzy clustering algorithm, and the cluster centers corresponding to the sample data are obtained. Based on the cluster centers, the initial application effect membership corresponding to each sample data is obtained and used as the initial application effect membership of each application area.
3. The method for evaluating the application effect of a sustained-release pesticide according to claim 1, It is characterized in that The Ochiia coefficient measurement method and the particle swarm algorithm are introduced, and the initial application effect membership is re-evaluated according to the Ochiia coefficient measurement method and the particle swarm algorithm to obtain the evaluated application effect membership, which is specifically: The Ochiia coefficient measurement method and the particle swarm algorithm are introduced, the number of iterations is set based on the particle swarm algorithm, the clusters corresponding to each initial application effect membership are obtained, and the Ochiia coefficients between the clusters corresponding to the initial application effect membership are calculated; Setting an Ochiia coefficient threshold value, and determining whether the Ochiia coefficient is greater than the Ochiia coefficient threshold value; When the Ochiia coefficient is greater than the Ochiia coefficient threshold, all clusters are output, and the application effect membership corresponding to each cluster is obtained and output as the evaluated application effect membership; When the Ochiia coefficient is not greater than the Ochiia coefficient threshold, iteration is performed based on the number of iterations, and the number of cluster centers is adjusted until the Ochiia coefficient is greater than the Ochiia coefficient threshold. Then, iteration is stopped, and the application effect membership corresponding to each cluster is obtained and output as the evaluated application effect membership.
4. The method for evaluating the application effect of a sustained-release pesticide according to claim 1, It is characterized in that According to the evaluated application effect membership, the application area where the abnormal application membership is located is obtained, specifically including: Preset a membership evaluation index, and determine whether the membership of the application effect after the evaluation is greater than the membership evaluation index; When the membership of the application effect after evaluation is greater than the membership evaluation index, the application area corresponding to the current membership of the application effect after evaluation is used as the release area of the abnormal membership; When the membership of the application effect after evaluation is not greater than the membership evaluation index, the application area corresponding to the current membership of the application effect after evaluation is used as the release area of the normal membership; The application area where the abnormal application membership is located is obtained, and the application area where the abnormal application membership is located is output.
5. The method for evaluating the application effect of a sustained-release pesticide according to claim 1, It is characterized in that Construct a large database of slow-release pesticides, specifically: Obtain the chemical composition data information of each controlled-release pesticide, and build a large database of controlled-release pesticides, introduce a graph neural network, use the chemical composition data information as the first node of the graph neural network, and use the type of controlled-release pesticide as the second node; Constructing a directed edge description relationship, connecting the first node and the second node based on the directed edge description relationship, constructing a topological structure graph, and acquiring a related adjacency matrix based on the topological structure graph; The related adjacency matrix is input into the storage space in the slow-release pesticide database for storage, and a query address is configured for each storage space.
6. The method for evaluating the application effect of a sustained-release pesticide according to claim 1, It is characterized in that Based on the application area where the abnormal application membership is located and the controlled-release pesticide database, the optimal controlled-release pesticide application plan is recommended, and the controlled-release pesticide is applied according to the optimal controlled-release pesticide application plan, specifically: Acquire chemical composition data corresponding to the controlled-release pesticide in the application area where the abnormal application membership is located, and input the chemical composition data corresponding to the controlled-release pesticide in the application area where the abnormal application membership is located into the controlled-release pesticide database; Calculate the Pearson correlation coefficient between the chemical composition data of each type of controlled-release pesticide in the controlled-release pesticide database and the chemical composition data corresponding to the controlled-release pesticide in the application area where the abnormal application membership is located; Presetting a Pearson correlation coefficient threshold, determining whether the Pearson correlation coefficient is not greater than the Pearson correlation coefficient threshold, and selecting a controlled-release pesticide type corresponding to a controlled-release pesticide type not greater than the Pearson correlation coefficient threshold as a candidate controlled-release pesticide application scheme; The sustained-release pesticide application scheme candidate with the largest Pearson correlation coefficient is selected as the optimal sustained-release pesticide application scheme, and the sustained-release pesticide application is performed according to the optimal sustained-release pesticide application scheme.
7. A system for evaluating the application effect of slow-release pesticides. It is characterized in that The system includes a memory and a processor, wherein the memory includes a method program for evaluating the application effect of a controlled-release pesticide, and when the method program for evaluating the application effect of a controlled-release pesticide is executed by the processor, the following steps are implemented: Obtaining real-time disease data and pest data of each slow-release pesticide in each application area, and obtaining the initial application effect membership of each application area according to the real-time disease data and pest data; Introducing an Ochiia coefficient measurement method and a particle swarm algorithm, and re-evaluating the initial application effect membership according to the Ochiia coefficient measurement method and the particle swarm algorithm to obtain the evaluated application effect membership; According to the evaluated application effect membership, the application area where the abnormal application membership is located is obtained, and a large database of slow-release pesticides is constructed; Based on the application area where the abnormal application membership is located and the large database of controlled-release pesticides, an optimal controlled-release pesticide application plan is recommended, and the controlled-release pesticides are applied according to the optimal controlled-release pesticide application plan.
8. A computer-readable storage medium, It is characterized in that The computer-readable storage medium includes a method program for evaluating the application effect of a sustained-release pesticide. When the method program for evaluating the application effect of a sustained-release pesticide is executed by a processor, the steps of the method for evaluating the application effect of a sustained-release pesticide as described in any one of claims 1 to 6 are implemented.
